Papers
10
Total Citations
39
H-Index
4
About
Mingjie Lin is a robotics and artificial intelligence researcher whose work spans robot motion planning, dexterous manipulation, reinforcement learning, and autonomous navigation. His research addresses some of the most demanding challenges in modern robotics: enabling machines to operate intelligently and safely in complex, dynamic real-world environments. Lin's most notable contributions include APEX, a generative diffusion model framework for ambidextrous dual-arm robotic manipulation (9 citations), and DAMON, a topological manifold learning approach for navigating amorphous obstacles (8 citations). His work on reactive trajectory optimization through RETRO further demonstrates his focus on real-time robotic decision-making under uncertainty. Beyond motion planning, Lin has made meaningful contributions to multi-agent reinforcement learning, developing constructive policy frameworks for connected systems (6 citations) and pioneering bio-inspired locomotion strategies using deep deterministic policy gradients. His research portfolio also extends to edge computing for human action recognition and survivable robotic control under mechanical failure — reflecting a remarkably broad technical vision. With work published across 2019–2024 and a growing citation record, Lin is an emerging voice in intelligent robotics, particularly at the intersection of generative AI, variational methods, and autonomous systems. His research holds significant promise for advancing robots capable of human-level adaptability and dexterity.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4
- 5
- 6
- 7
- 8Policy Reuse in Reinforcement Learning for Modular Agents2 citations · 2019
- 9
- 10