Wiley: Journal of Field Robotics: Table of Contents

Mobile Manipulator Robot for Autonomous In‐Situ Soil Measurements in Chile Pepper Cultivation

Roman Langenscheidt, Mahdi Haghshenas‐Jaryani, Heinz Bernhardt — Mon, 08 Jun 2026 05:43:45 -0700

ABSTRACT

Chile pepper farming in New Mexico faces critical constraints from water scarcity, soil salinity, and labor shortages. Precision agriculture technologies enabling data-driven resource management offer promising solutions. This paper presents an autonomous in-situ soil sensing system integrated with a mobile manipulator robot for automated soil data collection. The main contribution is a unified, failure-aware autonomous soil sensing system that integrates vision-based surface characterization, adaptive force-controlled sensor insertion, and insertion monitoring with failure detection and recovery into a single low-cost field-deployable robotic platform. The system comprises a two-stage visual alignment process using RGB-D camera data to adapt to terrain slope and identify obstacle-free insertion sites, a force-based contact detection mechanism to determine sensor-soil contact, and adaptive impedance control with Kalman filter-based soil stiffness estimation for controlled sensor insertion. The system is implemented on a mobile platform with a six DoF manipulator and TEROS 12 soil sensor. Field evaluation across 41 sensing operations in varying soil conditions during the early chile pepper season demonstrated a 75.6% success rate, with soil measurements correctly obtained upon full sensor insertion. In 90.2% of sensing operations, the system made correct decisions, including aborts when necessary. Main limitations included the inability to detect flush surface obstacles, occasional false contact detections, and incorrect insertion completion verification. Nevertheless, the results demonstrate the feasibility of autonomous in-situ soil sensing in chile pepper cultivation, providing a foundation for fully autonomous soil monitoring. The methods and approaches developed in this work may extend to other crops requiring in-situ soil measurements.

A Design Specifications Template for Wearable Haptic Interfaces: A Case Study for Robotic Gripper Applications

Amr M. El‐Sayed — Mon, 08 Jun 2026 05:42:47 -0700

ABSTRACT

Wearable haptic interfaces are increasingly important for enhancing human robot collaboration, particularly in decision critical tasks that require intuitive and reliable interaction. Despite advances in wearable systems, existing designs often lack a structured framework that systematically integrates sensing, actuation, control, and user-centered considerations, limiting consistency, scalability, and performance across robotic applications. This paper presents a design specifications template for wearable haptic interfaces, providing a structured approach to guide designers in addressing key parameters, including user functional needs, ergonomic requirements, and technical design data. A focused review of related technologies covering exoskeletons and wearable haptic devices, sensing technologies for touch, and recent robotic grippers was conducted to inform the template and identify gaps in current design practices. The template was validated using two complementary approaches. Theoretical validation involved mapping two existing wearable haptic systems to the template, revealing that coverage of user characteristics and functional requirements ranged from 25% to 37.5%, highlighting the need for more systematic consideration of human factors. Practical validation was performed by designing, fabricating, and evaluating a three-finger wearable haptic device integrated with a robotic gripper, demonstrating improved coverage of user-centered and technical parameters and confirming the template's practical applicability. Overall, the proposed framework provides a systematic, application-driven methodology for developing reliable and scalable wearable haptic interfaces. By enabling designers to integrate human factors, device functionality, and technical specifications at the pre-design stage, it supports improved human-robot collaboration and sets a foundation for future standardized and adaptable haptic systems in teleoperation, rehabilitation, and robotic manipulation tasks.

A Low‐Drift Legged Robot State‐Estimation System Through Combined Physics‐Informed Contact Estimation Network and Full Joint State

Zhentao Xie, Qinchuan Li, Xiaolong Zhou, Yabin Xu — Fri, 05 Jun 2026 05:39:16 -0700

ABSTRACT

Proprioceptive sensors are crucial for legged robots, as they provide reliable internal state information and are less affected by environmental disturbances. A robust proprioceptive base state estimator is essential for the localization and control capabilities of legged robots. Classical methods for estimation of legged robot state often use IMU integration for prediction and use the assumption of stationary foot contact for updates. However, they suffer from issues like IMU accelerometer noise from foot-end impacts, nonlinear foot-ground interactions, and sensor parameter uncertainties, which leads to estimation drift. To address these limitations, this paper proposes a novel system for estimating the low drift state of legged robots by combining contact and joint state estimation. Specifically, our method i) proposes a physics-informed contact estimation state network to obtain accurate contact states for legged robots, ii) estimates joint states of the legged robot and obtained body accelerations computed from joint accelerations, and iii) updates the base position, orientation, and velocity by gravitational acceleration components and the assumption of static contact points. Under standard operating conditions, experiments on both public and private datasets demonstrate that the proposed method outperforms state-of-the-art algorithms.

Multi‐Robot Collaborative Navigation Framework Based on 3D Voronoi Partitioning in Uneven and Unstructured Environments

Hongyang Zhao, Kunyu Xu, Nuo Xu, Xingdong Li, Jing Jin — Fri, 05 Jun 2026 01:43:50 -0700

ABSTRACT

Currently, research on cooperative navigation of multi-robot systems in uneven terrain environments is still relatively scarce. The complex and rugged terrain features often pose significant threats to the navigation performance of each robot, thereby presenting considerable challenges for conducting safe and efficient collaborative operations in such environments. This article proposes a multi-robot cooperative navigation framework aimed at addressing these challenges on uneven road surfaces. Based on three-dimensional Voronoi partitioning, a terrain-aware partitioning strategy (TAPM-IVP) is introduced, enabling each robot to perform real-time terrain analysis, categorizing the space into traversable space, non-traversable space, and free space, thus facilitating task allocation in complex uneven terrain. Based on the partition results of TAPM-IVP, a greedy heuristic sub-goal decision method is proposed, which selects safe, non-redundant, and collision-free target points, employing a hierarchical generation strategy to guide the robotic system in efficiently navigating in unknown environments, thereby significantly enhancing navigation adaptability and task completion efficiency in uneven scenarios. Finally, both simulations and real-world experiments validate the feasibility, safety, and efficiency of the proposed framework for cooperative navigation in uneven road conditions.

From Flybys to Sample Return: A Review of Space Probes and Robotic Sampling Technologies for Small Bodies

Xin Zhang, Hao Zhou, Dalin Zhou, Zhaojie Ju — Fri, 05 Jun 2026 01:42:30 -0700

ABSTRACT

As a crucial puzzle piece of deep space exploration, exploring small bodies can provide significant scientific insights and valuable mineral resources. Unlike missions to the Moon and Mars, small-body missions pose distinct technical challenges, including communication delays, weak gravity, and uncertain environments. This paper reviews a full mission spectrum of probe-based small-body missions to analyze the current status and core technologies, tracing from flyby detection to orbital observation, impact detection, in-situ sampling and analysis, and sample-return missions. Since sampling missions act as a bridge between detection and exploitation, robotic sampling has become one of the most cutting-edge and core technologies for space robotic probes. Space robots are the synergy of robotics and autonomy: robotics provides the physical capability for sample acquisition, while autonomy enables the robot to perceive environments, make decisions, and plan actions independently for robust and efficient sampling. Therefore, we investigate the state-of-the-art robotic sampling and onboard autonomy technologies, including robotic sampler design, autonomous touchdown, and compliant interaction. Given the significant uncertainties associated with small bodies, we propose a trade-off cobweb model to evaluate the comprehensive performance of various robotic samplers. Additionally, we review mainstream microgravity simulation technologies for testing robotic samplers on the ground. Finally, we analyze key lessons learned from past missions and discuss directions for future small-body exploration. This review aims to serve as a comprehensive and useful reference for researchers in the field.

Design, Development, and Field Testing of a Tomato Bunch Harvesting Robot

Can Xu, Zefeng Xu, Huiling Li, Yitong Zhou — Tue, 02 Jun 2026 05:44:47 -0700

ABSTRACT

With the aging population and labor shortages, the proportion of labor costs in tomato harvesting is increasing, making the development of tomato harvesting robots imperative. This study developed an integrated tomato bunch harvesting robotic system for cherry tomatoes. A combined cutting and gripping end-effector powered by a single actuator, achieving a cutting success rate of 93.33% and a gripping capacity of 1600 g. A parameterized camera arrangement was employed to match the robotic arm's field of view, thereby avoiding mutual interference. A tomato bunch and stalk recognition model was constructed based on the YOLOv4 algorithm to enable precise localization of harvesting points. The proposed tomato bunch-stalk matching method achieved a recall rate of 99.22%, while the stalk growth-direction qualitative discrimination method attained an accuracy of 97%. Field experiments demonstrated that the system achieved an average harvesting time of 12.23 s per tomato bunch and an overall harvesting success rate of 70.77% in unstructured environments, improving automation and operational efficiency compared to existing solutions. This research offers a solution integrating hardware optimization and perception algorithms for greenhouse harvesting robots, demonstrating potential for commercial application.

Performance Evaluation of Different Laser SLAM Algorithms for Unmanned Mining Vehicles

Jiangdong Wu, Tengfei Zhang, Qun Chao, Chengliang Liu — Mon, 01 Jun 2026 11:09:38 -0700

ABSTRACT

Unmanned mining technology is essential for enhancing safety, increasing efficiency, and reducing operational costs. The complex and hazardous nature of mining environments demands advanced positioning systems for autonomous vehicles, with laser simultaneous localization and mapping (SLAM) algorithms playing a critical role. This paper provides a systematic review of the core technical modules within laser SLAM algorithms, analyzing their development trends, strengths, and weaknesses. A comprehensive evaluation of fifteen mainstream SLAM algorithms on the AutoMine open-pit mining data set reveals significant insights. Experimental results demonstrate that traditional feature-based algorithms are prone to significant trajectory drift due to feature loss in sparse-feature mining environments. Notably, the study further identifies a specific “Ramp Drift” mechanism where recursive estimators suffer Z-axis instability on monotonic slopes. Comparative analysis suggests that while Light Detection and Ranging (LiDAR)–inertial fusion generally enhances robustness, degeneracy-aware architectures are the decisive factor for stability. Specifically, the LiDAR-only odometry GLO achieves the highest stability in relative pose error due to its Weighted Elastic Matching strategy, while the Adaptive-LIO demonstrates superior global consistency in absolute pose error. This study highlights a current lack of SLAM architectures specifically optimized for the unique challenges of open-pit mines. Future research should focus on feature extraction enhancement in open scenes, the development of optimized LiDAR–inertial–RTK fusion architectures, and the integration of artificial intelligence to improve adaptability in dynamic and degraded scenarios.

Survey on AI‐Enabled Computer Vision Technologies and Applications for Space Robotic Missions

Wed, 27 May 2026 05:37:04 -0700

ABSTRACT

This survey provides a comprehensive overview of recent advancements and challenges in Artificial Intelligence (AI)-enabled computer vision (CV) techniques for space robotic missions, spanning critical phases such as Entry, Descent, and Landing (EDL), orbital operations, and planetary surface exploration. Emphasis is placed on deep-learning–based approaches for image classification, object detection, semantic segmentation, relative pose estimation, and feature matching. State-of-the-art methods in terrain-relative navigation, crater-based or rock-feature matching, and pose estimation for uncooperative targets are highlighted, illustrating the progress achieved through hybrid pipelines combining deep neural networks with classical geometry. The paper also critically evaluates publicly available orbital and planetary data sets—along with the increasing role of synthetic data—for developing and benchmarking CV algorithms under strict resource limitations and harsh environmental conditions. Despite demonstrated success in tasks like autonomous landing, debris removal, and rover navigation, current solutions face significant hurdles. These include computational constraints on onboard hardware, insufficient coverage of planetary conditions in existing data sets, and limited adaptability to dynamically changing environments. To address these shortcomings, research must prioritize lightweight neural architectures, advanced synthetic data generation, adaptive or incremental learning, and robust multisensor fusion. By integrating these strategies, AI-based CV systems can advance autonomy, precision, and resilience in future space missions.

Innovative Soft Material‐Assisted Robot Grasping Devices: From Design Concept to Fabrication and Application Scenarios

Wed, 27 May 2026 05:37:04 -0700

ABSTRACT

Soft robotic grippers, a novel category of robotic arm end-effectors, have garnered significant interest owing to their distinct characteristics: soft structure, flexibility, and robust adaptability. These features grant them immense potential for applications across various domains. This study delves into a range of driving mode, encompassing tendon-driven, fluidic actuation, smart materials-based actuation, chemical reactive actuation, and variable stiffness approaches, and thoroughly analyzes the characteristics of each. The design of soft robotic grippers frequently draws inspiration from natural and biological organisms, is bolstered by advancements in materials science, and leverages hyperelastic materials to enable versatile manipulation capabilities. In the fabrication of these grippers, materials such as hydrogels, liquid crystal elastomers, electroactive polymers, and shape-memory alloys are routinely employed. Additionally, fabrication techniques, including mold casting and additive manufacturing, are comprehensively analyzed. The study discusses the expansive application prospects of soft robotic grippers in medical treatment, emergency rescue, agriculture, and industrial production, emphasizing their potential for cross-domain utilization. Furthermore, the paper outlines potential avenues for advancing soft robotic grippers in grasping strategies, key fabrication processes, and expanding application scenarios, thereby offering valuable insights into the development of innovative soft robots tailored for multifield operations.

Ergonomically Designed Assistive Robots: Where and How to Bring Comfort, Safety, and Independence to Elderly Care

Wed, 27 May 2026 05:37:04 -0700

ABSTRACT

The aging population worldwide presents significant challenges to elderly care, particularly in maintaining their comfort, safety, and independence. Ergonomically designed assistive robots offer a promising solution to address these challenges by providing personalized support that aligns with the physical and cognitive needs of older adults. This review paper will explore the role of elderly assistive robots in elderly care, focusing on their ergonomic design, functionality, and impact on enhancing the well-being of elderly individuals. Key design principles such as user-centered ergonomics, adaptability to various physical conditions, ease of interaction, and safety features will be discussed. Additionally, the review paper will highlight the integration of advanced technologies such as AI, machine learning, and sensor systems, which enable robots to assist with daily activities, mobility, medication management, and social interaction. Through case studies and recent advancements, we will examine the potential of these robots to improve elderly care by fostering independence, preventing injuries, and providing companionship. The session will conclude with an outlook on future research and the ongoing development of assistive robots to meet the evolving needs of the aging population.

