Highlights We exploit the characteristics of food delivery routes. We develop an improved inverse reinforcement learning method for route planning. We develop an approach to conduct route recommendation in the absence of road network information.

    Abstract In China, rapid development of online food delivery brings massive orders, which relies heavily on deliverymen riding e-bikes. In practice, actual delivery routes of most orders are not the same as the system recommended routes, and the road network information for some areas is outdated or incomplete. In this research, we develop a deep inverse reinforcement learning (IRL) algorithm to capture deliverymen’s preferences from historical GPS trajectories and recommend their preferred routes. Considering the characteristics of food delivery routes, we employ Dijkstra’s algorithm instead of value iteration, to determine the current policy and compute the gradient of IRL. Moreover, we plan routes at the presence and absence of road network information, providing accurate navigation when road network information is unknown. Numerical experiments on real delivery trajectories provided by Meituan-Dianping Group show that our approach improves F 1 - score distance by 8.0 % and 6.1 % at the presence and absence of road network information, respectively.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Integrating Dijkstra’s algorithm into deep inverse reinforcement learning for food delivery route planning


    Beteiligte:
    Liu, Shan (Autor:in) / Jiang, Hai (Autor:in) / Chen, Shuiping (Autor:in) / Ye, Jing (Autor:in) / He, Renqing (Autor:in) / Sun, Zhizhao (Autor:in)


    Erscheinungsdatum :

    2020-08-23




    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch