AI system
- System
-
Camera-based computer-vision riding-surface detection with in-app notifications, audible beeps and speed reduction on Spin shared e-scooters (maker not named in the paper)
- Model
-
Not assessed
- Release
-
Not assessed
- Application developer
-
Not named in the paper
- Role
-
Not assessed
- Configuration
-
Not assessed
- Inputs and outputs
-
Not assessed
- Autonomy
-
Not assessed
- Workflow
-
Camera-based surface classification that does not depend on GPS. Randomized disabling of feedback on half the equipped fleet with riders unaware of assignment. A dense urban grid with sidewalks, streets and bike lanes where sidewalk riding is unlawful.
- Human oversight
-
Not assessed
- Relation to AI
-
The computer-vision classifier produced the surface detections that triggered feedback. The randomized disabling of feedback isolates the feedback effect but not detection accuracy, which the paper does not report. Independent university authors with operator cooperation. The vendor is unnamed.
- AI contribution
-
The computer-vision classifier produced the surface detections that triggered feedback. The randomized disabling of feedback isolates the feedback effect but not detection accuracy, which the paper does not report. Independent university authors with operator cooperation. The vendor is unnamed.
Benefits
- Outcome identifiers
-
Not assessed
- Benefit
-
The feedback group spent 22% less time and 20% less distance on sidewalks
- Category
-
Increased Product Safety
- Status
-
Not assessed
- Beneficiary groups
-
Society. Organizations. 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
-
The feedback group spent 22% less time and 20% less distance on sidewalks
- Comparison
-
the no-feedback group (50 scooters with feedback mechanisms disabled at random)
- Results
-
Reference: 0.22 (mean fraction of trip time on sidewalks, no-feedback group, Table 1). Result: 0.17 (mean fraction of trip time on sidewalks, feedback group, Table 1).
- 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: Not named in the paper. Operator: Spin (shared e-scooter operator), with University of Washington researchers.
- Jurisdictions
-
Benefit: Santa Monica,
United States. Operator: United States. - Ownership and control
-
Not assessed
- Dependencies
-
Not assessed
- Cross-border connections
-
Not assessed
- Geopolitical implications
-
Not assessed
Follow-up
- Conditions for replication
-
Equipped scooters remain in service (theft removed them here). Riders cannot tell which scooters give feedback. Enough trips per arm for distributional tests.
- Replication attempts
-
1 follow-up entries. Outcome unresolved: 1.
- Later findings
-
The paper reports that targeted theft of camera-equipped scooters led Spin to withdraw all of them from operation, but it does not date the withdrawal, so it cannot be placed after the end of data collection.
- Availability
-
Not assessed
- Institutional decision
-
Not assessed
- Grounds
-
Not assessed
- Action and result
-
Not assessed
- Success criterion
-
Not assessed
Evidence
- Source numbers
-
AIBD-0243-source-0001
- Citations
-
Numbered references below.
- Language
-
Not assessed
- Source relationships
-
Operator
- 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
-
Society. Organizations. People.
- Depth
-
Not assessed
- Reasons
-
Society: Behavioral proxy (sidewalk time) measured across a cohort. No crash or injury outcome. Organizations: No outcome for Spin or the city is documented beyond compliance behavior. People: No identifiable individual outcome.
- Observed or intended
-
Not assessed
- Rubric
-
Not assessed
- Assessor and date
-
Not assessed
- Alternative assessments
-
Not assessed
- Fill
-
The deployer's account
Entry details
- Kind
-
Not assessed
- Related entries
-
Not assessed
- Field
-
Micromobility safety. Shared e-scooters / pedestrian conflict.
- Purpose
-
The camera system was built to detect sidewalk riding in real time and discourage it through alerts and speed limits.
- Dates
-
Date basis unassessed: 2023 (precision unassessed). Updated: 21 October 2026.
- Stage
-
Not assessed
- Version
-
SHA-256: 3bf48e9de290…
References
- Other identifiers
-
Not assessed
- Category mappings
-
Not assessed
- Brief
-
Not assessed
- Revisions
-
5 revisions. Latest: 21 October 2026.
Sources
-
Peer-reviewed study Deployer
Oshanreh MM, Malarkey D, MacKenzie D (2024). AI-Driven Feedback Systems Reduce Sidewalk Riding on Shared E-Scooters. Findings (Transport Findings), 20 Nov 2024. doi:10.32866/001c.125892.
Data from 488 trips revealed that feedback-equipped scooters spent 22% less time and 20% less distance on sidewalks.