• Citer

Adaptive Learning of a Robot Arm

par Patel, Mukesh J.;Dorigo, Marco
Référence Lecture notes in computer science, 865, page (180-194)
Publication Publié, 1994

Article révisé par les pairs

• Accès en ligne
• Détails
• Contenu
• Statistiques

Résumé :

Alecsys, an implementation of a learning classifier system (LCS) on a net of transputers was utilised to train a robot arm to solve a light approaching task. This task, as well as more complicated ones, has already been learnt by Alecsys implemented on AutonoMouse, a small autonomous robot. The main difference between the present and previous applications are, one, the robot arm has asymmetric constraints on its effectors, and two, given its higher number of internal degrees of freedom and its non anthropomorphic shape, it was not obvious, as it was with the AutonoMouse, where to place the visual sensors and what sort of proprioceptive (the angular position of the arm joints) information to provide to support learning. We report results of a number of exploratory simulations of the robot arm's relative success in learning to perform the light approaching task with a number of combinations of visual and proprioceptive sensors. On the bases of results of such trials it was possible to derive a near optimum combination of sensors which is now being implemented on a real robot arm (an IBM 7547 with a SCARA geometry). Finally, the implications these findings, particularly with reference to LCS based evolutionary approach to learning, are discussed.