Efficient and Adaptive Autonomous Guidance and Control of Planetary Rover With Improved Traction Controller and Dynamic Cost Map

Alessio De Luca, Luca Muratore, Nikos G. Tsagarakis, Martin Azkarate — Wed, 27 May 2026 05:37:04 -0700

ABSTRACT

Planetary exploration is rapidly gaining importance within the space research community. Autonomous locomotion of rovers requires consideration of several mobility aspects to ensure safety, including avoiding hazardous areas that can cause the robot to become immobilized in soft soil or damaged in sharp terrains. Furthermore, when executing autonomous guidance, selecting an appropriate path to follow is crucial to reduce energy consumption and improve the overall distance traveled by the rover. This directly impacts the rover's performance and the possible scientific outcome of the mission. This paper addresses the optimization of the autonomous locomotion of Mars rovers by acting on the guidance and control layers. Firstly, an enhanced velocity-based traction controller is proposed to simultaneously address slip and kinematic incompatibilities while permitting omnidirectional motion. The controller acts directly at the wheel command level to improve traction and tracking performances, reducing position and heading errors. This is achieved by enriching the controller's input with the rover's linear and angular velocity error. The performance metrics evaluated within the traction controller are then used to dynamically update the cost map of the environment. Finally, a higher-level path planner is integrated, considering kino-dynamic constraints, continuously providing new trajectories according to the map updates to select high-traction paths. The proposed framework has been validated through simulation and real-world experiments on the MaRTA rover of ESA's Planetary Robotics Laboratory. The results demonstrate that the proposed approach achieves better tracking performance and up to 62% traction improvements thanks to the enhanced controller and dynamic cost map updates.

Deep Learning‐Driven Steering Angle Prediction and Scene Understanding via Harmonic Carpet Weaver Optimization

Jayashree Pradip Tamkhade, Sumalatha Bandari, Krishna Murthy Inumula — Wed, 27 May 2026 05:37:04 -0700

ABSTRACT

Steering angle prediction refers to forecasting the steering angle as early as possible in advance to ensure smooth and precise vehicle control. Therefore, this article introduces a novel approach, called Quasi Recurrent Neural Network with Harmonic Carpet Weaver Optimization (QRNN_HarCWO), for predicting the steering angles. Primarily, the input video is assimilated from the database, and later, the video is split into multiple frames. Then, the pre-processing procedure is done by the Gaussian filter, which is exploited to denoise the video frame. Subsequently, the pre-processed output is fed into the scene understanding module, where semantic segmentation is performed by exploiting BlitzNet with the BiTopK loss function. Here, the BiTopK loss function is a new loss function formulated using binary cross-entropy and the TopK loss functions. Further, Harmonic Carpet Weaver Optimization (HarCWO) is utilized to train the BlitzNet. Finally, the Quasi-Recurrent Neural Network with HarCWO (QRNN_HarCWO) is used for performing steering angle prediction, based on which appropriate control action is taken. Moreover, the presented approach gained the minimum values of Mean Squared Error (MSE), Root Mean Square Error (RMSE), Mean Absolute Error (MAE), and Percent Bias (PBIAS) of 0.0368, 0.1918, 0.1766, and 0.0589. Also, the maximum values of 92.877%, 94.887%, 90.766%, and 88.876% are attained by the QRNN_HarCWO model for accuracy, True Positive Rate (TPR), Positive Predictive Value (PPV), and Negative Predictive Value (NPV) metrics. While the results demonstrate high accuracy, potential real-world challenges such as sensor noise and hardware limitations may affect the deployment of the model in real settings, which need to be addressed in future work.

D2GNet: Efficient 6‐DoF Grasp Detection in Cluttered Scenes via Density‐Aware Dual‐Dimensional Graph Networks

Mingxuan Quan, Xiaohua Wang, Jiayu Zhang, Wenjie Wang — Wed, 27 May 2026 05:37:04 -0700

ABSTRACT

In real scenes, objects are often disordered, heavily stacked, and occluded, posing significant challenges to robotic grasping. To address these challenges, we propose Density-Aware Dual-Dimension Graph Network (D2GNet). Our model adopts a two-stage architecture comprising a perception stage and an execution stage. In the perception stage, D2GNet employs a Dual-Dimension Attention Module (DDAM) that integrates in-degree-enhanced graph attention (D-GAT) and a Graph Channel Adaptive Attention (GCAA) to perceive local density and strengthen spatial reasoning in dense regions. In the execution stage, a target-guided point-cloud screening strategy extracts stable grasp candidates via multiscale structural enhancement and a rescoring mechanism. Experiments on GraspNet-1Billion show that, even with limited training data, D2GNet consistently outperforms existing methods. Compared with the graph-neural baseline GraNet, it achieves up to 16.83% improvement on RealSense evaluations and further exceeds the state-of-the-art toward scale-balanced 6-DoF grasp detection by 2.16%, while delivering even larger gains on Kinect benchmarks. Real-robot trials confirm its effectiveness; even under weak illumination, D2GNet exhibits strong robustness and clear potential for practical deployment.

A Novel High‐Voltage‐Wire Stripping Robot and Adaptive Fuzzy RBF Neural Network PID Controller Optimized by PSO‐GA Algorithm

Jun Zhong, Hongshan Feng, Xia Lu, Zhichao Wang — Wed, 27 May 2026 05:37:04 -0700

ABSTRACT

At present, a significant element of the maintenance of high-voltage transmission lines is the manual stripping of wire. However, manual stripping is a highly risky process. This paper introduces a high-voltage-wire stripping robot with the objective of enhancing operator safety, optimizing peeling efficiency, and reducing labor intensity. It is imperative that advanced control strategies be devised in light of the robot's nonlinear and high coupling properties. This paper presents three proportional–integral–derivative (PID) control algorithms for evaluation of the robot: the traditional PID, the fuzzy neural network PID (FNN PID), and the FNN PID control algorithm based on genetic algorithm and particle swarm optimization (PSO-GA FNN PID). Experiments are conducted with the objective of further demonstrating the superiority of the robot and the various control algorithms in the context of high-voltage-wire stripping. Furthermore, the traditional PID, FNN PID, and PSO-GA FNN PID algorithms are compared. The results demonstrate that the PSO-GA FNN PID algorithm exhibits the greatest self-adaptability, robustness, and steady-state performance.

Precision Error Compensation Algorithm for Automated Drill Pipe Gripping in Underground Coal Mine Drilling Robots

Wed, 27 May 2026 05:37:04 -0700

ABSTRACT

To address the industry challenge of traditional error compensation methods failing in large spaces under harsh conditions—such as high dust, strong vibrations, and the explosion-proof MA certification requirements in underground coal mines—this paper proposes a novel error compensation algorithm based on zoning and Gaussian regression. It develops a sensorless compensation framework that operates within explosion-proof constraints by integrating zonal calibration with Gaussian Process Regression (GPR), which overcomes the dual challenges of visual failure and the limited availability of MA explosion-proof sensors. To tackle the accuracy issue in large workspaces, a three-level partition-boundary-regression architecture is designed. The workspace, with a ± 20° azimuth angle and 16 layers of drill pipes, is divided into 12 sector cells. The boundary layer uses cubic polynomial error compensation, while the internal cells employ spatial continuity error prediction based on the RBF kernel function. Experimental results show a significant reduction in grasping errors after compensation (X/Y/Z ≤ 4.5/2.5/1.5 mm), with an accuracy improvement of 82%. Additionally, an industrial downhole test has completed 2448 rod pickings with a success rate of 98.5%. This study offers a novel solution for precision control of robots in highly constrained environments.

Design of a Multi‐Sensor Integrated Control System for Vehicle‐Mounted Tunnel Lining Inspection With Real‐Time Velocity and Posture Tracking

Wed, 27 May 2026 05:37:04 -0700

ABSTRACT

This study presents a holistically integrated multi-sensor control system for vehicle-mounted tunnel lining inspection, seamlessly combining Automated Track Vehicle (ATV) technology with robotic-arm posture tracking within a synergistic framework. The system achieves automated velocity regulation and millimeter-level positioning accuracy, significantly enhancing inspection efficiency and operational safety. Key innovations include: (1) a coupled kinematic/dynamic model of the vehicle-arm system to capture motion coupling effects; (2) an optimized feedback control architecture incorporating an Auto-Disturbance Rejection Controller (ADRC) with detailed design, tuning, and stability analysis; (3) real-time data transmission via industrial Ethernet and the Modbus/TCP protocol (with average latency 1.54 ms, ≤ 2 ms); (4) a multi-sensor fusion logic based on extended Kalman filter (EKF) for dynamic posture correction. Experimental validation confirms that the system maintains a dynamic deviation of ≤ 8 mm/s at operational speeds of 1–5 km/h, keeps the antenna-to-lining distance at 100 ± 20 mm, and ensures Ground Penetrating Radar (GPR) signal integrity at standoff distances ≤ 0.25 m. This research establishes a robust technological foundation for next-generation autonomous tunnel inspection systems and represents a significant advancement in the robustness of non-destructive testing methodologies for critical infrastructure.

Kalman Filter–Based Sensor Fusion for Navigation of Holonomic Unmanned Ground Vehicles

Hassan Ul Haq, Aminuddin Qureshi, Abdul Qayyum Khan — Wed, 27 May 2026 05:37:04 -0700

ABSTRACT

Autonomous unmanned ground vehicles (UGVs) require accurate and reliable navigation, capable of working in adverse conditions for secure mission completion. Navigation modules such as the Global Positioning System (GPS) sometimes deviate in outdoor environments or fail in indoor environments. The degradation in navigation leads the UGV to deviate from its desired position. This paper addresses the challenge of interruption in navigation during a mission. The sensor fusion scheme using the estimation architecture of Kalman Filter (KF) enables the robot to navigate itself by fusing the data from GPS, encoders and Inertial Measurement Unit (IMU). The scheme navigates the robot within practical limits during the GPS denial. Following a review of the Meccanum Wheel Robot's model dynamics and kinematics, we synthesized the KF-based sensor fusion scheme. Simulations and experiments are performed on different trajectories to evaluate the proposed scheme, with Root Mean Square Error as a quantitative measure. Results demonstrate the efficacy of KF-based sensor fusion for navigation in the presence of GPS denial, thereby ensuring the successful completion of the mission.

Formation Control of UAVs Based on Dynamic Vector Velocity Obstacle Method

Yimei Chen, Shichang Wei, Baoquan Li, Xiaolong Liang, Tao Dai — Wed, 27 May 2026 05:37:04 -0700

ABSTRACT

This paper proposes a multiple unmanned aerial vehicle (multi-UAV) formation obstacle avoidance strategy based on the dynamic vector velocity obstacle (DVVO) method, aiming to address the design challenges of the VO method in three-dimensional (3D) dynamic space applications. By considering the relative position and velocity between the UAV and obstacle, a dynamic avoidance plane (DA-Plane) is constructed, which can accurately reflect the collision risk of UAVs in 3D space. On this basis, a dynamic vector velocity obstacle space is designed, and the optimal constant critical escape velocity is selected outside this space to accomplish the obstacle avoidance task, thereby ensuring the smoothness of the flight process. Subsequently, this paper extends the DVVO method to multi-UAV formation based on fuzzy control and the virtual spring algorithm, and designs a differentiated obstacle avoidance strategy to ensure the safe operation of multi-UAV formation in dynamic environments. Simulation and real-world experiments demonstrate that the proposed method enables multi-UAV formation to effectively avoid dynamic obstacles in 3D space and reach the target in a desired formation shape. Compared to the citation algorithm, the DVVO method shows superior performance in terms of smooth motion and computational efficiency. This study effectively simplifies the complex obstacle avoidance problems of multi-UAV formation in 3D dynamic environments, demonstrating significant potential for applications.

A Novel Crawling Robot Based on the Hexagonal Mesh Structure and Enhanced PID Control Strategy

Meng Hongjun, Ren Yuke, Wei Jingtao, Zhang Shupeng, Zhang Wei — Wed, 27 May 2026 05:37:04 -0700

ABSTRACT

The locomotion of crawling robots is similar to that of caterpillars, relying on foot adhesion and body contraction to ensure flexible movement without compromising stability. However, most existing pneumatic soft crawling robots are incapable of simultaneously achieving forward, backward, turning, and climbing capabilities. To address this issue, this paper proposes a novel soft crawling robot that combines a hexagonal mesh structure with an adhesion mechanism and the enhanced PID control strategy. The innovative structural design ensures the implementation of the robot's locomotion functions. Notably, this study represents the first application of the Whale Optimization Algorithm to optimize the parameters of a PID controller for crawling robots. The results indicate that the optimized controller achieves significantly shorter rise time, overshoot, peak, and settling time compared to other intelligent optimization algorithms. During the experimental phase, a road circuit consisting of straight movement, lateral parking, reverse entry, and S-shaped turns successfully validated the robot's capabilities in forward, backward, and turning bending locomotion. Additionally, the robot demonstrated its ability to climb inclined surfaces at angles of 10°, 30°, 45°, and 60°, as well as 90° glass surfaces. Experimental results confirm that the proposed soft crawling robot exhibits exceptional locomotion capabilities and holds significant practical potential. The integration of its unique hexagonal mesh structure with an enhanced PID control strategy enables faster and more precise bending movements, offering both theoretical insights and practical foundations for future research in crawling robot control.

Optimized Object Detection in Road‐Vehicle Images Using Approximate Tree Multiplier‐Based Daubechies Wavelet Transform and YOLO Variant

Venkatnarayanan Chinnaraj, Somasundaram Devaraj — Wed, 27 May 2026 05:37:04 -0700

ABSTRACT

Object detection in road-vehicle images presents significant challenges due to variations in view angle, weather conditions, shooting height, noise, low contrast, geometric distortions, and atmospheric effects. The research proposes a novel methodology integrating Deep Learning and optimization techniques to enhance object detection performance. To address image quality issues, a Gaussian Blur with a Bilateral filter is employed for noise reduction and contrast enhancement. For feature extraction, a Lightweight Tree Multiplier–based Discrete Daubechies Wavelet Transform Convolutional Network is introduced, utilizing an advanced wavelet transform approach to capture both spatial and spectral features effectively. Feature selection is optimized using Adaptive Quantum-Informed Recursive Multiscale Feature Selection, incorporating Quantum-Informed Recursive Optimization to retain the most relevant features while reducing redundancy. For object detection, the extracted features are processed through the Improved Lightweight Harris Hawks YOLOv11 Network, for efficient and high-speed object detection. Improved Harris Hawks Optimization is also applied to optimize the loss function, enhancing detection accuracy. The outcomes of the implementation reached a precision rate of 99.8% and an accuracy rate of 99.7%. The model that proposed intends to be a powerful tool for the detection of road vehicles in difficult images, giving short processing time together with high-detection efficiency and reliability.

