Learning of Sensorimotor Contingencies to move a Four- Legged Robot

Autoren: Carsten Böhme, Philippe Büttner, Cornelius Wefelscheid und Tilman Wekel

In this paper, an approach for learning of crawling movements of a four-legged autonomous robot is presented. On the basis of a self-supervised strategy, the robot learns to choose its next movement by its sensorimotor states. This is based on feedback gained from the environment by actively tracking an object. Within a few hours of training, the robot shows interesting crawling behaviour patterns which occur in different stages, comparable to the learning of movement by infants.


AIBO, four-legged autonomous robot, feed-forward neural network, learning, artificial intelligence