The Stochastic Robotics Lab designs robust, learning-based and safety-critical controllers for legged robots and cyber-physical systems.
Congratulations to Dr. Manan Tayal on successfully defending his PhD thesis, “Towards Trustworthy Autonomy in Uncertain Environments: Synthesis of Verified Safe and Performant Control Policies for Autonomous Systems,” at the Department of Cyber-Physical Systems, IISc Bangalore!
Two of our recent works titled “Data-Driven Physics Embedded Dynamics with Predictive Control and Reinforcement Learning for Quadrupeds” and “VIP-Loco: A Visually Guided Infinite Horizon Planning Framework for Legged Locomotion” have been accepted to IEEE International Conference on Automation Science and Engineering (CASE) 2026, Shenyang, China!! 🇨🇳
Our recent work titled “A Co-Design Framework for High-Performance Jumping of a Five-Bar Monoped with Actuator Optimization” has been accepted to IEEE/ASME International Conference on Advanced Intelligent Mechatronics (AIM) 2026, Italy!!
Our recent work titled “V-OCBF: Learning Safety Filters from Offline Data via Value-Guided Offline Control Barrier Functions” has been accepted to Transactions on Machine Learning Research (TMLR)!!
Learning-based controllers that let robots walk, run, and adapt on real terrain.
Formal safety guarantees that keep legged robots out of harm's way.
Optimizing robot bodies and controllers together for maximum performance.
Pushing humanoid and bipedal robots toward real-world agility.
