About

Haoang Li is a robotics researcher whose work spans the critical intersection of large-scale multi-robot coordination, visual perception, and vision-language-action models for manipulation. His most impactful contributions address the fundamental challenge of coordinating hundreds of autonomous robots in logistics and industrial settings, where he has developed integrated frameworks for task assignment, path planning, and collision-free coordination under uncertainty—work that has garnered over 65 citations for his flagship 2021 paper. Li’s research is distinguished by its practical ambition: from the "San Francisco World" model, which exploits urban slope regularities to enable 3D visual compass navigation across building floors, to PD-VLA, a parallel decoding method that accelerates vision-language-action models for dexterous manipulation. He has also advanced SLAM with a novel LiDAR-based loop-closing approach combining equivariance and invariance on SE(3). More recently, his RoboDexVLM framework integrates visual language models with task planning and grasp detection for dexterous hands, pushing toward more generalizable robotic manipulation. Li’s work consistently bridges theoretical rigor with real-world deployability, making him a notable voice in the evolution of autonomous robotic systems.

Research Focus

Key Achievements

3
H-Index
6
Papers
89
Total Citations
15
Avg Citations/Paper
🏆 Most Cited Paper
Integrated Task Allocation and Path Coordination for Large-Scale Robot Networks With Uncertainties
65 citations · 2021
📈 Most Prolific Year: 2025 (3 Papers)
🤝 Key Collaborators: 26
🏛 Institutions: Chinese University of Hong Kong, Hong Kong University of Science and Technology, University of Hong Kong

Top Papers

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

Key Collaborators

Contact & Links

Available for collaboration
Content generated · 13 days ago