1994 Volume 56 Issue 4 Pages 53-60
This study intends to make an appropriate control system for a nonlinear vehicle kinematics, in view of developing autonomous agricultural vehicles. The kinematics of vehicles that operate on off-road has higher nonlinearity than that of vehicles on a road. Neural Networks (NN) that can be used to solve nonlinear problems was applied to the vehicle control. It was clear that this controller could give output appropriately for both the trained data and the untrained data. Furthermore, the accuracy of control using the neuro-controller was investigated by comparing with the PID controller, in order to evaluate the ability of neuro-controller as a following control system. It was discovered that the neuro-controller indicated higher accuracy than the PID controller, and it was effective for the vehicle control.
