Shanren Wang

About

Shanren Wang is a robotics researcher whose work centers on the dynamic locomotion control of legged robots, with a particular focus on reinforcement learning and gait optimization. His most notable contribution is a fast reinforcement learning framework that enables robots to acquire complex jumping skills from human demonstrations, addressing one of the most challenging problems in bionic robotics. This framework, detailed in his 2018 paper, demonstrates how dynamic policies can be learned to control a single leg's jumping motion, bridging the gap between human movement and robotic execution. Wang also contributed to the field of quadruped locomotion through his 2019 study on gait phase optimization for swing foot trajectories, which improves stability and efficiency in multi-legged robots. While his citation counts are modest—3 and 2 respectively—his work represents foundational steps in applying reinforcement learning to real-world robotic control, particularly for agile, human-like movements. His research is especially relevant for students and engineers interested in the intersection of machine learning and biomechanics, offering practical frameworks for teaching robots complex motor skills.

Research Focus

Key Achievements

Top Papers

1. 1
   Learning Jumping Skills From Human with a Fast Reinforcement Learning Framework

   3 citations · 2018
2. 2
   Gait Phase Optimization of Swing Foot for a Quadruped Robot

   2 citations · 2019

Key Collaborators

Contact & Links