English

Autonomous learning and chaining of motor primitives using the Free Energy Principle

Neural and Evolutionary Computing 2020-05-12 v1 Artificial Intelligence Machine Learning Robotics

Abstract

In this article, we apply the Free-Energy Principle to the question of motor primitives learning. An echo-state network is used to generate motor trajectories. We combine this network with a perception module and a controller that can influence its dynamics. This new compound network permits the autonomous learning of a repertoire of motor trajectories. To evaluate the repertoires built with our method, we exploit them in a handwriting task where primitives are chained to produce long-range sequences.

Keywords

Cite

@article{arxiv.2005.05151,
  title  = {Autonomous learning and chaining of motor primitives using the Free Energy Principle},
  author = {Louis Annabi and Alexandre Pitti and Mathias Quoy},
  journal= {arXiv preprint arXiv:2005.05151},
  year   = {2020}
}