1998 Volume 60 Issue 2 Pages 53-58
Agricultural vehicles operate in an offroad environment, and the attached implements are changed as occasion demands; thereby, the motion characteristics of the vehicle essentially change. The purpose of this study is to develop an adaptive steering controller using the measurement system of a position and a heading angle dealt in previous studies. To suit the environment change, an adaptable neuro-controller was developed, utilizing a self-organization function of a neural network. Computer simulations using a vehicle simulator were performed. As a result, the online neuro-controller could adapt to the change in the field surface condition, and make the vehicle travel precisely. Furthermore, in consideration of an actual vehicle system, position estimation using the vehicle simulator was developed for compensating a time delay of the positioning system. It was clear that the neuro-controller can appropriately adapt for the change in the field surface, and is also effective for a farm field by the experiment using the developed position estimation.