Small unmanned aircraft can help firefighters combat wildfires by providing real-time surveillance of fire evolution. However, guiding the aircraft autonomously given only wildfire images is challenging. We propose two approaches to state estimation from wildfire images obtained from noisy on-board cameras. The first approach uses a simple Kalman filter to reduce noise and update a belief map in observed areas. The second approach uses a particle filter to predict wildfire growth and uses observations to estimate uncertainties relating to wildfire expansion. The belief maps are used to train a deep reinforcement learning controller, which learns a policy to navigate the aircraft to survey the wildfire while avoiding flight directly over the fire. Simulation results show that the proposed controllers precisely guide the aircraft and accurately estimate wildfire growth. A study of observation noise demonstrates the robustness of the particle filter approach.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Image-based Guidance of Autonomous Aircraft for Wildfire Surveillance and Prediction


    Beteiligte:


    Erscheinungsdatum :

    11.10.2020


    Format / Umfang :

    897976 byte





    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Image-based Guidance of Autonomous Aircraft for Wildfire Surveillance and Prediction

    Julian, Kyle D. / Kochenderfer, Mykel J. | ArXiv | 2018

    Freier Zugriff

    Distributed Wildfire Surveillance with Autonomous Aircraft using Deep Reinforcement Learning

    Julian, Kyle D. / Kochenderfer, Mykel J. | ArXiv | 2018

    Freier Zugriff


    Guidance of Unmanned Aerial Gliders for Wildfire Surveillance

    El Tin, Fares / Sharf, Inna / Nahon, Meyer | AIAA | 2020


    GUIDANCE OF UNMANNED AERIAL GLIDERS FOR WILDFIRE SURVEILLANCE

    Tin, Fares El / Sharf, Inna / Nahon, Meyer | TIBKAT | 2020