Nested Actors and Critics With Uncertainty Parameter in Robot Path Planning

Yuwan Gu, Fang Meng, Yan Chen, Ronghai Miao, Jie Hao, Jidong Lv — Wed, 27 May 2026 05:37:04 -0700

ABSTRACT

Rapid advances in robotics sharpen the challenges of path planning in complex, dynamic settings, where adaptability, robustness, and learning efficiency remain limiting. Although TD3 performs well on difficult tasks, efficient and stable policy optimization under high uncertainty is still open. We propose NACUP (nested actors and critics with uncertainty parameter), a TD3-based framework that nests actors to hierarchically generate actions, decoupling complex control and improving task success. An uncertainty-quantification parameter is introduced into the critic to realize a probabilistic inference–based robustness mechanism, stabilizing value estimates and decisions under extreme conditions. We validate NACUP in a high-fidelity 3D point cloud simulator and benchmark against DDPG, SAC, and TD3. NACUP consistently improves cumulative reward and learning efficiency, and reduces collision rate by 29.4% relative to TD3. These results indicate that nesting policies with uncertainty-aware critics provide an effective solution for robot path planning in complex environments.

Real‐Time Detection of Undesired Human Interventions in Robotic Work Cells Using a Convolutional Neural Network‐Based Novel Architecture and Reliability Analysis With Explainable Artificial Intelligence

Merdan Ozkahraman — Wed, 27 May 2026 05:37:04 -0700

ABSTRACT

This study presents a task-specific deep-learning framework for real-time detection of undesired human interventions in robotic work cells, based on a customized convolutional neural network (CNN) architecture termed MerdanNet. Unlike general-purpose lightweight models, MerdanNet integrates progressive dropout, systematic batch normalization, and compact hierarchical depth to ensure reliable performance in low-data, safety-critical environments. The data set comprises 588 original images of human hand, upper body, and foot categories, expanded to 2940 samples through targeted augmentation (mirroring, grayscale transformation, and controlled noise). Three models, MerdanNet, YOLOv8, and MobileNet, were trained and evaluated using accuracy, precision, recall, and F1-score metrics; MerdanNet achieved the highest performance, with an accuracy of 98.76%. Beyond static evaluation, the framework was validated in a closed-loop robotic setup where detections directly triggered safety actions. Experiments across 90 trials confirmed consistent activation of slowdown and emergency stop functions with an average end-to-end latency of 92 ms (95th percentile: 124 ms), well within industrial safety thresholds. Interpretability was assessed using Grad-CAM and LIME, which revealed meaningful attention patterns and provided diagnostic insights, though quantitative explainable artificial intelligence (XAI) evaluation remains a target for future work. While the data set is limited in diversity, the study highlights this as a current limitation and outlines future directions, including expanded data collection, synthetic stress-test data sets, bounding box annotations for detector benchmarking, and transfer learning approaches. Overall, the findings demonstrate that combining tailored CNN architectures with XAI and closed-loop validation can yield deployable, transparent, and robust safety modules for industrial robotic environments.

Design, Development, and Field Test Analysis of a Multiarm Tomato Harvesting Robot

Wed, 27 May 2026 05:37:04 -0700

ABSTRACT

Tomato is one of the most widely cultivated vegetables globally; however, traditional hand-picking methods are inefficient, and thus, automated harvesting systems are becoming increasingly necessary. In response, this paper proposes the design of a multiarm collaborative picking robot system aimed at automating tomato harvesting. The system incorporates a three-axis grasp-pick-place mechanism, enabling asynchronous operation via a single controller, thereby enhancing harvesting efficiency. Additionally, a visual perception system has been developed for tomato recognition and localization, which includes fruit detection and the calculation of optimal picking points. Experimental results demonstrate that the tomato recognition rate exceeds 90%, with an average picking time of 4.62 s per fruit. The efficiency of the three-arm cooperative operation is 1.96 times greater than that of a single arm, and the overall picking success rate is 91.00%. These findings highlight the system's promising application potential and provide a foundation for future research to advance intelligent harvesting technologies for fruits and vegetables.

Biomimetic Design and Performance Analysis of a Magnetic H‐Shaped Microrobot

Sanxiu Wang, Xiaopeng Ni, Shuo Wang, Chun‐yi Su — Wed, 27 May 2026 05:37:04 -0700

Abstract

Magnetically actuated soft microrobots have demonstrated significant advantages in the biomedical field due to their adaptability, simplicity, and high degrees of freedom. Inspired by nature, researchers are also currently working on combining bionic technology with soft microrobotics. This paper presents a bionic H-shaped micro soft robot (H-MSR) driven by a magnetic field. The robot is designed based on the movement patterns of cats in nature and is made of composite magnetic materials. First, a quasi-static analysis of the H-MSR was performed to deduce its linear motion gait mechanism, which was then verified by Material Point Method (MPM) simulation. Subsequently, to investigate the factors influencing the motion velocity of the H-MSR, the effects of different magnetic field strengths and frequencies, various H-MSR sizes, alternative robot shapes, and slopes on its motion performance are experimentally examined for optimal design and control. In addition, this paper explores the steering motion principle of the H-MSR and develops two different path planning strategies (S-shaped and U-shaped) for path tracking experiments. Experimental results demonstrate that the velocity of the robot increases proportionally with both the magnetic field strength and the actuation frequency. Moreover, the velocity is positively correlated with leg width and inversely correlated with body thickness. The microrobot exhibits rapid linear locomotion, achieving a maximum speed of approximately 5.67 mm/s, exceeding half of its body width, which surpasses that of conventional inchworm-like robots. In addition to effective movement on flat surfaces, the H-MSR is also capable of climbing inclined planes with slopes ranging from 0° to 20°, indicating strong propulsion and adaptability. Furthermore, the robot exhibits flexible steering performance, enabling it to execute arbitrary curved trajectories within a two-dimensional plane.

Autonomous Navigation in Large‐Scale Underground Environments Based on a Purely Topological Understanding of Tunnel Networks

Lorenzo Cano, Danilo Tardioli, Alejandro R. Mosteo — Wed, 27 May 2026 05:37:04 -0700

ABSTRACT

This work presents a non-geometrical navigation approach based on a purely topological understanding of underground environments. By conceptualizing subterranean scenarios as a set of tunnels that intersect with each other, and taking a navigation approach based on topological instructions, we simplify the navigation problem to the sequential execution of human-understandable instructions. This approach is built on top of a lightweight Convolutional Neural Network (CNN) that processes the readings of a 3D LiDAR sensor and produces an estimation of the angular positions of the surrounding tunnels with respect to the robot. As a result of this approach, our method can navigate these underground environments by only being provided with the necessary topological instructions, without the need for a map, or for building one during navigation. Additionally, it can also rely on a lightweight graph representation of the environment. This graph can be either defined by the user, generated during navigation or explicitly built in an exploration task. To showcase these capabilities, this article provides an experimental evaluation of the method both in simulation and in a real environment.

A Season‐Robust Long‐Term Localization Method Using Trunk Semantic Features in Dynamic Orchard Environments

Enbo Liu, Wei Tang, Anmin Huang, Zeyu Zhou, Renyuan Zhang — Wed, 27 May 2026 05:37:04 -0700

ABSTRACT

Localization is pivotal for enabling mobile robots to perform precision agriculture in orchards. However, dynamic factors such as seasonal variations present significant challenges for achieving long-term localization. In dynamic orchard environments, tree trunks remain static and unaffected by seasonal changes, making them ideal landmarks for localization in dynamic scenarios. Therefore, we propose a novel season-robust long-term localization method using trunk semantic features. Firstly, we introduce a semantic extraction module that integrates camera and LiDAR data to capture tree trunk semantic features within a simultaneous localization and mapping (SLAM) framework, thereby generating lightweight static maps that remain invariant to seasonal fluctuations. Upon re-entering the orchard environment, the robot utilizes a particle filtering framework to fuse LiDAR and GNSS data for long-term localization based on the lightweight map. This process involves performing Normal Distribution Transform (NDT) registration on the original point cloud to predict particle states, comparing the trunk point cloud with the lightweight map to compute particle weights from LiDAR measurements, and optionally integrating GNSS measurements to enhance localization accuracy. Finally, we conducted extensive field data collection over a prolonged period in a real orchard environment, encompassing experimental data from both winter and summer. The performance of our proposed localization method, along with its capability to mitigate the effects of seasonal variations, was validated through localization experiments conducted across different seasons. Quantitative results indicate that the average error of the fused localization is 0.16 m, and the root mean square error (RMSE) is 0.18 m.

Guidance and Flocking Algorithm for a Distributed FW‐UAV Swarm System Under Coordinated Surveillance Missions in an Occluded Environment

Muhammad Imran Baig, Zhen Ziyang, Umair Javaid — Wed, 27 May 2026 05:37:04 -0700

ABSTRACT

In this study, an adaptive guidance and flock control (AGFC) algorithm is proposed for real-time navigation of a distributed fixed-wing unmanned aerial vehicle (FW-UAV) swarm system for coordinated surveillance missions (CSM) in an occluded environment. Under the concept of distributed guidance, a vector field-based intelligent swarm guidance (VF-ISG) model is designed, integrating attractive features for surveillance and repulsive features for obstacle avoidance upon detection. The repulsive VF feature enables intelligent path selection, dynamically adjusting trajectories based on the distance and angular relationships between the surveillance path and obstacle positions. In addition, we introduce gain functions to ensure a smooth transition between attractive and repulsive features, modulating the contribution of each VF component in real-time. Geometric factors during flight, such as the relative distances and angles between the FW-UAV, targets, and detected obstacles, parameterize these gain functions, enabling smooth and collision-free navigation of each FW-UAV. Later, leveraging the proposed VF-ISG model, a flock control algorithm with active obstacle avoidance (FC-AOA) and collision avoidance capabilities among swarm FW-UAVs is formulated for flock formation in complex environments. The adaptive parameters are introduced in the proposed FC-AOA algorithm, enabling flexible flock formation to maintain a safe distance from obstacles with minimal deviation from the CSM path. Mission-specific normalized weights combine the VF-ISG and FC-AOA schemes, maintaining stable performance. We design a CSM scenario in numerical simulation that complements navigation over unstructured terrain with occluded paths. A comparative numerical simulation with a hybrid flocking baseline demonstrates that the proposed AGFC algorithm significantly improves path feasibility, reduces collision risk, and maintains formation during occluded path traversal. Finally, we perform a hardware-in-loop experiment to validate the effectiveness and applicability of the proposed AGFC algorithm in actual CSMs.

Autonomous Grading Maneuver Determination Algorithm for Electric Dozers

Önder Halis Bettemir — Wed, 27 May 2026 05:37:04 -0700

ABSTRACT

State-of-the-art autonomous grading algorithms can handle small regions and simple tasks due to their high computational loads. To address the aforementioned literature gap, this study presents an algorithm that heuristically calculates the excavation, transportation, dumping, and return maneuvers required for autonomous excavation. The algorithm is particularly developed for electric dozers with limited power. The algorithm starts from the opposite side of the dump zone and begins excavation from the local maximum height to avoid upward excavation and hauling to minimize the resistive forces acting on the dozer. The excavation depth and hauling capacity were defined so as not to exceed the electric dozer's power. Excavation of an area of 45 m wide and 60 m long was simulated by considering the effects of the open circuit voltage drop of the batteries. Simulations were completed between 16 and 64 s, depending on the configuration of the electric dozer. Regression analysis revealed that computation time increases linearly with an increase in width and quadratically with an increase in length. Simulations demonstrated that the proposed algorithm is suitable for electric dozers with low rimpull.

Variable Structure Adaptive Soft Robot for Complex Pipeline Environments

Wed, 27 May 2026 05:37:04 -0700

ABSTRACT

At present, most pipeline robots can only work on a specific type of pipeline. However, the types of pipelines are always changing, which makes it difficult to meet diversified needs. Thus, a variable structure adaptive soft robot (VSASR) is proposed in this paper. The VSASR is driven by a coupled flexible actuator consisting of a flexible cantilever and a flexible track. The VSASR can change the driver structure according to different pipeline environments to adapt to a variety of complex pipeline environments. The VSASR has strong flexibility and adaptability; it can climb on the inner and outer walls of pipelines by changing the driver structure and has excellent performance in many kinds of unstructured complex pipes that may contain obstacles, sudden turns, and sudden changes in the diameter. Furthermore, The VSASR provide a feasible scheme for pipeline robots when they face various and complex pipeline environments.

Issue Information

Wed, 27 May 2026 05:37:04 -0700

Journal of Field Robotics, Volume 43, Issue 4, Page 2549-2551, June 2026.

Dynamic Environment Adaptive Path Planning for Mobile Robots: A Hybrid Enhanced Path‐Planning Approach

Junxu Hou, Hong Wang, Eryi Dong, Tao Wang, Fengkai Kang, Boyan Jiang — Tue, 26 May 2026 06:21:25 -0700

ABSTRACT

With the rapid advancement of mobile robotics, the demand for safe and efficient path planning has become increasingly prominent. This research aims to address the challenges of path redundancy and the lack of stable obstacle avoidance strategies encountered by mobile robots during path planning in dynamic environments. A novel hybrid enhanced path-planning algorithm is proposed, which integrates obstacle information, robot safety data, path-simplification techniques, and dynamic-obstacle avoidance strategies. By combining global and local path planning and introducing a path evaluation system based on robot status and dynamic-obstacle motion information, the algorithm achieves efficient and flexible path planning. The effectiveness and feasibility of the algorithm are validated through simulation experiments and real-world testing. The results demonstrate that the algorithm can achieve safe and efficient path planning under different speeds and dynamic-obstacle scenarios, significantly reducing the frequency of path switching and waiting times, thus enhancing the efficiency and autonomy of the robot's actual scene navigation. In the experimental scene, the overall travel time is saved by 8.3%, the traffic obstacle area time is saved by 48.9%, and the obstacle avoidance route is stable and efficient. Compared with the current advanced algorithm, the proposed algorithm can improve the driving efficiency of the robot by more than 12%, and the robot's behaviour is more secure in the face of dynamic obstacles. This research provides an effective solution for mobile robot path planning in complex environments, with significant theoretical and practical implications.

