Mobile Robot Navigation based on localisation using Hidden Markov Models.

摘要

In this paper, we implement a method of mobile robot naviga~ion using Hidden Markov Models (HMMs). It is a place-based navigation, in which the robot localises itself in previously learnt environment. We use the laser range data from the robot to scan the environment and to distinguish between different places. First the robot learns after several trials about the places, it then recognises the places again by finding a match between the learnt HMM network and the current environment. The system can generate HMM network representing a sequence ofplaces that are associated with a mission. The system is usedfor a tour guide robot. 1