Learning and regression in robotics by exploiting the structure and geometry of data (Sylvain Calinon - Idiap Research Institute)

23.05.2017 14:15 – 15:15

Human-centric robotic applications often require the robots to learn new skills by interacting with the end-users. From a machine learning perspective, the challenge is to acquire skills from only few interactions, with strong generalization demands. It requires: 1) the development of intuitive active learning interfaces to acquire meaningful demonstrations; 2) the development of models that can exploit the structure and geometry of the acquired data in an efficient way; 3) the development of adaptive control techniques that can exploit the learned task variations and coordination patterns. The developed models often need to serve several purposes (recognition, prediction, online synthesis), and be compatible with different learning strategies (imitation, emulation, exploration). For the reproduction of skills, these models need to be enriched with force and impedance information to enable human-robot collaboration and to generate safe and natural movements.

I will present an approach combining model predictive control and statistical learning of movement primitives in different coordinate systems and manifolds. The proposed approach will be illustrated in various applications, with robots either close to us (robot for dressing assistance), part of us (prosthetic hand with EMG and tactile sensing), or far from us (teleoperation of bimanual robot in deep water).

Lieu

salle 624, Séminaire d'analyse numérique

entrée libre