AI system
- System
-
Orca AI navigation platform (digital watchkeeper modules and software)
- Model
-
Not assessed
- Release
-
Exact release not established.
- Application developer
-
Orca AI
- Role
-
The platform detected navigational hazards for the ship’s crew to assess.
- Configuration
-
The vessel used Orca AI’s SeaPod system.
- Inputs and outputs
-
Not assessed
- Autonomy
-
Not assessed
- Workflow
-
Fleet-wide installation of a sensor-and-software watchkeeping platform. Twelve months of anonymized operational data per vessel. An insurer willing to analyze member-fleet data.
- Human oversight
-
Not assessed
- Relation to AI
-
The platform's detections feed bridge decisions. The reported reduction compares the same vessels early and late in their first year. Crew familiarization, seasonality and route changes are not separated from the system's effect.
- AI contribution
-
The platform's detections feed bridge decisions. The reported reduction compares the same vessels early and late in their first year. Crew familiarization, seasonality and route changes are not separated from the system's effect.
Benefits
- Outcome identifiers
-
Not assessed
- Benefit
-
high-severity close encounters fell from 2.7 to 1.3 per vessel-month
- Category
-
Increased Product Safety
- Status
-
Not assessed
- Beneficiary groups
-
Organizations. Society. People.
- 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
-
high-severity close encounters fell from 2.7 to 1.3 per vessel-month
- Comparison
-
the same vessels' first three months after installation (early post-implementation phase), no control fleet
- Results
-
Reference: 2.7 per vessel per month in the early post-implementation phase. Result: 1.3 by months 10–12 - a 52% reduction.
- 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: Orca AI. Operator: Operators of 139 container vessels insured with NorthStandard.
- Jurisdictions
-
Developer:
United Kingdom. - Ownership and control
-
Not assessed
- Dependencies
-
Not assessed
- Cross-border connections
-
Not assessed
- Geopolitical implications
-
Not assessed
Follow-up
- Conditions for replication
-
Crews keep using the system after the adaptation phase. The close-encounter definition stays constant across the comparison. Routes and traffic density are comparable between periods.
- Replication attempts
-
1 follow-up entries. Outcome unresolved: 1.
- Later findings
-
No development after the report of 15 April 2026 is established. The vendor's October 2025 post predates it.
- Availability
-
Not assessed
- Institutional decision
-
Not assessed
- Grounds
-
Not assessed
- Action and result
-
Not assessed
- Success criterion
-
Not assessed
Evidence
- Source numbers
-
AIBD-0251-source-0001–0006
- 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
-
Organizations. Society. People.
- Depth
-
Not assessed
- Reasons
-
Organizations: Aggregate change in a proxy metric; no collision, claim or cost outcome is documented. Society: No outcome beyond the proxy metric is documented. People: No individual outcome is documented.
- 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
-
Not assessed
- Field
-
Maritime safety. Commercial shipping / navigational decision support.
- Purpose
-
Orca AI's platform is built to give bridge teams AI-assisted situational awareness and earlier detection of risky targets.
- Dates
-
Date basis unassessed: 2026 (precision unassessed). Updated: 21 October 2026.
- Stage
-
Not assessed
- Version
-
SHA-256: 3e2ae9be3931…
References
- Other identifiers
-
Not assessed
- Category mappings
-
Not assessed
- Brief
-
Not assessed
- Revisions
-
7 revisions. Latest: 21 October 2026.
Sources
-
Report Developer
Orca AI and NorthStandard (Mar 2026). Orca AI and NorthStandard Safety Report: Orca AI's impact on navigational safety.
-
News report Independent author
Wingrove M (16 Apr 2026). NorthStandard study demonstrates benefits of AI navigation support. Riviera Maritime Media.
NorthStandard P&I club undertook a 12-month study with Orca AI, using its AI navigation services for a cohort of 139 container vessels.
-
News report Independent author
MarineLink / Maritime Activity Reports (15 Apr 2026). Study From Orca AI, NorthStandard Highlights Role of AI on Navigational Safety.
The study examined more than 10.8 million nautical miles of voyages, comparing the initial system adaptation period (first three months after installation) with the stabilized usage phase (months 10–12).
-
Press release Developer
Hellenic Shipping News (16 Apr 2026). Joint Orca AI-NorthStandard study highlights strong impact of AI on navigational safety (source credited as Orca AI).
What we’re seeing through our work with Orca AI, and now reinforced by this study, is that improved situational awareness and earlier risk detection can materially reduce close-quarters situations.
-
Press release Developer
Orca AI (2026). Orca AI and NorthStandard Safety Report (report landing page).
High-severity close encounters declined from 2.7 per vessel per month in the early post-implementation phase to 1.3 by months 10–12 - a 52% reduction.
-
Registry label Independent author
OECD AI Incidents and Hazards Monitor, incident 2026-04-15-b7a4: AI Navigation System Reduces Maritime Near Misses by 52%.
deploying Orca AI's navigation platform on 139 container vessels led to a 52% reduction in high-severity close encounters over 12 months