Papers
6
Total Citations
116
H-Index
4
About
Zhaoming Xie is a robotics researcher specializing in legged locomotion, deep reinforcement learning, and sim-to-real transfer for complex robotic systems. His work sits at the intersection of machine learning and physical robotics, with a particular focus on developing robust controllers that enable both quadruped and humanoid robots to navigate challenging real-world environments. Xie's most impactful contribution, OPT-Mimic, introduced a novel framework for imitating optimized trajectories rather than relying solely on motion capture data, enabling dynamic quadruped behaviors without exhaustive reward engineering — accumulating nearly 40 citations since 2023. His research on bipedal walking for humanoids using current feedback demonstrated that deep RL techniques, previously limited largely to quadrupedal platforms, could be successfully extended to more mechanically complex humanoid hardware. More recently, he has tackled the challenge of robust humanoid locomotion on compliant and uneven terrain, addressing critical deployment barriers for real-world robotics. Beyond locomotion, Xie has explored creative applications of robot learning, including designing 3D-printable object adaptations to improve robot manipulation. His co-authorship of a 2025 state-of-the-art survey on learning-based legged locomotion further underscores his growing influence in shaping the field's research directions and future trajectory.
Research Focus
Key Achievements
Top Papers
- 1
- 2Learning-based legged locomotion: State of the art and future perspectives34 citations · 2025
- 3Learning Bipedal Walking for Humanoids With Current Feedback32 citations · 2023
- 4
- 5
- 6