Honghu Xue
Papers
4
Total Citations
28
H-Index
3
About
Honghu Xue is a robotics researcher whose work sits at the intersection of machine learning, human-robot interaction, and assistive technology. Their primary research focuses on skill transfer between humans and robots, combining Learning from Demonstration (LfD) with Reinforcement Learning (RL) to enable robots to acquire and refine complex, dexterous behaviors. Xue’s most cited work, “ACNMP” (2020, 11 citations), introduces a novel framework that allows robots to learn from human demonstrations and then autonomously improve through self-exploration, addressing a fundamental challenge in robotics. They have also made significant contributions to understanding how humans interact with robotic systems, as evidenced by their comprehensive review on interactive skill transfer (2021, 9 citations), which bridges technical methods with user experience. Notably, Xue applies their expertise beyond traditional robotics, using probabilistic movement primitives to analyze human motion differences under transcranial current stimulation (2021, 6 citations), demonstrating the translational potential of their work in medical and rehabilitation contexts. Their recent research on deep reinforcement learning for mapless navigation (2023) further showcases their commitment to developing practical, autonomous systems for real-world applications like intralogistics.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4