Generating Shared Latent Variables for Robots to Imitate Human Movements and Understand their Physical Limitations
This work addresses the need for assistive robotics in healthcare by improving robot coaches for patient rehabilitation, though it appears incremental as it builds on existing GP-LVM methods.
The paper tackles the problem of enabling robots to imitate human movements and adapt to patients' physical limitations in rehabilitation settings, achieving promising results for both imitation and adaptation.
Assistive robotics and particularly robot coaches may be very helpful for rehabilitation healthcare. In this context, we propose a method based on Gaussian Process Latent Variable Model (GP-LVM) to transfer knowledge between a physiotherapist, a robot coach and a patient. Our model is able to map visual human body features to robot data in order to facilitate the robot learning and imitation. In addition , we propose to extend the model to adapt robots' understanding to patient's physical limitations during the assessment of rehabilitation exercises. Experimental evaluation demonstrates promising results for both robot imitation and model adaptation according to the patients' limitations.