This article provides an introduction to Simultaneous Localization And Mapping (SLAM), with the focus on probabilistic SLAM utilizing a feature-based description of the environment. A probabilistic formulation of the SLAM problem is introduced, and a solution based on the Extended Kalman Filter (EKF-SLAM) is shown. Important issues of convergence, consistency, observability, data association and scaling in EKF-SLAM are discussed from both theoretical and practical points of view. Major extensions to the basic EKF-SLAM method and some recent advances in SLAM are also presented.
2
Dostęp do pełnego tekstu na zewnętrznej witrynie WWW
Visual simultaneous localisation and map-building systems which take advantage of some landmarks other than point-wise environment features are not frequently reported. In the following paper the method of using the operational map of robot surrounding, which is complemented with visible structured passive landmarks, is described. These landmarks are used to improve self-localisation accuracy of the robot camera and to reduce the size of the Kalman-filter state-vector with respect to the vector size involving point-wise environment features only. Structured landmarks reduce the drift of the camera pose estimate and improve the reliability of the map which is built on-line. Results of simulation experiments are described, proving advantages of such an approach.
JavaScript jest wyłączony w Twojej przeglądarce internetowej. Włącz go, a następnie odśwież stronę, aby móc w pełni z niej korzystać.