Learning Adaptable Utility Models for Morphological Diversity

This paper introduces an approach to the integration of open-ended learning in modular robotics. We aim to provide these robots, equipped with morphological adaptability, with the capability to autonomously learn utility models specific to each morphology, discovering objectives on their own through a motivational system designed for open-ended learning. This system incorporates intrinsic motivations based on novelty and introduces a unique intrinsic motivation based on frustration to prevent learning stagnation. Furthermore, the paper addresses the autonomous learning of world models, enabling the robot to identify its morphology, all within the framework of a cognitive architecture. Experimental results showcase the effectiveness of this approach in both real and simulated environments.