{"resourceId":"usdot-intersection-safety-systems-derq","versions":[{"version":"external-4bca3c55fbdede2b9cdb3e0443e0fd4e8799b6fa09800a3fbcd3104e3ee6c8cd","resource":{"id":"usdot-intersection-safety-systems-derq","title":"Derq to test AI-powered crash prevention at U.S. intersections (USDOT Intersection Safety Systems)","organization":"U.S. DOT Intersection Safety Systems program; Derq with TxDOT, City of Houston, VDOT, Alexandria and Falls Church","sector":"Roadway safety / state DOT partners","geography":"Texas and Virginia, US","publishedAt":"Oct 23, 2026","publicationDate":"2026-10-23","eventDate":null,"sourceName":"Highways Today (republished by Derq)","sourceLabel":"Highways Today article","sourceUrl":"https://en.derq.com/press-coverage/derq-ai-intersections","evidenceClass":"independent-reporting","outcomeClass":"emerging","topics":["infrastructure","operating-model","governance-procurement"],"finding":"USDOT selected Derq as one of three teams (with teams led by UCLA and the University of Michigan) in the Intersection Safety Systems program to build and test AI that predicts conflicts such as red-light running and pedestrian crossings and triggers warnings, roadside signs or signal-operation changes. Testing starts at Virginia Smart Roads and TTI's RELLIS Proving Grounds before possible operational intersections. The solicitation estimated $5.5 million for Phase 1 and $11.5 million for Phase 2; no crash-reduction results exist yet.","sledRelevance":"Federal program with state DOT and city partners testing predictive, closed-loop intersection safety, including signal changes, which sets future procurement and validation expectations.","evidence":"Trade article hosted on the vendor's site; program facts cite USDOT materials; no performance data.","architectureImplications":"Fuses video, LiDAR or radar, signal controller events and V2X messages with roadside processing.","governanceImplications":"Interventions depend on local operating rules and control arrangements; validation needs surrogate safety measures.","securityPrivacyImplications":"Roadside video analytics raise retention and access questions not covered.","caveats":"Prototype stage; detecting conflicts is not the same as preventing crashes, as the article notes.","streamIds":["transportation"],"roles":{"sales":"The ISS program is a federal test of whether AI can prevent intersection crashes, not just detect them. State DOT and city partners will face decisions on interventions like signal changes. Do not claim safety results; none exist. Position independent evaluation using surrogate safety measures.","engineering":"Architecture fuses video, radar or LiDAR, controller events and V2X at the roadside. Key engineering issues are latency, prediction accuracy, controller integration and fail-safe behavior when the system requests signal changes. Evaluation should use time-to-collision and post-encroachment time.","delivery":"Delivery for partner agencies means defining control authority, test protocols and safety metrics before public-road trials. Criteria are proposals pending program outcomes."},"roleDetails":{"sales":{"customerProblem":"Agencies need evidence that predictive intersection AI prevents crashes before deploying interventions.","stakeholders":["State DOT traffic safety engineers","City traffic operations","USDOT program office"],"discoveryQuestions":["Which interventions will be permitted at operational intersections?","How will surrogate safety be measured?"],"valueHypothesis":"Independent evaluation could de-risk decisions about operational deployment.","potentialEngagement":"A bounded evaluation-design engagement for a partner agency.","unsupportedClaims":["Crash reductions","Detection accuracy"]},"engineering":{"fit":"Fits evaluation and controller-integration review.","architectureIntegration":"Roadside sensor fusion with signal controllers and V2X.","prerequisites":["Controller interface access","Sensor installation"],"constraints":["Prototype phase at test facilities"],"security":"Secure controller interfaces against unauthorized signal changes.","proofOfValue":["Surrogate safety metrics in controlled tests"]},"delivery":{"work":"Define test protocols and control authority before public-road evaluation.","dependencies":["Federal phase funding","Partner agency approvals"],"ownership":"Partner DOTs and cities with the vendor.","skillsAdoption":"Engineers trained on surrogate safety analysis.","governanceCheckpoints":["Approval before any automated signal intervention"],"acceptanceCriteria":["Proposed: documented fail-safe behavior"],"risks":["False alarms disrupting signal operations"]}},"retrievedAt":"2026-10-29T22:12:00-05:00","enrichedAt":"2026-10-29T22:12:23-05:00","enrichmentBasis":"retrieved source","accessibilityWorkforceImplications":"Agencies will need staff able to evaluate surrogate safety metrics.","procurementImplications":"Federal phases fund prototypes; operational deployment would require new procurement.","operatingModelImplications":"Moves intersections from monitoring toward automated intervention, requiring clear control authority.","sourceVerification":{"openedUrl":"https://en.derq.com/press-coverage/derq-ai-intersections","referenceExcerpt":"Correctly detecting a potential conflict is a useful technical result, but it is not equivalent to demonstrating that crashes have been prevented.","promptVersion":"sled-research-v4.0","model":null,"basis":"agent-reported inspection"}}}]}