Autonomous learning and chaining of motor primitives using the Free Energy Principle
This work addresses the challenge of autonomous motor skill acquisition for robotics or AI systems, presenting an incremental approach by combining existing principles with a novel network architecture.
The paper tackled the problem of autonomously learning and chaining motor primitives by applying the Free-Energy Principle with an echo-state network, resulting in a method that successfully generated repertoires of motor trajectories and demonstrated their use in a handwriting task for producing long sequences.
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.