An Embedded-Agent Architecture for Online Learning & Control in Intelligent Machines

This paper describes the design of a fuzzy controlled autonomous robot, incorporating Genetic Algorithms (GA) based rule learning, for use in an outdoor agricultural vehicle for path and edge following activities which involve spraying insecticide, distributing fertilisers, ploughing, harvesting, etc. The robot has to navigate under different ground and weather conditions offering complex problems of identification, monitoring and control. This paper addresses the development of an online self-learning system based on a modified version of the Fuzzy Classifier system (FCS) which provides rapid convergence suitable for online learning without the need for simulation. The controller was tested on both an in-door and out-door autonomous vehicle operating with different types of sensors (including a novel wand), propulsion and steering. Experiments include operating the vehicle following irregular crop edges (full of gaps) under different weather and ground conditions within a tolerance of 2 inches.