Papers

4

Total Citations

15

H-Index

3

About

Dun Li is a researcher at the forefront of intelligent robotics and industrial automation, with a focus on real-time visual perception and robust localization. Li’s work centers on enabling autonomous systems to perceive and navigate complex environments, addressing critical challenges in both sensing and state estimation. A key contribution is the development of a robust optimization-based framework that fuses GNSS with Visual-Inertial-Wheel Odometry, achieving drift-free state estimation for autonomous mobile robots—a foundational step for reliable navigation. In the realm of visual sensing, Li pioneered a method using multi-scale region convolutional neural networks to detect and interpret shadow features from visible light, enabling simultaneous communication and sensing for production items in industrial IoT settings. This work has garnered 6 citations, reflecting its relevance to smart manufacturing. More recently, Li has advanced real-time robotic vision by integrating detection and scene segmentation, and by optimizing YOLO-based models for hand keypoint detection, ensuring high performance on computationally limited embedded devices. With a growing citation record and a clear trajectory toward practical, deployable solutions, Dun Li is shaping the future of autonomous robotics in industrial and service applications.

Research Focus

Key Achievements

3
H-Index
4
Papers
15
Total Citations
4
Avg Citations/Paper
🏆 Most Cited Paper
Visible light sensing based on shadow features using multi-scale region convolutional neural network
6 citations · 2023
📈 Most Prolific Year: 2024 (2 Papers)
🤝 Key Collaborators: 14
🏛 Institutions: PLA Information Engineering University, Intelligent Health (United Kingdom), Tsinghua University

Top Papers

  1. 1
  2. 2
  3. 3
  4. 4

Key Collaborators

Contact & Links

Available for collaboration
Content generated · 13 days ago