Localization, i.e., estimating a robot pose relative to a map of an environment, is one of the most relevant problems in mobile robotics. The research community has devoted a big effort to provide solutions for the localization problem. Several methodologies have been proposed, among them the Kalman filter and Monte Carlo Localization filters. In this paper, the Clustered Evolutionary Monte Carlo filter (CE-MCL) is presented. This algorithm, taking advantage of an evolutionary approach along with a clusterization method, is able to overcome classical MCL filter drawbacks. Exhaustive experiments, carried on the robot ATRV-Jr manufactured by iRobot, are shown to prove the effectiveness of the proposed CE-MCL filter.
Gasparri, A., Panzieri, S., Pascucci, F., Ulivi, G. (2006). Monte Carlo Filter in Mobile Robotics Localization: A Clustered Evolutionary Point of View. JOURNAL OF INTELLIGENT & ROBOTIC SYSTEMS, 47, 155-174 [10.1007/s10846-006-9081-1].