Brasil
Indoor localization has been considered to be the most fundamental problem when it comes toproviding a robot with autonomous capabilities. Although many algorithms and sensors have been proposed,none have proven to work perfectly under all situations. Also, in order to improve the localization quality,some approaches use expensive devices either mounted on the robots or attached to the environment that don'tnaturally belong to human environments. This paper presents a novel approach that combines the bene ts oftwo localization techniques, WiFi and Kinect, into a single algorithm using low-cost sensors. It uses separateParticle Filters (PFs). The WiFi PF gives the global location of the robot using signals of Access Point devicesfrom di erent parts of the environment while it bounds particles of the Kinect PF, which determines the robot'spose locally. Our algorithm also tackles the Initialization/Kidnapped Robot Problem by detecting divergence onWiFi signals, which starts a localization recovering process. Furthermore, new methods for WiFi mapping andlocalization are introduced.
© 2001-2024 Fundación Dialnet · Todos los derechos reservados