Abstract | In this paper we describe the evolution of a discrete-time recurrent neural network to control a real mobile robot. In all our experiments the evolutionary procedure is carried out entirely on the physical robot without human intervention. We showthat the autonomous development of a set of behaviors for locating a battery charger and periodically returning to it can be achieved by lifting constraints in the design of the robot/environment interactions that were employed in a preliminary experiment. The emergent homing behavior is based on the autonomous development ofaninternal neural topographic map (which is not pre-designed) that allows the robot to choose the appropriate trajectory as function of location and remaining energy.

This paper successively describes the works of Boers & Kuiper, Gruau, Cangelosi et al., Vaario, Dellaert & Beer, and Sims, which all evolve the developmental program of an artificial nervous system. The potentialities of these approaches for automatically devising a control architecture linking the perceptions and the actions of an animat are then discussed, together with their possible contributions to the fundamental issue of assessing the adaptive values of development, learning and evolution.

Abstract. It is clear to all, after a moments thought, that nature has much we might be inspired by when designing our systems, for example: robustness, adaptability and complexity, to name a few. The implementation of bio-inspired systems in hardware has however been limited, and more often than not been more a matter of artistry than engineering. The reasons for this are many, but one of the main problems has always been the lack of a universal platform, and of a proper methodology for the implementation of such systems. The ideas presented in this paper are early results of a new research project, "Reconfigurable POEtic Tissue". The goal of the project is the development of a hardware platform capable of implementing systems inspired by all the three major axes (phylogenesis, ontogenesis, and epigenesis) of bio-inspiration, in digital hardware. 1

This paper successively describes the works of Boers and Kuiper, Vaario, Nolfi and Parisi, Gruau, and Dellaert and Beer, which all evolve the developmental program of an artificial nervous system. The potentialities of these approaches for automatically devising a control architecture linking the perceptions and the actions of an animat are then discussed, together with their possible contributions to the fundamental issue of assessing the adaptive values of development, learning and evolution.