Student Lounge

RoboSub Simulation Environment

Tanya Kuruvilla — Mon, 23 Mar 2026 16:45:39 +0000

In today’s blog, Abhishek Shankar from the Student Programs team at MathWorks introduces a newly released underwater RoboSub simulation environment built with Simulink, Simulink 3D Animation, and Unreal Engine that enables teams to test algorithms and accelerate development. Over to you, Abhishek…

Underwater robotics has been on the rise over the past few years, which reflects the rise in robotics in general. While it might appear to be a niche area, there are several areas in science and engineering that benefit from autonomous underwater vehicles (AUV) such as marine biology (collecting samples, tagging endangered animals, etc.), ship inspection and maintenance, deep sea exploration, military, etc. Seeing the potential impact of AUV is such areas, there have been several competitions to push the development of AUV’s. One such competition is RoboSub – an underwater robotics competition held by RoboNation. The competition pushes the participants to develop vision, navigation and control systems to perform several challenging tasks such as object avoidance, object detection, station keeping, localization and so on. The challenges come in various forms when underwater – lack of GPS is a main factor since the AUV must now use only on board sensors to localize itself, no help from satellites. Vision can also be tricky underwater due to distortions and reduced visibility the deeper the AUV dives. Further, the cost of development and testing increases quickly with the need of water proof bodies, underwater thrusters, expensive sensors such as DVL’s (Doppler Velocity Logger) and access to a pool or a lake for testing. Weather also plays a role as teams in the northern hemisphere have to deal with frozen lakes during winter, which reduces testing time by up to 4 months. To address some of these issues, we have now released a virtual environment to simulate the tasks at RoboSub. Simulation helps identify issues early, reduce development time, cost, and risk in the model-based design workflow. The environment is built in MATLAB 2025b and uses Simulink 3D Animation for photorealistic visualization while the physics are simulated in Simulink. The virtual environment can be cloned from this repository, and will be used for a virtual RoboSub competition in 2026.

Model Overview

The virtual environment has two main components. The Simulink model that takes in the AUV parameters and simulates the physics (left part of the above image) and a Unreal Engine based visualization environment for visualizing the AUV (right part of the image above).

Simulink Model

The Simulink model is at the heart of the virtual environment. The AUV block, which is a masked subsystem, takes in the properties of the AUV such as its mass, inertia, volume, thruster positions, sensor positions and actuators to simulate the physics of the body. The model calculates the AUV dynamics based on hydrostatic and hydrodynamic forces and computes the forces and moments from the thrusters. These are then fed into a 6-DOF block that computes the vehicle states (position, velocity, orientation, angular velocity) at each time step. The model breakdown is shown in the image below.

The sensor block takes in the robot state and simulates the reading of common underwater sensors such as IMU, DVL and camera. More sensors can be modeled as and when required by the user. The sensor readings are then the outputs from the AUV block. The noise profiles of these sensors can be edited to match the sensor the user is using to make the simulation more realistic and potentially reduce the sim-to-real gap. The actuator subsystem simulates the two main actuators used in RoboSub – torpedoes and marker dropper. These subsystems are shown below. The model simulates the physics of these objects by sampling the position of the AUV at the time of firing and appending the position based on the physics of the object.

The visualization block ties it all together by visualizing the AUV’s pose and states in a photorealistic environment built using Simulink 3D Animation which uses Unreal Engine in the background. The virtual environment is set to an Olympic sized swimming pool to reflect the competition environment but users can design their own environment based on their needs. In the next section, I will talk more about the photorealistic 3D environment.

Visualization

Simulink 3D Animation provides the user with the option to build their custom scene using Unreal Engine (UE). In this virtual environment, the visualization environment is an Olympic sized swimming pool. The features on the pool are modified using UE actors. The water is modeled using the experimental water plugin and the lighting is adjusted through custom shaders to make the underwater view realistic. Below, you can see a gif of the environment and how it interacts with the AUV’s with a positive buoyant force.

The environment also consists of other artifacts that relate to the competition such as navigation gates, torpedo target boards, marker target and octagon. These will further be modified to reflect the changes for the 2026 competition.

More information on the model and the blocks within it can be found in this detailed document in the GitHub repository.

Simulation

Now that we have an overview of the simulation environment, I can show how a simulation in this environment looks like. For this, I’ll take the task of navigating through a gate and firing a torpedo at the target board. For this example, I am assuming that the location of the gate and the board are known but for the competition, navigation will be based on vision. For the tasks, there is a Stateflow chart managing the AUV’s high level execution and individual PID’s to control the AUV and keep it close to the planned path. The Stateflow and control system is shown in the image below.

The gif below shows the AUV navigating and firing a torpedo at the board – a common task at RoboSub. Further, it is easy to connect this environment to ROS using our ROS toolbox, which allows the user to publish sensor messages through the ROS publisher block and subscribe to thruster inputs and torpedo or marker commands. This lets the user easily connect to an external navigation or control algorithms and visualize the simulation in Simulink. More information on the simulation interface and it’s ROS interface can be found in this video with RoboNation.

Conclusion

This blog goes over the newly released virtual environment for RoboSub using Simulink 3D Animation. The model simulates the physics of the user’s AUV closely based on the inputs such as mass, inertia and coefficients of drag. It also provides rich sensor data from various sensors used in underwater navigation. Two actuating systems are simulated – torpedoes and marker dropper which would help teams test these tasks out in simulation before deploying in the competition. MathWorks also offers a range of other products to help design autonomous behaviors. For example, Stateflow makes it easy to design state machines (a common decision making architecture), navigation and path planning capabilities using our Navigation toolbox, etc. These products are included in the competition license that is complimentary to all RoboSub participants! And finally, MathWorks will be launching a Virtual RoboSub Challenge to encourage more teams to test and validate in simulation and give them a chance to win up to $1000. So if you have registered for RoboSub, try to participate in the virtual challenge to test your algorithms in simulation and to stand a chance to win the prize money. Good Luck!

MathWorks Research Internship Experience: Divyamaan Sahoo

Tanya Kuruvilla — Mon, 09 Mar 2026 11:53:07 +0000

Today we’re talking to Divyamaan Sahoo, who participated in the Development Collaborative Research Grant program at MathWorks, which supports academic research aligned with development priorities for MATLAB and Simulink. Through the program, he contributed to the development of the Acoustic Library for Simscape, helping advance tools for modeling acoustic systems and transducers while supporting research and education in physical acoustics.

Meet Divyamaan Sahoo

My name is Divyamaan Sahoo and I am a puppeteer, sound artist, mathematician, and electroacoustic engineer. I am from Calcutta, West Bengal, India. I am currently pursuing my Ph.D. in Acoustics at The Pennsylvania State University in State College, PA. My area of study is physical acoustics, transducers and signal processing. I am interested in sound, acoustics and pure mathematics (number theory, geometry, and topology).

What’s your research about?

I am part of a team that is developing, testing, and documenting the Acoustic Library for Simscape, a foundational project that enables modeling acoustic phenomena using “lumped” elements. In broad terms, it is a method to break down a complex physical phenomenon into separate domains—electrical, mechanical, thermal, etc.—and describe the phenomenon in each domain using three elementary relationships: x is proportional to y, OR x is proportional to the derivative of y, OR x is proportional to the integral of y. The constants of proportionality here are denoted “R”, “L”, and “C” and x and y are defined such that their product x times y equals power. In the electrical domain, this describes the ubiquitous RLC circuit, where x is voltage and y is current. The fundamental idea here is that it is possible (and often beneficial) to define “R” “L” “C” elements in other physical domains. The reason is, instead of solving systems of (coupled) differential equations, one can draw analogous “R” “L” “C” circuits and evaluate the musing circuit analysis techniques. This is what Simscape achieves at its core.

Acoustic “R” “L” “C” circuits have been around for many decades and their inclusion in Simscape has been especially advantageous for studying and prototyping transducers .Dr. Stephen Thompson (my mentor and advisor) has been using these components to teach advanced transducer courses at Penn State with great success.

A simple example of how this is useful in a real-world application is the modeling of loudspeakers to determine the design and dimensions of their enclosures. Currently, the library highlights microphones, loudspeakers, and examples such as the multidomain modeling of earbud headphones inserted in a human ear. However, any physical acoustics problem using lumped elements can be modeled using this library. I anticipate that such a tool will have a tremendous impact on both industrial and educational contexts worldwide.

For someone who remains deeply curious about the art and science of transducers, it has been an especially rewarding experience to contribute to the Simscape Acoustic Library and have MathWorks support its development through the Development Collaborative Research Grant (DCRG) program. The library we see today is the result of Dr. Thompson’s research (and his advisor’s!) and is made possible thanks to cohorts of acoustics graduate students and faculty members at Penn State who have been using and refining these blocks over the years.

