Autonomous spatial orientation of robots using chaotic cognition and geometric cues

Abstract

In this paper an innovative methodology for geometrical orientation and robot control is proposed. The innovative method exploits the use of multisensory integration applied to a chaotic cognitive system for a mobile robot which is able to be controlled in real-time towards less complex orbits, such as periodic orbits or equilibrium points, considered as perceptive orbits. The strategy is inspired by the olfactory bulb neural activity observed in rabbits subjected to external stimuli. These are subject to real-time modifications on the basis of environmental changes acquired through a distributed sensory system. The mathematical details of the approach are given including simulation results in different geometric environments. The obtained results also demonstrate the significant impact of different geometric cues on reorientation performance as well as spatial updating performance for autonomous robots. Furthermore, the robot's reorientation performance is approximately inversely proportional to the rotational symmetry of the environment, whereas the spatial updating performance is equally good in angular environments but worse in a circular environment.