Experiments in feedback linearized iterative learning‐based path following for center‐articulated industrial vehicles

Abstract

This paper describes the design, industrial application, and field testing of a technique for autonomous wheeled‐vehicle path following that uses iterative learning control (ILC) in a feedback linearized space. One advantage of this approach is that ILC is used without having to employ approximate linearization at every time step. The main contribution of this paper is the unique field experiments that used two large industrial‐scale center‐articulated underground mining vehicles. The described field work not only tested the underlying technique on commercial vehicles, but also presents a method for parallel speed learning, wherein the speed is adjusted over subsequent learning trials to improve cycle productivity. Finally, presented are field results for an approach to prelearning through simulation before deployment in the field to reduce the initial path‐following errors.