The Research Internship Experience

The primary goal of my internship has been to collaborate with Signal Processing & Communications (Audio Toolbox team) and Control Design Automation to build a support package for the Acoustic Library for Simscape by creating documentation for all components, maintaining equivalent analogous circuits of all blocks, conducting preliminary unit testing, developing Simscape code to specified conventions, and devising a unique set of icons for the library.

So far I have established a solid theoretical foundation for the library and internal design documentation for each component, redesigned icons for all components, maintained an exhaustive list of all equivalent circuits for each block in the library, and delivered a series of three in-depth lectures providing an overview and background to the Acoustic Library, distilling the concepts necessary to model acoustic systems using Simscape. I also conducted preliminary unit tests, identified bugs, and maintained a faithful record of meetings with various team members and stakeholders to ensure a smooth development workflow.

The result has been an in-depth and comprehensive literature review of all canonical acoustics references, including numerous critical papers and unpublished texts on transducers to ensure that the underlying physics of each component and their analogous circuit representations are accurate. This internship has been instrumental in strengthening the foundation of my Ph.D. research project on the R&D of novel transducers and signal processing algorithms for hearing aids.

What’s next?

Thanks to the encouragement of my team, I recently submitted an abstract to present our research at the upcoming Acoustical Society of America/ Acoustical Society of Japan conference this December, for the special session “Acoustics in Multiphysics Measurements: Modeling and Applications,” hosted by the Physical Acoustics Technical Committee. We hope that this abstract will be accepted!

I hope to continue working on the DCRG research project as part of my Ph.D. dissertation research in the Fall and contribute toward the success of the Acoustic Library release. It would be a dream to pursue a full-time role at MathWorks, focusing on R&D and technical writing for acoustics/audio.

MathWorks Research Internship Experience: Tingkai Li

Tanya Kuruvilla — Mon, 23 Feb 2026 13:26:19 +0000

Today we’re talking to Tingkai Li, who participated in the Development Collaborative Research Grant program at MathWorks, which supports academic research aligned with development priorities for MATLAB and Simulink. Through the program, he advanced battery health estimation and degradation forecasting while helping translate research into practical industry tools.

Meet Tingkai Li

My name is Tingkai Li, born and grew up in Quanzhou, China. I hold my BS in mechanical engineering from Iowa State University, and I’m currently a 4th year PhD student in mechanical engineering at University of Connecticut. I’ve interned at MathWorks for summer 2024 and summer 2025, both times at the Apple Hill campus.

What’s your research about?

My research falls under the general topic of prognostics and health management (PHM) for lithium-ion batteries, in which I specialize in lifetime prediction, capacity fade forecasting, state of health (SOH) estimation, and degradation diagnostics.

Lithium-ion batteries have been widely used all over the place in our daily lives. Similar to other engineered systems and even human beings, lithium-ion batteries age gradually over time, both naturally and by usage. Research in PHM for lithium-ion batteries focuses on delivering a better understanding and a more accurate representation of the battery’s internal state, as well as a forecast of future degradation. All these advancements help with a better prediction of the performance of both batteries themselves and the systems relying on them for power supply by identifying potential failures that may cause chaotic accidents and by optimizing the maintenance scheduling for the systems.

The Development Collaborative Research Grant (DCRG)project I’m part of focuses on developing more accurate, robust, and trustworthy approaches to estimate the state of health (SOH) and forecast future degradation under varying usage conditions for batteries. My role in this project includes designing and running battery aging tests, eventually developing better approaches for SOH estimation and degradation forecasting.

The Research Internship Experience

For my internship I was located in the Apple Hill campus, working closely with the Predictive Maintenance Toolbox team to explore and develop some functionality for extracting features from battery usage data( e.g., charge/discharge measurements, electrochemical impedance spectra, etc.)for various data-driven battery modelling workflows (e.g., state of health estimation, remaining useful life prediction).These projects align very well with what I’ve learned and developed in my research, allowing me to bring my knowledge to customers by providing such features in MathWorks’ ecosystem.

So far, I have developed several prototype and examples during my two internships, some of which are expected to be shipping out in the future releases. One of my projects during my internship in Summer 2024 has been available in R2025a as an example (Automatic Data Segmentation and Feature Extraction for Reference Performance Test in Lab-Measured Battery Aging Data – MATLAB & Simulink).

What’s next?

I’ll go back to school and continue working on both the DCRG project and my other projects. With an expected graduation on Spring 2026, I am considering positions in the industry where I can leverage my domain knowledge in battery modelling and a broader context of AI application in engineering.

How Future Engineers Use MATLAB and Simulink at World Robot Olympiad

Tanya Kuruvilla — Mon, 09 Feb 2026 15:27:30 +0000

MathWorks began partnering with the World Robot Olympiad (WRO) last season (2025) to support student teams using modeling and simulation as part of their robotics workflows. As part of this partnership, we introduced the MathWorks Modeling Award, which recognizes teams that demonstrate creativity and technical skill using MATLAB and Simulink in their project designs 

The Pythons, winners of the MathWorks Modeling Award in the Future Engineers category, used MATLAB and Simulink to support their autonomous driving solution. The Future Engineers category is designed for older students (ages 14–22), with a challenge that changes every 3–4 years and currently focuses on building a robot with a steering drive that can navigate a track autonomously. 

For today’s blog, we’re joined by The Pythons, who will share their robot design and describe how MATLAB and Simulink supported their development process. Over to you… 

Introduction

We are The Pythons, an Egyptian robotics team founded by Innova STEM Education Co. in 2016 and based in Alexandria, Egypt. This was our first time participating in the World Robot Olympiad (WRO), and over the years we have also taken part in several local and international robotics competitions, including RoboCup Junior. Our goal as a team is to contribute to the robotics field and explore how robotics can be used to improve people’s lives through hands-on engineering challenges.

Meet our Robot

To tackle the autonomous driving challenge, we designed a robot centered around the Raspberry Pi 5, which handles all major processing tasks. Our system is responsible for:

Calculating deviation from center position using a sensor fusion algorithm that combines data from ultrasonic sensor and heading information calculated from MPU6050 sensor.
Issuing commands to motors to move according to data.
Detecting blocks and orange and blue lines using a custom trained YOLOv8 model running on a Google Coral Edge TPU.

Discovering the MathWorks Modeling Award

We had heard of MATLAB and Simulink, however we never had the opportunity to learn it but all that changed when we heard about the MathWorks Modeling Award from our national organiser.

After exploring the learning resources provided by MathWorks for WRO, including their official WRO webinars, along with the MATLAB and Simulink Onramp courses, getting started became much easier than we expected. These resources helped us understand how to use modeling and simulation tools effectively and showed us how they could take our robot design to the next level.

Simulate, Test, Improve: Our Implementation Approach

Using MATLAB, Simulink and Simscape saved us so much time and played a major role in our development process

MATLAB was useful for writing our mapping and control logic. Its clear syntax made it easy to implement and modify algorithms quickly
Simulink was by far the best tool we used! We were able to tune algorithms and filters without needing any hardware, we can just tune it with the click of a button! The modular structure made it easy to identify where issues were occurring, and the built-in visualization tools helped us understand the robot’s behavior and diagnose logical problems that might otherwise have taken days to uncover.
Simscape Electrical was used to simulate our electrical system. By modeling current draw and stall current, we identified issues with our original battery choice since we kept having power issues. Fixing this early through simulation prevented a mistake that could have cost us the competition, and it’s a tool we plan to continue using in future robotics projects.

Models and graphs

Our main control model takes input from two different sources that both estimate deviation from the center of the lane. These signals are passed through a complementary filter, which produces an estimated deviation value. This output is then sent to a PID controller, mapped to a servo range, and finally sent to the steering servo

We intentionally kept this algorithm as simple as possible while maintaining reliable performance. This simplicity made tuning faster and troubleshooting more straightforward once the system was deployed.

When simulating we encountered a problem as there was no way to simulate camera readings, so as a work-around, we got readings from our test-runs and inputted it as a step function to know the output as shown in this graph

The output starts at 90, representing no deviation
It then moves to 60, commanding the servo to steer right

This approach allowed us to validate our control logic even without a fully simulated vision pipeline

As for the complementary filter sub-system. We used a simple complementary filter to fuse the sensor readings and calculate estimated deviation from the centre of the lane using the following equation:

 
θt =α(θt-1+ωtΔt)+θ acc,t(1-α)

where

θt = Estimated angle at time t

θt-1 = Angle estimate from the previous time step

ωt = Angular velocity from the gyroscope at time t

Δt = Sampling time interval

θacc,t = Angle estimated from the accelerometer at time t

α = Complementary filter coefficient (0 < α < 1)

Using Simscape Electrical

We developed a Simscape model of the robot’s electrical subsystem to perform system-level analysis which was not that difficult thanks to the detailed documentation on each block used in addition to the tutorial on the official MATLAB YouTube channel, we did come across a problem which was how to simulate microcontrollers so we used the Simscape power consumption block and calculated the maximum power consumption of the microcontrollers and used it as a parameter in the Simscape power consumption block

From the simulation results:

Maximum current usage was approximately 7 A
Required operating voltage was around 11.1 V

These results directly informed our battery selection and improved system reliability during competition runs.

