THE ROLE OF SENSORY-MOTOR COORDINATION - Identifying Environmental Motion Dynamics with Dynamic Neural Networks

Abstract

We describe three recurrent neural architectures inspired by the proprioceptive system found in mammals; Exo-sensing, Ego-sensing, and Composite. Through the use of Particle Swarm Optimisation the robot controllers are adapted to perform the task of identifying motion dynamics within their environment. We highlight the effect of sensory-motor coordination on the performance in the task when applied to each of the three neural architectures.