About

Yecheng Shao is a leading researcher in legged robotics, specializing in reinforcement learning (RL) for quadruped locomotion. His work addresses core challenges in enabling robots to move with agility, speed, and versatility. Shao’s major contributions include developing a phase-guided controller that allows robots to learn free gait transitions—a longstanding hurdle in robotics—enabling smooth shifts between walking, trotting, and bounding without pre-programmed rules. His imitation-relaxation RL framework achieved high-speed quadrupedal locomotion, pushing the boundaries of dynamic movement. Most recently, Shao introduced a learning-based control pipeline for generic motor skills, aiming to create a single, universal controller capable of performing diverse tasks like jumping, turning, and climbing. His top papers have garnered over 135 citations, reflecting significant impact in the field. Notably, his work on gait transitions (73 citations) and high-speed locomotion (62 citations) are widely recognized for advancing practical, real-world deployment of legged robots. Shao’s research is pivotal for students and engineers seeking to understand how RL can unlock robust, adaptive, and efficient locomotion in complex environments.

Research Focus

Key Achievements

2
H-Index
3
Papers
137
Total Citations
46
Avg Citations/Paper
🏆 Most Cited Paper
Learning Free Gait Transition for Quadruped Robots Via Phase-Guided Controller
73 citations · 2021
📈 Most Prolific Year: 2021 (1 Papers)
🤝 Key Collaborators: 7
🏛 Institutions: Zhejiang University of Science and Technology, Zhejiang Institute of Mechanical and Electrical Engineering, Zhejiang University

Top Papers

  1. 1
  2. 2
  3. 3

Key Collaborators

Contact & Links

Available for collaboration
Content generated · 14 days ago