Papers
14
Total Citations
550
H-Index
10
About
Benoit Gosselin is a prominent biomedical and electrical engineering researcher whose work sits at the intersection of human-machine interfaces, neural signal processing, and assistive robotics. Best known for pioneering the application of deep learning to surface electromyography (sEMG), Gosselin has made transformative contributions to how robotic prosthetic devices interpret human muscle signals. His 2017 paper on transfer learning for sEMG-based hand gesture recognition (174 citations) and his 2016 convolutional neural network approach for robotic arm guidance (138 citations) established him as a leading voice in bridging advanced machine learning with rehabilitation engineering — overcoming the critical challenge of limited training data in clinical populations. Beyond signal processing, Gosselin has championed accessible, intuitive human-robot interaction for individuals with upper-body disabilities. His multimodal adaptive wireless control interfaces and proportional robotic arm control systems reflect a consistent commitment to real-world usability, leveraging wearable sensor networks and high-density sEMG to serve diverse user needs. His work extends further into swarm robotics control through natural body motion. With cumulative citations surpassing 500 across his most impactful publications, Gosselin's research has meaningfully advanced the frontier of assistive technology, making sophisticated robotic systems more responsive, intuitive, and accessible for people living with physical disabilities.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4Intuitive Adaptive Orientation Control for Enhanced Human–Robot Interaction38 citations · 2018
- 5
- 6
- 7Engaging with Robotic Swarms23 citations · 2019
- 8
- 9
- 10