Skip to main content

USDoT Intersection Safety Challenge moves to next level

Derq & Miovision among organisations through to next round of competition
By Adam Hill January 9, 2025 Read time: 2 mins
(© Andrii Biletskyi | Dreamstime.com)

Derq and Miovision are among the companies, universities and other organisations which have won through to the latest, $4m, stage of the US Department of Transportation (USDoT)'s Intersection Safety Challenge.

The awards for Stage 1B of the multi-stage prize competition - System Assessment and Virtual Testing - were announced at the Transportation Research Board Annual Meeting in Washington, DC: 10 teams will be given amounts ranging from $166,666 to $750,000, for a total of $4m in prize awards. 

The challenge supports the US National Roadway Safety Strategy (NRSS) and was set up to encourage teams of innovators and end users to develop, prototype and test intersection safety systems which use emerging technologies including AI and machine learning.

In Stage 1A, the winning teams each received $100,000 for proposing their concepts. In Stage 1B, they had to demonstrate the technical aspects of their safety systems by identifying vehicles and people moving on the road - both inside and outside of a vehicle - and predicting potential collisions using real-world scenarios.

Their challenges included sensor fusion, classification, path and conflict prediction using USDoT's real-world sensor data collected on a closed course at the Federal Highway Administration Turner-Fairbank Highway Research Center.

In this round, Tier 1 winners get $750,000 each: these are Derq USA; plus the universities of Michigan, California (Los Angeles) and Hawaii.

The University of Michigan team includes Mcity, General Motors Global R&D, Ouster and Texas A&M University.

Tier 2 winners get $166,666 each: Orion Robotics; Florida A&M University and Florida State University; University of Washington; University of California (Riverside); Ohio State University; and Miovision, which includes Miovision USA, Carnegie Mellon University, Amazon Web Services and Telus.

These systems are set to identify and mitigate unsafe conditions involving vehicles and vulnerable road users at roadway intersections - and the next stage is for prototyping and field-testing.

USDoT principal deputy assistant secretary for research and chief scientist Dr. Robert C. Hampshire, says: "Enhancing the safety of vulnerable road users at our nation’s roadway intersections is a critically important element in driving down fatalities on our roads to zero.”

For more information on companies in this article

Related Content

  • Derq AI embraces Texas Paradigm
    September 5, 2022
    AI specialist's Insight and Sense solutions will be key part of new partnership
  • Free transport access in Pittsburgh
    September 6, 2022
    Year-long UBM pilot aimed at 50 'eligible participants' using Move PGH transport options
  • Affordable and versatile traffic data
    January 20, 2012
    Houston TranStar, which has been collecting travel time and segment speed data using vehicle probe data since 1995, has an extensive coverage area that envelops most local commuters' daily freeway routes. However, expanding the existing Automated Vehicle Identification (AVI) system would be cost-prohibitive except for high-volume freeways. The partners of the Houston TranStar consortium needed a new method to measure speeds and travel times on arterial roadway systems and rural freeways. Instead of using co
  • Predicting and solving future transport problems?
    August 10, 2012
    Can the future be predicted? With what accuracy can ‘predictive analytics’ be used to help anticipate demand? This is a relatively new science for transportation and over the next few years it will be interesting to see to what extent it can solve some common problems. Transportation authorities may be close to finding the golden chalice that is accurate prediction of how traffic will behave as congestion occurs. Predictive algorithms are not necessarily new, but the coming together of conditions needed for