Zhihong Chen

China Academy of Launch Vehicle Technology, Beijing Jingshida Electromechanical Equipment Research Institute, Tongji University

Papers

Total Citations

H-Index

About

Zhihong Chen is a robotics researcher whose work bridges deep learning, physical simulation, and intelligent control for robotic systems, with a particular focus on space applications. Chen’s most-cited paper, “Robot Arm Dynamics Control Based on Deep Learning and Physical Simulation” (23 citations), addresses the challenge of accurate dynamic modeling by integrating Newton-Euler formulations with deep learning to overcome parameter estimation errors and model simplifications. Building on this foundation, Chen proposed a “Space Robot Target Intelligent Capture System Based on Deep Reinforcement Learning Model” (11 citations), which enhances autonomy in on-orbit capture tasks by replacing traditional trajectory planning with reinforcement learning, improving control precision in space environments. More recently, Chen contributed to multi-robot SLAM with “Robust Loop Closure Selection Based on Inter-Robot and Intra-Robot Consistency for Multi-Robot Map Fusion” (7 citations), tackling false-positive loop closures that distort global maps. Chen’s innovative work also extends to soft robotics for space debris mitigation, as demonstrated in “Detumbling a Space Target Using Soft Robotic Manipulators” (5 citations), which proposes a novel, safe approach to reducing target rotation before capture. With a growing citation record and contributions spanning dynamics, learning-based control, and multi-robot mapping, Zhihong Chen is advancing the frontier of intelligent, autonomous robotic systems for challenging environments.