Haifeng Yao

China University of Mining and Technology

Papers

Total Citations

H-Index

About

Haifeng Yao is a robotics researcher whose work centers on the intersection of reinforcement learning and autonomous motion planning for robotic systems. His research addresses one of the field's most persistent challenges: enabling robotic arms to plan and execute movements efficiently without relying on exhaustive manual demonstration or traditional programming approaches. Yao's most notable contributions include pioneering the application of residual reinforcement learning to robotic arm motion planning, a method that significantly improves training efficiency and convergence compared to training agents from scratch — work that has garnered 17 citations since its 2021 publication. Complementing this, his research on curriculum reinforcement learning for robotic arms offers an adaptive framework that responds to rapidly shifting application environments, accumulating 9 citations in the same year. Together, these two papers reflect a cohesive research vision: making reinforcement learning agents faster to train, more reliable, and better suited to real-world deployment. With a combined citation count of 26 across just two publications in a single year, Yao has demonstrated a meaningful early-career impact in intelligent robotics. His work is particularly relevant for researchers and students exploring data-efficient learning strategies and next-generation automation in industrial and collaborative robotic environments.