Results and Key Takeaways

Using MATLAB, Simulink, and Simscape allowed us to model, simulate, and test our robot’s systems before deploying them on hardware. This helped us identify issues early, refine control strategies, and improve overall performance, ultimately contributing to our team winning the MathWorks Modeling Award.

The project taught us the importance of system-level thinking, simulation-based verification, and careful integration of hardware and software.

Looking ahead, we plan to enhance our models with more detailed sensor dynamics, environmental variability, and figure out a way to fully simulate our system including motion camera readings and implementing advanced mechanical steering.

Why Students Should Learn Model-Based Design: Insights from Industry Leaders at MATLAB EXPO

Tanya Kuruvilla — Mon, 26 Jan 2026 13:21:04 +0000

Introduction: Why These Skills Matter

Engineering today is a dynamic, fast-moving field. Whether you’re designing autonomous vehicles, aerospace systems, or renewable energy solutions, one truth remains: success depends on mastering both cutting-edge tools and foundational skills.

At MATLAB EXPO, Paul Shears, Chief Engineer at BAE Systems, talked with Ronald van Loon and shared insights that resonate deeply with students and early-career engineers. His message was clear:

Model-Based Design (MBD) is transforming how complex systems are developed.
Curiosity and hands-on learning are the keys to thriving in this evolving landscape.

After watching Paul’s interview we’ll explain why MBD matters, how you can start learning it today, and what core skills will set you apart in your engineering journey.

Why Model-Based Design Matters

Imagine you’re tasked with designing a flight control system for a fast jet aircraft; a system where safety is non-negotiable and precision is everything. Traditionally, such projects required 12 months and a team of 30 engineers. But at BAE Systems, using Model-Based Design (MBD) with tools like Simulink and Simscape, the same task was completed in under three months by just six engineers; and delivered with zero defects.

So, what makes MBD so powerful?

Instead of writing thousands of lines of code upfront, engineers create graphical models that represent system behavior. These models can be simulated early in the design process, allowing teams to verify performance before hardware is built. Once validated, the models can automatically generate production-quality code for embedded systems.

Paul explained how this approach transformed their workflow:

“We use a very multi-domain model based approach which covers the entire V life cycle of a product development life cycle. I think one of the examples where we’re quite proud is in the development of a full authority digital flight control computer. So we used great technologies from MathWorks like Simulink to design that software and then use that to autocode the software. Now as you can imagine that’s a very large complex piece of software. Very safety critical indeed. We’re able to autocode that. So shaving lots of time and money off the development cost and actually deliver it to the customer with uh with defects.” 

Another example involved hydraulic actuator control systems for fast jets. Using Simulink and Simscape, the team modeled the physical system, tested control logic, and auto-generated code for FPGA hardware. When integrated into real hardware, it worked first time; a testament to the reliability of simulation-driven design.

Why It Matters for Students

Industry Standard: Model-Based Design is widely adopted in aerospace, automotive, robotics, and beyond.
Efficiency: It reduces development time and cost while improving reliability.
Career Advantage: Employers value engineers who understand simulation-driven workflows and can bridge theory with practice.

Getting Started with Model-Based Design

You don’t need a defence lab to learn MBD. You can start right now with tools and resources available to students:

Begin with MATLAB and Simulink basics. These platforms are the foundation of MBD and are widely used across industries. Explore free tutorials on the MathWorks MATLAB and Simulink Resources for Students webpage, which offers step-by-step guides for beginners.

Next, simulate simple systems. For example, model a DC motor or a PID controller in Simulink. Experiment with parameters and observe how changes affect performance. This hands-on approach helps you understand the cause-and-effect relationships in system design.

Once you’re comfortable, dive into Simscape for physical modeling. Simscape lets you represent multidomain domain systems in a unified environment—perfect for multidisciplinary projects.

Pro Tip: Use MATLAB Live Scripts to combine code, equations, and visualizations in one interactive document. This makes your work easy to share and present, whether for coursework or competitions.

Core Skills for Early-Career Engineers

Technical tools are essential, but they’re not enough. Paul’s advice? “Be a tinkerer.”The most successful engineers are creators who love experimenting and learning by doing.

Start by writing simple scripts in MATLAB or Python. These languages form the backbone of modern engineering workflows. Solve problems on coding challenge platforms to sharpen your logic and algorithmic thinking.

Then, take it a step further: build prototypes. Use Arduino boards, sensors, and servos to create small systems. This hands-on approach teaches you how software interacts with hardware—a skill that’s invaluable in embedded systems, robotics, and IoT.

And don’t do it alone. Collaboration is key. Join a student club, participate in a competition hackathon, or work on team projects. Engineering is a team sport, and employers look for candidates who can communicate effectively and adapt to different roles.

Soft Skills to Cultivate:

Problem-Solving: Break down complex challenges into manageable steps.
Creativity: Think beyond the obvious—innovation often comes from unconventional ideas.
Continuous Learning: Technology evolves fast; stay curious and keep upskilling.

Paul summed it up perfectly:

“For a successful career in engineering and I’ve been one for 25 years, I think it’s always about challenging yourself and learning new things and that that passion to learn and grow, rather than just sitting on a static piece of knowledge.”

Building a Career Mindset

In industries like aerospace and defense, projects can span decades. That means continuous learning isn’t optional—it’s essential. Knowledge retention and adaptability are key to staying relevant.

Paul highlighted a unique challenge:

“A lot of our products we have support contracts that extend out like 40 or 60 years and we have to support things in the field. So as you can imagine knowledge retention and business continuity is a big problem. At the same time you know someone doesn’t want to work on one thing all their career right so you need an organization where people can move around rotate so they can continuously learn and grow and upskill themselves.” 

One enabler of this flexibility is Model-Based Engineering, which provides a common language and toolset across product groups. For students, this means learning tools like MATLAB and Simulinkisn’tjust about oneproject—it’sabout building a foundation that applies across domains.

How to Stay Ahead:

Rotate through different areas—controls, AI, embedded systems—to broaden your perspective.
Learn emerging technologies like AI and machine learning, but understand their ethical and safety implications.
Build networks: Join student clubs, attend hackathons, and participate in events like MATLAB EXPO to connect with peers and industry experts.

These experiences often lead to internships, research opportunities, and full-time roles. More importantly, they help you develop the adaptability that modern engineering careers demand.

Conclusion: Your Journey Starts Now

Engineering is about solving interconnected problems—and the tools and methods will keep evolving. Combine technical mastery (MATLAB, Simulink, AI) with curiosity and collaboration, andyou’llbe ready for the challenges—and opportunities—of modern engineering.

Start today:

Explore MathWorks tutorials and learning paths.
Build your first simulation.
Share your projects with the community.

The future of engineering needs problem-solvers like you. Be inspired, be creative, and keep learning.

Watch the full video here.

Click here to find MATLAB and Simulink resources for students.

UK Expo 2025

From Inspiration to Grand Prize: How MATLAB Helps You Stand Out in Electronic Design Competitions

Tanya Kuruvilla — Tue, 06 Jan 2026 04:49:29 +0000

Every year, outstanding graduate students from fields such as electronics, communications, computer science, and integrated circuits gather at the China Graduate Electronics Design Competition (GEDC).

There, they tackle cutting-edge technical challenges, receive in-depth guidance from industry mentors, and collaborate with like-minded peers—gaining valuable experience in teamwork and technical development.

This year, the 20th GEDC successfully concluded in mid-August, with numerous innovative projects standing out. Among them, the teams that received MathWorks Awards focused on advanced fields such as communications, power electronics, and robotics.

They proposed innovative solutions to address current research hotspots and real-world societal needs. Some of the winning team members are research experts, others are engineering talents, and some started out simply as newcomers curious about electronic design. Yet all of them used MATLAB to accelerate the design and development of their projects, ultimately earning prestigious national-level awards.

In today’s blog, let’s take a closer look at how the winning teams of the MathWorks Awards at GEDC used MATLAB to ignite their dreams and shape the future!

Winning Projects at a Glance

Channel Characteristic Modeling and Hardware-in-the-Loop Simulation Integrated Verification System (“Leading Goose and Vanguard” team, Beijing Jiaotong University)

Targeting emerging application scenarios such as 5G/6G and the industrial internet, the team developed a comprehensive integrated system that combines channel measurement, modeling, and hardware link verification. Leveraging an RFSoC-based multi-phase parallel architecture, the system achieves ultra-wideband channel simulation at 1 GHz.

The team also introduced an automated modeling platform and high-fidelity channel reproduction for multiple scenarios, supporting various multi-source modeling methods. This greatly enhances the reliability and efficiency of communication testing in complex environments.

MATLAB was used to implement key algorithms for channel modeling, such as CIR calculation, path loss fitting, and Doppler analysis. Simulink was employed to build link-level simulation models, ensuring a high degree of consistency between channel parameters and hardware behavior.

