AI system
- System
-
Large Animal Activated Roadside Monitoring and Alert System (LAARMA)
- Model
-
Not assessed
- Release
-
Not assessed
- Application developer
-
University of Sydney Australian Centre for Robotics and QUT CARRS-Q
- Role
-
Not assessed
- Configuration
-
Not assessed
- Inputs and outputs
-
Not assessed
- Autonomy
-
Not assessed
- Workflow
-
A known animal crossing hotspot with high strike rates. Self-training detection pipeline that improved over the trial. Variable message signs drivers can see in time to slow.
- Human oversight
-
Not assessed
- Relation to AI
-
Machine-learning detection of cassowaries activated the warning signs. TMR attributes the speed reduction and the 31 percent fall in fatal crashes to the system. But the figures are trial aggregates without a peer-reviewed analysis. The 31 percent figure is reported only by the ABC citing TMR. The consortium's project page reports detection and speed results without a collision figure.
- AI contribution
-
Machine-learning detection of cassowaries activated the warning signs. TMR attributes the speed reduction and the 31 percent fall in fatal crashes to the system. But the figures are trial aggregates without a peer-reviewed analysis. The 31 percent figure is reported only by the ABC citing TMR. The consortium's project page reports detection and speed results without a collision figure.
Benefits
- Outcome identifiers
-
Not assessed
- Benefit
-
fatal crashes fell 31 percent during the trial
- Category
-
Increased Product Safety
- Status
-
Not assessed
- Beneficiary groups
-
People. Organizations. Society.
- Beneficiaries
-
Not assessed
- Reach
-
Not assessed
- Distribution and access
-
Not assessed
- Duration
-
Not assessed
- Expected?
-
Yes
- Costs and harms
-
Not assessed
Measurement
- Studies
-
Not assessed
- Study design
-
Not assessed
- Measurement
-
Not assessed
- Setting and sample
-
Not assessed
- Measures
-
fatal crashes fell 31 percent during the trial
- Comparison
-
fatal cassowary vehicle strikes at the Kuranda crossing before the three-month AI trial, per the department (a speed-limit cut from 80 to 60 km/h for cyclone repair works coincided)
- Results
-
Reference: not stated. Result: 31 per cent decrease in fatal crashes.
- Additional value from AI
-
Not assessed
- Limitations
-
Not assessed
- Denominators
-
Not assessed
- Materials for replication
-
Not assessed
Money
- Kind of value
-
Not assessed
- Amount
-
Not assessed
- Currency and prices
-
Not assessed
- Period and unit
-
Not assessed
- Realization
-
Not assessed
- Recipients and payers
-
Not assessed
- Gross or net
-
Not assessed
- Included costs
-
Not assessed
- Comparison
-
Not assessed
- Method
-
Not assessed
- Return and payback
-
Not assessed
People and places
- Participants
-
Developer: University of Sydney Australian Centre for Robotics and QUT CARRS-Q. Operator: Queensland Department of Transport and Main Roads.
- Jurisdictions
-
Benefit: Kuranda,
Australia. Developer: Australia. Operator: Australia. - Ownership and control
-
Not assessed
- Dependencies
-
Not assessed
- Cross-border connections
-
Not assessed
- Geopolitical implications
-
Not assessed
Follow-up
- Conditions for replication
-
Detection accuracy on the target species. Driver compliance with flashing warnings. Permanent funding, which TMR said it was still pursuing.
- Replication attempts
-
1 follow-up entries. Outcome unresolved: 1.
- Later findings
-
The ABC reported that the equipment would be removed from the site after the trial while funding for a rollout was discussed with research partners; no later deployment was found.
- Availability
-
Not assessed
- Institutional decision
-
Not assessed
- Grounds
-
Not assessed
- Action and result
-
Not assessed
- Success criterion
-
Not assessed
Evidence
- Source numbers
-
AIBD-0104-source-0001–0003
- Citations
-
Numbered references below.
- Language
-
Not assessed
- Source relationships
-
Independent, Developer
- Original evidence
-
Not assessed
- Access and versions
-
Not assessed
- Supported findings
-
Not assessed
- Evidence links
-
Not assessed
- Evidence strength
-
Not assessed
- Missing evidence
-
Not assessed
Grades
- Assessed benefits
-
People. Organizations. Society.
- Depth
-
Not assessed
- Reasons
-
People: Trial-level aggregate (speed reduction, 31 percent fewer fatal crashes) with no discrete attributable event. Organizations: Aggregate program result reported by the operating agency. Society: Aggregate result over a three-month trial. Baseline and statistical detail not published.
- Observed or intended
-
Not assessed
- Rubric
-
Not assessed
- Assessor and date
-
Not assessed
- Alternative assessments
-
Not assessed
- Fill
-
Independently reported
Entry details
- Kind
-
Not assessed
- Related entries
-
Autonomous vehicle's perception system did not detect or slow for a nesting duck and killed it; LAARMA exists to detect cassowaries at roadsides and slow drivers.
- Field
-
Conservation and biodiversity. Wildlife-vehicle collision prevention.
- Purpose
-
Detect large animals near the road in real time and warn drivers via variable message signs to reduce animal-vehicle collisions.
- Dates
-
Date basis unassessed: 2025 (precision unassessed). Updated: 21 October 2026.
- Stage
-
Not assessed
- Version
-
SHA-256: 09beff2764d4…
References
- Other identifiers
-
AI Incident Database: 1678.
- Category mappings
-
Not assessed
- Brief
-
Not assessed
- Revisions
-
7 revisions. Latest: 21 October 2026.
Sources
-
News report Independent author
ABC News (2025). Artificial intelligence used to reduce cassowary road deaths in Queensland.
The technology was 97 per cent accurate in identifying the bird, which led to a 31 per cent decrease in fatal crashes, the department said.
-
News report Independent author
Tech Xplore (2025). Researchers develop world's first AI roadside technology to prevent animal–vehicle collisions.
the system was correctly detecting animals 78.5% of the time within 100 meters
-
Press release Developer
iMOVE Australia CRC (n.d.). Large Australian animals and cars: Safety for all. Project page with final reports.
Partners with iMOVE on this research were the Department of Transport and Main Roads (Queensland), the University of Sydney's Australian Centre for Robotics, and the Queensland University of Technology's CARRS-Q.