Abstract
In this paper, we propose a design method of a two-wheel vehicle regulator using a neurocontroller (NC) op-timized by a genetic algorithm (GA). The two-wheel vehicle can be modeled as a driftless system and is known to be in the class of nonholonomic systems. Many control methods have been presented for nonholonomic systems. One method is the time-state control form that utilizes a chained form conversion. The chained forms are powerful and useful for designing the nonholonomic control system. However, in the case of a two-wheel vehicle, the time-state control form has some limitations in the controllable ranges due to the conversion. In this paper, we propose a design method of a state feedback controller for a two-wheel vehicle system using an NC without chained forms. The NC is trained by a genetic algorithm. In the controller design, the abilities of pattern recognition and generalization of the neural network are utilized. In this study, we prepared 45 sets of initial positions and angles for controller training. In the GA process, NCs are evaluated on the basis of control performance in which the squared errors that result from the control simulations starting from all the initial states are calculated. Based on the control performance, NCs are evolved through the GA processes. Results of simulations show that the NCs trained using a GA exhibit good control performance of the two-wheel vehicle system. One of the control strategies of the NC resembles that of time-state control form. The proposed method has no limitations in the controllable ranges in the initial states.
