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

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

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

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 the robots' understanding to patients' physical limitations during assessment of rehabilitation exercises. Experimental evaluation demonstrates promising results for both robot imitation and model adaptation according to patients' limitations.

Mots clés: Robot imitation; Transfer knowledge; Physical rehabilita-tion; Shared Gaussian Process Latent Variable Model; Motion analysis

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

Maxime Devanne, Sao Mai Nguyen. Generating Shared Latent Variables for Robots to Imitate Human Movements and Understand their Physical Limitations. Workshop on Transferring and Adapting Source Knowledge in Computer Vision, in conjunction with ECCV2018, Sep 2018, Munich, Germany. ⟨hal-01886728v1⟩