Generating Shared Latent Variables for Robots to Imitate Human Movements and Understand their Physical Limitations

Maxime Devanne (1) , Sao Mai Nguyen (2)

1 IMT Atlantique - INFO - Département Informatique
2 Lab-STICC_IMTA_CID_IHSEV

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.

Mots clés: motion analysis; shared Gaussian Process Latent Variable Model; Physical rehabilitation; Robot imitation; transfer knowledge

Domaines: Intelligence artificielle [cs.AI]; Vision par ordinateur et reconnaissance de formes [cs.CV]; Interface homme-machine [cs.HC]; Apprentissage [cs.LG]; Robotique [cs.RO]

Maxime Devanne, Sao Mai Nguyen. Generating Shared Latent Variables for Robots to Imitate Human Movements and Understand their Physical Limitations. IEEE ECCV Workshop on Transferring and Adapting Source Knowledge in Computer Vision (TASK-CV), Sep 2018, Munich, Germany. pp.190-197, ⟨10.1007/978-3-030-11012-3_15⟩. ⟨hal-01891414v4⟩