Jindai Zhang

Papers

Total Citations

H-Index

About

Jindai Zhang is a rising researcher in legged robotics, whose work centers on bridging the sim-to-real gap for bipedal locomotion through reinforcement learning. Their most cited paper, “Safe and Efficient Auto-tuning to Cross Sim-to-real Gap for Bipedal Robot” (2024), tackles a fundamental challenge in robotics: the discrepancy between simulated and real-world dynamics that often prevents controllers from transferring effectively. Zhang’s contribution lies in developing an auto-tuning framework that safely and efficiently adapts policies trained in simulation to physical hardware, reducing the need for extensive manual calibration. While early in their career, with this work already accumulating citations, Zhang is establishing a reputation for practical, safety-conscious approaches to deploying learned controllers on real robots. Their research sits at the intersection of robot control, machine learning, and system identification, offering a promising path toward more robust and deployable bipedal systems. As the field increasingly relies on simulation for training, Zhang’s methods for crossing the reality gap represent a critical step forward, making their work of growing interest to both roboticists and reinforcement learning practitioners.