Hanran Wu

Papers

Total Citations

H-Index

About

Hanran Wu is a robotics researcher whose work focuses on the intersection of reinforcement learning, control theory, and legged locomotion. His primary research areas include inverse reinforcement learning, bipedal robot control, and adaptive locomotion over complex terrains. Wu's most notable contribution is his pioneering approach to teaching bipedal robots to navigate highly uneven and dynamically changing environments. In his highly cited 2024 paper, "Infer and Adapt: Bipedal Locomotion Reward Learning from Demonstrations via Inverse Reinforcement Learning," he introduced a novel framework that enables robots to learn reward functions directly from human demonstrations, bypassing the need for hand-crafted reward engineering. This work, which has already garnered 6 citations in its first year, addresses a fundamental challenge in robotics: the difficulty of modeling complex robot dynamics and unpredictable terrain interactions. By combining inverse reinforcement learning with adaptive control strategies, Wu's approach allows bipedal robots to generalize their learned behaviors to unseen environments, significantly improving their robustness and versatility. His research represents a critical step toward deploying legged robots in real-world applications such as search-and-rescue, disaster response, and planetary exploration, where adaptability to unpredictable terrain is essential.