Papers
2
Total Citations
28
H-Index
2
About
Canghai Liu is a robotics researcher specializing in legged locomotion, motion planning, and reinforcement learning for autonomous systems. His work focuses on enabling robots to navigate complex, unstructured environments with greater efficiency and adaptability. In his highly cited 2023 paper, Liu introduced a novel hierarchical framework (HFG-DRL) that combines free gait motion planning with deep reinforcement learning for hexapod robots, achieving robust multi-contact locomotion in challenging terrains—a significant step toward practical field robotics. This work has already garnered 25 citations, reflecting its impact on the legged robotics community. Earlier, Liu explored reinforcement learning for mobile robot path planning, proposing a rule-based shallow-trial method to address slow convergence and high iteration costs common in traditional RL approaches. His research bridges the gap between theoretical reinforcement learning algorithms and real-world robotic applications, with a particular emphasis on improving sample efficiency and motion stability. Liu’s contributions are shaping the next generation of autonomous robots capable of traversing rough terrain, with potential applications in search-and-rescue, planetary exploration, and industrial inspection.
Research Focus
Key Achievements
Top Papers
- 1
- 2