Automatic generation of fuzzy rules for control of a mobile robot with track chasis based on numerical data

In this paper, we consider the problem of generating a set of fuzzy rules for the Mamdani fuzzy inference system based on numerical data obtained in the learning process of a managed system. The approach proposed inthe article to solve this problem is based on algorithms for clear and fuzzy clustering, such as the mining clusteringalgorithm and the Gustafson–Kessel algorithm. It allows you to significantly simplify the process of forminga set of fuzzy rules and minimize the participation of a person in this process, allowing you to automaticallyselect the number of rules, as well as determine all the necessary parameters for each of them. To implement theproposed approach, two computer programs were written. The first of them collects numeric data when a personmanages a robot. Based on the collected data, this program builds a base of fuzzy rules for controlling mobilerobot on a tracked chassis. This base of fuzzy rules and its computer implementation is further used in the secondprogram for automated control of a mobile robot in the plane by varying the tractive force of each of the tracksdepending on the position of the target to which the robot should approximate a given distance.