A Depth Control Method for Full Ocean Depth AUV

Yueming Li, Enrui Sui, Jian Cao, Ye Li, Yanqing Jiang, Bo Wang, Teng Ma — Mon, 25 May 2026 05:56:35 -0700

ABSTRACT

This paper presents an integrated vertical control method for online identification and compensation of residual buoyancy, designed for full-ocean-depth (FOD) autonomous underwater vehicles (AUVs) that rely on vertical thrusters for depth-keeping or height-keeping hovering tasks. To address the residual buoyancy drift caused by vehicle hull compression and seawater density variations under extreme hydrostatic pressure, the proposed method constructs a condition-triggered bidirectional switching framework between velocity and position control modes: During the large-error stage, a velocity control mode is employed to rapidly drive the vehicle into a low-speed region. Once the depth error and vertical velocity satisfy predefined threshold conditions, the system switches to a position control mode. In this mode, the equivalent residual buoyancy is estimated online via thruster force equilibrium and applied as feedforward compensation to achieve precise and stable hovering. If operating conditions change, the switching and identification mechanisms can be retriggered to maintain control performance. The proposed method was validated through test-tank experiments and sea trials for the 1000-, 7000-, and 11,000-m classes using the Wukong FOD AUV. Field results demonstrated that the system achieved average height tracking errors of 0.0124 and 0.0668 m in the test tank and 11,000-m class trials, respectively. These results verify the effectiveness and engineering applicability of the proposed method in rejecting unknown residual buoyancy disturbances and achieving stable hovering in hadal environments.

Pose Estimation Accuracy Improvement Using Different Orientation Representations With Neural Networks: Case Study for the VIVE HTC Tracker

Mon, 25 May 2026 05:30:49 -0700

ABSTRACT

In robotic applications, the HTC VIVE tracker is frequently used for Learning from Demonstration. This solution and similar devices are not industrial-grade, meaning that their accuracy in tracking movements in three-dimensional space needs to be refined to ensure it is sufficient for programming precise robot positioning tasks. Several different methods are often used to improve position tracking accuracy, such as polynomial correction and neural networks. Various methods of parameterizing position and orientation are also frequently used, such as Euler angles or quaternions, although trade-offs between compactness and numerical stability mean that they are suitable for different correction methods. In this study, we explore four different ways of representing the pose orientation (axis-angle representation, quaternion, rotation matrix, Zhou representation) for the purpose of implementing pose tracking accuracy correction for the HTC VIVE tracker. The paper investigates the applicability of these representations for the Neural Network correction methods and compares the results with the classical polynomial correction method. As part of the study, three experiments were conducted involving measurements of the actual and measured positions of the robot and the tracker. An industrial UR5e robot arm from Universal Robots was used as the reference system for collecting measurement data, with an HTC VIVE tracker mounted on its wrist. The obtained results confirm that both the representation and neural network architecture significantly influence calibration effectiveness of HTC VIVE tracker. The results of the experiments showed that the Zhou parametrization of the orientation, combined with neural network rectification, performs best and results in a 17-fold improvement in the pose estimation accuracy of the HTC VIVE tracking system. The PMC algorithm offers a valuable alternative when fast calibration is required, providing significant accuracy improvements with minimal computational cost.

Deep Reinforcement Learning Based Autonomous Decision‐Making for Cooperative Uncrewed Aerial Vehicles: A Search and Rescue Real World Application

Thomas Hickling, Maxwell Hogan, Abdulla Tammam, Nabil Aouf — Mon, 25 May 2026 05:29:31 -0700

ABSTRACT

This paper presents the first end-to-end framework that combines guidance, navigation, and centralized task allocation for multiple UAVs performing autonomous search-and-rescue (SAR) in GNSS-denied indoor environments. A twin delayed deep deterministic policy gradient controller is trained with an artificial potential field (APF) reward that blends attractive and repulsive potentials with continuous control, accelerating convergence and yielding smoother, safer trajectories than distance-only baselines. Collaborative mission assignment is solved by a deep Graph Attention Network that, at each decision step, reasons over the drone-task graph to produce near-optimal allocations with negligible on-board compute. To arrest the notorious Z-drift of indoor LiDAR-SLAM, we fuse depth-camera altimetry with IMU vertical velocity in a lightweight complementary filter, giving centimeter-level altitude stability without external beacons. The resulting system was deployed on two 1 m-class quad-rotors and flight-tested in a cluttered, multi-level disaster mock-up designed for the NATO-Sapience Autonomous Cooperative Drone Competition. Compared with prior DRL guidance that remains largely in simulation, our framework demonstrates an ability to navigate complex indoor environments, securing first place in the 2024 event. These results demonstrate that APF-shaped DRL and GAT-driven cooperation can translate to reliable real-world SAR operations.

QRIVAS: Quadruped Robot‐Based Intelligent Visual Acquisition System for Bridge Component Inspection

Wed, 20 May 2026 00:27:09 -0700

ABSTRACT

Bridge inspection constitutes a critical yet labor-intensive task in civil infrastructure maintenance, often requiring access to confined, structurally complex environments. Conventional manual inspection suffers from low efficiency and high operational risks, and the robotic solutions encounter limitations in GNSS-denied and low illumination environments with texture-deficient surfaces. This study proposes QRIVAS (quadruped robot based intelligent visual acquisition system), an autonomous framework for structural component image acquisition without relying on prior maps to reduce the workload for manual close-proximity inspection. QRIVAS integrates 3D LiDAR SLAM with real-time semantic segmentation, enabling reliable navigation and precise structural component identification. In this paper, we focus on the exploration and inspection of bridge column—a representative and critical structural component of bridge systems. Experimental validation across simulated concrete railway viaducts and physical laboratory-scale bridge models (1:3 scale) shows that QRIVAS achieved 100% navigation success rate in simulation environments and 96.7% average task navigation success rate across six bridge columns in laboratory-scale bridge specimen. Compared to existing research, QRIVAS shows consistent performance improvements across varying tolerance conditions (25 cm and 50 cm radius), maintaining robust operation under both flat concrete floor and rough artificial grass terrain conditions. This work demonstrates the potential of AI-driven robotic systems to transform traditional infrastructure maintenance practices.

Fuzzy Based Control Strategy and Dynamic Torque Adjustment in a Four Wheeled Coconut Tree Climber

Mon, 18 May 2026 02:14:52 -0700

ABSTRACT

Inherent dangers and limitations of manual labor led to the development of coconut tree climbing robots as a safer and more efficient coconut farming method. Coconut tree climbing robots face significant challenges due to structural constraints, control complexities, and the unique dimensions of coconut trees. Limited research exists on effective designs, with many struggling to balance accuracy, speed, and adaptability. The study presents a novel control law tailored to critical climbing scenarios, enhancing both stability and efficiency. The proposed method ensures reliable ascent and descent by dynamically adapting to challenges such as tree inclines and varying diameters, switching control logic based on situational demands. Key climbing scenarios, including normal cases, wheel-out-of-contact situations, and wheel-at-wedge cases, were considered. A fuzzy inference system was integrated to further refine the control strategy, dynamically adjusting torque based on real-time parameters like inclination, current, encoder values, and diameter variations, thereby optimizing performance across diverse conditions. Detailed static and dynamic analyses shaped the development of a four-wheeled climber, equipped with gas springs to maximize traction. Simulations validated the proposed control law, achieving a steady state climbing velocity of 0.2 m/s and a displacement of 4 m. Observed transient oscillations and initial peak angular velocities, ranging from 10−16 ${10}^{-16}$ to 0.5 rad/s, underscore the importance of accounting for real-world dynamics. The climber was tested in three different scenarios and achieved a 96.67% overall success rate, completing 29 out of 30 trials. It performed flawlessly in two conditions and had a single failure on a straight tree with varying diameter.

Improved ESO‐LOS Guidance Strategy for AUV: Theory and Experiment Validation

Zijian Zhu, Peizhou Du, Guocheng Zhang, Ye Li — Mon, 18 May 2026 01:57:42 -0700

ABSTRACT

To address autonomous underwater vehicle (AUV) path tracking under time-varying disturbance, this paper proposes an Extended State Observer (ESO)-based Line-of-Sight (LOS) guidance strategy that accounts for time-varying ocean currents, model uncertainties, and drift angles. The disturbances are treated as a lumped term without assumptions on their magnitude or variation. A kinematic error model incorporating these effects is established, and an ESO is designed for real-time disturbance estimation and compensation. An adaptive look-ahead distance is introduced to enhance responsiveness to the AUV's tracking state. A virtual control input is then integrated into the traditional LOS framework to formulate an improved guidance law, forming a closed-loop cascaded system of tracking and estimation errors. Using input-to-state stability (ISS) theory and the cascaded systems theorem, the overall system is proven to be ISS, and the ultimate bound of the cross-track error is derived under bounded disturbances. The proposed method was compared with several existing approaches in simulations, demonstrating its superiority. Finally, three field experiments were conducted to track straight-line, polyline, and circular paths, respectively, achieving a mean cross-track error of no more than 0.48 m across three tested path types and an average estimation error of ESO no greater than 0.0163 m.

Modeling, Identification, and Validation of a Vector Propelled Amphibious Vehicle

Ye Wang, Sihuan Feng, Lingbo Zhang, Jiaqi Chen, Huilong Yu, Junqiang Xi — Mon, 18 May 2026 01:55:12 -0700

ABSTRACT

High-fidelity models play an essential role in advancing the structural optimization and motion simulation of amphibious vehicles. However, the complexity of hydrodynamics poses significant challenges in dynamic modeling, parameter identification, and experimental validation. To address these challenges, this research derives a six-degree-of-freedom dynamic model for a vector propelled amphibious vehicle based on maneuvering theory, including a dedicated propulsion system dynamic model. Given the system identification challenges posed by the highly coupled multi-parameter dynamics, a systematic experimental framework is devised, featuring decoupled measurements of the propulsion and maneuvering dynamics. A staged parameter identification methodology integrating the genetic algorithm and the least squares method is proposed. The methodology initially identifies a subset of parameters through decoupled reduced-order models, and subsequently performs a systematic identification of the remaining parameters based on the complete coupled model. For model validation, a simulation platform based on numerical integration methods is developed, with real-time visualization implemented in Unreal Engine 4 (UE4). Field tests and hardware-in-the-loop (HIL) validation demonstrate that the established model with identified parameters can accurately capture the motion characteristics of the amphibious vehicle.

Design and Kinematic Analysis of a Six‐Wheeled Robot With a Passive Suspension for Integrated Terrain Adaptability and Vibration Mitigation

Xiaoliang Zhang, Longjin Liang, Pingyi Liu, Ying Chen, Hengda Li, Liang Sun — Wed, 13 May 2026 23:58:17 -0700

ABSTRACT

This paper presents a six-wheeled mobile robot equipped with a novel passive adaptive suspension system. By integrating spring dampers into the bogies, the system yields two distinct configurations: a tandem lateral swing suspension and a parallel longitudinal swing suspension. Both designs allow the bogies to pivot relative to the robot body in response to low-frequency terrain undulations, while the integrated spring dampers effectively absorb high-frequency excitations from the ground. This mechanism ensures continuous wheel-terrain contact on complex terrain while effectively reducing vibrations at high speeds. To assess motion smoothness and posture stability, the influence of spring-damper deformation on the robot's attitude was first quantified. Subsequently, kinematic models of the centroid and spatial posture were established. These models determine the maximum centroid region radius and condition-specific inverse solutions, and their validity was confirmed through multi-body simulations, demonstrating high predictive accuracy. Field experiments show that the novel adaptive suspension reduces vertical chassis acceleration by approximately 25% compared with a rigid suspension. The integration of three adaptive suspension units significantly enhances posture stability under extreme terrain conditions, improves step-climbing performance, and enables a payload-to-weight ratio of 1.41, which exceeds that of most existing wheeled platforms. Overall, the design resolves long-standing trade-offs among terrainability, vibration attenuation, and payload capacity, making it well-suited for demanding tasks such as hilly farmland operations, disaster relief, and resource exploration.

BM3D‐Based Optical Flow Tracking for Enhanced Visual Simultaneous Localization and Mapping Systems in Mobile Robotics

Yu Xin Qin, Wei Jie Zhou, Liang Long Chen, Yu Chen — Tue, 12 May 2026 21:43:23 -0700

ABSTRACT

In existing research on SLAM systems, the corner point detection problem of the vision front-end is usually abstracted as a feature recognition problem. However, traditional corner point detection algorithms are too sensitive to noise and susceptible to scale variations and luminance fluctuations, failing to fully and effectively capture the image information obtained from the vision front-end sensors. To address this challenge, this paper proposes a new vision front-end based ORB-SLAM3 method, hereinafter referred to as BLO-SLAM. The following three main innovations are proposed: (1) An optimized system model incorporating the BM3D denoising strategy, which significantly enhances feature extraction efficiency and improves edge feature-point matching in low-texture and low-light environments; (2) To tackle the challenge of accurately capturing local pixel motions in scenarios involving rapid or minimal motion, an improved Lucas-Kanade (LK) optical flow tracking algorithm is proposed. This enhancement reduces feature-point matching errors caused by camera displacement and rotation, thereby improving the robustness of the vision front-end; and (3) The application of BLO-SLAM to multi-robot systems. Extensive evaluations on public datasets and self-constructed datasets demonstrate that the proposed method effectively enhances feature matching efficiency and reduces the influence of irrelevant feature points. As a result, the proposed system improves feature matching accuracy while suppressing the influence of irrelevant feature points, leading to a more robust and reliable map representation.

