Self Localization ofan AutonomousRobot: Using an EKF tomerge OdometryandVision basedLandmarks
Armando Jorge Sousa, Paulo JoseCosta, António Paulo Moreira, Adriano Carvalho · 2005
Localization isessential to modernautonomous robots inorderto enable effective completion of complex tasks over possibly large distances inlow structured environments. Inthis paper, a Extended KalmanFilter isusedin order toimplement self-localizatio n. Thisisdoneby merging odometry andlocalization information, when available. Theusedlandmarks are colored poles that can berecognized whiletherobot moves around performing normal tasks. This paper models measurements with verydifferent characteristics indistance andangle tomarkers and showsresults oftheself-localizatio n method. Results ofsimulations andreal robot tests areshown.