SAREnv: a shared benchmark for wilderness search and rescue

September 2025 · Published in Drones (MDPI)

‹ ›

Benchmarks only work if everyone measures against the same reality. With SAREnv, published open-access in the journal Drones, we give the UAV search-and-rescue community a shared dataset and evaluation framework for informed wilderness SAR planning.

What SAREnv provides

• 60 high-resolution geospatial scenarios with probabilistic lost-person models.
• Four baseline path-planning algorithms and three performance metrics.
• Tools to generate custom synthetic search-and-rescue datasets.

SAREnv gives the community a standardized, reproducible way to compare UAV search strategies and accelerate innovation in autonomous systems for real-world search and rescue. The project is open source and lives under the NAMUR GitHub organization, growing out of the WildDrone/HERD collaboration with the University of Bristol.

It's already being put to work: University of Bristol undergraduates extended and deployed SAREnv scenarios for their third-year projects, presented at the EuroDroS conference at SDU.