VARIABLE-TARGET-TIME TRAVEL CONTROL ALGORITHM OF A ROBOT VEHICLE BY ANEURAL-NETWORK CONSIDERING THE CENTRIFUGAL FORCE

The derivation of mathematical models for robot vehicles is extremely difficult due to the high nonlinearity of the motion characteristics, making it hard to apply the conventional control theory without using approximation methods which assume constant speed, etc. In this paper, the motion control method using a neural model proposed by Uno, Kawat o et al. is extended in such a way to allow its application to the tra vel control problem of a robot vehicle, which is highly nonlinear with respect to the driving force and steering angle, and a method that ge nerates motion commands and performs trajectory planning at the same t ime is proposed. In this case, the internal coordinates of the identif ication module which learns the motion characteristics of the robot ve hicle are viewed as motion coordinates, and a method to convert the ab solute coordinates for each discrete time into motion coordinates is p roposed, making it possible to reduce greatly the number of learning p atterns. Furthermore, a variable target time algorithm is proposed tha t counteracts the centrifugal force effects which act on the robot veh icle when the curvature of the generated trajectory is large. The prop osed algorithm restrains the centrifugal force and generates optimal m otion commands and trajectory, producing results close to those obtain ed by a human driver. The effectiveness of the proposed method is demo nstrated by computer simulation.