Landmark-based autonomous navigation in sewerage pipes

摘要

We describe a method for an autonomous mobile robot to navigate through a system of sewerage pipes. Landmarks signalling positions in the pipe system have to be detected and classified, where classification is allowed do be unreliable. Self localization is interpreted as a partially observable Markov decision problem and solved accordingly. The method is implemented and used on a prototype robot platform operating in a dry sewage pipe test network.