Channel parameters generated by MATLAB can be seamlessly imported into the FPGA simulator, facilitating collaborative software and hardware development. This significantly accelerated progress on challenging tasks such as 1 GHz ultra-wideband signal processing.

Channel Emulation Simulator and Channel Measurement & Parameter Extraction User Interfaces

Design and Implementation of an Integrated Communication and Remote Sensing Low-Earth Orbit Satellite System (“Xinglian ComSense Squad” Team, Zhejiang University)

Aiming at the future demands of 6G and space-based information systems, the team innovatively integrated broadband communication and high-resolution remote sensing into a single low-Earth orbit satellite, achieving a deep convergence of communication and remote sensing functions.

This approach provides new solutions for fields such as emergency rescue and intelligent transportation. The project adopts Orthogonal Delay-Doppler Division Multiplexing (ODDM) waveforms and an integrated transmission protocol, overcoming the limitations of traditional discrete systems. This deep integration significantly enhances the robustness of satellite-to-ground communication and the precision of SAR imaging.

In this project, MATLAB was used not only to implement complex integrated communication and remote sensing protocols, as well as baseband processing algorithms, but also to fully leverage features such as high-dimensional matrix operations, multithreading, and GPU parallel computing.

This enabled efficient processing of large-scale data and ensured real-time performance, providing a solid foundation for the high-performance requirements of satellite-to-ground communication and SAR imaging.

Integrated Communication-Sensing LEO Satellite System Prototype, User Interface, and Test Scenarios

Full SiC Multifunctional Photovoltaic Inverter (“EnerVision” Team, Huazhong University of Science and Technology)

To address issues such as slow switching speeds and high losses in traditional photovoltaic inverters that use Si-IGBTs, the team innovatively adopted SiC-MOSFETs as the main power devices, achieving leading metrics such as a peak conversion efficiency of 99% and a volumetric power density of 1.5 kW/L.

The team introduced several technological innovations, including a low-parasitic silicon carbide power bridge design, lightweight passive filter components, and high-bandwidth differential/common-mode power flow decoupling control.

These advancements significantly improved the inverter’s conversion efficiency, power density, and control performance, providing both theoretical and practical foundations for the development of high-performance domestic photovoltaic inverters.

During the development of the project, MATLAB and Simulink played a crucial role. The team used MATLAB for double-pulse test data processing and independently developed test scripts, reducing development costs.

In key stages such as modulation strategy formulation, passive filter component design, and controller parameter tuning, MATLAB/Simulink was used for loss calculation, parameter optimization, and simulation verification, greatly improving development and debugging efficiency.

For example, by using MATLAB programming to optimize the filter inductor design, the inductance was reduced by about 30%. With Simulink, the team built a complete system model and combined it with S-Function, increasing controller development efficiency by approximately 30%.

Full SiC Multi-Functional PV Inverter Prototype and Simulink Model

RailGaidian – Monorail Robot for Clustered Railway Fastener Maintenance in Intelligent Infrastructure (“RailGaidian” Team, Beijing Jiaotong University)

To meet the demand for efficient and intelligent maintenance of China’s vast railway network, the team developed a modular, clustered monorail robot system capable of automatic detection, removal, and replacement of railway fasteners. This greatly enhances the automation and safety of railway maintenance operations, providing strong technological support for the strategy of building a transportation powerhouse.

RailGuardian Robot Operating On a Monorail Track

The project achieved several technological breakthroughs in areas such as structural design, 3D points cloud recognition, GPR pressure prediction, and path planning. The team used MATLAB and Simulink for robotic arm dynamics analysis, point cloud data processing, algorithm modeling, and simulation.

Robotic Manupulator Dynamics Analysis, Point-cloud Data Processing, and Simulink Modeling & Simulation

Smart Swallowing Assistant – Self-Sensing Multi-Modal Soft Gripper Based on Annular Optical Waveguide (“Grab & Learn” Team, Nanjing University of Information Science & Technology)

Aimed at applications in industrial automation and medical-assisted surgery, the team innovatively integrated optical waveguide sensors with soft robotic structures, achieving unified actuation and sensing.

Inspired by the physiological movements of sea anemones, the device features three biomimetic working modes: expansion, swallowing, and tactile sensing at the end-effector.

It can sense the shape, hardness, and roughness of objects in real time and, by combining multimodal signals with machine learning algorithms (such as KNN and LSTM), achieve high-precision intelligent recognition.

In this project, the team used Simulink to build modules for sensor signal acquisition and pneumatic drive control, while MATLAB was employed for data processing, feature extraction, and machine learning model training.

They also innovatively implemented real-time radar chart visualization of eight-channel sensor signals, greatly improving experimental efficiency and the intuitiveness of results presentation.

How Did MATLAB Help the Winning Teams?

MATLAB played a crucial role in the success of the winning teams by providing a comprehensive platform for algorithm development, data analysis, simulation, and hardware integration.

During their preparation for the competition, the teams made full use of the following advantages of MATLAB and Simulink:

Integrated Development Workflow: MATLAB and Simulink cover the entire process from algorithm design, simulation, and data processing to hardware co-debugging, significantly shortening development cycles.
High-Performance Parallel Computing: Fully leverage GPU acceleration, matrix operations, and multithreading capabilities to meet stringent requirements for real-time and large-scale data processing.
Software-Hardware Co-Innovation: Support seamless integration between models and hardware, facilitating rapid algorithm deployment and system performance optimization.
Powerful Visualization and Debugging Tools: Enhance team collaboration efficiency and project presentation, accelerating experimental iteration and problem-solving.
Abundant Learning Resources and Community Support: Official documentation, case studies, and forums provide strong support for team members to quickly get started and tackle challenges.

MATLAB & Simulink not only accelerate innovation and enhance engineering implementation capabilities but also inject new momentum into the future development of electronic information industry and intelligent society.

Insights and Advice from Winning Teams

The winning teams not only achieved breakthroughs in technological innovation but also gained valuable experience in learning and applying MATLAB and Simulink. Here are some insights and advice they shared:

– Beijing Jiaotong University’s “Leading Goose and Vanguard” team offered the following advice:

“When learning and applying MATLAB and Simulink, we recommend starting with official training, documentation, and case studies. Combine these resources with hands-on practice using the Communications Toolbox, and gradually master script writing, model building, and hardware co-debugging skills through project-driven learning.”

– Zhejiang University’s “Xinglian ComSense Squad” members shared:

“MATLAB has concise syntax, is easy to learn, and offers abundant resources, making it especially suitable for scientific simulation and engineering implementation. We suggest not only focusing on the syntax, but also understanding MATLAB’s execution mechanisms and its relationship with hardware deployment, such as high-dimensional matrix operations and parallel computing.”

– Nanjing University of Information Science & Technology’s “Grab & Learn” team summarized:

“Learning by doing and problem-driven approaches are the most effective ways to master MATLAB. We recommend that beginners deepen their understanding step by step through real projects and make good use of official MATLAB documentation and forum resources. Code standards and model readability are crucial for team collaboration. Future participants should familiarize themselves early with data acquisition and signal processing workflows, and practice with real-world cases as much as possible.”

Members of these teams all expressed that the powerful features and rich ecosystem of MATLAB have greatly improved their project development efficiency and research innovation capabilities!

Empowering Your Innovation Journey with MATLAB & Simulink

Whether you are a research enthusiast, engineering expert, or newcomer to electronic design, MATLAB and Simulink can be your “best partners” on the road to innovation.

They not only provide a strong technical foundation for participating teams, but also serve as important platforms for driving innovation, accelerating engineering practice, and achieving deep integration of industry, academia, and research.

With MATLAB and Simulink, you can make team collaboration more efficient, turn your ideas into reality faster, and pave a broader path for your future studies, competitions, and research!

Congratulations to all the winning teams! Now it’s your turn!

DD ROBOCON India 2025 MathWorks Modeling Award: From Simulation to the Real-World with BRACT’s VIT Pune

Tanya Kuruvilla — Mon, 15 Dec 2025 12:56:03 +0000

In today’s blog, we have Tanmay Bora and Saumitra Kulkarni from Team BRACT’s Vishwakarma Institute of Technology, Pune, India. The team won the MathWorks Modeling Award at the DD ROBOCON India 2025 competition. Over to you..

Abstract

This blog highlights Team BRACT’s VIT Pune’s journey to a personal best finish of All India Rank 3 at DD ROBOCON India 2025, and how MathWorks tools enabled to transition their robots from simulation to reality. The blog covers their use of model-based design in Simulink and Simscape, image processing and computer vision workflows with the Computer Vision Toolbox and Deep Learning Toolbox, and a custom MATLAB App Designer-based interface for monitoring performance of their robots. The blog concludes with their key learnings from the competition and experience with MathWorks tools.

