Papers
20
Total Citations
212
H-Index
9
About
Yunhan Lin is a robotics researcher whose work spans mobile robot navigation, human-robot interaction, and the integration of artificial intelligence into autonomous systems. With a career arc stretching from foundational kinematics and path planning to cutting-edge applications of large language models, Lin has consistently pushed the boundaries of intelligent robot behavior. Lin's early contributions addressed core challenges in robot motion, including a hybrid path planning method combining case-based reasoning with modified artificial potential field techniques (2015, 33 citations) and geometric-analytical approaches to inverse kinematics for modular manipulators. His work on human-robot-environment interaction produced a notable object sorting system capable of natural language understanding and 3D environmental perception (2017, 26 citations), later extended into industrial automation contexts. More recently, Lin has embraced deep learning and large language models, proposing LLM-BT — a framework pairing ChatGPT with Behavior Trees to enable adaptive robotic task execution under real-world disturbances (2024, 30 citations). His reinforcement learning contributions, including LSTM-enhanced TD3 algorithms for dynamic environments, demonstrate a sustained commitment to practical, deployable solutions. Collectively accumulating over 175 citations, Lin's body of work offers valuable insights for researchers pursuing intelligent, adaptive robotic systems.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4
- 5
- 6
- 7
- 8An Autonomous Task Algorithm Based on Behavior Trees for Robot11 citations · 2019
- 9
- 10