How AI-Guided Thermal Drones Rescued Hikers in Australia's Snowy Mountains

Fire and Rescue NSW located two missing hikers in Kosciuszko National Park on 25 June 2026 using an AI-equipped drone fitted with thermal imaging. Members from the Jindabyne Fire Station launched the drone and conducted the search operation across the Snowy Mountains terrain, according to Fire and Rescue NSW.
The Snowy Mountains create a practical search problem that traditional methods struggle with. Kosciuszko National Park covers roughly 6,900 square kilometres of alpine and subalpine terrain—dense forest at lower elevations, exposed and featureless at altitude. Ground search teams move slowly through this landscape, especially in winter, and a lost person hiding in scrub or a hollow becomes nearly invisible to human eyes. Thermal imaging detects body heat against the cold ground, cutting through both darkness and obscuring vegetation.
The AI component adds an operational advantage. A drone operator reading a thermal feed in real time must distinguish human heat signatures from warm rocks (heated by lingering sunlight), animals like wombats, or even embers from a fire. This mental sorting takes experience and sustained focus. AI filtering systems automate this task—they flag candidate heat signatures instantly—which compresses the time between detection and confirmation. In a fast-moving search where a missing person faces deteriorating conditions like hypothermia—a real risk in the Snowy Mountains, especially in colder months—this speed difference can alter outcomes.
ABC News confirmed the Jindabyne crew's involvement. Jindabyne sits at the main entry point to the Kosciuszko high country, making it the natural base for alpine emergencies in the region.
That a fire agency deployed the drone rather than a dedicated wilderness rescue service reflects a shift in how emergency services operate as drone technology has matured. Australian fire agencies have systematically built in-house drone pilot and operator teams over several years, now capable of launching for non-fire incidents. An ISR asset—intelligence, surveillance, and reconnaissance equipment—launched from a local station without waiting for specialist aviation resources shortens the critical early hours of a missing-persons response substantially.
The operation succeeded: two hikers located and recovered. What the public reports do not provide is operational detail—how long the hikers were missing before the drone launched, how long the aerial search took, what ground teams were positioned nearby for extraction. These specifics matter for evaluating how much the technology genuinely contributed compared with conventional search methods, and they shape doctrine for future deployments.
The trajectory moving forward points toward AI-assisted thermal drones becoming a standard first response, not an add-on resource. As capable thermal drones become cheaper and AI classification models improve on equipment carried by the drone itself, the decision to launch one shifts from "do we have spare resources?" to "is this a missing person?" As that calculus spreads across rescue operations, incidents like the Kosciuszko rescue will likely become routine.


