Autonomous vehicle identification, control and piloting through a new class of associative memory neural networks

摘要

Addresses the use of a class of neural nets for the intelligent motion control and piloting of a variety of autonomous vehicles as part of an ESPRIT II mobile robotics project. Intelligent controllers are necessary in order to cope with the vehicle complexities, internal parametric changes, safety imposed dynamic constraints as well as the effects of a dynamic environment. Single-layer, associative memory neural networks, the modified Albus CMAC and B-splines, are proposed as the basis for an intelligent piloting system. These algorithms have an initially exponential convergence rate, are temporally stable (unlike the multilayer perceptron), noise resilient and exhibit known generalisation (interpolation) characteristics. Two alternative control architectures are presented and parallels are drawn with the more common fuzzy logic, radial basis functions and Kanerva's sparse distributed memory model.