Studying How Innate Motivations Can Drive Skill Acquisition in Cognitive Robots

• Main Authors: Alejandro Romero, Francisco Bellas, Jose A. Becerra, Richard J. Duro
• Format: Article
• Language: English
• Published: MDPI AG 2019-07-01
• Series: Proceedings
• Subjects: Cognitive Developmental Robotics; open-ended learning; motivational system; skill learning
• Online Access: https://www.mdpi.com/2504-3900/21/1/2

In this paper, we address the problem of how to bootstrap a cognitive architecture to opportunistically start learning skills in domains where multiple skills can be learned at the same time. To this end, taking inspiration from a series of computational models of the use of motivations in infants, we propose an approach that leverages two types of cognitive motivations: exploratory and proficiency based, the latter modulated by the concept of interestingness as an implementation of attentional mechanisms. This approach is tested in an illustrative experiment with a real robot.