Motivation and Objective

The Team participated in DD ROBOCON India 2025 to enhance their robotics skills by solving real-world engineering challenges. By using MathWorks tools to model, analyze, and optimize robot performance in dynamic environments, they aimed to surpass their previous quarterfinal finishes at this competition.

Problem statement for DD ROBOCON India 2025

At DD ROBOCON India 2025, each student team deployed two robots to compete in a fast-paced basketball match that emphasized both offensive and defensive strategies in a two-minute game with a 20-second shot clock. One robot specialized in scoring baskets, while the other focused on defense. As is required in a game of basketball, agility, strategy and precision, were key attributes demanded in the robots.

GIF 1: BRACT’s VIT Pune (in red) scoring a three-pointer on their way to the semi-finals.

GIF 2: BRACT’s VIT Pune (in red) demonstrating precise dribbling and agile movement across the court.

Approach

The Team simulated and tested prototypes of their robots in Simulink and Simscape to analyze mechanical design and control strategies. Canonical camera-based depth estimation and deep-learning based object-detection workflows, implemented with the Image Processing Toolbox , Computer Vision Toolbox, and Deep Learning Toolbox, facilitated real-time detection of the basketball and hoop to assist shots. ROS nodes, integrated using the ROS Toolbox, established a middleware that resulted in agile and semi-autonomous robot performance on the court.

(A) Hardware

Dribble:

GIF 3: The ball-dribbling mechanism designed and tested in Simscape (left) translated well into the real-world (right).

A pneumatically driven piston was engineered to deliver quick, controlled, and consistent basketball dribbles, with a motorized catching-system for ball retrieval. Back-of-the-envelope component sizing was optimized using MATLAB scripts and Simscape Multibody simulations, accelerating the development of this physical mechanism.

Throw:

Figure 1: An electric motor-driven double-rotor mechanism conceptualized for the mechanism that shoots a basketball into a hoop.

An electric motor-driven shooter with counter-rotating rotors compressed the basketball before launching it. For a given distance from the hoop, height of the hoop, angle of launch of the ball, and mass of the ball, repeated tests in simulations using the Multibody Explorer of Simscape narrowed down the candidate launch velocities, forces of ball-compression, angles of launch, and motor RPMs, for this mechanism.

Figure 2: The Simscape model of an electric motor sketched by the Team.

The electric motors were modelled in Simscape and tested over a series of load torques – applied as step inputs – to simulate launch commands. Metrics such as RPM, current, and power, were monitored. The MY6812 DC motor was selected for its high torque and reliability, and its integration into the double-rotor mechanism enabled consistent launch velocities. Motor RPM was empirically mapped to robot position relative to the hoop and regulated by a PID controller tuned using the Zeigler-Nichols method.

GIF 4: A well-tuned electric motor-driven double-rotor mechanism shoots a basketball into the hoop in a Simscape simulation (left) and in the real-world (right).

Defense:

GIF 5: A belt-and-pulley driven net blocked and defended against the opponents’ shots at the hoop, in simulation (left) as well as in the real-world (right).

A motor-driven belt-and-pulley system deployed a flexible net on the second robot to block opponent shots. The net was modelled in Simscape with spring-damper properties to replicate realistic energy absorption. A 555 PMDC motor actuated and stabilized the defense mechanism against load-torque variations during a block.

Motion:

Figure 3: Omni-directional wheels modeled in Simscape (left) were arranged at 120-degree intervals on the robot base (right).

Three motor-driven omnidirectional wheels enabled agile and holonomic movement for both robots. Each wheel was modeled in Simscape with disks and perpendicular rollers that realistically simulated wheel-ground interactions.

(B) Software

Detecting the basketball and hoop:

Figure 4: Detecting basketballs (top) and hoops (bottom) from different point-of-views in images using a MATLAB-OpenCV-YOLOv4 pipeline.

A computer vision pipeline in MATLAB, with OpenCV integrated, was used to detect the basketball and hoop in real-time. This detection was the first step to predict the trajectory of the ball for an attempted shot from a given position on the court and provided real-time feedback to the student operator to correctly position the robot before taking a shot.

Preparing the dataset – The Image Labeler application in the Computer Vision Toolbox was used for annotating a dataset of 1000 images of basketballs and hoops, collected from diverse point of views of the camera. Data-augmentation techniques such as horizontal flips, random colour jitter, scaling, and image cropping, were applied to the training samples for robustness against variations in lighting conditions, camera angles, and ball orientations, typically encountered during a match. Preprocessing techniques such as aspect ratio preservation and pixel scaling were applied to normalize images fed into a machine learning model for detecting basketballs and hoops. This improved convergence and reduced overfitting at the time of training the model.

Creating an object detection network – The yolov4ObjectDetector MATLAB function was used to create the YOLOv4 one-stage object detector provided in the Deep Learning Toolbox. Techniques such as Mosaic data augmentation, DropBlock regularization, and Self-Adversarial Training, available in the ‘Bag of Freebies’ in YOLOv4, improved object detection in different lighting conditions and noise levels, and reduced the size of the dataset required.

Training and evaluating the YOLOv4 object detector: An appropriate batch size, learning rate, and number of epochs, were provided to train the YOLOv4 one-stage object detector after splitting the dataset for training (60%), validation (10%) and testing (30%). The average precision metric and the precision-recall curve generated in the Deep Learning Toolbox were used to evaluate the accuracy of the object detector. Over the course of training, an average precision of 0.97 and 0.95 was achieved for the hoop and basketball, respectively.

Deployment on Jetson Xavier with ROS integration:

Figure 5: The workflow used to deploy the YOLOv4-based object detection models on an NVIDIA Jetson Xavier computer.

The flowchart shown above outlines the workflow used to deploy the YOLOv4-based object detection model on an NVIDIA Jetson Xavier computer. The detector was launched on the computer by converting MATLAB-trained models into an ONNX format, optimized using TensorRT. These models were integrated into ROS nodes, developed in the ROS Toolbox, and transferred to the Jetson Xavier, where GPU acceleration enabled fast, reliable detection and trajectory estimation from live mobile video feeds on the robot.

Camera Calibration:

Figure 6: Using a checkerboard pattern to calibrate cameras for depth-estimation.

The Team installed camera-equipped mobile phones on the robots. Camera-calibration was performed using a checkerboard pattern to accurately map object-detections from image space to real-world coordinates. The estimateCameraParameters MATLAB function of the Computer Vision Toolbox estimated both intrinsic and extrinsic parameters and corrected for lens distortion. Calibration helped relate the basketball and hoop in a 2D image to their 3D location relative to the robot on the basketball court.

Using ArUco Markers to estimate distance from the hoop:

Figure 7: Using an ArUco marker to estimate real-time position and orientation of the robot relative to the basketball hoop.

The calibrated mobile phone camera was used with an ArUco marker to estimate the real-time position and orientation of the robot relative to the basketball hoop. The Team positioned the marker on a flat surface close to the hoop during the pre-match setup window offered to students. The readArucoMarker MATLAB function was used to detect the marker in a live video stream from the mobile phone. Therefore, during a match, the team could estimate the distance and heading of the robot relative to the hoop, and command motor RPMs if needed, before taking a shot to score a basket. In autonomous mode, the position and orientation data would be relayed to an internal PID based control system that pointed the robot at the hoop.

Estimating trajectory of the basketball:

Figure 8: Tracking the position and velocity vector of the center of the basketball.

The center-pixel of the ball was tracked over multiple image frames to predict its velocity and future trajectory. This capability allowed the student operator to judge, in real time, if the ball would pass through the hoop, and aided in manually adjusting the pose of the robot, and the motor RPMs of the shooting mechanism.

Real-time performance monitoring on a GUI:

Figure 9: A graphical user interface developed in the MATLAB App Designer to monitor robot health.

A live video-stream, overlaid with the detections of the basketball and hoop, was relayed to a graphical user interface (GUI) that displayed on screens fit onto remote controllers used by the students to control the robot. This GUI was developed using the MATLAB App Designer. In addition to the object detections, the GUI also displayed the estimated distance of the robot to the hoop, the anticipated trajectory of the basketball before a shot was taken, and data to monitor system health.

Results

At the DD ROBOCON India 2025 competition, the team achieved an All India Rank 3 and brought home the MathWorks Modelling Award, the NAM:TECH Award for Second Runner-Up, and the IHFC Award for Robotics and AI. These honors recognized their innovation and technical skill, highlighting the importance of simulations and mathematical modeling in robotics. The Team leveraged a model-based design workflow to evaluate multiple concepts, fine-tune mechanisms, and eventually finalize designs that were both practical and competition-ready.

Learning

The key positives observed by the team can be summarized as

1) Model-based design and simulations allow a system to be virtually tested, optimized, and verified, before being fabricated. This saves time, effort, and resources

2) Building and deploying a robot to solve real-world engineering problems provides exposure to skills spanning mechanical design, electrical systems and circuits, computer engineering, computer science, optics, sensor integration, and fabrication .

