Jianyin Fan
Papers
7
Total Citations
42
H-Index
4
About
Jianyin Fan is a leading researcher in bio-inspired robotics, focusing on the intersection of muscle-skeleton robot design, reinforcement learning, and neural decoding. Their work centers on developing humanoid robotic systems that mimic biological structures, particularly through the use of pneumatic artificial muscles and McKibben actuators. Fan’s major contributions include pioneering the integration of spiking neural networks for EMG-based motion decoding, enabling intuitive human-robot interaction by translating muscle activity into continuous control signals. They have also advanced model-based reinforcement learning frameworks for trajectory tracking in musculoskeletal robots, addressing challenges like sensor limitations and actuator lifespan. With over 40 citations across their most-cited works, Fan’s impact is evident in papers such as their 2022 study on EMG decoding (12 citations) and their 2024 semiparametric musculoskeletal model (11 citations). Notable achievements include the design of a novel multifilament McKibben muscle and the application of large language models to enhance reinforcement learning for high-precision control. Fan’s research bridges neuroscience, robotics, and AI, offering transformative insights for adaptive, human-like robotic systems.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4
- 5
- 6
- 7