Robotic self-representation improves manipulation skills and transfer\n learning

Le résumé fourni par la source

Cognitive science suggests that the self-representation is critical for\nlearning and problem-solving. However, there is a lack of computational methods\nthat relate this claim to cognitively plausible robots and reinforcement\nlearning. In this paper, we bridge this gap by developing a model that learns\nbidirectional action-effect associations to encode the representations of body\nschema and the peripersonal space from multisensory information, which is named\nmultimodal BidAL. Through three different robotic experiments, we demonstrate\nthat this approach significantly stabilizes the learning-based problem-solving\nunder noisy conditions and that it improves transfer learning of robotic\nmanipulation skills.\n

Ce résumé expose les affirmations des auteurs. BNTIC ne l’interprète pas comme une validation indépendante des résultats.