Traversability Risk Assessment and Path Planning for Off‐Road Autonomous Vehicles in Winter Conditions

Nan Wang, Xiang Li, Shilong Xu, Youkang Zhang, Jixin Wang, Dongxuan Xie — Tue, 12 May 2026 21:39:19 -0700

ABSTRACT

While off-road autonomous vehicles have achieved substantial deployment success, winter conditions introduce unprecedented operational challenges, potentially leading to critical failure modes such as slipping, rollover, collision, and sinking. This paper presents an integrated technical solution to address these winter navigation challenges. First, a vehicle speed prediction model is developed by fitting probability distributions and training a Multilayer Perception to forecast key parameters of the probability density function. For traversability risk assessment, mechanical principles are first leveraged to analyze the inherent correlations among hazard events, terrain characteristics, and vehicle dynamics. A hybrid framework integrating a Variational Bayesian Network with a Long Short-Term Memory network (VBN-LSTM) is then constructed to predict the probabilities of hazard occurrences by jointly leveraging causal structural priors and temporal dynamics. Building on this, a joint probability model for hazard events and vehicle speed is established, explicitly accounting for their interdependencies to enable comprehensive traversability risk evaluation. Finally, the Hybrid A* algorithm is enhanced by integrating speed distribution prediction and traversability risk assessment, facilitating safer and more reliable navigation in winter off-road environments. The improved algorithm is validated in real-world winter terrains through comparisons with other algorithms. Experimental results demonstrate that the planned paths generated by the proposed approach outperform competitors in terms of estimated risk, path efficiency, and travel time.

A Critical Review of Reinforcement Learning Algorithms for Mobile Robot Path Planning

P. Ramya, P. Natesan, S. Venkatachalam — Tue, 12 May 2026 21:36:48 -0700

ABSTRACT

Mobile robots are increasingly deployed across industrial and service sectors, where autonomous navigation is required in both time-invariant, static environments and time-variant, dynamic environments. During navigation, robots must handle diverse obstacles, including fixed and moving objects, while minimizing travel distance, execution time, and collision risk. Although various machine-learning-based path planning approaches have been proposed to address these challenges, many depend on pre-collected data sets, and obtaining such data in real-time, unpredictable environments is difficult and often impractical. This review focuses on reinforcement-learning-based path planning, wherein mobile robots learn obstacle characteristics, path structure, and optimal policies directly from the environment through trial-and-error interaction, largely without relying on external training data. The study examines key challenges associated with autonomous navigation and analyzes reinforcement learning techniques in terms of their advantages, limitations, applications, performance metrics, obstacle categories, and obstacle avoidance mechanisms. A quantitative assessment of 58 selected papers reveals that 51 percent of the studies concentrate on local path planning, 32 percent on global planning, and 17 percent on hybrid approaches that integrate both planning strategies. These findings highlight a growing research shift towards data-efficient reinforcement learning approaches for dynamic and uncertain environments, while global planners remain prevalent in static settings. The insights provided in this review support researchers and practitioners in selecting suitable reinforcement-learning-based path planning algorithms aligned with specific environmental conditions and navigation requirements.

The Evolution of Autonomous Systems for Planetary Cave Exploration: A Review

Sarah Swinton, Daniel Mitchell, Jamie Blanche, Euan McGookin, David Flynn — Sun, 10 May 2026 23:36:15 -0700

ABSTRACT

The exploration of Subsurface Access Points (SAPs), such as lava tubes on the Moon and Mars, has gained significant interest due to their potential as stable environments shielded from surface radiation and temperature extremes. These sites are considered high-value targets for detecting water and signs of ancient life, and assessing their suitability as habitats for human missions. However, SAP exploration presents significant challenges, including navigating unknown and hazardous terrains, operating in low-light conditions, and managing limited communication capabilities. Recent advances in high-resolution imaging, Synthetic Aperture Radar, and other sensing technologies have enabled better identification and characterization of SAPs, providing critical data for potential exploration missions. This review presents a structured critical analysis of the challenges in planetary cave exploration and evaluates the state-of-the-art robotic platforms which offer a cost-effective and safe alternative to human exploration in hazardous environments, in addition to sensor technologies that aid the understanding of SAPs, such as seismic studies, geological characterization, and biosignature detection. This article emphasizes the advantages of multirobot teams in generating comprehensive data sets and improving mission resilience. By combining the unique capabilities of heterogeneous robotic systems, these teams represent a crucial step toward enabling the exploration of SAPs and advancing our understanding of planetary subsurface environments.

LMBC: Low‐Power Marine Benthos Counting Framework for Underwater Robotic Real‐Time Applications

Ning Wang, Haiyan Zhao, Tao Zheng — Sun, 10 May 2026 23:30:40 -0700

ABSTRACT

Accurate and efficient marine benthos counting is vital for aquaculture management and ecological monitoring, yet it remains highly challenging in underwater environments characterized by limited visibility, cluttered backgrounds, and the constraints of low-power robotic platforms. This paper proposes a low-power-deployed marine benthos counting (LMBC) framework, specifically designed for real-time, robust, and energy-efficient enumeration on embedded underwater robots. The LMBC framework integrates three task-oriented modules: (i) a lightweight prediction head optimized detector (LPHOD) that enhances tiny benthos detection while maintaining low computational complexity, (ii) a confidence ranking–cascade matching tracker (CRCMT) that improves identity preservation under occlusions and fluctuating detection confidence, and (iii) an accurate classification counting module that refines final counts by filtering spurious tracks and enforcing temporal consistency. Quantitative evaluations demonstrate that the proposed LPHOD achieves a detection accuracy of 86.2% mAP@0.5 on the DUO data set, while the CRCMT attains a HOTA score of 57.5 with substantially reduced identity switches compared with representative trackers. End-to-end counting experiments further show that LMBC achieves a root mean square error of 13.8 and a mean absolute percentage error of 17.5%, outperforming baseline tracking-based counting schemes. Implemented on an NVIDIA Jetson Xavier NX, the complete framework operates in real time at 13.3 FPS, validating its suitability for field-deployed autonomous underwater robots in aquaculture and ecological monitoring scenarios.

Simulation Platforms for Underwater Robotic Applications: Architectures, Capabilities, and Research Directions

Subham Kumar Shaw, Prasanna Muppidwar, Jagadeesh Kadiyam — Sun, 10 May 2026 23:28:29 -0700

ABSTRACT

As underwater robotics advances, simulation platforms have become essential for enhancing research, development, and operational strategies. These platforms are crucial because they lower vehicle fabrication costs, mitigate risks, and recreate intricate marine environments. This review offers a detailed examination of prominent underwater simulators, emphasizing essential factors such as environmental modeling, robot kinematics and dynamics, control systems and navigation, sensor emulation, communications and their integration with artificial intelligence and machine learning workflows. We have given special focus to hydrodynamic modeling, visual rendering, and the simulation of realistic underwater phenomena like turbidity, wave interactions, and marine habitat dynamics. The review also evaluates each simulator's effectiveness in operator training, technology validation, and planning for multi-robot missions. By comparing their designs, advantages, limitations, and specific applications, this study aims to assist in choosing suitable simulation tools. It also outlines potential developments to improve simulation accuracy and interoperability within underwater robotics.

AmphiHFW: Single Actuated Amphibious Mechanism With Undulation Fin and Leg‐Wheel Structure

Yang Tian, Shugen Ma, Takeki Ohira, Guoteng Zhang — Mon, 04 May 2026 22:47:07 -0700

ABSTRACT

Amphibious robots have garnered considerable attention and interest due to their versatility in various conditions. Recent advancements in hybrid mechanisms enhance robot adaptability but increase complexity, requiring more actuators and leading to intricate control systems and reduced robustness. This paper introduces a novel approach to amphibious mechanism design that integrates an undulation fin, legs, and wheels, all operated by a single actuator. With an analysis of several simple function mechanisms, a concept of the fin-leg-wheel combination is proposed. Through the analysis of the fin-wheel structure and the exploration of soft materials, a novel driving method with a simple mechanism design is proposed. Subsequently, a leg-wheel structure is adopted to enhance the robot's capabilities. Experimental results confirm that the developed robot prototype performs robustly under various conditions. Moreover, its ability to carry payloads significantly exceeding its own weight, combined with a low cost of transport, suggests that this mechanism can be readily adapted to enhance existing amphibious vehicles with multiple wheels.

Exploring the Use and Impact of Composite Materials in Robotics: A Systematic Review

Tue, 28 Apr 2026 12:04:46 -0700

ABSTRACT

Lightweight and high-strength materials are important in robotics, as structural design impacts efficiency, payload capacity, and energy consumption. Composite materials, with their superior stiffness-to-weight ratios and multifunctional properties, offer clear advantages over conventional metals and polymers. This review critically examines the use of composites in robotics, with a focus on their structural, active, and sensory functions. A systematic literature review based on an adapted PRISMA framework identified over 100 publications from 1988 to 2026, revealing continuous research growth and rising interest in soft robotics, piezoelectric composites, and carbon-based structures. In contrast, bioinspired systems have declined due to integration and manufacturing challenges. Despite the progress, major barriers remain, particularly scalability, long-term reliability, and cost. This work proposes a functional taxonomy of composites in robotics and outlines future directions, including sustainable bio-based materials, multimaterial additive manufacturing, and 4D-printed adaptive systems. By integrating materials science and robotics, this review provides a concise roadmap, in composite structures, for developing high-performance, multifunctional, and sustainable robotic technologies.

A Field‐Adaptive Mechanical Weeding System Coupling Oscillating Pneumatic Mechanism With Deep Learning for Intra‐Row Weed Control in Lettuce

Rui‐Feng Wang, Chang‐Tao Zhao, Yu‐Hao Tu, Zi‐Qiu Chen, Wen‐Hao Su — Mon, 27 Apr 2026 05:24:24 -0700

ABSTRACT

Intra-row weeding is a critical yet unresolved problem in precision horticulture, where crops and weeds exhibit tight spatial proximity and strong visual similarity under fluctuating field conditions. Addressing this challenge requires not only reliable crop-weed discrimination but also accurate crop-center localization tightly coupled with fast and safe actuation. This study introduces a field-adaptive intra-row weeding system that integrates an oscillating pneumatic mechanism with a purpose-designed deep learning framework, LettPointNet. LettPointNet leverages multi-scale feature fusion and a geometric center-point constraint to enhance spatial robustness, yielding 95.1% precision, 96.8% recall, 95.9% F1-score, 98.3% mAP50, and 90.6% mAP at a modest 7.7 GFLOPs, thereby supporting real-time embedded operation. Relative to lightweight YOLOv11n/12n baselines, LettPointNet improves F1-score and mAP by 3.4–3.9 and 6.5–6.6 percentage points, respectively. Conveyor-based evaluations (0.05–0.20 m/s; three weed-density levels) demonstrated 84.6% lettuce localization and 81.1% weeding performance, with response-surface analysis confirming significant interactions between speed and density. Polytunnel trials further validate system robustness, achieving 82.2% and 80.9% weeding rates under favorable and low-light conditions, respectively, with minimal crop damage (1.99% and 2.57%). Collectively, the results establish that precise perception-actuation coupling enables reliable, real-time intra-row weeding and offers a viable pathway toward automated and sustainable protected-crop management.

GFT‐VINS: Robust Visual–Inertial Localization via Geometric Feature Track Selection

Mon, 27 Apr 2026 05:08:54 -0700

ABSTRACT

Visual–inertial navigation systems (VINSs) are a cornerstone technology for autonomous robotics, leveraging visual measurements and inertial sensor data to achieve accurate state estimation through feature tracking. However, current VINS approaches often indiscriminately incorporate all feature tracks without distinguishing which ones meaningfully contribute to estimation quality. This oversight leads to suboptimal accuracy, reduced stability, and computational inefficiency. To address these limitations, we propose a novel visual–inertial framework that intelligently prioritizes informative feature tracks using normal epipolar geometry. Our method enhances state estimation by jointly optimizing feature appearance similarity and observation consistency across frames, formalized as a submodular partition optimization problem. Extensive experiments on public benchmarks demonstrate that our approach significantly outperforms five state-of-the-art methods, achieving a 26.1% improvement in accuracy, 43.3% higher stability, and real-time processing speeds of up to 125 FPS. These advancements highlight the efficacy of selective feature track utilization in overcoming the limitations of conventional VINS.

TriRock6W: Autonomous Mobile Robot With Six Wheels, Three Rocker Arms in Complex Environments

Shaocong Wang, Ting Wang, Shiliang Shao, Cunyi Pan, Kai Zhang, Jinguo Liu — Mon, 27 Apr 2026 05:06:11 -0700

ABSTRACT

Autonomous mobile robots are increasingly used to replace humans in long-term, high-frequency, and repetitive tasks. However, large-scale, high-dynamics, and diverse terrain significantly challenge the stable application of mobile robots in complex environments. In this paper, we design and develop TriRock6W, a mobile robot for outdoor complex environments. The robot adopts a unique configuration with six wheels and three rocker-arms that passively adapts to terrain, enabling enhanced mobility and obstacle-crossing capability. A tightly coupled LiDAR SLAM system is developed to integrate mapping and re-localization, where multi-source feature registration improves robustness and a keyframe-based feature map enhances re-localization efficiency. Moreover, a hierarchical obstacle avoidance strategy is employed to ensure safety during navigation in highly dynamic environments. For long-term application, we proposes a SLAM-based adaptive PID controller that enables autonomous charger docking, assisted by a V-shaped passive guiding mechanism for safe and stable docking process. Extensive experiments were conducted to evaluate the robot's capabilities, demonstrating reliable performance in complex environments. Notably, the robot underwent field trials over 8-months in densely populated complex environments, validating its suitability for long-term deployment.

Fault Tolerant Attitude Control for Spacecraft Considering Input Delay and Actuator Saturation: Theory and Experiment

Yasamin Naderi Koupai, Maryam Malekzadeh, Shahram Hadian Jazi — Mon, 27 Apr 2026 05:02:26 -0700

ABSTRACT

This study presents an advanced fault estimation and control strategy for spacecraft attitude control systems operating under time-varying input delays and actuator saturation. An adaptive fast terminal sliding mode fault-tolerant control (AFTSMFTC) framework is proposed to mitigate actuator faults, estimation errors, and input constraints. Two adaptive laws are designed to dynamically tune the control gains, thereby enhancing performance and robustness under fault conditions. A multipurpose sliding surface is formulated to ensure that the reaction wheels come to rest after maneuvering, improving momentum management and energy efficiency. Furthermore, a nonlinear disturbance observer (NDO) is developed to estimate external disturbances, unmodeled inertia variations, and time-varying input delays, while an integrated fault detection mechanism identifies actuator failures in real time. The closed-loop stability is rigorously proven using Lyapunov theory. The proposed controller and observer are validated through a high-fidelity spacecraft attitude control simulator, with results demonstrating superior performance and robustness compared to state-of-the-art methods.

