Fewer warning events on Virginia buses with Shield+, amid false alarms

VTRC found that event rates fell at five of six Virginia transit agencies once Shield+ alerts went live. Of surveyed operators, 75% often or sometimes noticed false alarms.

  • 2 an organization

    Event rates fell after alerts went live at five of six agencies analyzed, a measured change in how operators drove.

  • Not rated society

    The evaluators measured warning events, and the report gives no crash figures, so no gain in road safety is shown.

Depth runs from 1, a convenience or time saved, to 5, a life or a livelihood preserved.

Status
Reported and intended benefits.
Evidence

foundstudiedreportedclaimed

Only the evaluators support the benefit.

Compared with

The same buses in stealth mode, when the system logged events without alerting operators. Measured.

The system’s part
The same buses logged events with alerts hidden and then shown, so the change isolates the effect of the alerts. The comparison is before and after, and operators, routes and seasons also changed. The report describes camera sensors that detect pedestrians and cyclists but does not describe the detection method or machine learning.
Limits
Not yet checked.
Costs and harms
Not yet checked.
Later
Not yet checked.

Download data Cite Suggest a correction

Benefit type
Reduced Risk
System
Mobileye Shield+ Advanced Driver Assistance System
Made by
Mobileye
Used by
Virginia Department of Rail and Public Transportation (DRPT), with nine transit agencies including Hampton Roads Transit, WMATA and DASH
Where
Virginia, United States
Stage
In a pilot
Date
, when the source was published
Kind
Aggregate result
Broad benefit
Monitoring Processes, Materials, or Surroundings, Identifying Objects, Actions, and Events
Collections
Scrutiny and findings, Cross-border records
Last revised
31 October 2026

Sources

  1. Evaluation report, by an evaluator that the makers or users commissioned.

    Goodall, N. J., and P. B. Ohlms. Evaluation of a Transit Bus Collision Avoidance Warning System in Virginia. Final Report VTRC 22-R18, Virginia Transportation Research Council for the Virginia Department of Transportation and the Federal Highway Administration, February 2022.

    The study found that the benefits of the CAWS in a transit operating environment were mixed: the driving performance of operators, as measured by event rates in the CAWS data, generally improved after they began receiving system alerts.

Details

AI system

Workflow

Four cameras on each bus fed alerts to three displays near the operator. Each bus ran in stealth mode, logging events without alerts, before its alerts went live. Transit agencies and the vendor trained the operators.

Follow-up

Conditions for replication

The buses run in daylight, since most alerts were disabled at night or in deep shadow. Operators accept the alerts despite false alarms in areas with many pedestrians.

Entry details

Sector

Road safety / transit buses.

Purpose

Mobileye built Shield+ to warn bus operators of pedestrians and cyclists near the bus, of possible collisions, of lane departures and of speeding.

Not yet checked: model, release, provider, role, configuration, inputs and outputs, autonomy, human oversight, beneficiaries, reach, distribution and access, duration, every measurement question, every money question, ownership and control, dependencies, cross-border connections, geopolitical implications, replication attempts, availability, institutional decision, grounds, action and result, success criterion, every evidence question, observed or intended, alternative assessments, related entries, other identifiers, category mappings.

Cite this record

Peter H. Vartanian. (2026). Fewer warning events on Virginia buses with Shield+, amid false alarms (AIBD-0903). Artificial Intelligence Benefits Database, edition of 31 October 2026. https://petervartanian.xyz/aibd/records/AIBD-0903.html (archived at https://doi.org/10.7910/DVN/AADSII, version 4.0)

BibTeX Data Field definitions