Adaptive learning with the growing competitive linear local mapping network for robotic hand-eye coordination

Abstract

Traditionally, linear local mapping networks learn the entire workspace, and the neurons are placed according to the Kohonen map or its variant, the "neural gas". In this paper a new neural network is introduced, which allocates neurons adaptively following the current trajectory, according to an error criterion. The resulting network has a small number of neurons and is thus very efficient. It also learns very quickly: employing active learning and the RLS algorithm, just one pass is sufficient for our algorithm to acquire the Jacobians that are needed to perform a given positioning of the robot's gripper on the target. Also, an online adaptation of the Jacobians is proposed.