Developing an Experimental In Situ Floating Buoy to Investigate the Impacts of Future Floating Wind Farms

Mon, 27 Apr 2026 04:51:52 -0700

ABSTRACT

Offshore wind farms are expanding rapidly in response to climate change. Along the French Mediterranean coastline, floating wind farms are favored, yet their environmental and socio-economic impacts remain poorly understood. The EolBio project aims to provide insights by developing and deploying an instrumented buoy to evaluate the potential effect of offshore wind farms on the marine local environment. Located in the Northwestern Gulf of Lion (Mediterranean Sea), the buoy operated over a 3-year period in the vicinity of the future floating wind farm, Eolmed. It integrates a suite of cutting-edge sensors to continuously record physical, chemical, and biological parameters, enabling real-time and long-term environmental characterization. This device represents a novel robotic approach to ecosystem monitoring in offshore environments. The in situ collected data, in addition to characterizing the modifications generated by the introduction of a floating structure, serve as inputs for trophic ecosystem models to simulate the spatiotemporal dynamics of marine food webs under different wind farm scenarios. This modelling work aims to anticipate the ecological and socio-economic consequences of floating offshore wind farms and help sustainable deployment strategies. Here, we present the design, deployment, and operational process of the EolBio buoy system, along with a methodological workflow combining laboratory analyses, artificial intelligence, and ecosystem modelling. This approach provides a unique framework for assessing the early impacts of offshore infrastructures on marine ecosystems and illustrates how instrumented buoys can play a central role in large-scale environmental monitoring.

Visual 3D Spatiotemporal Fields‐Driven Obstacle Avoidance Using Model Predictive Control for Nursing Robots in Unstructured Environments

Guoqiang Fu, Yina Wang — Tue, 21 Apr 2026 11:46:10 -0700

ABSTRACT

Monocular detectors typically provide 2D features, which limit a nursing robot's ability to perceive and adapt to changes in complex 3D environments. To address this challenge, this paper proposes a monocular 3D object detection framework capable of estimating objects' 3D locations, sizes, velocities, and predicted trajectories. The framework employs a Nursing Robot Convolutional Neural Network (NRCNN) to generate 2D bounding boxes for objects, followed by a 2D-pixel-to-3D-world coordinate transformation algorithm to recover their 3D spatial positions. Subsequently, an ID-assignment-based tracking module associates detections across sequential D435i video frames, enabling prediction of objects' spatiotemporal dynamics. To enhance 2D detection accuracy, a multibranch efficient channel attention (MECA) module is embedded within a cross-stage partial network in the backbone of the NRCNN detector. This design enhances interchannel and cross-layer information interactions to adaptively capture the cross-channel and cross-layer dimensional features. It departs from the traditional approach of improving feature extraction solely through increasingly deep dilated convolutional network structures, thereby enabling more effective feature extraction. Additionally, a bi-directional channel spatial feature fusion pyramid network (Bi-CSFFPN) is integrated into the neck of the NRCNN detector to fuse multi-level, cross-channel, and spatial features. This approach overcomes the limitation of conventional feature fusion networks that only fuse features along a single dimension and results in substantial performance improvements. Using outputs from the monocular 3D object detector, a dynamic lattice map is constructed that integrates real-time object volume, position, and velocity information. This map allows the nursing robot to plan the shortest feasible path from its initial position to the target location while avoiding moving obstacles via a model predictive control (MPC)-based trajectory tracking controller. Extensive experimental results demonstrate that the proposed MECA-CSP and Bi-CSFFPN modules significantly improve NR-CNN detection performance and enhance downstream tasks, including 3D object localization and dynamic lattice-map-based MPC obstacle avoidance control.

Biomimetic Multifinger Tactile Sensing and Contact‐Regulated Palpation for Autonomous Breast Tumor Localization

Tue, 21 Apr 2026 00:00:00 -0700

ABSTRACT

Early detection of breast abnormalities remains challenging: manual palpation is subjective and operator-dependent, while imaging modalities may miss small or subtle stiffness anomalies. This paper presents a biomimetic multifinger robotic palpation approach intended to support early breast-cancer screening and follow-up assessment as a proof-of-concept. The system integrates tactile arrays with a contact-regulation scheme under standardized protocols. Each fingertip produces spatial tactile heatmaps, and a human-like multifinger pressing strategy is used to elicit finger-wise normal-interaction responses under controlled contact conditions. The feedback variable is a resultant tactile signal obtained by aggregating taxel readings and is treated as a proxy of normal interaction rather than an absolute force measurement. A real-time Kalman filter is employed to improve signal fidelity during dynamic contact. The platform is validated on breast-inspired silicone phantoms with embedded rigid inclusions at varying depths and orientations. Across the tested scenarios, the system achieves repeatable real-time localization, with stiffness-weighted centroid errors within 10 mm of the nominal inclusion coordinates and a low incidence of spurious detections under the standardized protocol. We clarify that this study is a proof-of-concept focusing on stiffness anomaly localization under controlled phantom conditions rather than clinical diagnosis or benign/malignant classification.

Intelligent Autonomy: A Novel Hybrid Navigation System for Autonomous Load‐Haul‐Dump Vehicles

Yuanjian Jiang, Pingan Peng, Xiaofeng Huo, Jiaheng Wang, Liguan Wang — Mon, 20 Apr 2026 12:25:17 -0700

ABSTRACT

The automation and intelligence of underground mining vehicles are vital for ensuring safety and improving production efficiency, representing an essential trend in the evolution of the mining industry. However, achieving autonomous navigation for load-haul-dump (LHD) vehicles in GPS-denied underground environments poses significant challenges. To address these challenges, we introduce a novel hybrid navigation (HN) strategy that combines the strengths of absolute navigation (AN), which relies on precise localization using pre-mapped environments, with reactive navigation (RN), which utilizes real-time sensor data for immediate navigation decisions. In this strategy, the AN facilitates map-referenced positioning during turns, while the RN dynamically adjusts the trajectory on straight segments through real-time sensor feedback, independent of absolute localization. This integration enhances the robustness of navigation. We conducted simulation experiments to compare RN, AN, and HN systems. The results demonstrate that the HN system effectively merges the adaptability of RN with the precision of AN, ensuring reliable navigation through narrow intersections and stable performance on straight paths. Field trials further validated the HN system's ability to operate an LHD vehicle at a linear speed of approximately 1.8 m/s and a turning speed of 0.6 m/s, underscoring its practical applications in real-world scenarios. These findings highlight the HN system's potential for robust autonomous operation in complex underground environments.

Combining Neural Network and RRT*: A Novel Path Planning Method for Hyper‐Redundant Manipulators With 2N + 1 DOF

Zhe Wang, Dean Hu, Detao Wan, Chang Liu, Wei Xiao — Mon, 20 Apr 2026 00:01:04 -0700

ABSTRACT

Path planning has long been a research focus for hyper-redundant manipulators. However, in complex environments, the process often entails substantial computational costs. This issue is compounded by kinematic constraints. Therefore, achieving efficient path planning under these conditions remains a significant challenge. To address this issue, this paper proposes a novel path planning method for hyper-redundant manipulators with 2n + 1 degrees of freedom (DOF), which integrates a Neural Network model with the Rapidly-exploring Random Tree Star (RRT*) algorithm. First, a general kinematic model of the manipulator is established. Based on this model, the relationship between the manipulator's joint angles and the path corner angle is analyzed. This relationship is then incorporated into the RRT* algorithm to ensure that the generated paths comply with the kinematic constraints of the manipulator. Next, a Neural Network model is developed and trained using a dataset generated by the improved RRT* algorithm. The trained model predicts path points toward a designated goal. To address potential non-ideal path points in the predictions, a modification strategy combining the Artificial Potential Field (APF) method and a spatial meshing strategy is introduced. This strategy employs a dual adjustment mechanism to reposition non-ideal path points, enabling obstacle avoidance and mitigating the issue of bilateral distribution in the predicted path points. The predicted path points are then incorporated into the sampling process of the improved RRT* algorithm to guide tree expansion, thereby accelerating the path search. Additionally, the APF method is integrated into the search mechanism to further enhance planning efficiency. A series of experiments was conducted to evaluate the performance of the proposed method. The results demonstrate that the manipulator successfully reaches designated targets along the generated paths while avoiding obstacles and adhering to kinematic constraints. Compared to the RRT and RRT* algorithms, the proposed method shows superior overall performance, particularly in computation time, where it achieves a reduction of over 50% compared to RRT*. Prototype experiments further confirm the feasibility and safety of the paths generated by the proposed approach.

Review of Essential Generic Technologies for Visual Perception in Underground Coal Mine Robots

Yuxin Du, Jianhua Zhang, Liang Liang, Bin Song — Sun, 19 Apr 2026 22:58:18 -0700

ABSTRACT

Visual perception technology serves as the core support for establishing the “perception-decision-control” closed-loop system of underground coal mine robots (UCMRs). Research on its key generic technologies is crucial to promoting the large-scale deployment of UCMRs in underground mines. This paper initially reviews the development status of UCMRs and elaborates on the functional roles and application scenarios of five core categories: tunneling, coal mining, auxiliary operations, inspection, and rescue robots, thereby clarifying the fundamental requirements of visual perception across diverse underground scenes. Subsequently, it concentrates on the generic technological system essential for UCMR visual perception, presenting an in-depth analysis of the principles, research advancements, and application challenges related to four technical modules: environmental adaptability under extreme conditions, target detection and recognition in complex scenarios, 3D spatial perception and positioning, and lightweight algorithms suitable for edge computing. Finally, aligned with practical industry needs, the paper projects future development trends and practical challenges, proposing four strategic pathways for breakthroughs, namely human-machine-environment integrated active perception, automated iteration of datasets and models, cluster perception and interaction, and cross-technology integration, and highlighting four core challenges, including environmental adaptability, hardware reliability, communication collaboration, and industry access compatibility. It aims to provide a valuable theoretical reference and technical support for the technological development, achievement transformation, and advancement of mine intellectualization.

Research on Collision Avoidance Methods for Logistics Unmanned Aerial Vehicle Based on Dynamic Controlled Interactive Collaborative Fusion

Sun, 19 Apr 2026 22:38:10 -0700

ABSTRACT

As urban air-traffic density rises, the risk of mid-air collisions among low-altitude logistics drones has become a critical concern. We therefore introduce Dynamic Controlled Interactive Collaborative Fusion (DCICF), a framework that couples multimodal perception with Probabilistic Reciprocal Velocity Obstacles (P-RVO) modeling to enable safe, cooperative flight in dynamic environments. Simulations with 50 static obstacles yielded zero collisions; in dynamic-obstacle scenarios the collision rate was 0.083 while each drone completed an average of 2.400 missions; and in clustered multi-drone tasks the collision rate fell to 0.043 with 2.350 missions per drone. Hardware tests further demonstrated an average decision latency of 120–150 ms, minimum separation distances of > 0.8 m indoors and > 1.2 m outdoors, and a 100% mission-success rate. Relative to state-of-the-art baselines such as DQN, MILP and RRT*, DCICF offers superior safety, real-time responsiveness, and scalability, making it a robust solution for urban logistics drone operations.

Actuation Strategies for Underwater Jet‐Propelled Soft Robots

Angel Kitone, Mohammed Anteet, Pawandeep S. Matharu, Yara Almubarak — Sun, 19 Apr 2026 00:00:00 -0700

ABSTRACT

This review article examines jet-propulsion mechanisms in underwater soft robotic systems, focusing exclusively on physically fabricated and experimentally validated robots. Covering research published from 2013 to 2025, this study classifies and evaluates jet-propulsion robots based on their actuation mechanisms. This review outlines the fundamental working principles, discusses the key advantages and limitations, and assesses the practicality of these mechanisms for underwater applications. Additionally, a list of robots employing each actuation method is presented, illustrating the diversity of approaches within the field. By systematically comparing these studies, this review identifies critical performance trade-offs, potential challenges, and opportunities for innovation in jet-propulsion-based underwater robotics. Ultimately, this work serves as a valuable resource for researchers and engineers, facilitating advancements in the design and application of bioinspired underwater jetting robots.

The Shifting Paradigms of Disaster Robotics Three Decades of Research

Qin Hu, Komagata Tomoko, Kanbara Sakiko, Ting Yu, Yan Jiang — Thu, 16 Apr 2026 00:05:55 -0700

ABSTRACT

The increasing frequency and magnitude of natural disasters worldwide have raised the demand for advanced robotic systems in disaster response. In this research, a comprehensive bibliometric analysis of 2,201 Web of Science database papers was investigate systematically global research trends, patterns and emerging frontiers in disaster robotics. CiteSpace, the Bibliometrix R package, and VOSviewer were used for data analysis. The results reveal a fluctuating yet consistently rising publication trends from 1992 to 2025. Asia leads global research output, with Japan as the most productive country but with limited international collaboration, while European countries engage in more extensive international cooperation. The Journal of Field Robotics is identified as the most influential publication in this field. Over time, research on disaster robots has gradually shifted from hardware development to intelligence technologies, such as deep learning and perception-enabled robotic systems. The study provides valuable insights to guide future research directions and strengthen global collaboration in disaster robotics.

Soft Computing Techniques Applied to Adaptive Hybrid Navigation Methods for Tethered Robots in Dynamic Environments

Thu, 16 Apr 2026 00:00:00 -0700

ABSTRACT

Tethered robots face unique constraints: the physical tether can cause mission failure through snagging or excessive tension. Existing methods either require global maps (Tethered A*) or lack tether awareness (Bug algorithms). We present the first hybrid framework combining reactive obstacle avoidance with predictive tether management. Our system integrates (1) a tether-aware cost function for 3–5 step snag prediction, (2) fuzzy logic for dynamic tension adaptation, and (3) genetic algorithms for tether routing optimization. Validation on a humanoid robot (ATLAS-T) with instrumented sensors demonstrates 52% fewer snag incidents versus state-of-the-art methods (Tethered A*, TSLAM), 94.7% success in tether-critical scenarios, and 43% better odometry-drift resilience. Real-world experiments confirm practical viability.

