Developmental Learning for Social Robots in Real-World Interactions

Alexandre Galdeano (1, 2) , Alix Gonnot (1, 2) , Clément Cottet (1, 2) , Salima Hassas (1) , Mathieu Lefort (1) , Amélie Cordier (2)

1 SyCoSMA - Systèmes Cognitifs et Systèmes Multi-Agents
2 Hoomano R&D [Lyon]

This paper reports preliminary research work on applying developmental learning to social robotics for making human-robot interactions more instinctive and more natural. Developmental learning is an unsupervised learning strategy relying on the fact that the learning agent is intrinsically motivated, and is able to incrementally build its own representation of the world through its experiences of interaction with it. Our claim is that using developmental learning in social robots could dramatically change the way we envision human-robot interaction, notably by giving the robot an active role in the interaction building process, and even more importantly, in the way it autonomously learns suitable behaviors over time. Developmental learning appears to be an appropriate approach to develop a form of "interactional intelligence" for social robots. In this work, our goal was to set up a common framework for implementing, experimenting and evaluating developmental learning algorithms with various social robots.

Mots clés: Interactions; Hierarchical Learning; Social Robotics; Enaction; Developmental Learning; Intrinsic Motivation

Domaines: Intelligence artificielle [cs.AI]; Robotique [cs.RO]; Interface homme-machine [cs.HC]

Alexandre Galdeano, Alix Gonnot, Clément Cottet, Salima Hassas, Mathieu Lefort, et al.. Developmental Learning for Social Robots in Real-World Interactions. First Workshop on Social Robots in the Wild at the 13th Annual ACM/IEEE International Conference on Human-Robot Interaction (HRI 2018), Mar 2018, Chicago, IL, United States. pp.5. ⟨hal-01852233⟩