Design of Backward Movement Control for a Truck System with Two Trailers Using Neurocontrollers Evolved by Genetic Algorithms

Abstract

In this paper, we propose a design method of neurocontrollers (NCs) evolved by a genetic algorithm (GA) for the backward movement control of a truck system with two trailers. The difficulty and complexity of the backward movement control depend on the number of connected trailers and the angular limitations of the trailer-truck system. In order to search for the best neurocontroller more quickly and effectively, for the two-trailer system which has extremely small angular limitations, we propose a modified GA which adaptively changes the number of offspring and the mutation rate according to the diversity of NC population. The simulation results show that the modified GA significantly improves the search performance. We apply the control method not only to computer simulations but also to experiments of a small-scale real mechanism. The results of both show that the control method is highly effective.