The autonomous navigation of aerial robots in unknown and complex outdoor environments is a challenging problem that typically requires planners to generate collision-free trajectories based on human expert rules for fast navigation. Presently, aerial robots suffer from high latency in acquiring environmental information, which limits the control strategies that the vehicle can implement. In this study, we proposed the SAC_FAE algorithm for high-speed navigation in complex environments using deep reinforcement learning (DRL) policies. Our approach consisted of a soft actor–critic (SAC) algorithm and a focus autoencoder (FAE). Our end-to-end DRL navigation policy enabled a flying robot to efficiently accomplish navigation tasks without prior map information by relying solely on the front-end depth frames and its own pose information. The proposed algorithm outperformed existing trajectory-based optimization approaches at flight speeds exceeding 3 m/s in multiple testing environments, which demonstrates its effectiveness and efficiency.


    Access

    Download


    Export, share and cite



    Title :

    Efficient Focus Autoencoders for Fast Autonomous Flight in Intricate Wild Scenarios


    Contributors:
    Kaiyu Hu (author) / Huanlin Li (author) / Jiafan Zhuang (author) / Zhifeng Hao (author) / Zhun Fan (author)


    Publication date :

    2023




    Type of media :

    Article (Journal)


    Type of material :

    Electronic Resource


    Language :

    Unknown




    Making Intricate, Thin Gaskets

    Geouge, Wayne D. | NTRS | 1988


    Rotary machine makes intricate parts

    Downs,J.J. / Crookston,R. / Cummins | Automotive engineering | 1984


    New techniques produce intricate composites

    Carlisle,B.H. | Automotive engineering | 1982


    Pressed steel solves intricate problems

    Fay, Thomas J. | Engineering Index Backfile | 1910


    The intricate patterns of stress

    Macke, H.J. / Sant, T.D. | Tema Archive | 1982