A backpropagation neural network is proposed as a controller for an automated guided vehicle (AGV) system. At the present stage of development, the input layer consists of two neurons and receives the state signals of the tracking errors from the camera image processor, and the sole neuron in the output layer provides the command signal of a reference yaw rate signal for the vehicle. Simulations and preliminary experimentation on a prototype vehicle showed that one hidden layer was adequate to provide good driving for such a time-varying nonlinear dynamic system. A comparison with a previous proportional controller is included. >