Next Steps

Looking ahead, the Team plans to build on their present work by

1) using the PID Tuner app for automatic tuning of the PIDs that control motor RPMs, and

2) using the Reinforcement Learning Toolbox from MathWorks to train the robots in adversarial scenarios and improve high-level decision making in dynamic environments (for e.g., to shoot a basket or pass the ball?).

Leveraging Photosynthesis for Carbon Sequestration with MATLAB to win NACME’s 2025 National Virtual Bridge Engineering Design Challenge

Tanya Kuruvilla — Mon, 01 Dec 2025 15:35:27 +0000

Today’s guest blogger is Kathy Zhang, who will be sharing her conversation with the winning team from NACME’s 2025 National Virtual Bridge Engineering Design Challenge. The team was made up of incoming engineering students heading off to different US universities and they worked together to develop a prototype that can sequester carbon dioxide from the air using photosynthesis. Let’s dive into the team’s process of coming up with this innovative design!

What is the NACME 2025 National Virtual Bridge Engineering Design Challenge?

This summer, 39 students matriculating into their first year of undergraduate engineering had the unique opportunity to attend the five-week NACME National Virtual Bridge program (NVB), supported in part by MathWorks. The goal of the program is to support students’ academic and social transitions to college, including a curriculum taught by professors and graduate student teaching assistants from around the country spanning calculus, programming, physics, and engineering design. As part of the Engineering Design course taught by Dr. Taylor Lightner and Nicole Jefferson, students were challenged to work in teams and develop a product that addresses one of the 14 National Academy of Engineering grand challenges of the 21st century. In the final week of the program, each team presented their design to a panel of judges from academia and industry.

Jeremiah Cojon-Keddie, Hollis Davies, Katie Finn, Caroline Hortin, Andres Sanchez-Gonzalez, Chauncey Tillman, and Aiyrub Umatiya decided to tackle the challenge of carbon sequestration. They designed a plant window box that leverages photosynthesis to capture carbon dioxide from the atmosphere – turning every apartment window in an urban city into a micro-carbon filter. Their prototype, named the “C- filtration box”, won the program’s Engineering Design Challenge.

Pictured clockwise from the top left- Caroline Hortin, Andres Sanchez-Gonzalez, Aiyrub Umatiya, and Hollis Davies of the winning NACME National Virtual Bridge Engineering Design Challenge team. Not pictured are teammates Jeremiah Cojon-Keddie, Katie Finn, and Chauncey Tillman.

How does the C- filtration box work?

The C- filtration box intakes city air and filters it using plants housed inside. The design went through several rounds of iteration: while the team had first considered a prototype that simply captured CO2 from the air, they realized that transporting the captured CO2 would generate as many emissions as they had captured. When Aiyrub discovered that plant growth could be enriched by CO2, the team agreed that a biotechnological solution better served their mission. The C- filtration box contains sensors to monitor the box’s internal conditions and uses actuators, such as fans and UV light, to automatically adjust the temperature, humidity, and light penetration. The goal is to maximize photosynthesis efficiency and therefore the plants’ CO2 absorption. The sensor data is then visualized on an outer control panel screen so the user can monitor how much light is entering the box, the rate of photosynthesis, the rate of CO2 absorption, and the amount of power being consumed.

Sketches of the C- filtration box prototype. Images courtesy of Hollis Davies.

Hollis explained that they decided to use plants as the carbon filtration method after going through the process of visualizing the data in MATLAB: “Seeing a good visualization of how the plant’s CO2 absorption rate would correspond with different factors like heat or light index – a lot of it came down to looking at those graphs and seeing, OK this can work.” The clear relationship between the environmental conditions in the box and the plants’ rate of CO2 absorption gave the group confidence in their design because they realized they could essentially control the rate of CO2 absorption as easily as turning on a UV light or a fan. The MATLAB code below shows how they visualized the relationship using a 3D graph:

% Light Intensity Data – PAR in hours, values derived from a database

x = [0,0,0,5,10,50,100,186,290,390,480,520,530,510,450,420,320,300,230,120,70,30,0,0];

% Photosynthesis rate – derived from a second dataset

r = [3/20,9/200,4.5/100,2.5/200,1/180];

% Function that obtains photosynthesis rate for each light value

function e = getrate(a,t)

 e = [];

 for i = 1:length(a)

 if a(i)>499

 e(end+1) = 17+((a(i)-499)*t(5));

 elseif a(i)>299

 e(end+1) = 12.5+((a(i)-299)*t(4));

 elseif a(i)>210

 e(end+1) = 9+((a(i)-210)*t(3));

 elseif a(i)>20

 e(end+1) = 3+((a(i)-20)*t(2));

 else

 e(end+1) = (a(i)*t(1));

end

end

end

% Conform light and photosynthesis rates to a 2D plane

[x1,y1] = meshgrid(x,getrate(x,r));

% Create a trendline to approximate CO2 data from photosynthesis rate

rt = 0:0.5:19.5;

c = 0:2.5:97.5;

coef = polyfit(rt,c,5);

zFit = (polyval(coef,y1)).*((x.^2)./(x.*100));

% Create graph

surf(x1,y1,zFit);

% Add labels

xlabel(‘Light Intensity (umol/m^2)’);

ylabel(‘Photosynthetic Rate (umol/m^2/s)’);

zlabel(‘CO2 Absoprtion Concentration (ppm)’);

shading interp

title(‘CO2 Absorption’)

view([66 8])

When it came to implementing their design with code, Hollis said he started with a flowchart: “My class [in high school], it was always a template – OK, do XYZ. But I felt that it’s most helpful to start with a flowchart, just on a piece of paper. I’ll start with inputs and then I’ll get to a point where I [figure out what] I need to do [with them].” For this project, the inputs were simulated sensor data, and he needed to compute and visualize photosynthesis and CO2 absorption rates. To do this, Hollis got help online: “Some parts, I would run something and then, OK, clearly, I’m not doing something right. That’s when I would turn to outside stuff like YouTube. There’s a lot of tutorials on five dedicated MATLAB channels and they just have thousands of videos. So, it was really easy to find what we needed.”

Key Takeaways

Reflecting on their win, team members agreed while the technical aspects of their project gave them an edge, their teamwork leading up to delivering an effective presentation was the key factor contributing to the team’s win. As instructors who have participated in the program for the past three years, Dr. Lightner and Nicole shared that the competition has always been a favorite moment of theirs. Both instructors expressed that the students’ challenge presentations demonstrate how far the students come in just a few weeks not only in their technical knowledge, but also in the community they build with peers. For Dr. Lightner, she hopes that the engineering challenge helps students realize the importance of active engagement in their courses and submitting work that they are genuinely proud of.

Aiyrub’s lasting lesson from participating in the challenge embodies those goals: “At first, I was a little hesitant to share my Python code, but what I understood after doing [the project], you need to challenge yourself to learn. If I didn’t push myself to write the code, maybe we wouldn’t have won. It gave me a confidence boost that my effort wasn’t in vain, so I’m going to continue to challenge myself.”

With the program wrapped up and the fall semester about to begin, Andres said he was “very excited and quite literally counting the days” to start his degrees in Cybersecurity and Computer Engineering at the University of Cincinnati. Caroline agreed and said she felt like the bridge program was a “cliffhanger. I have this drive and this momentum I want to keep going into college.” She will be starting her first year of Chemical Engineering at the University of Kentucky, Hollis is heading to the University of Cincinnati to study Architectural Engineering, and Aiyrub is off to Texas A&M to start his degree in Aerospace Engineering. With this exciting challenge win under their belt, we are excited to see what these students will accomplish in the future!

Artificial Intelligence Challenge 2025 – Meet the Winners

Tanya Kuruvilla — Mon, 17 Nov 2025 15:57:19 +0000

For today’s post, Roberto Valenti, who leads the MathWorks Challenge Projects program, will introduce the winners of the 2025 Artificial Intelligence Challenge. Over to you, Roberto..

Artificial intelligence is rapidly transforming how we approach complex problems across all kinds of fields. Inspired by this momentum, we launched the AI Challenge as part of the MathWorks Challenge Projects Program, inviting students to take on real-world problems from our curated AI list. Our challenge attracted many creative and technically rigorous submissions from students around the world, making the judging process both exciting and exceptionally difficult, but it was the three winning teams that stood out for their innovation and impact.

I am excited to introduce the three winning teams and their projects, and to share a bit about their journeys in the challenge. Their stories are a great example of what can happen when talented students tackle real-world challenges with fresh ideas and teamwork.

First Place Winner: Adit Shah – Top Quark Detection Using Deep Learning and Big Data

Meet the Winner:

Adit Shah is a final-year undergraduate student in Electronics and Communication Engineering at Dwarkadas J. Sanghvi College of Engineering, Mumbai. He first heard about the AI Challenge 2025 from his professor on a WhatsApp group. What really piqued his interest was discovering that deep learning could be implemented in MATLAB—something he had not realized before. After exploring the Deep Network Designer App and finding it intuitive, Adit was drawn to the challenge statement on “Top Quark Detection using Deep Learning and Big Data.” As someone fascinated by particle physics and all the exciting research happening at CERN, the choice was obvious for him.

