Chenkun Yin
Papers
2
Total Citations
12
H-Index
2
About
Chenkun Yin is a robotics researcher specializing in adaptive control and reinforcement learning for autonomous systems. His work focuses on enabling robots to operate effectively in uncertain, dynamic environments—particularly in manipulation and search-and-rescue domains. In his most-cited paper (2021, 9 citations), Yin introduced a model-free adaptive predictive tracking control method for robot manipulators with uncertain parameters, using compact form dynamic linearization to transform nonlinear systems into data-driven models. This approach eliminates the need for precise mathematical models, making it highly practical for real-world applications. In a subsequent study (2022, 3 citations), Yin applied soft actor-critic reinforcement learning to humanoid robot search-and-rescue tasks in complex enclosed spaces, designing a Markov Decision Process with multi-stage auxiliary rewards to improve exploration and task completion. His contributions bridge the gap between theoretical control methods and practical robotic deployment, offering scalable solutions for uncertain environments. Yin’s work is particularly notable for its emphasis on data-driven, model-free techniques that reduce reliance on system identification, a significant advantage for real-time robotic applications.
Research Focus
Key Achievements
Top Papers
- 1
- 2