Sampling-Based Constrained Policy Optimization
Proposed a sampling-based weight-space projection framework for enforcing safety constraints during policy updates.
•
1 min read
Proposed a sampling-based weight-space projection framework for enforcing safety constraints during policy updates.
Supervised undergraduate research on vision-based dynamics modeling and path planning for off-road vehicles.
Developed a vehicle dynamics simulator based on dynamic bicycle model with standard gymnasium APIs and a CARLA connector.
Designed a constraint-aware imitation learning framework incorporating an actor-critic structure for explicit safety modeling.
Engineered a rapidly deployable autonomous ground robot capable of exploring, mapping, and navigating previously unseen terrain.
Developed a CNN-based end-to-end controller for high-speed autonomous racing using RGB camera input and velocity feedback.
Optimized parallel curve generation for rapid filling of planar areas.