The Project:

Quarks are the fundamental building blocks of matter, and the top quark is the heaviest and most elusive of them all. Because it decays almost instantly, its presence must be inferred from the jets of particles it leaves behind in high-energy collisions—a process that’s both complex and error-prone. Adit’s project tackled this challenge by using deep learning to distinguish top-quark events from the vast background of other jets, making identification faster and more accurate.

Innovative Approach:

Adit’s method started by aligning the jet images in a consistent way. Since the dataset didn’t have a standard orientation, he rotated each jet so that the second most energetic constituent pointed along the positive X-axis, helping the model focus on the distribution patterns rather than arbitrary directions. To further standardize the images, he ensured the area with the most energy was always at the bottom, flipping images when needed. This careful preprocessing meant the model learned the right features, not just orientation quirks. He also applied z-score normalization to make sure all features contributed fairly during training.

To enrich the information available to the model, four additional global statistics were computed for each jet: Energy Skewness, Transverse Momentum Skewness, Energy Kurtosis, and Transverse Momentum Kurtosis. These parameters were calculated radially from the jet center and provided a summary of the jet’s structure beyond what was visible in the images. This multimodal approach fused these statistics with the CNN’s final layers, giving the network both local and global perspectives on each jet.

Neural Network Model and Channel Attention:

The core of the solution was a custom ResNeXt-based Convolutional Neural Network, which leverages aggregated residual transformations with grouped convolutions. In this architecture, the channels are divided into separate groups, and each group learns to extract distinct features from the data, which is more effective than processing all channels together. As the network deepens, the number of channels increases and their relative importance can vary significantly.

To address this, Squeeze-and-Excitation (SE) blocks were integrated after major grouped convolution layers. These SE blocks apply channel-level attention by explicitly modeling the importance of each channel for the classification task. They assign higher weights to channels that carry more discriminative information and suppress less useful channels, ensuring that the network’s focus remains on the most relevant features for distinguishing top-quark jets from background jets. This channel-wise attention mechanism was key to boosting the model’s performance and interpretability. Training and experimentation were performed in MATLAB’s Deep Learning Toolbox and Deep Network Designer, enabling rapid iteration and testing of different architectures and preprocessing strategies.

The Neural Network architecture

Results:

The final model achieved a testing accuracy of 90.87%, with an ROC of 0.968 and an AUC of 0.971, demonstrating strong discrimination between top-quark and background jets. The workflow also included converting the trained network into HDL code for FPGA deployment, highlighting the potential for real-time applications in experimental physics environments.

Experience & Reflections:

Adit spent about two weeks just getting to grips with the dataset and researching the key statistics needed to tell different types of jets apart. “I was initially unaware that deep learning could be implemented in MATLAB, so I decided to explore the Deep Network Designer app and found it to be very intuitive,” he shared. The process was a deep dive into both particle physics and practical AI, combining his academic interests with hands-on learning.

“I learned so much while doing this project. It was full of head-scratching moments, but I loved it because I was naturally drawn to particle physics and Machine Learning. The ending days were particularly stressful because I had another competition submission just before the submission of this challenge and I was left with all the documentation, video recording and writing comments for this one. But this is the kind of stress that made the results worth it.

What began as an experiment to combine my interests in particle physics and machine learning turned into one of the most rewarding moments of my academic journey. Winning this challenge inspired me to pursue research in AI and Electronics. I thank Dr. Roberto G. Valenti for continuous support and discussion on improving my project even further after the competition, and for his help with the related research paper.”

Explore Adit’s solution – GitHub repository

Second Place Winners: Nicola Gallucci, Matteo Malagrinò, Giacomo Aragnetti – Classify RF Signals Using AI

Meet the winning team:

Nicola, Matteo, and Giacomo are undergraduate students in Computing Systems and Telecommunications Engineering at the Polytechnic of Milano. They discovered the AI Challenge through a LinkedIn post by MathWorks. Motivated by curiosity and a passion for wireless technologies, they decided to participate as an extracurricular project outside their regular coursework. For these students, this project was more than just a competition; it was their first major “mission” at university. It introduced them to the SmartBAN protocol—an emerging standard for Body Area Networks (BANs)—which was new to almost all of them. Their work not only deepened their technical expertise but also caught the attention of a professor connected to the European Telecommunications Standards Institute (ETSI) SmartBAN Technical Committee. As a result, they were invited to present their project at an ETSI meeting, giving them a unique opportunity to share their research with leading experts in the field.

The team is now looking forward to research careers and has even written a paper about their project, which they hope will be accepted at a conference—a testament to the impact this experience has had on their academic journey.

The team: from left to right: Giacomo Aragnetti, Matteo Malagrinò, and Nicola Gallucci

The Project:

In modern wireless environments, critical medical transmissions from Body Area Network (BAN) nodes can easily be masked by overlapping signals from technologies like WLAN, ZigBee, and Bluetooth. This interference poses a significant challenge: how can we reliably detect and classify BAN-related signals—especially those using the emerging SmartBAN standard—when the spectral environment is crowded and noisy?

Their Approach:

The team focused on the SmartBAN standard, which is designed for ultra-low-power radio communication and features a simplified MAC layer with a central Smart Coordinator managing network nodes (such as physiological sensors). Since SmartBAN is still under development and not yet available in commercial devices, the team simulated what a SmartBAN transmission would look like in a spectrogram.

To address the detection challenge, they developed a deep learning framework for Smart RF Signal Recognition. Their system is capable of detecting and classifying SmartBAN transmissions even in the presence of strong interference.

Key Steps:

Synthetic Data Generation: They created a large dataset (about 30,000 samples) of synthetic spectrograms, each simulating a realistic mix of ZigBee, WLAN, Bluetooth, and SmartBAN signals. Signals were randomly combined, overlapped, and scaled to various SNR levels to reflect real-world conditions.
Pixel-Level Labeling: Each spectrogram was paired with a mask assigning every pixel to one of five classes: Unknown (noise), WLAN, ZigBee, Bluetooth, or SmartBAN. Overlapping signals were resolved using a deterministic priority scheme: Bluetooth > SmartBAN > ZigBee > Wi-Fi.
Deep Learning Models: The team trained convolutional neural networks—specifically, U-Net (with optional additive attention gates) and DeepLab v3+ architectures, using either ResNet-18 or ResNet-50 backbones. The attention gates helped the model focus on relevant features and suppress noise, improving segmentation in challenging scenarios.
Experimental Validation: They used ADALM-PLUTO SDRs to collect real-world captures, overcoming hardware limitations by synchronizing two devices to jointly capture an 80 MHz-wide spectrogram of the ISM band. MATLAB’s parallel computing tools enabled efficient data acquisition and processing.

Results:

Their system processes 256×256 pixel spectrogram tiles and classifies each pixel. The initial models performed well on synthetic data but struggled with signal boundaries and noise in real-world data. By introducing attention mechanisms and noise-augmented training, they significantly improved real-world classification performance—especially in distinguishing between structurally similar signals like ZigBee and Bluetooth.

The system accurately segments Bluetooth packets and ignores interference in a crowded spectrum

Experience & Reflections:

Nicola, Matteo, and Giacomo spent long hours working through the complexities of the challenge, often running into obstacles that tested both their technical skills and their ability to collaborate under pressure. They recall the ups and downs vividly: “We are so proud to have finished in second place in this amazing challenge! It was definitely tough, and we ran into several obstacles that really tested us. However, overcoming them was incredibly motivating, and we learned many valuable lessons that will be useful in our future professional lives. The best part was how well we worked together as a team, and we truly enjoyed the experience. Finally, we owe special thanks to Professor Maurizio Magarini and Professor Francesco Linsalata for all the support they gave us during the competition.”

For the team, what began as a technical competition became a memorable journey of teamwork and growth, leaving them better prepared and inspired for future challenges.

Explore Nicola, Matteo, and Giacomo’s solution – GitHub repository

Third Place Winner: Soham Gupta – Fluid Flow Simulation Using Physics-Informed Neural Networks

Meet the winner:

Soham Gupta is a third-year undergraduate student in Chemical Engineering at the Indian Institute of Technology, Ropar. Soham learned about the MathWorks AI Challenge 2025 while searching for a project that would combine his interests in chemical engineering and machine learning. The challenge’s focus on fluid dynamics immediately caught his attention, and he decided to participate alongside his academic commitments.

The Project:

Simulating fluid flow is a cornerstone problem in chemical engineering and physics, governed by complex partial differential equations (PDEs) such as the Burgers’ and Navier–Stokes equations. Traditional data-driven neural networks often struggle to generalize or respect the underlying physics, especially with limited or noisy data. Soham’s project, detailed in his PINN_Fluids repository, tackled this challenge by using Physics-Informed Neural Networks (PINNs) to solve canonical fluid flow problems. By directly embedding the governing equations into the neural network’s loss function, PINNs ensure that the learned solutions are both data-driven and physically consistent.

