Learning-based Methods for Robotics & Autonomous Driving

We focus on developing robotic control and autonomous driving policy learning methods that could directly learn from real-world data, bypassing or alleviating sim-to-real gap, while achieving robust and generalizable performance.

Our current research focus include:

• Offline RL / IL / planning methods for autonomous driving and robotic control
• Offline policy optimization for safety-critical scenarios
• Foundation models for robotic control
• Sim-to-real adaptation