固定翼UAVによる海上環境での探索戦略と船舶検出
A Search Strategy and Vessel Detection in Maritime Environment Using Fixed-Wing UAVs
GNSSが使えない未知の海上環境で固定翼UAVが効率的に船舶を探索・検出するため、確率マップに基づく情報活用型と事前経路に沿う非情報型の探索手法、およびシミュレータの合成データで学習した船舶検出手法を提案し、比較実験で有効性を示した。
著者: Marijana Peti, Ana Milas, Natko Kraševac, Marko Križmančić, Ivan Lončar, Nikola Mišković, Stjepan Bogdan
分類: cs.RO
原文アブストラクト
In this paper, we address the problem of autonomous search and vessel detection in an unknown GNSS-denied maritime environment with fixed-wing UAVs. The main challenge in such environments with limited localization, communication range, and the total number of UAVs and sensors is to implement an appropriate search strategy so that a target vessel can be detected as soon as possible. Thus we present informed and non-informed methods used to search the environment. The informed method relies on an obtained probabilistic map, while the non-informed method navigates the UAVs along predefined paths computed with respect to the environment. The vessel detection method is trained on synthetic data collected in the simulator with data annotation tools. Comparative experiments in simulation have shown that our combination of sensors, search methods and a vessel detection algorithm leads to a successful search for the target vessel in such challenging environments.
