Dynamic UAV-based search operations using probabilistic diffusion modeling of Man Overboard incident victims

2026-08-03

AI Summary

This study addresses the low success rate of maritime search-and-rescue operations, particularly under delayed response scenarios. To tackle this challenge, the authors propose an Improved Probability-Informed Search (IPIS) method that uniquely integrates probabilistic diffusion modeling with dynamic unmanned aerial vehicle (UAV) path planning. The approach combines an extended Kalman filter with a Leeway drift model to predict the target’s time-evolving location and introduces five distinct search strategies—including Zigzag, Boustrophedon, Spiral, and two novel probability-guided patterns—to handle environmental uncertainties. Experimental results demonstrate that, even under stringent conditions where UAV deployment is delayed by 20 minutes and single-pass detection probability is only 30%, IPIS achieves an average search success rate exceeding 80%, substantially outperforming existing methods.

Abstract

More than 70% of the people that fell overboard cruise ships in the period 2010-2019 lost their lives. This paper presents a strategy for reliably predicting the area a person may be in after a man overboard incident, and describes in detail the search methods to find them utilizing UAV technology. The search area prediction method employs an Extended Kalman Filter that capitalizes on the information from the Leeway model to track the missing person in the sea by taking into account the uncertainty of the movement of the person and the weather conditions in the area. Then, a UAV uses this information to search for the person. Five different methods for searching in this dynamic area are presented and evaluated - the Zigzag, the Boustrophedon, the Spiral, the Probability Informed Search and the Improved Probability Informed Search (IPIS) methods. The IPIS method provides success rate of over 80% on average for finding a person, even if the UAV initiates the search mission 20 minutes after the man overboard incident and even assuming a detection method with a success rate of 30%. All code for the simulation environment and the evaluation of the methods is available on our GitHub page at https://github.com/diangeli/pdms-man-overboard.

Problem

• Man Overboard
• UAV search
• search area prediction
• probabilistic diffusion modeling
• maritime rescue

Innovation

• probabilistic diffusion modeling
• Extended Kalman Filter
• UAV-based search
• Leeway model
• Improved Probability Informed Search