Fengming Li
Papers
11
Total Citations
253
H-Index
7
About
Fengming Li is a leading researcher in intelligent robotic assembly, with a primary focus on skill acquisition, deep reinforcement learning, and multi-modal perception for industrial automation. His most influential work, "Robot skill acquisition in assembly process using deep reinforcement learning" (110 citations), pioneered the use of reinforcement learning to enable robots to autonomously learn complex assembly tasks, moving beyond traditional programming. Li’s contributions are particularly significant in addressing the challenges of assembling deformable and elastic components, where he developed frameworks that leverage visual perspectives, force sensing, and multi-modal information to adapt to dynamic uncertainties. His research on "A Robotic Automatic Assembly System Based on Vision" (45 citations) and "Skill learning for robotic assembly based on visual perspectives and force sensing" (29 citations) has directly advanced the intelligence level of production lines, especially in the mobile phone industry. Li has also made notable strides in force perception modeling and contact state recognition using support vector regression, enhancing precision in high-stakes assembly operations. With over 240 total citations, his work bridges the gap between machine learning and practical robotics, offering scalable solutions for flexible manufacturing.
Research Focus
Key Achievements
Top Papers
- 1Robot skill acquisition in assembly process using deep reinforcement learning110 citations · 2019
- 2A Robotic Automatic Assembly System Based on Vision45 citations · 2020
- 3
- 4
- 5
- 6
- 7
- 8Robot Bolt Skill Learning Based on GMM-GMR5 citations · 2021
- 9
- 10