The Stochastic Robotics Lab designs robust, learning-based and safety-critical controllers for legged robots and cyber-physical systems.
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)!!
Our recent work titled “COMPAct: Computational Optimization and Automated Modular design of Planetary Actuators” has been accepted to IEEE International Conference on Robotics and Automation (ICRA) 2026, Vienna, Austria !!
Our recent work titled “A Collision Cone Approach for Control Barrier Functions” has been accepted to Transactions on Control System Technology (TCST)!!
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.
