Action selection (AS) is thought to represent the mechanism involved by natural agents when deciding what should be the next\nmove or action. Is there a functional elementary core sustaining this cognitive process? Could we reproduce themechanism with an\nartificial agent and more specifically in a neurorobotic paradigm?Unsupervised autonomous robots may require a decision-making\nskill to evolve in the real world and the bioinspired approach is the avenue explored through this paper.We propose simulating an\nAS process by using a small spiking neural network (SNN) as the lower neural organisms, in order to control virtual and physical\nrobots.We base ourAS process on a simple central pattern generator (CPG), decision neurons, sensory neurons, andmotor neurons\nas themain circuit components.As novelty, this study targets a specific operant conditioning (OC) context which is relevant in an AS\nprocess; choices do influence future sensory feedback. Using a simple adaptive scenario, we show the complementarity interaction\nof both phenomena.We also suggest that this AS kernel could be a fast track model to efficiently design complex SNN which include\na growing number of input stimuli and motor outputs. Our results demonstrate that merging AS and OC brings flexibility to the\nbehavior in generic dynamical situations.
Loading....