Using fuzzy behaviors for the outdoor navigation of a car with low-resolution sensors

An approach using superposition of elemental fuzzy behaviors to emulate humanlike qualitative reasoning schemes is discussed. The authors describe how a previously developed navigation scheme implemented on custom-designed VLSI fuzzy inferencing boards for indoor navigation of a small laboratory-type robot was progressively enhanced and used to investigate two control modes for driving a car in a priori unknown environments on the basis of sparse and imprecise sensor data. In the first mode, the car navigates fully autonomously, whereas in the second mode, the system acts as a driver´s aid providing the driver with linguistic (fuzzy) commands, depending on the obstacles perceived by the sensors. Experiments with both modes of control are described in which the system uses only three acoustic range (sonar) sensor channels. Simulation results, as well as indoors and outdoors experiments, are presented and discussed