William Choi

Papers

Total Citations

H-Index

About

William Choi is a robotics researcher whose work focuses on the intersection of teleoperation, human-robot interaction, and reinforcement learning for dynamic motion control. His key research areas include time-delayed teleoperation systems and model-based exploration strategies for robotic skill acquisition. In his most cited work, "Negotiating Corners With Teleoperated Mobile Robots With Time Delay" (2018, 8 citations), Choi addresses a critical challenge in remote robotics: safely maneuvering mobile robots around corners when video feedback is delayed—a scenario directly applicable to Earth-to-space teleoperation. His second notable paper, "Model-Based Action Exploration for Learning Dynamic Motion Skills" (2018, 3 citations), tackles a fundamental problem in deep reinforcement learning: how to efficiently generate training data for continuous action spaces. Rather than focusing on data exploitation like many contemporaries, Choi investigates how to best produce the data itself, advancing methods for learning complex motion skills. Though early in his career, his work bridges practical teleoperation challenges with foundational reinforcement learning research, offering valuable insights for students and researchers working on real-world robotic systems where communication delays and efficient learning are paramount.