FRNSW drone AI finds two lost hikers in under five hours

AI system

System: Fire and Rescue NSW remotely piloted aircraft system with thermal imaging and AI person-detection software (software vendor not named in the sources)
Model: Not assessed
Release: Not assessed
Provider: Not assessed
Role: Not assessed
Configuration: Not assessed
Inputs and outputs: Not assessed
Autonomy: Not assessed
Workflow: Thermal-capable drone with onboard AI person detection launched at night from the search command post. Subjects within drone range whose detection can be confirmed by thermal camera.
Human oversight: Not assessed
Relation to AI: The AI flagged the hikers in the drone feed, and the thermal camera confirmed the find. The inspector overseeing the search credits it with cutting the search short. The hikers also signaled with a phone light, and the software vendor is not named. FRNSW's own media release was not available and is not cited. No cited source dates it.
AI contribution: The AI flagged the hikers in the drone feed, and the thermal camera confirmed the find. The inspector overseeing the search credits it with cutting the search short. The hikers also signaled with a phone light, and the software vendor is not named. FRNSW's own media release was not available and is not cited. No cited source dates it.

Studies: Not assessed
Study design: Not assessed
Measurement: Not assessed
Setting and sample: Not assessed
Measures: located less than five hours after the report
Comparison: Assumed alternative: a conventional search without the AI drone
Results: Assumed comparison. Reference: several days (the inspector's estimate of the search time avoided). Result: less than five hours after they were reported missing.
Additional value from AI: Not assessed
Limitations: Not assessed
Denominators: Not assessed
Materials for replication: Not assessed

Participants: Operator: Fire and Rescue NSW.
Jurisdictions: Benefit: Dead Horse Gap track, Kosciuszko National Park, New South Wales, Australia (about 35 km south-west of Jindabyne). Operator: Australia.
Ownership and control: Not assessed
Dependencies: Not assessed
Cross-border connections: Not assessed
Geopolitical implications: Not assessed

Conditions for replication: Weather permits flight. Detections are verified by the pilot before ground teams are directed.
Replication attempts: Not assessed
Later findings: No development dated after the 23 June 2026 rescue was found in the cited sources.
Availability: Not assessed
Institutional decision: Not assessed
Grounds: Not assessed
Action and result: Not assessed
Success criterion: Not assessed

Assessed benefits: People. Organizations.
Depth: People: 3. Organizations: 2.
Reasons: People: Two young men on a winter night in alpine bushland were found with mild exposure within five hours. The inspector overseeing the search says it could otherwise have become a long-term incident. Organizations: FRNSW, police and SES avoided an overnight multi-agency search and the risk to rescuers that Inspector Eberle described.
Observed or intended: Not assessed
Rubric: Not assessed
Assessor and date: Not assessed
Alternative assessments: Not assessed
Fill: Independently reported

Kind: Not assessed
Related entries: Not assessed
Field: Search and rescue. Fire and rescue services.
Purpose: Built to detect people, vehicles and vessels in drone imagery for search and rescue; this benefit is that purpose.
Dates: Date basis unassessed: 2026 (precision unassessed). Updated: 21 October 2026.
Stage: Not assessed
Version: SHA-256: 8c39dd93c592…

News report Independent author

McGuirk-Scolaro, M. (2026). Hikers lost in Kosciuszko National Park rescued by drones powered by AI. ABC News (Australia).
News report Independent author

Sams, C. (2026). How AI saved two hikers lost in the unforgiving alpine wilderness. About Regional.
News report Independent author

Matler, A. (2026). AI-assisted drone helps rescue lost Kosciuszko hikers in NSW first. iTWire.