The simultaneous localization and mapping (SLAM) problem is concerned with using sensor data to build an environmental map, while also localizing an autonomous agent within this map. Two approaches are currently prevalent (Bayesian filtering and graph-based optimization), however these both involve approximations and have the potential to be improved. In this paper, we propose novel high-performance SLAM algorithms derived from variational Bayes inference. By using mean-field type approximations, the resulting computational complexity is linear. We also add an empirical Bayes assumption to improve the flexibility of the inference. Experiments are conducted on both synthetic data and real RGB-D images. The proposed approach achieves 42% average error reduction in all scenarios on synthetic data, and 26% average error reduction on real images (with respect to two other baseline algorithms).


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Linear-complexity stochastic variational Bayes inference for SLAM


    Contributors:
    Jiang, Xiaoyue (author) / Hoy, Michael (author) / Yu, Hang (author) / Dauwels, Justin (author)


    Publication date :

    2017-10-01


    Size :

    575838 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English




    Normalized Gaussian Network Based on Variational Bayes Inference and Hierarchical Model Selection

    Yoshimoto, J. / Ishii, S. / Sato, M.-a. | British Library Online Contents | 2003


    Variational-Bayes Optical Flow

    Chantas, G. | British Library Online Contents | 2014


    Trajectory Prediction Algorithm Based on Variational Bayes

    Ma, Xiaolong / Liu, Gang / He, Bing et al. | IEEE | 2018


    The Bayes Linear Altimeter Retracker

    Challenor, P. / Andrianakis, Y. / European Space Agency | British Library Conference Proceedings | 2010