Workshops and Tutorials
Workshops
Workshop 1: Reinforcement Learning for Robotics using MATLAB and Simulink - By MathWorks
Controlling nonlinear systems is a challenging task, traditionally tackled by linearizing the system at different operating points or using advanced techniques like Model Predictive Control (MPC). However, with the growing adoption of Machine Learning in robotics and automation, Reinforcement Learning (RL) has emerged as a powerful approach for solving complex control problems using deep neural networks. In this workshop, we will introduce the fundamentals of Reinforcement Learning for robotics applications using MATLAB and Simulink. Participants will learn key concepts, including neural networks, setting up environment models, and designing reward structures to guide the learning process.
Timings: 9:30 AM – 11:30 AM on Day 1: July 2, 2025 (Wednesday)
Venue: LHC-1 , 308
Workshop 2: Advances in Medical Robotics by Prof. Deepak Raina, Prof. Nirav Patel & Prof. Bhivraj Suthar
Medical robotics is rapidly transforming modern healthcare by enabling precise, minimally invasive, and patient-specific interventions. With the integration of advanced sensing, control, and machine learning techniques, robotic systems are now capable of performing complex diagnostic and therapeutic tasks with increasing autonomy and reliability. This workshop aims to highlight recent research advancements, emerging clinical applications, and translational challenges in medical robotics.
The session will cover topics such as robot-assisted surgery, ultrasound-guided interventions, robot-assisted rehabilitation, learning-based control, and human-robot interaction in medical settings. Emphasis will also be placed on the development of affordable and context-sensitive solutions suitable for resource-constrained settings like rural healthcare in India. Through a combination of expert talks, interactive discussion, and Q&A, this workshop will bring together researchers, clinicians, and engineers to share knowledge and explore opportunities for collaboration.
This workshop will serve as a platform for young researchers and students to gain insights from leading experts, understand clinical needs, and explore avenues for impactful research.
Timings: 9:30 AM – 1:00 PM on Day 1: July 2, 2025 (Wednesday)
Venue: LHC-1 , 305
Workshop 3: Dynamics of Robotic Systems: Theory and Practice by Prof. S. K. Saha & Prof. Paramanand
This physical workshop intends to help participants to get overview of the fundamental dynamics of rigid and flexible multibody system, recursive dynamic formulation, and provide hands-on with the Recursive Dynamics Simulator (ReDySim) GUI to solve different robotic systems. ReDySim is the DeNOC-based recursive solver for dynamic analyses of robotic and multibody systems. It consists of efficient recursive inverse and forward dynamics algorithms for the control and simulation of open and closed-loop multibody systems, respectively.
Timings: 3:00 PM – 6:00 PM on Day 1: July 2, 2025 (Wednesday)
Venue: LHC-1 , 305
Session
Mini Drone hands-on sessions by MATHWORKS for Students
The MathWorks Minidrone Workshop is a hands-on, gamified session designed to introduce students to Model-Based Design using Simulink, Stateflow, Image Processing Apps, and Simulink Support Packages. Students will learn by doing-building, simulating, and deploying their designs on hardware.
The workshop fosters an interactive learning environment where students from different universities can collaborate, compete, and exchange ideas. It emphasizes rapid prototyping, guiding participants from simulation to real-world deployment. The session concludes with a fun, friendly competition, where participants put their skills to the test in an engaging drone-based challenge.
Timings: 11:30 AM – 6:00 PM on Day 1: July 2, 2025 (Wednesday)
Venue: LHC-1 , 304
Tutorials
Tutorial 1: Probabilistic Robotics 2.0: Uncertainty in Deep Neural Networks by Jongseok Lee, DLR, Germany
Probabilistic robotics, a vibrant field that has gained enormous popularity since its inception, provides a compelling paradigm for autonomous robots to contend with the complex real world. Probabilistic representations yield beneficial properties for trustworthy learning-enabled robots deployed in the real world, e.g., uncertainty estimation, ways to elegantly handle incomplete data and the unifying perspective on perception, control and learning. On the other hand, recent advances in deep learning have dramatically improved the suitability and performance of robot learning, e.g., large language models (LLMs), visual foundational models, and Neural Radiance Fields (NeRFs), to name a few. Though there have been advances in pursuing the probabilistic extension of these concepts in recent years, many core challenges associated with real-world deployment remain unsolved. This tutorial offers an overview of probabilistic representations in deep learning, with a primary emphasis on uncertainty quantification through probabilistic reasoning. Several applications of probabilistic robotics will also be presented.
Timings: 12:00 PM – 1:00 PM on Day 1: July 2, 2025 (Wednesday)
Venue: LHC-1 , 308
Tutorial 2: Challenges in On-ground Validation of Orbital Robotic Missions by Dr. Marco De Stefano, DLR, Germany
Spacecraft equipped with robotic manipulators are a promising technology to perform on orbit servicing tasks in orbit. A challenge is the on-ground validation and the design of a coordinated control strategy between the spacecraft and the manipulator while considering the restricted requirements of the space missions. The focus of this presentation will be on the on-ground validation of a complete robotic mission. To this end, a state-of-art robotic-based facility, namely the OOS-SIM, was developed in DLR. The set-up is based on industrial robots equipped with force-torque sensors to simulate satellite dynamics in space and interaction forces between different bodies. Hence, an overview on the challenges and solutions in replicating 0-g conditions with a hardware-in-the-loop facility will be part of this presentation. In addition, passivity-based controllers for the coordination of the orbital robotic arm mounted on a satellite will be part of the presentation.
Timings: 2:00 PM – 3:00 PM on Day 1: July 2, 2025 (Wednesday)
Venue: LHC-1 , 308
Tutorial 3: Deep Reinforcement Learning in Making Robots Intelligent by TCS Research
This tutorial provides a comprehensive and captivating journey through the world of Deep Reinforcement Learning (DRL) for robotics. We will delve into the foundational concepts, ignite your imagination with the possibilities of DRL in Embodied AI, explore advanced techniques like RL with Human feedback (RLHF) that are shaping the future of human-robot continual learning, confront the challenges and pitfalls that lie ahead, equip you with practical tips and tricks from a practitioner’s perspective, showcase the power of DRL through demonstrations, and unveil the exciting open research areas that are ripe for groundbreaking discoveries.
Timings: 3:00 PM – 4:30 PM on Day 1: July 2, 2025 (Wednesday)
Venue: LHC-1 , 308
Tutorial 4: Surgical Robotics – Ingredients of Clinically Driven Robotics Research by Julian Klodmann, DLR, Germany
After a brief overview of robotics research at the German Aerospace Center, a research project focused on developing a robotic assistant for flexible endoscopy in the urinary tract will be presented. This project was strongly driven by clinical needs and the corresponding methods necessary for its success will be presented. After that the talk will proceed in a more holistic perspective on focus areas of research, which need to be combined to develop mature research prototypes.
Timings: 5:00 PM – 6:00 PM on Day 1: July 2, 2025 (Wednesday)
Venue: LHC-1 , 308