RL-Driven Robotic Manipulation
Reinforcement learning for robotic manipulation, including reward design, obstacle-aware behavior, and simulation-based evaluation.
This project area studies reinforcement learning methods for embodied control and robotic manipulation. The emphasis is on reward design, obstacle-aware behavior, and evaluation of learned policies in simulated or embodied settings.
Current focus
- Reward design for robot learning.
- Obstacle-aware manipulation, including Gaussian Process Distance Field representations.
- Robust behavior under obstacles or changing task structure.
- Simulation-based evaluation for embodied decision making.
TODO
- TODO: add representative project image.
- TODO: add paper, code, or demo links when public.