I’m a PhD student in Robotics (MEMS) at Duke University.

• 🧠 Large Language Models (LLMs): Leveraging LLMs for more intuitive and effective human-robot communication.
• 🤖 Residual Reinforcement Learning: Optimizing low-level manipulation control in robotics through reinforcement learning.
• 🦾 Human-Assistive Robotics: Developing intelligent systems that enhance the quality of life by assisting humans in daily tasks, rehabilitation, and collaborative activities, integrating LLMs to improve interaction and adaptability.

• Reinforcement Learning (PPO, DDPG, SAC, A2C, and more.)
• Robot Locomotion & Control (Lagrangian Dynamics, Rigid-Body Dynamics, MPC)
• Robotic simulation environments (Isaac Gym, MuJoCo)

• Email: tianwei.bao@duke.edu