01 / Overview

Understand How Your Routes Change

Follow traffic and travel times on selected, eligible routes. Roads Management Insights supports analysis over time and operational integration through its supported data delivery options.

See How Routes Get Captured How It's Delivered

Selected Routes, Observed Over Time

Conceptual Overview

Selection

Your Routes

Define routes and check their eligibility.

Observation

Traffic Over Time

Review travel times and supported traffic observations.

Delivery

Analysis And Integration

Use BigQuery data and supported Pub/Sub feeds.

Coverage and capabilities depend on the service configuration. Update cadence and end-to-end delivery latency are different measures.

At A Glance

Provides: Monitoring and analysis for approved, selected routes.
Not: Every-road coverage, direct vehicle counts, or crash prediction.

2 mindocumented Pub/Sub update cadence

1 hourBigQuery batch availability cadence

10 yearshistorical table retention

60 daysrecent-roads table retention

RMI overview docs

02 / Capture Your Own Routes

You Choose The Roads — RMI Does The Watching

Nothing gets tracked until you say so. Submit an origin, a destination, and any waypoints as coordinates through the Roads Selection API, and RMI validates the route against two gates before it will report anything on it: is this road inside your approved jurisdiction, and does it carry enough real traffic to report on without exposing individual drivers.

The Two Gates

Jurisdiction: one or more polygons defining your approved territory — routes can extend up to ~20 km beyond it with verification, but not much further.
Road utility: a minimum-traffic-volume threshold, so quiet residential streets never get published — this is a privacy floor, not a bug.

Coverage isn't a one-time approval: RMI re-checks traffic volume every quarter, and a route that stays quiet for four consecutive quarters is automatically retired.

Usage guidelines & limitations

Origin, destination, waypointssubmitted as lat/lng via the Roads Selection API

Jurisdiction checkis this road inside territory you manage?

Road utility checkdoes it carry enough traffic to publish safely?

Active tracked routedata collection begins from this point forward

your_project.rmiper selected route

historical_travel_timeTABLE

recent_roads_dataTABLE

routes_statusTABLE

Additional capabilities: verify access and launch stage

03 / Traffic & Travel Time

Compare Travel Time And Speed Categories

Use traffic-aware and static duration to describe relative delay, and the speed intervals to summarize reported traffic categories. These are synthetic worked examples using the documented fields; the illustrative ratio is not an official SRI category classifier.

Travel-Time Ratio

Latest available observation per route in the selected window

WITH latest AS (
 SELECT selected_route_id, display_name, record_time,
 duration_in_seconds, static_duration_in_seconds
 FROM `YOUR_PROJECT.rmi.historical_travel_time`
 WHERE record_time >= TIMESTAMP_SUB(CURRENT_TIMESTAMP(), INTERVAL 1 HOUR)
 QUALIFY ROW_NUMBER() OVER (PARTITION BY selected_route_id
   ORDER BY record_time DESC) = 1
)
SELECT display_name,
 ROUND(SAFE_DIVIDE(duration_in_seconds, static_duration_in_seconds), 2) AS ratio
FROM latest
ORDER BY ratio DESC
LIMIT 4

Illustrative output · No request executed

display_name	Ratio
Example Connector	2.40
Example River Crossing	1.90
Example Airport Route	1.50
Example Industrial Loop	1.10

Speed Reading Intervals

A route can appear in more than one category

WITH latest AS (
 SELECT selected_route_id, speed_reading_intervals
 FROM `YOUR_PROJECT.rmi.recent_roads_data`
 WHERE record_time >= TIMESTAMP_SUB(CURRENT_TIMESTAMP(), INTERVAL 1 HOUR)
 QUALIFY ROW_NUMBER() OVER (PARTITION BY selected_route_id
   ORDER BY record_time DESC) = 1
)
SELECT sri.speed,
 COUNT(DISTINCT selected_route_id) AS routes_affected
FROM latest CROSS JOIN UNNEST(speed_reading_intervals) AS sri
GROUP BY sri.speed
ORDER BY routes_affected DESC

Illustrative output · No request executed

Speed	routes_affected
NORMAL	142
SLOW	31
TRAFFIC_JAM	6

Accumulated Data Schema

04 / Disruptions

Investigate Potential Disruptions

Google has announced disruption and Early Signal Detection capabilities for identifying closures and possible incidents from traffic changes. Treat an inferred incident as a signal to investigate, not a confirmed crash or guaranteed advance warning. Verify access and launch stage before relying on it operationally.

