Knowledge Acquisition of Control Strategy and Tactics for Collision Avoidance Using Fuzzy Neural Networks

Abstract

Acquisition of control rules have been actively studied for improving performances of control systems. This paper deals with a collision avoidance problem for avoiding a moving object. The controlled object is a large ship with a large inertia. It has been difficult to obtain the collision avoidance rules which coincide with operators' knowledge. This paper shows that the operators' avoiding rules can be acquired directly from data, which operators probably observe, using a Fuzzy Neural Network (FNN). This paper also shows that the FNN can obtain portions of the fuzzy rules for the inferences of the static and dynamic degrees of danger and the decision table based on the degrees of danger.