Wei-Chao Chen
Papers
2
Total Citations
5
H-Index
2
About
Wei-Chao Chen advances the frontier of agile robotic locomotion, focusing on reinforcement learning (RL) for real-world deployment. His major contributions center on two critical challenges: enabling versatile, multi-gait movement and ensuring policy smoothness for hardware safety. In his 2023 work, Chen introduced the *transition-net*, a robust strategy that distributes the complexity of different gaits into dedicated policies, allowing a robot to seamlessly switch between behaviors using a latent state representation—expanding real-world versatility. His 2024 paper systematically benchmarks methods to reduce high-frequency oscillations in continuous control policies, a pervasive issue that degrades hardware performance. By identifying, categorizing, and comparing mitigation techniques, Chen provides a foundational framework for deploying smoother, more reliable RL policies on physical robots. While his citation counts (3 and 2) reflect the recency of this work, its practical focus on bridging simulation-to-reality gaps positions him as a key voice in robust, deployable locomotion. His research is essential reading for roboticists and RL practitioners aiming to move beyond simulation into the unpredictable real world.
Research Focus
Key Achievements
Top Papers
- 1
- 2