UAV-Supported Maritime Search System: Experience from Valun Bay Field Trials

TL;DR

This paper describes a comprehensive UAV-based maritime search system tested in Valun Bay, integrating flow modeling, probabilistic search control, and deep learning detection to improve autonomous search and rescue operations under complex conditions.

Contribution

It introduces a novel integrated system combining flow modeling, probabilistic control, and machine vision for autonomous maritime search, validated through real-world field trials.

Findings

Reliable detection of floating targets achieved

System performs well under environmental uncertainties

Field trials demonstrate practical effectiveness

Abstract

This paper presents the integration of flow field reconstruction, dynamic probabilistic modeling, search control, and machine vision detection in a system for autonomous maritime search operations. Field experiments conducted in Valun Bay (Cres Island, Croatia) involved real-time drifter data acquisition, surrogate flow model fitting based on computational fluid dynamics and numerical optimization, advanced multi-UAV search control and vision sensing, as well as deep learning-based object detection. The results demonstrate that a tightly coupled approach enables reliable detection of floating targets under realistic uncertainties and complex environmental conditions, providing concrete insights for future autonomous maritime search and rescue applications.