Innovative Approach:

Soham began by exploring standard black-box neural networks on benchmark datasets, but quickly found that these models failed to capture the essential physics, resulting in poor accuracy. Learning from this, he shifted to PINNs, utilizing automatic differentiation to incorporate PDE residuals directly into the training process. His implementation in MATLAB’s Deep Learning Toolbox required careful selection of activation functions—opting for smooth alternatives to ReLU to avoid vanishing gradients in higher-order derivatives. Soham also experimented with network architectures and fine-tuned the balance between data-driven and physics-based loss terms, iteratively improving the model’s ability to simulate both 1D and 2D fluid flow scenarios. The result was a set of neural networks that could robustly approximate solutions to the Burgers’ and Navier–Stokes equations, even with sparse data.

Neural Network Model and Physics Integration:

At the core of Soham’s solution was a fully connected neural network designed to approximate the solution field for each fluid dynamics problem. The model was trained to minimize a composite loss: one part measuring the error between predicted and observed data, and another enforcing that the predictions satisfy the governing PDEs at a set of collocation points. Automatic differentiation enabled efficient computation of derivatives required for the physics-based loss terms. Training and experimentation were performed in MATLAB, leveraging its intuitive structure and built-in support for deep learning and symbolic math. This workflow allowed Soham to rapidly prototype, test, and refine his PINN models for different fluid dynamics problems.

Results:

Soham’s final PINN models achieved accurate and stable solutions for benchmark fluid flow equations, outperforming purely data-driven approaches and demonstrating strong agreement with analytical or high-fidelity numerical solutions. The project not only showcased the power of combining physics and machine learning, but also highlighted the practical potential of PINNs for real-world engineering simulations.

Model Performance: Velocity Magnitude and Vectors (True vs Predicted)

Experience & Reflections:

Soham’s journey was filled with both challenges and personal growth. “When I started, the problem seemed impossible. My first attempts failed miserably, but each failure taught me something new about both machine learning and fluid dynamics,” he reflects. Diving into research papers, learning to tune complex models, and experimenting with MATLAB’s Deep Learning Toolbox all contributed to his understanding. “This project gave me the confidence to approach interdisciplinary problems and played a big role in helping me secure my internship in machine learning. I truly believe that consistent effort and curiosity can turn even the most intimidating tasks into achievements.”

What began as a personal quest to combine his interests in engineering and AI ended up as a defining academic experience. “As Nelson Mandela said, ‘It always seems impossible until it’s done.’”

Explore Soham’s solution – GitHub repository

Applying Math to Real-World Problems: Matthew Brun’s Journey from Competition to Research

Tanya Kuruvilla — Mon, 03 Nov 2025 11:54:43 +0000

Today we’re talking to Matthew Brun, an M3 Challenge alum who competed in 2017 and 2018. After earning his BA in Operations Research from Rice University in 2022, Matthew is now pursuing his PhD in Operations Research at MIT, where he is expected to graduate in 2027. Currently a PhD student at MIT, he continues to build on the passion for problem-solving and applied math that began during his high school competition days. Over to you, Matthew… 

Why did you choose to participate in the M3 Challenge in high school?

When I was a sophomore in high school, some friends put together a team for the M3 Challenge and invited me to join. However, the competition was limited to only juniors and seniors, so I was sidelined until the following year. The concept of spending a whole day (but just one day) focused on a single project with a group of peers who have a similar analytical mindset appealed to me, and I eagerly awaited the opportunity to compete in the next two challenges. Junior year, my team worked on a project studying the impact of changes in sea level on U.S. National Parks. We proposed a creative (but unsophisticated) method for estimating the amount of submerged park coastline without access to large-scale topographical data. This was my first exposure to the field of mathematical modeling for a real-world problem.Thanks to the contributions of my team, this solution received an honorable mention in the competition.

Loyola Academy M3 Challenge Team, 2017

Did the experience change how you thought about math or real- world problem solving?

Despite the long, 14-hour day spent completing the competitions, I came home in the evening energized and excited about the ideas our teams generated. Prior to the Challenge, I expected to study computer science in college; however, these experiences convinced me that the part of computer science which attracted me was the need to think about a problem in a rigorous mathematical way. From this realization, I discovered the field of applied math, which takes the best of both worlds from pure mathematics and computer science. I ended up studying Computational and Applied Mathematics for the first few years of my undergraduate career and eventually specialized in the field of Operations Research (OR). I received a BA in OR and am currently pursuing a PhD, also in OR.

How was your first experience using MATLAB? What was that learning curve like as a student?

My first exposure to MATLAB was in the first semester of my undergraduate career at Rice, when I took a class called Introduction to Engineering Computation. Each week of the course explored a different area of applied math (optimization, graphs, machine learning, numerical partial differential equations…) and implemented an experiment in MATLAB.

I had a lot of fun seeing for the first time many areas in which math is used in the real-world. MATLAB was an intuitive language that I found to be effective for quickly implementing analysis for the style of project in the class. The interactive debugging environment made it very easy to write and understand MATLAB code. I continued to use MATLAB extensively in the remainder of my undergraduate career, and I worked as a TA for the course in my six remaining semesters.

Can you tell us about your current research at MIT and what you’re focusing on?

At MIT, I am pursuing a PhD in Operations Research. OR is a field that applies mathematical tools to assist in making better decisions, with techniques that range from analytics to machine learning to mathematical optimization. I focus primarily on optimization, with applications drawn from energy systems. In this area, we study how to improve the design and operations of these systems, which include the power grid, electrified systems, and renewable energies. To do so, we propose new mathematical models for these systems and introduce algorithms and techniques to solve them effectively and efficiently.

One recent project focuses on long-term planning for investments in electric vehicle battery recycling facilities. Recycling is a promising approach to dispose of used batteries and to reuse the valuable materials in new batteries. Our work suggests an approach, based in mathematical optimization, for recyclers to decide how much recycling capacity to construct under uncertainty related to adoption of electric vehicles, and we analyze the impact of external policies (like grants and tax credits) on domestic investment in these technologies.

Another project focuses on efficient operation of the power grid. Grid operators need to satisfy electricity demand by deciding when to turn generators on and how much power they produce, all while ensuring minimizing operating costs. Due to the complex physics of AC power transmission, it is very difficult to solve this problem at scale. We propose a new penalty alternating direction method, an algorithm that alternates between solving small pieces of the overall problem, which finds high quality solutions to large instances of this problem efficiently. Our solution placed 2nd overall (out of 14 teams) in a competition organized by ARPA-E and demonstrates to the industry that this kind of problem can be solved.

Overall, I think that the complex nature of these systems poses many interesting problems that can be tackled with mathematical optimization. Moving forward, I plan on studying how optimization can support new modes of operating these systems and help mitigate threats like wildfire.

How are you using MATLAB in your current research or academic work?

I use MATLAB to explore theoretical concepts and help identify research questions. Many of the theoretical questions I have worked on admit a geometric perspective, which makes it helpful to visualize different aspects of the problem. Using MATLAB, I put together figures which help describe the geometry of the problem, which can confirm (or reject) my hypotheses or suggest new ways to think about the problem.

For example, during my undergraduate senior year, I worked on problems in multiobjective integer optimization. These models simultaneously minimize multiple expressions with constraints that require that the variables take discrete values. Understanding these models is highly geometric, as the objective expressions form a vector of values which can be visualized in multiple dimensions. In the early days of this research, I used MATLAB to visualize simple instances of these problems. Eventually, we generalized these insights into new results that apply to all instances from this class. Specifically, we provide conditions that describe the quality of the Lagrangian dual for these problems, helping qualify how and why this dual problem is a useful tool. (The Lagrangian dual is a modified optimization problem which is used to certify [or bound] the quality of a solution to the original problem).

Above are figures generated with MATLAB in the early days of this project, and below is a similar figure from our paper on this topic.

What do you enjoy most about working with MATLAB? Why do you think students should consider learning it?

MATLAB is a great language for quickly prototyping ideas and testing hypotheses. Being able to scroll through the variable space in the IDE and quickly put together detailed plots helps with many tasks through the research pipeline. I also make extensive use of the Symbolic Math Toolbox, which helps with differentiation and integration of symbolic expressions, some of which I desperately want to avoid computing by hand.

What advice would you give high school students who are participating in the M3 Challenge?

The M3 Challenge is a great way to explore the world of applied math. Competing helped me to think about problems in a mathematical way and to design creative ways to analyze problems without access to significant amounts of data, skills which I use extensively in my research today. I would suggest that participants try to think about other topics they see in the world through the same mathematical lens as the challenge encourages, to consider educational paths and careers that utilize this style of thinking, and, most importantly, to have fun with their team!

Registration is now open for the 2026 M3 Challenge: Register here