Jiangwei Zhong

Papers

Total Citations

H-Index

About

Jiangwei Zhong is a robotics researcher whose work focuses on bridging the critical gap between simulation and real-world robotic performance, with a particular emphasis on dynamic locomotion and reinforcement learning. His research addresses two fundamental challenges in modern robotics: enabling legged robots to operate with dynamic, untethered capabilities, and overcoming the persistent Sim2Real transfer problem. In his 2024 study on motion planning for legged soccer robots, Zhong tackled the complex integration of perception, manipulation, and dynamic movement—a challenge that has long limited the autonomy of legged systems. His most impactful contribution, however, lies in his 2025 investigation into the underexplored role of static friction in robotic reinforcement learning. By identifying that conventional domain randomization methods typically exclude static friction from their parameter space, Zhong has opened a new avenue for improving the fidelity of simulation-to-real-world transfer. His work has already garnered attention within the robotics community, with his papers accumulating citations that underscore the growing relevance of his findings. Zhong’s research is particularly valuable for students and engineers working on legged locomotion and Sim2Real challenges, offering practical insights that could accelerate the deployment of more robust, adaptable robots in unstructured environments.