Vieri Giuliano Santucci

Biography

Vieri Giuliano Santucci received the B.Sc. degree in philosophy from the University of Pisa, Pisa, Italy, and the M.S. degree in theories and techniques of knowledge from the Faculty of Philosophy, University of Rome “La Sapienza,” Rome, Italy, and the Ph.D. degree in computer science from the University of Plymouth, Plymouth, U.K., in 2016, with a focus on the development of robotic architectures that allow artificial agents to autonomously improve their competences on the basis of the biologically-inspired concept of intrinsic motivations. He is a Researcher with the Istituto di Scienze e Tecnologie della Cognizione, Consiglio Nazionale delle Ricerce, Rome. He published in peer-reviewed journals and attended several international conferences, and actively contributed to the European Integrated Projects “IM-CLeVeR— Intrinsically-Motivated Cumulative-Learning Versatile Robots.” and “GOAL-Robots – Goal-based Open-ended Autonomous Learning Robots”. His current research interests include learning processes, motivations as well as to the concept of representations, in both biological and artificial agents.

Abstract

Architectures for intrinsically motivated open-ended learning: from autonomous goal discovery to skill learning

In this talk I will present some of the systems we developed to allow artificial agents to autonomously interact with the environment, setting their own goals and widening their repertoire of skills on the basis of intrinsically motivated mechanisms. In particular, I will first present GRAIL, a Goal-Discovering Robotic Architecture for Intrinsically-Motivated Learning, which represents the main reference for our next works. I will then introduce a system where goals are used as a pivot for the early development of body knowledge, and another work where we tested in a real robot an architecture able to leverage autonomously learnt goals and skills for the achievement of user’s assigned goals. Finally, I will describe two ongoing works: one aiming to use a controlled camera to support generalisation over space in an open-ended system, and the other one integrating autonomous learning of goals/skills with the autonomous formation of operators to support high-level symbolic planning.