Hidden Markov Models and Vector Quantization for Mobile Robot Localization

J. Savage, E. Marquez, F. Lepe-Casillas (Mexico), and M.A. Morales A. (USA)

Keywords

Localization of mobile robots, Hidden Markov Models, Viterbi Algorithm.

Abstract

This paper describes a localization system for a mo bile robot equipped with sonars. The function of this lo calization system is the estimation of the region where the robot is located. Due to errors in the movement of the robot and errors in the sensors that detect them, after sev eral movements, the real position of the robot needs to be estimated. In this paper it is shown that an estimation of the region where the robot is located can be found using only quantized sonar readings combined with Hidden Markov Models and the Viterbi algorithm.

Important Links:



Go Back