What It Enables

Check which disruption capabilities are available for your approved routes
Combine inferred signals with authoritative incident information
Dispatch and rerouting require your application, operating rules, and human oversight

Disruptions & Early Signal Detection announcement

From Signal To Operational Decision

Observe

An available feed indicates a disruption or traffic anomaly.

Assess

Check source, timing, affected route, and corroborating information.

Act

Your dispatch workflow decides whether to reroute or notify a crew.

Illustrative integration flow; not an automatic RMI rerouting action.

05 / Vehicle Counts

Use Estimated Volume With Its Methodology

Google has announced vehicle-count capabilities that estimate traffic volumes. Confirm availability, methodology, coverage, and fitness for the decision before using the data in engineering studies or grant applications. These estimates do not automatically replace calibrated field counts.

Justify capital projectsBack a widening, signal, or repaving budget with estimated volume with documented coverage and uncertainty.

Prioritize safety fixesCorrelate volume against historical incident data to find where a fix has the most impact.

Strengthen grant applicationsCheck whether the estimated volume meets the grant program’s evidence requirements.

Track change over timeCompare estimated volume over time while accounting for method and coverage changes.

Vehicle counts announcement

Who Asks For This Number

Capital planning teams Grant reviewers Road safety auditors Public works budgeting

Compare With

Manual tube counts Stale traffic studies Independent estimates

06 / Hard-braking Events

Hard Braking Is Research Evidence, Not A Crash Forecast

Google Research has studied aggregated hard-braking events as a correlate of road-segment crash risk. Sudden deceleration is not proof of a near miss. Research findings do not establish that a production RMI feed includes the signal or can predict the time of a future crash.

Why It Beats Crash Reports Alone

The cited Google study examines California and Virginia road-segment data
Correlation can support further investigation; it does not identify an inevitable future crash
Use a matching source for each statistic and verify product access separately

Google Research Study

Research-to-Use Boundary

Research Input

Aggregated hard-braking observations and historical crash data

Research Finding

A statistical association at road-segment level

Operational Requirement

Validate local relevance, access, methodology, and the proposed decision

No claim of individual tracking, confirmed near misses, or weeks/months of predictive lead time.

07 / Delivery & Architecture

Separate Updates From Delivery

Accumulated data in BigQuery supports planning and reporting; Pub/Sub supports a streaming integration. Route-data updates, batch availability, and end-to-end application latency are different measures. A SQL query does not execute unchanged against a message stream.

BigQuery

Duration data updates on a 10-minute cadence
Batch data becomes available hourly
Historical table: 10-year retention
Recent-roads table: 60-day retention

Pub/Sub

Documented update cadence: approximately 2 minutes
Route messages need subscriber processing
Measure end-to-end delivery latency in your integration
Verify the supported message format and fields

Budget for applicable RMI access and cloud usage. Pub/Sub basic throughput is $40/TiB after 10 GiB/month free; BigQuery subscription export is $50/TiB without that same free allowance. These are different delivery tariffs. Rates checked September 14, 2026; BigQuery storage and queries may add cost.

Ask It In Plain Language

the RMI ADK agent pairs a conversational root agent with a BigQuery sub-agent that writes and runs the SQL
runs on Gemini, querying the same historical_travel_time and recent_roads_data tables shown above

Delivery Overview Accumulated Data Pub/Sub Pricing

08 / Who It's For

Confirm Eligibility For The Use Case

Road authorities, planners, utilities, and fleet teams have different access needs. Google has announced expansion toward private-sector use and new capabilities. Confirm current onboarding, jurisdiction requirements, and feature availability with the Maps Platform team before committing to an implementation.

Access Today

Confirm organization and route eligibility through current onboarding
Verify the launch stage and entitlement for each requested capability

RMI overview docs RMI availability announcement

Road PlanningCompare travel-time patterns on eligible selected routes.

Capital AnalysisCombine documented route observations with engineering evidence.

Dispatch IntegrationEvaluate supported feeds and define response rules in your own application.

Fleet EvaluationConfirm access and coverage for the fleet’s actual operating area.