Target Representation on an Autonomous Vehicle with Low-Level Sensors

Abstract

How can low-level autonomous robots with only very simple sensor systems be endowed with cognitive capabilities? Specifically, we consider a system that uses seven infrared sensors and five microphones to avoid obstacles and acquire sound targets. The cognitive abilities of the vehicle consist of representing the direction in which a sound source lies. This representation supports target detection, estimation of target direction, selection of one out of multiple-detected targets, storage of target direction in short-term memory, continuous updating of memory, and deletion of memorized target information after a characteristic delay. We show that the dynamic approach (attractor dynamics) employed to control the motion of the robot can be extended to the level of representation by using dynamic neural fields to interpolate sensory information. We show how the system stabilizes decisions in the presence of multivalue sensorial information and activates and deactivates memory. Smooth integration of this target representation with target acquisition, in the form of phonotaxis, and obstacle avoidance is demonstrated.