Yuliu Wang

About

Yuliu Wang is a rising star in the field of robotics, specializing in the intersection of reinforcement learning and motion planning for legged and manipulator systems. His research focuses on enabling highly dynamic and reactive behaviors in robots, moving beyond simple locomotion to skills like jumping and bipedal walking. Wang’s major contribution lies in developing hierarchical frameworks that integrate multi-agent reinforcement learning with Riemannian motion policies (RMPs). This novel approach allows robots to generate complex, reactive motions in cluttered and dynamic environments, offering a mathematically elegant solution to challenging motion planning problems. His most-cited work, "Learning Advanced Locomotion for Quadrupedal Robots" (2024, 7 citations), demonstrates the potential of this framework for quadrupedal agility, while his 2023 paper on manipulator reactive motion generation (4 citations) extends the concept to robotic arms. Though early in his career, Wang’s innovative fusion of learning-based and geometric methods is already attracting attention, positioning him as a key contributor to the next generation of intelligent, agile robots.

Research Focus

Key Achievements

Top Papers

1. 1
   Learning Advanced Locomotion for Quadrupedal Robots: A Distributed Multi-Agent Reinforcement Learning Framework with Riemannian Motion Policies

   7 citations · 2024
2. 2
   A Hierarchical Robot Learning Framework for Manipulator Reactive Motion Generation via Multi-Agent Reinforcement Learning and Riemannian Motion Policies

   4 citations · 2023

Key Collaborators

Contact & Links