Ziwen Zhuang

Papers

Total Citations

H-Index

About

Ziwen Zhuang is an emerging robotics researcher specializing in legged locomotion, reinforcement learning, and agile robot control. His work sits at the cutting edge of enabling quadrupedal and legged robots to perform complex, dynamic movements in unstructured real-world environments — a challenge that bridges machine learning, control theory, and physical robotics. Zhuang's most notable contribution, "Robot Parkour Learning" (2023), has garnered 10 citations and represents a significant advance in vision-based locomotion. The work tackles one of the field's grand challenges: training robots to rapidly navigate diverse obstacles without relying on hand-crafted rewards or reference motion capture data, pushing the boundaries of what autonomous legged systems can physically accomplish. His more recent work, "Playful DoggyBot: Learning Agile and Precise Quadrupedal Locomotion" (2025), extends this vision further by enabling robots to interact dynamically with real-world objects — mimicking the nimble, purposeful movements seen in trained animals. This research highlights Zhuang's broader ambition to close the gap between biological agility and robotic capability. For students interested in robot learning and embodied AI, his work represents an exciting frontier in making robots genuinely useful in complex physical environments.