Papers
13
Total Citations
74
H-Index
5
About
Decai Li is a robotics and artificial intelligence researcher whose work spans autonomous navigation, machine learning, and environmental modeling for robotic systems. His research focuses on enabling robots to perceive, learn, and operate effectively in complex real-world environments, with particular emphasis on path planning, reinforcement learning, and large-scale terrain representation. Among his most notable contributions, Li has advanced deep learning approaches to robot path planning and developed incremental learning frameworks that allow autonomous robots to adapt to varying environments through Q-learning and adaptive kernel methods. His biogeography-based optimization techniques for mobile robot path planning have drawn significant attention, with multiple papers in this area accumulating citations that underscore their relevance to the field. Li has also tackled the computational challenges of large-scale unstructured environments, proposing efficient terrain modeling and occupancy mapping frameworks that address real-world storage and processing constraints. His work extends into multi-robot cooperation using deep reinforcement learning and UAV recovery in demanding marine conditions, reflecting a broad systems-level perspective on robotics. With his most-cited works attracting over ten citations each and a consistent publication record through 2022, Li represents a productive voice in the growing intersection of intelligent robotics and scalable environmental perception.
Research Focus
Key Achievements
Top Papers
- 1Vision-Based Robot Path Planning with Deep Learning12 citations · 2017
- 2
- 3
- 4
- 5
- 6An experience-based policy gradient method for smooth manipulation4 citations · 2019
- 7
- 8
- 9GPU-based heuristic escape for outdoor large scale registration3 citations · 2016
- 10