Zufeng Zhang

Wuhan Branch of the National Science Library, Suzhou University of Science and Technology, Tsinghua University

Papers

Total Citations

H-Index

About

Zufeng Zhang is a leading researcher in the field of bipedal and humanoid robotics, with a primary focus on intelligent gait control and motion optimization. His work bridges reinforcement learning and swarm intelligence to solve high-dimensional, continuous control problems. Zhang’s most notable contribution is the development of a **parallel Deep Deterministic Policy Gradient (DDPG) algorithm**, which dramatically accelerates the learning of stable walking gaits for biped robots—a problem that traditional methods struggle to solve efficiently. He further advanced the field by introducing a **parallel comprehensive learning particle swarm optimizer (PCLPSO)** for humanoid gait optimization, and a **multiobjective collaborative deep reinforcement learning** framework for complex jumping maneuvers. Collectively, his top papers have garnered over 50 citations, reflecting growing recognition in the robotics community. Zhang’s work is particularly impactful for its emphasis on parallelization and multi-objective trade-offs, enabling robots to achieve faster, more stable, and more agile locomotion. His research is essential reading for anyone working on legged robotics, reinforcement learning, or evolutionary optimization.