Ruofan Wu
Papers
5
Total Citations
134
H-Index
4
About
Ruofan Wu is a robotics and rehabilitation engineering researcher whose work sits at the intersection of machine learning and assistive prosthetic technology. His research focuses primarily on applying reinforcement learning (RL) and inverse reinforcement learning (IRL) to automatically configure and optimize control systems for robotic knee prostheses, with the ultimate goal of restoring natural locomotion for individuals with lower-limb disabilities. Wu's most significant contributions center on developing intelligent impedance control frameworks that eliminate the need for manual, clinician-driven parameter tuning — a longstanding bottleneck in prosthetic adoption. His actor-critic reinforcement learning approach, detailed in two highly cited studies from 2021 and 2022 (accumulating 39 and 44 citations respectively), enables robotic prostheses to dynamically track and mimic intact human knee motion across continuous locomotion tasks. Extending this work, Wu has pioneered the use of inverse reinforcement learning to infer human-robot performance objectives during real-world movement, offering a principled method for personalizing assistive devices to individual users. His 2022 study on inferring locomotion objectives (26 citations) represents a notable advance toward true human-robot symbiosis. Collectively, Wu's research is reshaping how intelligent prosthetic systems adapt to their users autonomously.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4
- 5