Kashino, Zendai (University of Toronto), Nejat, Goldie (University of Toronto), Benhabib, Beno (University of Toronto)

Multi-UAV Based Autonomous Wilderness Search and Rescue Using Target Iso-Probability Curves

Scheduled for presentation during the Regular Session "UAS Applications III" (ThA2), Thursday, June 13, 2019, 10:20−10:40, Heritage C

2020 International Conference on Unmanned Aircraft Systems (ICUAS), June 11-14, 2019, Athens, Greece

This information is tentative and subject to change. Compiled on April 23, 2024

Abstract

The application of unmanned aerial vehicles (UAVs) to searches of lost persons in the wilderness can significantly contribute to the success of the missions. Maximizing the effectiveness of an autonomous multi-UAV search team, however, requires optimal task allocation between the team members, as well as the planning of the individual flight trajectories. This paper addresses this constrained resource-allocation optimization problem via the use of iso-probability curves that represent probabilistic target-location information in a search region growing with time. The optimization metric used is the allocation of the search effort proportional to the target location likelihood. The proposed method also avoids redundancy in coverage while planning the UAV trajectories.

Numerous simulated search experiments, two of which are detail herein, were carried out to demonstrate our method’s effectiveness in wilderness search and rescue (WiSAR) planning using a multi-UAV team. Extensive comparative studies were also conducted to validate the tangible superiority of our proposed method when compared to existing WiSAR techniques in the literature.