Arthur Zhang

Papers

Total Citations

H-Index

About

Arthur Zhang is a leading researcher in humanoid robotics, with a primary focus on reinforcement learning (RL) for whole-body locomotion and control. His most impactful work, "Whole-body Humanoid Robot Locomotion with Human Reference" (2024), has already garnered 31 citations, reflecting its timely contribution to the field. Zhang’s major contribution lies in addressing the critical challenge of designing complex reward functions for humanoid robots—a bottleneck that has long hindered the deployment of RL in real-world systems. By integrating human motion reference data into the training pipeline, he has enabled more natural, stable, and adaptive locomotion, bridging the gap between simulation and physical hardware. This approach not only simplifies the reward engineering process but also enhances the transferability of learned policies to full-body control tasks. Zhang’s work is notable for its practical impact, offering a scalable framework that accelerates the development of humanoid robots capable of navigating unstructured environments. As a rising figure in robotics, his research is shaping the next generation of autonomous humanoids, with applications ranging from disaster response to assistive technology.