Papers
13
Total Citations
100
H-Index
6
About
Xiaoguang Wu is a leading researcher in bipedal robotics and rehabilitation engineering, with a focus on passive dynamic walking, human–robot interaction, and intelligent control systems. His work bridges the gap between theoretical gait dynamics and practical robotic applications, particularly for lower-limb rehabilitation and assistive devices. Wu’s most cited paper, “Motion Control for Biped Robot via DDPG-based Deep Reinforcement Learning” (2018, 32 citations), introduces a reinforcement learning framework to prevent falls in passive biped robots on slopes, demonstrating a novel integration of AI with mechanical design. He has also made significant contributions to multi-domain signal processing, as seen in his 2014 study on synchronous EEG and sEMG feature extraction for power-assist rehabilitation robots (13 citations). His research on period-doubling bifurcations and chaotic gait in compass-gait biped models (2011, 11 citations) has deepened understanding of gait stability and energy efficiency. Wu’s work on adaptive trajectory planning based on EMG and human–robot interaction (2016, 8 citations) further highlights his commitment to safe, personalized rehabilitation. With over 90 total citations, his studies are foundational for developing more natural, stable, and responsive bipedal robots and rehabilitation systems.
Research Focus
Key Achievements
Top Papers
- 1Motion Control for Biped Robot via DDPG-based Deep Reinforcement Learning32 citations · 2018
- 2
- 3
- 4
- 5
- 6
- 7
- 8
- 9
- 10