Existing multi-agent deep reinforcement learning (MADRL) methods for multi-UAV navigation face challenges in generalization, particularly when applied to unseen complex environments. To address these limitations, we propose a Dual-Transformer Encoder-Based Proximal Policy Optimization (DTPPO) method. DTPPO enhances multi-UAV collaboration through a Spatial Transformer, which models inter-agent dynamics, and a Temporal Transformer, which captures temporal dependencies to improve generalization across diverse environments. This architecture allows UAVs to navigate new, unseen environments without retraining. Extensive simulations demonstrate that DTPPO outperforms current MADRL methods in terms of transferability, obstacle avoidance, and navigation efficiency across environments with varying obstacle densities. The results confirm DTPPO’s effectiveness as a robust solution for multi-UAV navigation in both known and unseen scenarios.


    Access

    Download


    Export, share and cite



    Title :

    DTPPO: Dual-Transformer Encoder-Based Proximal Policy Optimization for Multi-UAV Navigation in Unseen Complex Environments


    Contributors:
    Anning Wei (author) / Jintao Liang (author) / Kaiyuan Lin (author) / Ziyue Li (author) / Rui Zhao (author)


    Publication date :

    2024




    Type of media :

    Article (Journal)


    Type of material :

    Electronic Resource


    Language :

    Unknown