Yanlin Zhou
Papers
4
Total Citations
31
H-Index
2
About
Yanlin Zhou’s research lies at the intersection of robotics, control systems, and computer vision, with a focus on enabling autonomous agents to navigate and interact safely in complex environments. His most cited work, “Adaptive Leader-Follower Formation Control and Obstacle Avoidance via Deep Reinforcement Learning” (2019, 24 citations), introduces a novel deep reinforcement learning (DRL) framework that decouples perception from control, allowing nonholonomic robots to perform tracking, formation, and obstacle avoidance without requiring sophisticated physics or 3D models. This work has been influential in advancing scalable, vision-based multi-robot coordination. Zhou has also contributed to unsupervised depth and ego-motion estimation through feature map warping, a technique critical for autonomous navigation and collision avoidance. More recently, he has applied data-driven modeling with hysteresis compensation to the I²RIS robot for retinal microsurgery, addressing the high-precision demands of delicate intraocular procedures. By bridging reinforcement learning, visual perception, and medical robotics, Zhou’s work demonstrates a clear trajectory from foundational autonomy algorithms to impactful applications in surgery. His growing citation record reflects the relevance of his contributions to both academic research and real-world robotic systems.
Research Focus
Key Achievements
Top Papers
- 1
- 2Unsupervised Learning of Depth and Camera Pose with Feature Map Warping3 citations · 2021
- 3
- 4