About

Jinhui Liu is a pioneering robotics researcher whose work spans wheel-legged locomotion, 3D perception, and hierarchical reinforcement learning. His most influential contribution is the design and dynamic analysis of a jumping wheel-legged robot with a parallel four-bar mechanism, which overcomes the poor balance and limited mobility of traditional wheeled robots on rough terrain (31 citations). Liu also advanced point cloud understanding through KVGCN, a graph convolutional network that combines K-nearest neighbor searching with Vector of Locally Aggregated Descriptors for robust semantic segmentation—critical for robot navigation and scene reconstruction (14 citations). In reinforcement learning, he introduced a hierarchical approach using reachability-based reward shaping to dramatically reduce sample complexity in long-horizon tasks (10 citations). His innovative work extends to underwater bionic fish with hybrid propulsion (9 citations), 3D positioning via QR codes and monocular vision (9 citations), and aerial manipulator control using nonlinear disturbance observers (4 citations). Notably, his TKO-SLAM algorithm addresses keyframe loss during rapid motion, preventing trajectory drift in visual SLAM (4 citations). With over 80 total citations across these seven papers, Liu’s research is shaping the future of autonomous robots operating in complex, unstructured environments.

Research Focus

Key Achievements

5
H-Index
7
Papers
81
Total Citations
12
Avg Citations/Paper
🏆 Most Cited Paper
Design and dynamic analysis of jumping wheel-legged robot in complex terrain environment
31 citations · 2022
📈 Most Prolific Year: 2021 (2 Papers)
🤝 Key Collaborators: 31
🏛 Institutions: Nanjing Institute of Technology, Xidian University, Guangdong University of Technology, Harbin Institute of Technology, Anhui Polytechnic University

Top Papers

  1. 1
  2. 2
  3. 3
  4. 4
  5. 5
  6. 6
  7. 7

Key Collaborators

Contact & Links

Available for collaboration
Content generated · 13 days ago