AN ACQUISITION OF OPERATORS RULES FOR COLLISION-AVOIDANCE USING FUZZYNEURAL NETWORKS

The procedure for acquiring control rules to improve the performance o f control systems has received considerable attention recently. This p aper deals with a collision avoidance problem in which the controlled object is a ship with inertia which must avoid collision with a moving object. It has proven to be difficult to obtain collision avoidance r oles, i.e., steering rules and speed control rules, which coincide wit h the operator's knowledge. This paper shows that rules of this type c an be acquired directly from observational data using fuzzy neural net works (FNN's). This paper also shows that the FNN can obtain portions of the fuzzy rules for the inferences of the static and dynamic degree s of danger and the decision table based on the degrees of danger to a void the moving obstacle.