Reactive methods of control get caught in local minima. Fortunately schema-based reac-tive control systems have built-in redundancy that enables multiple conngurations with different modes. We describe a model-based method that exploits this redundancy, and, under certain conditions, reconngures schema-based reactive control systems trapped in be-havioral cycles due to the presence of local minima. The qualitative model speciies 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 be-havioral cycles, analyzes the processing trace, identiies potential modiications, and reconng-ures the reactive architecture. We report on experiments with a simulated robot navigating a complex space.
[1]
Paul R. Cohen,et al.
Failure Recovery: A Model and Experiments
,
1991,
AAAI.
[2]
Ronald C. Arkin,et al.
Integrating behavioral, perceptual, and world knowledge in reactive navigation
,
1990,
Robotics Auton. Syst..
[3]
Ronald C. Arkin,et al.
Motor Schema — Based Mobile Robot Navigation
,
1989,
Int. J. Robotics Res..
[4]
Eleni Stroulia,et al.
Learning Problem-Solving Concepts by Reflecting on Problem Solving
,
1994,
ECML.
[5]
Eleni Stroulia,et al.
A Model-Based Approach to Blame Assignment: Revising the Reasoning Steps of Problem Solvers
,
1996,
AAAI/IAAI, Vol. 2.