Model-Based Reconfiguration of Schema-Based Reactive Control Architectures

Abstract

Reactive methods of control get caught in local minima. Fortunately schema-based reactive control systems have built-in redundancy that enables multiple configurations with different modes. We describe a model-based method that exploits this redundancy, and, under certain conditions, reconfigures schema-based reactive control systems trapped in behavioral cycles due to the presence of local minima. The qualitative model specifies the functions and modes of the perceptual and motor schemas, and represents the reactive architecture as a structure-behavior-function model. The model-based method monitors the reactive processing, detects failures in the form of behavioral cycles, analyzes the processing trace, identifies potential modifications, and reconfigures the reactive architecture. We report on experiments with a simulated robot navigating a complex space.