Back office ops · Production

INRIX accelerates transportation planning with Amazon Bedrock and generative AI visualization

The problem

Generating actionable transportation safety countermeasures and their conceptual visualizations traditionally required extensive collaboration among multiple specialized teams, with each iteration cycle involving many rounds of reviews and approvals, frequently extending timelines and delaying implementation of safety improvements.

Workflow diagram · grounded in source
1
Natural language query input
trigger
“users can ask natural language queries such as, Where are the top five locations with the highest risk for vulnerable road users? and Can you recommend a suite of proven safety countermeasures at each of these locations?”
2
RAG-powered risk identification
ai_action
“Compass AI uses RAG and Amazon Bedrock powered foundation models (FMs) to query the roadway network to identify and prioritize locations with systemic risk factors and anomalous safety patterns”
3
Countermeasure recommendation output
output
“The solution provides prioritized recommendations for operational and design solutions and countermeasures based on industry knowledge”
4
Street-view image generation
ai_action
“the system employs image generation functionality to create street-view representations corresponding to specific longitude and latitude coordinates where interventions are proposed”
5
Countermeasure in-painting
ai_action
“the in-painting capability enables precise placement of countermeasures within the generated street view scene”
6
Multi-team visualization review
human_review
“This prototyped solution enables rapid iteration of conceptual drawings that can be efficiently reviewed by various teams”
Reported outcome

The generative AI-powered approach provides significant planning acceleration compared to traditional methods, potentially reducing the design cycle from weeks to days, and delivers substantial improvements in both time-to-deployment and cost-effectiveness through automated generation and modification of visualizations.

Reported metrics
Design cycle durationpotentially reducing the design cycle from weeks to days
Planning accelerationsignificant planning acceleration
Time-to-deployment and cost-effectivenesssubstantial improvements in both time-to-deployment and cost-effectiveness
Reported stack
INRIX CompassAmazon BedrockAmazon Nova Canvas
Source
https://aws.amazon.com/blogs/machine-learning/how-inrix-accelerates-transportation-planning-with-amazon-bedrock?tag=soumet-20
Read source ↗

Frequently asked questions

What did this team achieve with this AI workflow?

The generative AI-powered approach provides significant planning acceleration compared to traditional methods, potentially reducing the design cycle from weeks to days, and delivers substantial improvements in both ti…

What tools did this team use?

INRIX Compass, Amazon Bedrock, Amazon Nova Canvas.

What results were reported?

Design cycle duration: potentially reducing the design cycle from weeks to days; Planning acceleration: significant planning acceleration; Time-to-deployment and cost-effectiveness: substantial improvements in both time-to-deployment and cost-effectiveness (source-reported, not independently verified).

How is this back office ops AI workflow structured?

Natural language query input → RAG-powered risk identification → Countermeasure recommendation output → Street-view image generation → Countermeasure in-painting → Multi-team visualization review.

Related back office ops cases