Localization algorithm of mobile robot based on single vision and laser radar

Robot self-localization is one of the key problems to improve robot autonomous ability. In order to increase the localization precision of mobile robot, a self-localization algorithm based on odometry, single vision and laser radar is proposed. First, odometry estimated robotpsilas pose at every sampling time. At the same time, the angles between any two of the landmarks were measured by means of the camera. Laser radar obtained the information that indicating distance and angle of landmarks. Then, the data provided by odometry, single vision and laser radar were fused together by means of an extended Kalman filter (EKF) technique. Finally, the position of robot was reset by matched environment feature, and the position estimation of robot was given accurately. Experiment result proves that such an algorithm achieves good localization effect under multi-corner and long-distance conditions, and improves the localization precision efficiently.