Behavior-based AI techniques for vehicle control

Abstract

In behavior-based artificial intelligence (AI), intelligence is realized as an emergent process which arises from interactions between otherwise "unintelligent" simple behaviors of agents and between these agents and their environment. A set of algorithms which uses Subsumption Architecture (SA) for controlling vehicles operating in close vicinity has been developed. SA is a dominant behavior-based AI technique. The algorithms collectively generate desirable manoeuver capabilities for vehicles which must travel through a dynamic interactive environment. A successful application of the approach to a small-scale but fully situated and embodied vehicle control problem using scaled down mobile robots is described.