Robotic Choreography Creation Through Symbolic AI Techniques

Symbolic Artificial Intelligence (AI) techniques in robotic choreography contribute to the broader field of human-robot interaction and address the main limitations of learning approaches in terms of computational requirements. A general symbolic approach leveraging dance sequence rules and constraints can (1) reduce computational effort and (2) allow the possibility to easily insert aesthetic and musical constraints. In this direction, this paper presents a preliminary approach based on symbolic AI techniques that is able to plan a robotic choreography based on a general problem description and music input. The algorithm is adaptable using different symbolic AI techniques, and by considering different user requirements. For the demonstration phase, a challenge in a Master course on AI was organized, with resulting choreographies available in a public repository. The possibility to easily insert aesthetic constraints also allows to a more intuitive and expressive communication between humans and robots. This has implications not only in the field of entertainment but also in different areas like healthcare and education.