The IM-CLeVeR project: Intrinsically motivated cumulative learning versatile robots

This short paper presents the core ideas of the IM-CLeVeR Project. IM-CLeVeR aims at developing a new methodology for designing robot controllers that can: (a) cumulatively learn new skills through autonomous development based on intrinsic motivations, and (b) reuse such skills for accomplishing multiple, complex, and externally-assigned tasks. This goal will be pursued by investigating three fundamental issues: (a) the mechanisms of abstraction of sensorimotor information; (b) the mechanisms underlying intrinsic motivations; (c) hierarchical architectures that permit cumulative learning. The study of these issues will be conducted on the basis of empirical experiments run with monkeys, children, and human adults, with bio-mimetic models aimed at reproducing and interpreting the results of such experiments, and through the design of innovative machine learning systems. The models, architectures, and algorithms so developed will be validated with experiments and demonstrators run with the simulated and real iCub humanoid robot.