Feed-forward multilayer neural network model for vehicle lateral guidance control

Abstract

An advanced vehicle lateral guidance control technology is necessary in order to develop intelligent transportation and manufacturing systems with flexibility and immediate adaptability. PID control, optimal control, and fuzzy control have often been used for designing a vehicle lateral guidance controller; in addition automatic guidance methods by spline curve and inverse dynamics are also used in mobile robots (e.g. differential drive), but they are not sufficient to develop a highly intelligent vehicle lateral guidance controller which can adapt to varying environments, because they lack some behavior like learning ability and adaptability. In this paper, the possibility to apply neural networks for developing a vehicle lateral guidance controller is exposed. A new neuron activation function suitable for vehicle lateral guidance control is suggested, a feed-forward multilayer neural network (FMNN) with the suggested neuron activation function is proposed and a vehicle lateral guidance controller (VLGC) is developed by use of the FMNN. The VLGC can be applied to automobiles of different parameters and roads of various widths. It can be also applied to mobile robots. Its input variables are proposed to be defined as kind of relative quantities by using the road width, automotive parameter, automotive position, and orientation on the corner course as 90°. Its output variable is the automotive steering angle. Its teaching data are collected by automobile driving simulation, and its connection weights and threshold values are tuned through the error back-propagation algorithm. The training process and the result of neural network by different learning rate coefficients and momentum parameters are compared. Four VLGCs are generated through training by using different learning rate coefficients, momentum parameters, and repeat training times. Automated guided automobile simulations and mobile robot experiments for each VLGC are carried out. Good training result as well as automated guided simulation and experimental results are obtained.