Guizhou Deng
Papers
3
Total Citations
42
H-Index
3
About
Guizhou Deng is a leading researcher in legged robotics, with a focused expertise in motion planning and control for hexapod robots operating in complex, unstructured environments. His core contributions lie at the intersection of hierarchical motion planning and deep reinforcement learning (DRL), where he has pioneered methods to enable multi-contact locomotion across challenging terrains. Deng’s most influential work, "Hierarchical Free Gait Motion Planning for Hexapod Robots Using Deep Reinforcement Learning" (2023), has garnered 25 citations for its novel HFG-DRL framework that structurally decomposes complex free-gait planning. He further advanced the field with a DRL-based approach for navigating uneven plum-blossom piles (2021, 13 citations), and recently introduced an incremental reinforcement learning technique (HMC-IRL) for traversing large-scale discrete obstacles (2023, 4 citations). Collectively, his research addresses the critical challenge of integrating static and dynamic obstacle avoidance into legged locomotion, offering scalable solutions that bridge theoretical planning with real-world robotic agility. Deng’s work is essential reading for anyone interested in autonomous navigation, reinforcement learning applications, or the future of adaptive, multi-contact robotic movement.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3