Development of Dual‐Functional Flexible Ultrasonic Sensor Array of Proximity Sensing and Material Recognition for Safety Control of Robot

Lijie Zhou, Yuan Li, Zhan Duan, Zhentao Zhou, Tiezhu Liu, Jia Zhang — Wed, 15 Apr 2026 00:04:22 -0700

ABSTRACT

The operational safety of robots in complex environments is a critical consideration in contemporary robotics applications, since it directly impacts both task completion and the robot's own integrity. Currently, safety control in robots is predominantly achieved through multimodal sensor fusion technologies involving vision, LiDAR, and radar systems. However, these approaches still present limitations such as high hardware costs, large data volumes, complex data processing requirements, and slow response times. Herein, we present a dual-modal ultrasonic sensing system that simultaneously measures object proximity and identifies material properties, thereby enhancing robotic perception. The system addresses key challenges mentioned above and achieves a 98\% classification accuracy for 13 common industrial materials and maintains a proximity sensing error within 3 mm. Meanwhile, the system also maintains a good real-time performance with milliseconds of response. These outcomes contribute to safer robot control and improve environmental suitability.

Six‐Dimensional Digital Twin System for Autonomous Underwater Vehicles: Conceptualization and Twin Experiments

Lin Yu, Lei Qiao — Tue, 14 Apr 2026 01:12:01 -0700

ABSTRACT

To promote the efficient, comprehensive, reliable, and low-cost testing and application of intelligent algorithms for autonomous underwater vehicles (AUVs), this paper proposes an innovative six-dimensional digital twin (6D DT) conceptual model and provides detailed engineering implementation strategies of this twin system. This model integrates six core dimensions, including physical entity, virtual entity, virtual native entity (VNE), twin data, services, and communication connection. The concept of VNE is introduced to significantly enhance the practicability, security, and reliability of AUV testing by constructing diversified test scenarios. To implement the proposed model, a high-fidelity underwater Cyberspace visualization is developed using Unreal Engine 5, which improves the granularity of virtual–real mapping and enhances human–computer interaction. An efficient data bridge plugin is implemented to ensure real-time, stable bidirectional communication. The DT system (DTS) supports both offline simulation and online DT modes, enabling flexible testing from pure software simulation to real-time virtual–physical interaction, thereby enhancing the credibility of algorithm validation. Two experimental cases conducted on this DTS demonstrate the technical feasibility and reliability of the proposed conceptual model. The approach provides a valuable reference for applying digital twin technology in underwater unmanned systems and accelerates the development of autonomous intelligent AUVs.

Optimization of Magnetic Adsorption Units for Wall‐Climbing Robots via Integrated Response Surface Methodology and Genetic Algorithm

Zan Wang, Qixiang Zhang, Jinghua Wu, Shuaikang Li — Sun, 12 Apr 2026 21:03:11 -0700

ABSTRACT

To address the requirement for stable adsorption of climbing robots in confined spaces during ship hull cleaning operations, this study proposes a multi-objective optimization design method for arc-shaped magnetic adsorption units based on the response surface method-genetic algorithm. By analyzing the influence relationships among magnetic circuit topology, hull plate thickness, and air gap dimensions, the study reveals the superior performance of a five-loop Hallbarth array within specific air gap ranges and identifies the nonlinear impact of arc angle on magnetic adsorption units. A multi-parameter coupling optimization framework linking arc angle to permanent magnet geometric parameters has been established to determine the optimal configuration of permanent magnet structural parameters and arc angle. Experimental validation demonstrates a 15.37% increase in magnetic adsorption force per unit mass after optimization, with robotic stability confirmed through motion testing. This research holds significant value for achieving stable adsorption and engineering applications of wall-climbing robots on ship hull surfaces.

4SWLR: A Switched System and Skid Steer Integrated Whole‐Body Control Framework for Wheeled‐Legged Robots

Mingfan Xu, Ziyi Yang, Chuyan Xu, Jing Zhao, Yechen Qin — Sun, 12 Apr 2026 20:56:01 -0700

ABSTRACT

Inspired by mammalian locomotion and vehicle skid-steering principles, this paper proposes a real-time motion planning and tracking control framework for wheeled-legged robots, integrating the obstacle-crossing capability of legged robots with the skid-steering mechanism of wheeled platforms. Unlike conventional wheeled-legged robot control methods that rely on external swing joints, the proposed framework leverages differential wheel actuation while comprehensively accounting for the robot-environment coupling effects under high-speed conditions, enabling efficient and stable high-speed steering. First, a hierarchical wheel-terrain contact dynamics model and a skid-steering kinematics model are established for wheeled-legged robots with skid-steering. By combining switched-system skid-steering kinematics with refined wheel–environment interaction dynamics, the framework effectively addresses active wheel torque control during high-speed steering. Second, a skid-steering-based motion paradigm is introduced, which co-optimizes legged dynamics and wheeled skid-steering kinematics, eliminating the need for continuous leg-lifting maneuvers to generate lateral forces and ensuring smooth high-speed steering. Finally, extensive experiments conducted in challenging environments—including staircases, trenches, ramps, single-side bridges, and unpaved terrains—validate the robustness and efficacy of the proposed approach. Comparative studies with state-of-the-art wheeled-legged control methods further demonstrate the superior mobility performance and enhanced wheel–terrain interaction dynamics achieved by our framework.

Foundation Model‐Driven Grasping of Unknown Objects via Center of Gravity Estimation

Kang Xiangli, Yage He, Xianwu Gong, Zehan Liu, Yuru Bai — Fri, 10 Apr 2026 03:15:03 -0700

ABSTRACT

This study presents a grasping method for objects with uneven mass distribution by leveraging diffusion models to localize the center of gravity (CoG) on unknown objects. In robotic grasping, CoG deviation often leads to postural instability, where existing keypoint-based or affordance-driven methods exhibit limitations. We constructed a dataset of 790 images featuring unevenly distributed objects with keypoint annotations for CoG localization. A vision-driven framework based on foundation models was developed to achieve CoG-aware grasping. Experimental evaluations across real-world scenarios demonstrate that our method achieves a 49% higher success rate compared to conventional keypoint-based approaches and an 11% improvement over state-of-the-art affordance-driven methods. The system exhibits strong generalization with a 76% CoG localization accuracy on unseen objects. This provides an innovative solution for precise and stable grasping tasks, with its scientific validity further validated in complex and dynamic scenarios.

Fusion‐Guided and Distillation‐Optimized Framework for Freespace Detection in Off‐Road Environments

Fri, 10 Apr 2026 01:02:03 -0700

ABSTRACT

In response to the challenges posed by the dynamic and diverse terrain of off-road environments, the limited scale of data samples, and the insufficient generalization capability of models, this paper proposes an off-road freespace detection framework called OFF-LIP SAM. This framework employs a cascaded fusion approach, using dense point clouds as prompts to interactively guide the inference of the Segment Anything Model (SAM) vision large model. The framework first constructs a point cloud densification algorithm, calculating multi-frame point cloud pose transformation matrices through a lidar inertial odometer and building a dense local point cloud map using a dynamic adaptive keyframe strategy. A dynamic keypoint sampling algorithm is then designed to construct feature point clouds, which are used as prior information to interactively generate regions of interest, enabling knowledge and data to jointly drive SAM model segmentation inference. Finally, this study proposes and implements a two-stage knowledge distillation framework based on dynamic sampling prompts. This significantly improves the SAM inference speed while maintaining accuracy and generalization, making it applicable directly in resource-constrained real-vehicle environments. The experimental results demonstrate that the proposed OFF-LIP SAM detection framework achieves competitive performance on the ORFD, RELLIS-3D, and WildScenes data sets, outperforming current state-of-the-art algorithms and strong baseline models. Real-vehicle experiments conducted on the ORIN vehicle-mounted computing platform validate the feasibility and effectiveness of the OFF-LIP SAM detection framework.

A Feature‐Decoupled and Gated‐Interaction‐Enhanced Deep Reinforcement Learning for Path‐Following of Large‐Inertia Vessels

Tue, 07 Apr 2026 23:17:51 -0700

ABSTRACT

Path-following control for large-inertia surface vessels remains challenging due to slow yaw dynamics and environmental uncertainties. This paper proposes a hybrid framework integrating Line-of-Sight (LOS) guidance, drift-angle compensation, and an Adaptive Gated Interaction Twin Delayed Deep Deterministic Policy Gradient (AGI-TD3) controller. The primary innovation lies in the hierarchical feature-processing architecture of the AGI-TD3 agent. By implementing decoupled encoding for heterogeneous state-action subspaces, the network isolates interference from disparate physical semantics. Furthermore, an adaptive gated interaction mechanism is introduced to selectively modulate information flows, reinforcing the causal relationship between heading errors and control actions. Simulation results and full-scale experiments on a 40 m-class vessel demonstrate that the proposed method significantly improves path following performance and robustness under realistic operating conditions.

Development of Spatial Path Tracking Algorithm and Controller for a 6‐SPS Stewart Parallel Manipulator: A Simulation and Experimental Study

Dev Kunwar Singh Chauhan, Pandu R. Vundavilli — Wed, 01 Apr 2026 22:50:20 -0700

ABSTRACT

The Stewart parallel robot is popular for its high payload capacity due to its six prismatic links. Researchers worldwide are exploring it for various applications. In this work, the authors have developed an inverse kinematics-based spatial path tracking algorithm for the Stewart platform that allows it to track circular paths in multiple planes. Authors also conducted experiments to test the algorithm. Initially, they established the inverse kinematics, Jacobian, and singularity of the robot. Next, they established motion planning for the robot using a third-order polynomial in task space. Subsequently, they developed a motion controller for an individual joint actuator, employing a PID control strategy to precisely control its motion. After that, they controlled the overall motion of the Stewart manipulator using inverse kinematics by utilizing the actuator's PID-based motion controller. The authors accomplished a novel path tracking method after breaking the whole path into multiple small trajectories and matching the endpoint velocities. Later, they used the developed path-tracking algorithm to generate a circular shape on the aluminum disc. The developed algorithm successfully created a circular form on the aluminum disc for the incremental form application.

Redefining Optimal Coverage Path Planning for FLS‐Equipped AUVs With Deep Reinforcement Learning

Lorenzo Cecchi, Alberto Topini, Alessandro Bucci, Alessandro Ridolfi — Wed, 01 Apr 2026 00:00:00 -0700

ABSTRACT

Autonomous Underwater Vehicles (AUVs) have emerged as indispensable tools for a variety of subsea tasks, from habitat monitoring and seabed mapping to infrastructure inspection and mine countermeasures. A fundamental challenge in this field is Coverage Path Planning (CPP), the problem of ensuring complete and efficient area coverage. Within this research activity, we propose a Deep Reinforcement Learning (DRL)-based framework for CPP in underwater environments using a Forward-Looking Sonar (FLS). We validate the proposed methodology through simulation experiments comparing it with the classical lawnmower path and a state-of-the-art sampling-based algorithm. Results demonstrate that our DRL-based solution outperforms these baseline approaches in terms of coverage time per unit area and path length. Additionally, we present on-field deployment outcomes on FeelHippo AUV, showcasing the feasibility and practicality of our framework in real-world underwater missions.

A Wheeled Robot Inspection System for Long‐Term Operation in Large‐Scale Industrial Environments

Chenpeng Yao, Chengju Liu, Hong Chen, Qijun Chen — Fri, 27 Mar 2026 22:20:58 -0700

ABSTRACT

Robotic navigation and object detection technologies have advanced significantly. However, deploying inspection systems in large-scale industrial environments, particularly for long-term operations, remains challenging due to the lack of a comprehensive software and hardware platform. To address these challenges, this paper presents a wheeled robotic inspection system designed for sustained operation in large-scale industrial settings. A novel roadmap construction method is introduced to optimize spatial structures for real-time processing. Additionally, a feedback mechanism is proposed to ensure stable and high-performance operation over extended periods. The system is further supported by a hardware platform that seamlessly integrates with the software framework, enhancing overall operational performance and reliability. Experimental results validate the effectiveness of the proposed method, while real-world testing demonstrates the system's feasibility and stability for long-term deployment. This work provides a comprehensive solution for robotic inspection in large-scale environments, offering a practical and scalable reference for researchers and practitioners.

DURAL: Degradation‐Resistant Robust Adaptive Localization by LiDAR‐Inertial‐UWB‐Wheel Fusion for Coal Mine Robots

Kun Hu, Menggang Li, Zhiwen Jin, Chaoquan Tang, Eryi Hu, Gongbo Zhou — Mon, 23 Mar 2026 00:17:13 -0700

ABSTRACT

Simultaneous Localization and Mapping (SLAM) in large-scale, complex, global positioning system (GPS)-denied underground coal mines poses significant challenges. In these environments, abnormal conditions hinder sensor performance: GPS unavailability impedes scene reconstruction and geographic referencing; uneven or slippery terrain degrades wheel odometer accuracy; and long, feature-poor tunnels reduce light detection and ranging (LiDAR) effectiveness. To address these challenges, we propose DURAL, a multimodal SLAM framework based on the Iterated Error-State Kalman Filter that fuses multiple sensors from coal mine robots to overcome individual sensor limitations. First, LiDAR-inertial odometry is tightly coupled with Ultra-Wideband (UWB) absolute positioning constraints to establish an absolute coordinate system. Next, the wheel odometer is integrated through tight coupling, enhanced by nonholonomic constraints and vehicle lever arm compensation, to mitigate performance degradation beyond the UWB measurement range. Finally, an adaptive fusion mode switching mechanism dynamically adjusts sensor constraints based on UWB coverage and environmental conditions. Experimental results indicate that our method achieves state-of-the-art accuracy and robustness in both simulated tunnel environments and real-world underground coal mines. In real-world experiments, the system attains an absolute pose error of 0.167 m within the UWB range, maintains a relative pose error of 6.53% outside this range, and improves mapping accuracy to 6.456 cm, significantly outperforming existing approaches in challenging mining scenarios.

