Trabajo presentado al ICRA 2005 celebrado en Barcelona del 18 al 22 de abril. ; In this article we propose an algorithm to reduce the affects caused by linearization in the typical EKF approach to SLAM. The technique consists in computing the vehicle prior using an Unscented Transformation. The UT allows a better nonlinear mean and variance estimation than the EKF. There is no need however in using the UT for the entire vehicle map state, given the linearity in the map part of the model. By applying the UT only to the vehicle states we get more accurate covariance estimates. The a posteriori estimation is made using a fully observable EKF step, thus preserving the same computational complexity as the EKF with sequential innovation. Experiments over a standard SLAM data set show the behavior of the algorithm. ; This work was supported by projects: 'Active vision systems based in automatic learning for industrial applications' (), 'Integration of robust perception, learning, and navigation systems in mobile robotics' (J-0929). This work is supported by the Spanish Council of Science and Technology under projects DPI 2001-2223, and DPI 2004-5414. ; Peer Reviewed


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Unscented transformation of vehicle states in SLAM


    Beteiligte:

    Erscheinungsdatum :

    2005-01-01



    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch


    Klassifikation :

    DDC:    629



    Unscented SLAM with conditional iterations

    Zhu, Jihua / Zheng, Nanning / Yuan, Zejian et al. | IEEE | 2009


    Unscented SLAM with Conditional Iterations

    Zhu, J. / Zheng, N. / Yuan, Z. et al. | British Library Conference Proceedings | 2009


    Recursive vehicle mass identification based on Unscented Transformation

    Ameyoe, Ablamvi / Atheupe, Gael / Mouton, Xavier | IEEE | 2024


    Vehicle-trailer lateral velocity estimation using constrained unscented transformation

    Habibnejad Korayem, Amin / Khajepour, Amir / Fidan, Baris | Taylor & Francis Verlag | 2022