Robotic self-representation improves manipulation skills and transfer learning

TL;DR

This paper introduces multimodal BidAL, a model that enhances robotic manipulation and transfer learning by incorporating self-representation based on action-effect associations, inspired by cognitive science.

Contribution

It presents a novel computational model linking self-representation with reinforcement learning, improving robotic manipulation stability and transfer learning capabilities.

Findings

Stabilizes learning under noisy conditions

Enhances transfer learning of manipulation skills

Validates effectiveness through three robotic experiments

Abstract

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