Motion Comfort

Motion comfort research aims to understand and optimize the experience of movement in various contexts, from autonomous vehicle rides to human-robot collaboration. Current research focuses on integrating physiological data (e.g., pupil dilation, ECG) with machine learning models, including transformers and reinforcement learning, to predict and adapt to individual comfort levels in real-time. This work is significant for improving safety and user experience in diverse applications, ranging from industrial robotics and autonomous driving to assistive technologies and healthcare.