Designing a hierarchical fuzzy controller for backing-up a four wheel autonomous robot

Abstract

Fuzzy controller, formulated on the basis of human understanding of the process or identified from measured control actions, can be regarded as an emulator of human operator. Truck backer-upper system is a typical problem in nonlinear motion control of nonholonomic robots. Controller design, however, may become difficult, especially if the number of state variables is large. This paper recommends a fuzzy control design method for this problem. The addressed problem is the diagonal parking for an autonomous vehicle in which it has to successfully back up to a constrained domain. The fuzzy controller is based on a hierarchical scheme, which is a combination of two fuzzy modules. The rules of each module have been obtained from heuristic knowledge and numerical data. The goal of the control system is to provide short paths with continuous curvature. Approximated trajectories are composed of circular arcs of minimum turning radii and straight line segments. Compared with traditional controller, this fuzzy controller demonstrates advantages on the control performance, convenience and feasibility.