A collaborative US pilot project has shown it can detect road condition and damaged street furniture, including guardrails and shoulder drop-offs, with extremely high accuracy.
The prototype Proactive Roadway Maintenance System in the state of Ohio is said to have achieved 99% accuracy for detecting damaged and obstructed signs and 93% accuracy for damaged guardrails.
Car maker Honda and DriveOhio, the smart mobility hub of the Ohio Department of Transportation (ODOT), said the project is a first-of-its-kind to demonstrate how real-time, vehicle-generated data can detect and report road deficiencies. The pilot was conducted in collaboration with technology partners i-Probe, consulting engineering firm Parsons and the University of Cincinnati. The two-year pilot verified the feasibility of an automated road-condition management and reporting system to help departments of transportation around the US to proactively optimise maintenance while reducing costs and creating safer roadways.
Honda said it has been developing its prototype Proactive Roadway Maintenance System since 2021. During the pilot, ODOT team members drove Honda test vehicles, equipped with advanced vision and LiDAR sensors, to monitor around nearly 5,000km (3,000 miles) of roads in central and southeastern Ohio. The vehicles operated under a wide range of real-world conditions, including multiple road types in rural and urban environments, varied weather and different times of the day.
The Proactive Roadway Maintenance System detected road conditions and infrastructure deficiencies. Some of the conditions detected were worn or obstructed road signs, damaged guardrails and cable road barriers, potholes and shoulder drops, including percentage and depth of drop-off. Even the road’s ride quality was detected.
As the Honda test vehicles detected the condition of critical roadway surfaces, pavement markings and roadside assets, ODOT operators were able to review the deficiencies in real time through web dashboards developed by Honda and Parsons. ODOT used the data to cross-reference its regular visual inspections.
Data collected by the vehicles was processed using edge AI models, transmitted to a Honda cloud platform for analysis and integrated into Parsons iNET Asset Guardian system. This allowed for automatically generated, prioritised work orders for ODOT maintenance teams. Work orders can be grouped by severity and proximity, with the iNET Asset Guardian system streamlining workflows to enhance efficiencies across field-maintenance operations.
Data validation was provided by i-Probe, as well as analysis expertise for road roughness and lane-marking conditions. The University of Cincinnati helped Honda integrate the sensors on the test vehicles and led the damage-detection-feature development including potholes, guardrails, signs and shoulder drops. Honda also provided system-maintenance service to the ODOT during the trial operation.
Pilot results
The pilot programme showed a 99% accuracy for identifying damaged or obstructed road signs, a 93% accuracy for damaged guardrails and an 89% average accuracy for detecting potholes. Importantly, an AI-feedback loop pipeline was built that enabled ODOT team members to flag misdetections, helping the system learn and improve over time.
Insights showed that only a small percentage of roads had insufficient lane markings, suggesting that restriping schedules could be optimised.
Vehicle-sensor data also reliably measured road-roughness levels and provided valuable insights for maintenance planning. The Proactive Roadway Maintenance System further detected high‑severity shoulder drop‑offs that were difficult to identify through routine visual inspection.
By reducing the need for manual inspections, the system enhances safety for maintenance crews and minimises their exposure to traffic hazards. The project team estimates that automated road-condition detection could save ODOT more than $4.5 million annually through less manual inspection time, optimised maintenance schedules and prevention of costly deferred repairs through proactive inspection.
As part of the next phase of testing, the project team is exploring ways to scale the prototype Proactive Roadway Maintenance System for real-world operations. In the future, Honda aims to empower its customers to contribute to safer, better roads through anonymised data sharing from their vehicles. This community-focused approach creates a sense of shared ownership at the road-operation level, enabling drivers to move from simply using the roadways to actively improving them.
More information on the project team is available from Honda by clicking here.
For a video explanation of the project,click here.
