One of the most demanding skills for a mobile robot is to be intelligent enough to know its own location. The global localization problem consists of obtaining the robot's pose (position and orientation) in a known map if the initial location is unknown. This task is addressed applying evolutionary computation concepts (Differential Evolution). In the current approach, the distances obtained from the laser sensors are combined with the predicted scan (in the known map) from possible locations to implement a cost function that is optimized by an evolutionary filter. The laser beams (sensor information) are modeled using a combination of probability distributions to implement a non-symmetric fitness function. The main contribution of this paper is to apply the probabilistic approach to design three different cost functions based on known divergences (Jensen-Shannon, Itakura-Saito, and density power). The three metrics have been tested in different experiments and the localization module performance is exceptional in regions with occlusions caused by different obstacles. This fact validates that the non-symmetric probabilistic approach is a suitable technique to be applied to multiple metrics. ; This work was supported by the Competitive Improvement of Drilling and Blasting Cycle in Mining and Underground-Works through New Techniques of Engineering, Explosives, Prototypes, and Advanced Tools, which is a Research and Development project undertaken by the following companies: Obras Subterr a neas, MaxamCorp Holding, Putzmeister Iberica, Subterra Ingenieria, Expace On Boards Systems, Dacartec Servicios Informaticos, and Cepasa Ensayos Geotecnicos.


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Using the Jensen-Shannon, density power, and Itakura-Saito divergences to implement an evolutionary-based global localization filter for mobile robots



    Erscheinungsdatum :

    2017-07-07


    Anmerkungen:

    AR/0000021458



    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Klassifikation :

    DDC:    629



    Graph Kernels from the Jensen-Shannon Divergence

    Bai, L. | British Library Online Contents | 2013


    Jensen-Shannon boosting learning for object recognition

    Xiangsheng Huang, / Li, S.Z. / Yangsheng Wang, | IEEE | 2005


    An Analysis of Edge Detection by Using the Jensen-Shannon Divergence

    Gomez-Lopera, J. F. / Martinez-Aroza, J. / Robles-Perez, A. M. et al. | British Library Online Contents | 2000


    Landmark Based Global Self-localization of Mobile Soccer Robots

    Bais, Abdul / Sablatnig, Robert | Springer Verlag | 2006


    Landmark Based Global Self-localization of Mobile Soccer Robots

    Bais, A. / Sablatnig, R. | British Library Conference Proceedings | 2006