{"resourceId":"umtri-safeti-usdot-intersection-crash-prevention-2026-11-04","versions":[{"version":"external-4c8f520d2e78fbaed2a3aebb2381c7d40a474312fb79a67f9e91626fa10ed2b5","resource":{"id":"umtri-safeti-usdot-intersection-crash-prevention-2026-11-04","title":"UMTRI SAFETI wins $5.66M U.S. DOT award for AI intersection crash-prevention with MDOT and Ann Arbor","organization":"University of Michigan Transportation Research Institute (UMTRI) with Michigan DOT, City of Ann Arbor and SEMCOG","sector":"Roadway safety / traffic signals","geography":"Ann Arbor, Michigan, USA","publishedAt":"2026-11-04","publicationDate":"2026-11-04","eventDate":null,"sourceName":"University of Michigan Civil and Environmental Engineering","sourceLabel":"University research announcement of U.S. DOT-funded project","sourceUrl":"https://cee.engin.umich.edu/2026/11/04/u-m-to-improve-pedestrian-vehicle-safety-at-intersections-with-5-66-million-from-u-s-dot/","evidenceClass":"academic-research","outcomeClass":"emerging","topics":["infrastructure","data-security","accessibility-workforce"],"finding":"UMTRI received $5.66 million from U.S. DOT for SAFETI (Safety Actions for Everyone at Traffic Intersections), advancing open-source roadside perception (MSight) into near-miss prediction that can warn drivers and pedestrians via dashboards, in-pavement lights, phones or signal changes. U.S. DOT attributes roughly one quarter of traffic fatalities and about half of injuries to intersections. Phase 1 (~18 months) prototypes at Mcity with GM, Volkswagen and Ford; Phase 2 deploys at four Ann Arbor intersections over a 3.5-year program. Privacy design: Ann Arbor fisheye cameras cannot resolve plates or faces; the algorithm classifies object type only. Public partners include MDOT, Ann Arbor and SEMCOG.","sledRelevance":"A U.S. DOT-funded, DOT/city-partnered path from lab perception to signalized intersection interventions with explicit privacy design—usable as a reference architecture for state DOT safety programs.","evidence":"University announcement of award and planned methods; no field crash-reduction results yet.","architectureImplications":"Roadside cameras/LiDAR plus V2X, signal control hooks, smartphone and in-vehicle alerts on an open-source perception stack, with optional green extension for predicted red-light runners.","governanceImplications":"Multi-year phased evaluation including human-factors testing before public deployment; open-source release planned.","securityPrivacyImplications":"Fisheye and blurring choices aim to prevent plate/face identification; object-class-only inference stated.","caveats":"Pre-deployment research; Phase 2 limited to four intersections; OEM partners may shape vehicle integration; crash outcomes unknown.","streamIds":["transportation"],"roles":{"sales":"Sales framing: U.S. DOT is funding UMTRI to turn roadside perception into real-time intersection conflict warnings with MDOT and Ann Arbor as public partners. For state DOTs, the opening is a phased safety pilot tied to existing signals and cameras—not a robotaxi pitch. Ask which intersections dominate injury crashes and what privacy rules bind traffic cameras. Interpretation; no outcome data yet.","engineering":"Engineering focus is MSight near-miss prediction hooked to signals, V2X, phones and in-vehicle alerts, with fisheye/blur privacy controls. Pre-sales engineers should inventory camera types, controller APIs, V2X readiness and human-factors test plans. Open-source intent matters for agency reuse. Interpretation.","delivery":"Delivery is a 3.5-year two-phase program: Mcity prototype with OEM partners, then four Ann Arbor intersections. MDOT/city own field sites; UMTRI owns research. Acceptance criteria should be proposed around conflict detection precision and human response to warnings. Interpretation; field results are future."},"roleDetails":{"sales":{"customerProblem":"Intersections account for a large share of U.S. traffic deaths and injuries.","stakeholders":["State DOT safety engineer","City traffic engineer","MPO","Law enforcement / Vision Zero"],"discoveryQuestions":["Which intersections drive fatal and serious injury crashes?","What camera and signal assets exist there?","What privacy policy governs traffic video?"],"valueHypothesis":"Near-miss prediction with multi-channel warnings may reduce conflicts if humans respond; unproven in the field here.","potentialEngagement":"Site selection and evaluation design for a bounded intersection safety AI pilot.","unsupportedClaims":["Crash or fatality reductions","Nationwide readiness","Driver/pedestrian compliance with alerts"]},"engineering":{"fit":"Fits cities/DOTs with instrumented intersections and signal control access.","architectureIntegration":"Roadside perception to alerts and optional signal timing changes via V2X and controller interfaces.","prerequisites":["Camera/LiDAR coverage","Signal controller integration path","Privacy-compatible imaging"],"constraints":["3.5-year research timeline","OEM vehicle integration dependencies","Four-intersection Phase 2 scope"],"security":"Prevent re-identification from video; harden roadside compute and V2X links.","proofOfValue":["Conflict prediction precision/recall at Mcity","Human recognition of warnings","False-alert rate in field"]},"delivery":{"work":"Prototype, human-factors tests with robot VRUs, then four-intersection deployment.","dependencies":["U.S. DOT funding","MDOT/Ann Arbor/SEMCOG","GM/VW/Ford/Ouster"],"ownership":"UMTRI research lead; public agencies own field operations.","skillsAdoption":"Operator training on alert dashboards and signal interventions.","governanceCheckpoints":["Phase 1 human-factors gate","Privacy review before Phase 2","Open-source release readiness"],"acceptanceCriteria":["Proposed: near-miss detection metrics met","Proposed: warning comprehension thresholds","Proposed: no plate/face leakage in audits"],"risks":["Alert fatigue","Controller integration delays","Public trust if mis-alerts occur"]}},"retrievedAt":"2026-11-05T22:09:20-06:00","enrichedAt":"2026-11-05T22:12:57-06:00","enrichmentBasis":"retrieved source","accessibilityWorkforceImplications":"Pedestrian and cyclist warnings are central; Phase 1 studies whether people understand interventions.","procurementImplications":"Federal research award with university and OEM/public partners; not a commercial RFP award.","operatingModelImplications":"Research-to-operations path via MDOT and city partners at real intersections.","sourceVerification":{"openedUrl":"https://cee.engin.umich.edu/2026/11/04/u-m-to-improve-pedestrian-vehicle-safety-at-intersections-with-5-66-million-from-u-s-dot/","referenceExcerpt":"SAFETI predicts conflicts and responds through warnings, in-pavement lights or signal changes","promptVersion":"sled-research-v4.0","model":null,"basis":"agent-reported inspection"}}}]}