Feasible online learning neural and fuzzy intelligent control for a mobile vehicle

The goal of the paper is to submit an idea from the practical point of view for control technologies. Our basic idea is to make a mobile vehicle (NMV) be capable of evaluating results of actions and modifying the inputs of the controller itself in order to drive optimal or near-optimal paths. The NMV system consists of a charge-coupled device (CCD) camera, a Von Neumann type computer and a neurocomputer, and image processing units etc. The hardware neurocomputer RN-2000 is the kernel part of the system. The purpose of the paper is to solve the problem of how to realize the hardware neurocomputer by backpropagation (BP) neural network learning online. The strategy presented in the paper is based on modifying the past patterns and adjusting the content of the driving patterns by a new algorithm. Learning happens during the driving procedure of the mobile vehicle. This research shows the possibility of the neurocomputer which the BP neural network is inside can learn human knowledge online by the aid of software. Some words about our past researches are also given to help understanding the new method