Line-Crawling Robot Navigation: A Rough Neurocomputing Approach

Abstract

This chapter considers a rough neurocomputing approach to the design of the classify layer of a Brooks architecture for a robot control system. This paradigm for neu­rocomputing that has its roots in rough set theory, works well in cases where there is uncer­tainty about the values of measurements used to make decisions. In the case of the line-crawling robot (LCR) described in this chapter, rough neurocomputing works very well in classifying noisy signals from sensors. The LCR is a robot designed to crawl along high-voltage transmission lines where noisy sensor signals are common because of the electro­magnetic field surrounding conductors. In rough neurocomputing, training a network of neurons is defined by algorithms for adjusting parameters in the approximation space of each neuron. Learning in a rough neural network is defined relative to local parameter ad­justments. Input to a sensor signal classifier is in the form of clusters extracted from con­vex hulls that “enclose” similar sensor signal values. This chapter gives a fairly complete description of a LCR that has been developed over the past three years as part of a Mani­toba Hydro research project. This robot is useful in solving maintenance problems in power systems. A description of the locomotion features of a line-crawling robot and the basic architecture of a rough neurocomputing system for robot navigation are given. A brief description of the fundamental features of rough set theory used in the design of a rough neural network is included in this chapter. A sample sensor signal classification ex­periment using a recent implementation of rough neural networks is also given.