Moreno Lorente, Luis EnriqueArmingol Moreno, José MaríaGarrido Bullón, Luis SantiagoEscalera Hueso, Arturo de laSalichs Sánchez-Caballero, Miguel2010-03-022010-03-022004-11Journal of Intelligent and Robotic Systems, 2002, vol. 34, n. 2, p. 135-1540921-0296 (Print)1573-0409 (Online)https://hdl.handle.net/10016/7106A mobile robot requires the perception of its local environment for position estimation. Ultrasonic range data provide a robust description of the local environment for navigation. This article presents an ultrasonic sensor localization system for autonomous mobile robot navigation in an indoor semi-structured environment. The proposed algorithm is based upon an iterative non-linear filter, which utilizes matches between observed geometric beacons and an a-priori map of beacon locations, to correct the position and orientation of the vehicle. A non-linear filter based on a genetic algorithm as an emerging optimization method to search for optimal positions is described. The resulting self-localization module has been integrated successfully in a more complex navigation system. Experiments demonstrate the effectiveness of the proposed method in real world applications.application/pdfeng© Kluwer Academic PublishersMobile robotsLocalizationUltrasonic sensorsGenetic algorithmsresearch articleRobótica e Informática Industrial10.1023/A:1015664517164open access