Max Robotics — Global Service Robot Directory + US Certification

About

Michael Drolet is a robotics researcher whose work sits at the intersection of human-robot interaction, rehabilitation engineering, and wearable sensing. His primary research areas include robot-assisted gait rehabilitation, physical human-robot interaction, and ubiquitous control interfaces. Drolet’s major contributions center on developing algorithms that enable robots to understand and respond to human movement and intent. Notably, his most-cited work (2020, 11 citations) investigates how visual anticipation of floor compliance changes affects human gait, advancing model-based approaches for post-stroke rehabilitation. This research highlights the potential of combining multiple rehabilitation methods to maximize patient outcomes. In a more recent line of work (2023, 5 citations), Drolet devised an optimized machine learning approach for estimating human arm pose from a single smartwatch, enabling anytime, anywhere robot control and teleoperation. This innovation offers a practical, low-cost alternative to traditional motion capture systems. Additionally, his work on learning and blending robot hugging behaviors (2023, 3 citations) introduces Blending Bayesian Interaction Primitives (B-BIP), an imitation learning algorithm that predicts appropriate robot responses during complex physical interactions. Through these contributions, Drolet is shaping the future of intuitive, responsive, and accessible robotic systems.