Papers
2
Total Citations
6
H-Index
1
About
Chunyang Li is a robotics researcher specializing in bio-inspired locomotion and reinforcement learning for multi-legged and serpentine robotic systems. His work focuses on enabling autonomous, adaptive movement in complex, unstructured environments—a critical challenge in field robotics. Li’s most cited paper (2021, 5 citations) introduces a path-integral-based reinforcement learning algorithm for goal-directed locomotion of snake-shaped robots. This model-free, online Q-learning approach allows snake robots to navigate 3D environments by iteratively exploring action strategies and optimizing decision-making, effectively bridging the gap between simulation and real-world terrain adaptability. More recently, Li has advanced quadruped robot control with his work on gait learning reproduction using experience evolution proximal policy optimization (2023). This method leverages prior locomotion knowledge to accelerate policy learning, enabling more efficient and stable gait transitions. While his citation counts are still growing, Li’s contributions are notable for their practical emphasis on sample efficiency and real-time adaptation—key bottlenecks in deploying RL for physical robots. His research sits at the intersection of reinforcement learning, control theory, and biomimetic design, offering promising pathways toward more resilient autonomous systems for search-and-rescue, inspection, and exploration tasks.
Research Focus
Key Achievements
Top Papers
- 1
- 2