Skip to Main Content
This paper addresses the problem of global localization for mobile robots in changeable environments, i.e. to estimate self-position using a map that is partially or completely different from the environment. It is difficult to detect changes when both of the self-position and the map have large uncertainties. To solve the problem, in this paper, we extend Monte Carlo localization (MCL) and sensor resetting localization (SRL), so as to generate a number of hypotheses about the change as well as the self-position. As a result of tests in a number of environments as well as changes, we found the proposed method is effective even when "rate of changes (ROC)" is high in the environment.
Pattern Recognition, 2004. ICPR 2004. Proceedings of the 17th International Conference on (Volume:4 )
Date of Conference: 23-26 Aug. 2004