精準且可靠之定位資訊是實現無人機群應用的先決條件。 然而，傳統全球定位系統或基於射頻的定位方法無法良好運作於高度動態且不穩定之移動隨意網路環境中。 在本論文中，我們提出一種新穎的無線定位方法，在具有異常全球定位系統訊號的未知通訊環境中，根據無人機之間的接收訊號強度來準確地定位無人機群。 所提方法在無人機應用情境中，其挑戰性在於同時考量異常定位訊號問題以及要求高精準之定位。 該方法的關鍵概念是透過改進凸鬆弛公式來解決位置匹配問題，並考慮待定位目標是否位於由錨點構成之凸包內或外。 此外，根據估計位置之分布，我們提出利用變分自編碼器來計算異常分數。 不同錨點組合所得之異常分數被進一步描述成分數背包問題，並經過求解以獲得最佳錨點選擇。 我們透過數值模擬與真實數據驗證所提之方法。 結果指出，所提方法相較於現有方法能取得較高的偵測準確度與定位精準度，同時對於接收訊號強度之量測誤差有較好的穩健性。;Accurate and reliable localization is a prerequisite for unmanned aerial vehicle (UAV) swarm applications. However, conventional GPS or RF-based localization systems do not work well in highly dynamic and unstable mobile ad-hoc environments. In this paper, we present a new approach to accurately localize UAVs in unknown communication environments with anomalous GPS reception, based on the received signal strength (RSS) between the UAVs. The proposed approach is non-trivial given the combinational nature of the considered problem and the requirement of high localization accuracy in the UAV application scenario. The key idea of the proposed approach is to solve the position mapping problem by refining the convex relaxation formulation which considers that the target to be localized is inside or outside the convex hull formed by the anchors. Besides, a variational autoencoder is used to calculate the anomaly score based on the estimated position distributions. The optimal anchor node selection is obtained by solving a fractional knapsack problem which takes into account the anomaly score of different node combinations. We evaluate our approach through numerical simulations and field tests with real GPS data collected from a quadrotor UAV. Our results indicate that the proposed approach achieves higher detection and localization accuracy and is more robust to RSS measurement errors compared to the baseline schemes.