Enhanced Unscented Kalman Filter With Time‐Varying Attenuation Factor for Cross‐Domain Unmanned Surface Vehicle/Autonomous Underwater Vehicle Tracking Using Time‐Direction of Arrival Measurements

Huaxia Zhang, He He, Shaowei Rong, Fenggang Sun, Huigang Wang — Fri, 20 Mar 2026 03:12:56 -0700

ABSTRACT

In cross-domain target tracking involving an unmanned surface vehicle (USV) and autonomous underwater vehicle (AUV), the high maneuverability of these platforms combined with complex marine environments may result in tracking latency and filter divergence. This paper introduces a time-varying attenuation UKF (TA-UKF) method designed to dynamically adapt the state covariance matrix in response to target maneuvers and environmental disturbances. The proposed methodology integrates time and direction-of-arrival measurements within a CT rate and velocity motion model. By incorporating the instantaneous innovation sequence to regulate the attenuation factor, the algorithm effectively adjusts the prediction covariance during model mismatches to prioritize real-time measurements. Monte Carlo simulations demonstrate that the TA-UKF outperforms not only standard filters (EKF/UKF) but also advanced methods. Specifically, it eliminates the model-switching latency in the interacting multiple model and the statistical adaptation lag of Sage-Husa methods. Furthermore, the algorithm exhibits robustness to unmodeled ocean currents and non-Gaussian measurement outliers. Field experiments conducted at Liquan Lake further validate the algorithm's practicality and robustness under real-world acoustic conditions.

Constrained Adaptive Fractional‐Order Sliding‐Mode Controller for Stabilizing the Two‐Degree‐of‐Freedom Gimbal System With Limited Field‐of‐View Sensors: Theoretical and Experimental Discussion

Amir Naderolasli — Thu, 19 Mar 2026 00:18:40 -0700

ABSTRACT

This research outlines the development and implementation of a constrained adaptive fractional-order sliding-mode controller specifically designed for a two degree-of-freedom Gimbal system equipped with sensors that have a limited field-of-view (FOV) constraint. A fractional-order sliding-mode controller, which employs the Barrier Lyapunov function, is utilized to stabilize this system, ensuring that the state variables of the system remain within acceptable boundaries, thereby addressing the constraints posed by the sensors' restricted FOV in real-world applications. The angular velocities of both the elevation and azimuth axes are driven towards zero through the adaptive fractional-order sliding-mode controller that has been meticulously designed. The design process takes into account the cross-coupling effects between the inner and outer Gimbals, as well as the uncertainties arising from the moment's products and external disturbances. Both simulation and experimental findings confirm that the stabilizing controller, which incorporates a constrained adaptive fractional-order sliding-mode framework, successfully stabilizes the nonlinear two degree-of-freedom Gimbal system.

Analysis of Unilateral Track Movement for Tracked Unmanned Combat Vehicles

Jin Chengke, Xie Xinyang, Yuan Ying, Wang Yongjuan — Mon, 16 Mar 2026 11:37:31 -0700

ABSTRACT

With the increasing deployment of unmanned combat vehicles (UCVs) in modern warfare, it is noteworthy that these vehicles differ from manned vehicles in their susceptibility to damage from antipersonnel mines or antiarmor weapons. Such attacks can lead to the breakage of a single track, rendering on-site repairs impractical. Consequently, unilateral track movement emerges as a critical strategy for UCVs to continue combat operations or retreat to maintenance facilities after sustaining such damage. To investigate the ultimate conditions and steering capabilities under unilateral track motion, we established and analyzed a dynamic model. The study provides methodologies for calculating maximum angular displacement during sudden acceleration or deceleration under various operational scenarios. Furthermore, based on parameters such as vehicle torque, optimal steering control strategies were derived. To validate the feasibility of unilateral track movement, dynamic simulations were conducted using ADAMS software, and experimental prototypes were fabricated for empirical testing. The results indicate that turning through sudden acceleration is significantly more efficient than turning via sudden deceleration. This finding corroborates the accuracy of the theoretical analysis and simulation outcomes, thereby offering valuable reference points for the future design and development of UCVs.

Control System for the Navigation of the Agricultural Robots: A Review

Mon, 16 Mar 2026 11:36:33 -0700

ABSTRACT

Control systems for the navigation of autonomous agricultural robots—particularly those operating in uneven terrain and in the presence of static or dynamic obstacles—have advanced considerably in recent years. As conventional machinery evolves toward increasingly automated systems, the design of reliable navigation controllers has become central to improving field efficiency and reducing operational risks. This review provides a systematic analysis of control strategies implemented in real agricultural environments over the past 11 years, examining how robotic platforms integrate perception, traction, steering, and actuation to follow trajectories and execute tasks in semi-structured or fully unstructured terrain. Data from 36 robots (eight commercial and twenty-eight research prototypes) were examined, along with 29 navigation control strategies, implemented in different combinations across the platforms. The findings show a predominance of model predictive control (MPC), proportional-integral-derivative (PID), and pure pursuit control (PPC), reflecting their suitability for regulating wheel actuation, maintaining trajectory precision, and handling variable terrain conditions. Less common approaches—such as sliding mode control, linear quadratic regulation, fuzzy controllers, and reinforcement learning—highlight emerging opportunities rather than established practices. Overall, the review underscores the importance of selecting control strategies consistent with robot morphology, sensor configurations, and task requirements, and identifies the need for standardized evaluation metrics (e.g., tracking errors ≤0.05 $\le 0.05$ m) and more diverse field testing across crop cycles. These insights help guide future development of robust, scalable navigation systems for autonomous agricultural robots.

Giving Autonomy to Empty‐Headed Robots: Design and Deployment Challenges

Sun, 15 Mar 2026 10:19:53 -0700

ABSTRACT

This paper presents a 3D LiDAR-based autonomy-transferring platform designed to enable autonomy for legacy non-autonomous robots and to address difficulties encountered at industrial systems. The proposed platform integrates essential hardware and core software modules for perception, decision-making, and control, ensuring adaptability across various industrial applications. It primarily consists of three key hardware components: perception sensors, a computation board, and a protective case, providing a comprehensive turnkey solution that facilitates seamless integration into existing navigation-free robots. The software architecture processes synchronized sensor data to support perception, planning, and control functionalities, ultimately generating velocity commands for autonomous navigation. By enabling real-time intelligence, the proposed system contributes to scalable smart city applications and industrial IoT deployments. Comparative evaluations with existing commercial solutions highlight the limitations of current autonomy platforms and demonstrate how the proposed platform effectively addresses these constraints. The platform's interoperability was validated across diverse robotic and cyber-physical environment in industry, logistics, research, and retail. And then, to systematically assess its performance, two types of evaluations were conducted: one focused on harsh environments and another across four fields and practical industrial applications in smart retail, logistics hubs, and urban mobility systems. The results confirm the platform's scalability, flexibility, and effectiveness, establishing it as a viable solution for real-world autonomy implementation. The proposed autonomy-supporting platform serves as a valuable reference for implementing autonomy in non-autonomous robotic systems, advancing the transformation toward cyber-physical environment across smart infrastructure.

Autonomous Driving in Unstructured Off‐Road Environments: How Far Have We Come?

Sun, 08 Mar 2026 22:18:38 -0700

ABSTRACT

Research on autonomous driving in unstructured outdoor environments is less advanced than in structured urban settings due to challenges like environmental diversities and scene complexity. These environments–such as rural areas and rugged terrains–pose unique obstacles that are not common in structured urban areas. Despite these difficulties, autonomous driving in unstructured outdoor environments is crucial for applications in agriculture, mining, and military operations. Our survey reviews over 250 papers for autonomous driving in unstructured outdoor environments, covering offline mapping, pose estimation, environmental perception, path planning, end-to-end autonomous driving, datasets, and relevant challenges. We also discuss emerging trends and future research directions. This review aims to consolidate knowledge and encourage further research for autonomous driving in unstructured environments. To support ongoing work, we maintain an active repository of up-to-date literature and open-source projects at: https://github.com/chaytonmin/Survey-Autonomous-Driving-in-Unstructured-Environments.

VISTA‐Campus Dataset: VersatIle Slam DaTAset With Multimodal Sensor for Campus Environments

Sun, 08 Mar 2026 21:30:25 -0700

ABSTRACT

Simultaneous localization and mapping (SLAM) is fundamental to reliable navigation in unmanned ground vehicles (UGVs), particularly in campus environments. In this paper, we present VISTA-Campus, a multimodal dataset collected across a university campus with dual LiDARs, a stereo camera, and surround-view cameras featuring extensive overlapping coverage. The dataset spans diverse temporal conditions, illumination changes, pedestrian densities, and geographic zones, and is designed to support both current and emerging perception modalities. It incorporates multiple loop closure detection conditions while providing long-distance sequences, making it particularly suitable for long-term SLAM evaluation. We also provide partial annotations for object detection and drivable area segmentation. The dataset's quality is validated by benchmarking popular SLAM algorithms. We expect VISTA-Campus to advance SLAM and autonomous driving research in diverse campus-like settings. The dataset is available at https://github.com/VISTA-Campus/VISTA_Campus.

Advances in Autonomous Vehicle Testing: The State of the Art and Future Outlook on Driving Datasets, Simulators, and Proving Grounds

Wed, 04 Mar 2026 21:57:06 -0800

ABSTRACT

As autonomous driving technology rapidly advances, effective testing tools and methods become crucial. This paper comprehensively assesses the capabilities and limitations of publicly available autonomous driving datasets, simulators, and proving grounds, exploring their roles in testing autonomous vehicles. The aim of the paper is to analyze how these tools can assist in evaluating the capabilities of autonomous driving systems and their tasks in the actual verification process of autonomous driving technology. Furthermore, this paper discusses the challenges faced by autonomous driving datasets, simulators, and proving grounds, as well as future directions for development. Additionally, we propose the Integrated Testing Framework for Autonomous Vehicles (ITF-AV), which unifies these tools into a cohesive testing strategy, providing guidance for researchers and practitioners to select appropriate methods based on specific testing needs.

A Novel Global Path Planning Algorithm for Underwater Vehicle Engineering Applications

Qiongxiao Liu, Xiaoting Xu, Qi Wang, Miao Wang, Bo He — Mon, 02 Mar 2026 00:54:17 -0800

ABSTRACT

This paper presents an intelligent global path planning technology aimed at safely and intelligently navigating autonomous underwater vehicles to the operational area in specific engineering application scenarios, and reducing the cost of manual remote control. Firstly, a novel environment modeling method named SDS-DNP, which consists of the Satellite Map Semantic Segmentation Network (SatDeepSeg) and the Distance Normalization Processing Algorithm (DistNormProc), is introduced. This method swiftly converts satellite maps into high-precision safety factor maps, providing accurate environmental information for AUVs. Secondly, the AIW-CE-SMO (Adaptive Weight and Cooperative Evolution Spider Monkey Optimization) algorithm is proposed for global optimal path search. The simulation and lake experiment results show that the SDS-DNP method can accurately model the environment even when the contrast between islands and lakes in satellite maps is low. In addition, the proposed method takes only 0.84 s, while the grid method takes 3.96 s, which is based on the premise of selecting a larger grid. Its efficiency is 78.84% higher than the grid method. Compared with traditional intelligent algorithms, the AIW-CE-SMO algorithm proposed in this paper has an optimal path length standard deviation between 0.55 and 5.99, and a running time between 10 and 15 s, which proves the stability and high efficiency of the algorithm. In addition, the actual experiment in the lake proves the effectiveness of the proposed algorithm.

Virtual Elastic Tether: A New Approach for Multi‐Agent Navigation in Confined Aquatic Environments

Mon, 02 Mar 2026 00:47:45 -0800

ABSTRACT

Underwater navigation is a challenging area in the field of mobile robotics due to inherent constraints in self-localization and communication in underwater environments. Some of these challenges can be mitigated by using collaborative multi-agent teams. However, when applied underwater, the robustness of traditional multi-agent collaborative control approaches is highly limited due to the unavailability of reliable measurements. In this paper, the concept of a Virtual Elastic Tether (VET) is introduced. VET introduces the concept of a virtualised tether to connect multiple robots by innovatively using dual camera views for two-sided visual servoing. This enables individual robots to perform autonomous maneuvers while maintaining mutual proximity. The concept of VET is formulated and validated through an AUV-ASV multi-agent underwater system. Within this framework, a vision-based leader-follower approach for an autonomous underwater vehicle and an autonomous surface vehicle is developed. The proposed system has been tested in both simulation and physical experiments, with performance benchmarks against the traditional single Image-Based Visual Servoing approach. Results indicate that while the leader-follower formation of the baseline system failed under external perturbations, the VET-enhanced system's formation recovered to its pre-perturbation state within 5 s. Moreover, the VET-enhanced system successfully navigated a confined water pond where the baseline approach failed to perform adequately.

Underwater Image Enhancement Based on Accelerated Conditional Diffusion Probabilistic Model

Baizhong Chen, Chonglei Wang, Chunyu Guo, Yumin Su — Mon, 02 Mar 2026 00:45:09 -0800

ABSTRACT

Underwater images often suffer from significant color distortion and blurred features due to optical loss and dispersion. This degradation can hinder tasks such as underwater object detection. To address this issue, this study proposes an underwater image enhancement (UIE) model based on an accelerated conditional diffusion probabilistic model (UW-DDPM). This model is a rapid denoising diffusion probabilistic model designed specifically for UIE. The UW-DDPM directly establishes a diffusion generation relationship between degraded and reference images based on the conditional diffusion probabilistic model (CDDPM) redesigning an implicit accuracy diffusion model for direct image translation, which not only improves the quality of image enhancement but also addresses the slow sampling speed issue of the CDDPM. Simultaneously, speed-UIE was designed for processing training on conditional images, which is a lightweight model network. Specifically, we combined a pre-trained diffusion model with a lightweight UIE algorithm, using speed-UIE to guide conditional generation. The diffusion prior mitigates the drawbacks of poor-quality synthetic images, whereas the lightweight model addresses the issue of the diffusion model lacking high-quality prior conditions, resulting in higher-quality images. Ablation experiments demonstrate that enhancing the conditional images before inputting them improves the visual quality of the output images. Extensive experiments on publicly available UIE datasets have verified that the UW-DDPM outperforms existing traditional and deep learning-based methods in terms of full-reference, no-reference image quality assessment metrics, and generation speed. The UW-DDPM and other state-of-the-art (SOTA) methods are used to compare the image enhancement experiments of underwater robots in the field. The UW-DDPM still demonstrated excellent robustness in practical applications.