Detection strategy for kidnapped robot problem in Monte Carlo localization based on similarity measure of environment

This paper investigates new alternative approaches to detect the kidnapped robot problem event in Monte Carlo Localization. The underlying idea is based on the local similarity measures of the environment seen by the robot at two consecutive time instances. Six different similarity measures are investigated and tested against particles weight-based detectors to see how good each detector’s ability to distinguish normal condition from kidnapping event. These simulations show that similarity based-detectors promises better general accuracy across all kidnapping points compared to particles weight-based detectors and the accuracy is not affected by the result of re-localization