Robot Sonar Mapping by Bayesian Search

Kenneth D. Harris and Michael Recce

This paper describes a new method by which a mobile robot can construct a map of its environment from sonar sensory data. A model of sensor behaviour is used to construct a probability function on the space of all maps, which is then searched for the map of highest probability. Because of the very large dimension of this space, specialised search techniques are required. The algorithm was tested on real sonar data collected in three heterogeneous environments, and the quality of maps produced by the new method were quantitatively compared to those of two previous mapping systems.

This page is copyrighted by AAAI. All rights reserved. Your use of this site constitutes acceptance of all of AAAI's terms and conditions and privacy policy.