Haojun Guan
Papers
3
Total Citations
44
H-Index
3
About
Haojun Guan is a researcher whose work bridges the frontiers of robotics, autonomous learning, and intelligent perception. His primary research areas include robot skill acquisition, reinforcement learning, and the design of specialized robotic systems. Guan’s most significant contribution lies in advancing how robots learn autonomously. In his highly cited 2017 paper, "Combining Model-Based Q-Learning With Structural Knowledge Transfer for Robot Skill Learning" (37 citations), he tackled a core challenge in reinforcement learning—balancing exploration and exploitation—by integrating structural knowledge transfer to accelerate skill acquisition. This work has informed subsequent research in autonomous robotics and adaptive learning algorithms. Guan also made notable contributions to infrastructure inspection with his 2009 paper on a biped line-walking robot for power transmission lines, where he designed a novel mechanism to minimize hip joint torque, enhancing efficiency and stability. Additionally, his 2014 work on multi-sensory household object recognition explored how robots can use interactive exploratory behaviors to identify materials, mimicking human perceptual strategies. Through these diverse contributions, Guan has demonstrated a sustained commitment to making robots more autonomous, perceptive, and practically deployable in real-world environments.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3