Traffic Technology TodayTraffic Technology Today
  • News
    • A-D
      • Appointments & Staffing
      • Asset Management
      • Autonomous Vehicles & ADAS
      • Awards
      • Cloud Computing
      • Congestion Reduction
      • Connected Vehicles
      • Covid-19
      • Cybersecurity
      • Data & Modeling
      • Deals, Acquisitions & Mergers
    • E-J
      • Electric vehicles & infrastructure
      • Emissions & Low Emission Zones
      • Enforcement
      • Event News
      • Funding
      • Incident Detection
      • Infrastructure
      • Intersections & Traffic Signals
      • ITS
    • K-S
      • Legal / Government Regulation
      • Machine Vision / ALPR
      • Mapping
      • Mobility as a Service
      • Multimodality & Micromobility
      • Planning, Testing, R&D
      • Public transit
      • Safety
      • Smart Cities
      • Smart Parking
    • T-Z
      • Tolling
      • Traffic counting & categorization
      • Traffic Management
      • Traveler Information Systems
      • Tunnels & Bridges
      • Variable Message Signs
      • Vulnerable Road Users
      • Weather systems
  • Features
    • Features
    • Opinion
  • Online Magazines
    • September 2023
    • May 2023
    • March 2023
    • Nov/Dec 2022
    • September 2022
    • Archive Issues
    • Subscribe Free!
    • > Tolltrans
  • Videos
  • Audio
    • The Transportation Podcast
    • Additional Audio
  • Events
  • Webinars
  • Technology Profiles
LinkedIn YouTube X (Twitter)
LinkedIn YouTube X (Twitter)
Subscribe >
Traffic Technology TodayTraffic Technology Today
  • News
      • Appointments & Staffing
      • Asset Management
      • Autonomous Vehicles & ADAS
      • Awards
      • Cloud Computing
      • Congestion Reduction
      • Connected Vehicles
      • Covid-19
      • Cybersecurity
      • Data & Modeling
      • Deals, Acquisitions & Mergers
      • Electric vehicles & infrastructure
      • Emissions & Low Emission Zones
      • Enforcement
      • Event News
      • Funding
      • Incident Detection
      • Infrastructure
      • Intersections & Traffic Signals
      • ITS
      • Legal / Government Regulation
      • Machine Vision / ALPR
      • Mapping
      • Mobility as a Service
      • Multimodality & Micromobility
      • Planning, Testing, R&D
      • Public transit
      • Safety
      • Smart Cities
      • Smart Parking
      • Tolling
      • Traffic counting & categorization
      • Traffic Management
      • Traveler Information Systems
      • Tunnels & Bridges
      • Variable Message Signs
      • Vulnerable Road Users
      • Weather systems
  • Features
    • Features
    • Opinion
  • Online Magazines
    1. September 2023
    2. May 2023
    3. March 2023
    4. Nov/Dec 2022
    5. September 2022
    6. Archive Issues
    7. Subscribe Free!
    8. > Tolltrans
    Featured
    September 15, 2023

    In this Issue – September 2023

    Online Magazines By Tom Stone
    Recent

    In this Issue – September 2023

    September 15, 2023

    In this Issue – May 2023

    May 4, 2023

    In this Issue – March 2023

    March 20, 2023
  • Videos
  • Audio
    • The Transportation Podcast
    • Additional Audio
  • Events
  • Webinars
  • Technology Profiles
LinkedIn YouTube X (Twitter)
Traffic Technology TodayTraffic Technology Today
Autonomous Vehicles & ADAS

U-M develops new method to test AVs that could cut 99.9% of validation costs

Tom StoneBy Tom StoneMay 25, 20172 Mins Read
Share LinkedIn Twitter Facebook Email

Mobility researchers at the University of Michigan (U-M) have devised a new way to test autonomous vehicles (AVs) that bypasses the billions of miles they would need to log for consumers to consider them road-ready.

The process, which was developed using data from more than 25 million miles (40 million kilometers) of real-world driving, can significantly cut the time required to evaluate self-driving vehicles’ handling of potentially dangerous situations, which could save 99.9% of testing time and costs, according to the team. The researchers have outlined the approach in a new white paper published by Mcity, a U-M-led public-private partnership to accelerate advanced mobility vehicles and technologies.

The new accelerated evaluation process breaks down difficult real-world driving situations into components that can be tested or simulated repeatedly, exposing AVs to a condensed set of the most challenging driving situations. In this way, just 1,000 miles of testing can yield the equivalent of 300,000 to 100 million miles of real-world driving. However, it is not enough to certify the safety of an AV, because the difficult scenarios they need to zero in on are rare. A crash that results in a fatality occurs only once in every 100 million miles of driving. For consumers to get the confidence levels to accept driverless vehicles, researchers say test vehicles would need to be driven in simulated or real-world settings for 11 billion miles.

The researchers analyzed data from 25.2 million miles of real-world driving collected by two U-M Transportation Research Institute projects: Safety Pilot Model Deployment and Integrated Vehicle-Based Safety Systems, which involved nearly 3,000 vehicles and volunteers over two years. From that data, the team:

• Identified events that could contain ‘meaningful interactions’ between an AV and human-driven vehicle, and created a simulation that replaced all the uneventful miles with meaningful interactions;

• Programmed their simulation to consider human drivers the major threat to AVs and placed them randomly throughout;

• Conducted mathematical tests to assess the risk and probability of certain outcomes, including crashes, injuries, and near-misses;

• Interpreted the accelerated test results, using ‘importance sampling’ to learn how the AV would perform, statistically, in everyday driving situations.

“Test methods for traditionally driven cars are something like having a doctor take a patient’s blood pressure or heart rate, while testing for automated vehicles is more like giving someone an IQ test,” said Ding Zhao, U-M research scientist and co-author of the white paper.

Share. Twitter LinkedIn Facebook Email
Previous ArticleTexas A&M College of Engineering tackles problem of autonomous vehicle cyberattacks
Next Article Stanley Robotics installs autonomous parking system at Paris airport
Tom Stone

Tom has edited Traffic Technology International (TTi) magazine and its Traffic Technology Today website since May 2014. During his time at the title, he has interviewed some of the top transportation chiefs at public agencies around the world as well as CEOs of leading multinationals and ground-breaking start-ups. Tom's earlier career saw him working on some the UK's leading consumer magazine titles. He has a law degree from the London School of Economics (LSE).

Related Posts

Autonomous Vehicles & ADAS

FEATURE: The FHWA’s Framework for automated-vehicle testing explained

November 23, 20238 Mins Read
Autonomous Vehicles & ADAS

CAVForth wins first Self-driving Industry Vehicle of the Year award

November 21, 20232 Mins Read
Autonomous Vehicles & ADAS

New ITS America resources consolidate autonomous vehicle best practice

November 9, 20233 Mins Read
Latest Posts

Kapsch TrafficCom funds establishment of mobility chair

December 5, 2023

INRIX announces new AI technology that uncovers root causes of traffic problems

December 5, 2023

POLIS Conference shows how sustainable mobility action pays off

December 5, 2023
FREE WEEKLY NEWS EMAIL!

Get the ‘best of the week’ from TrafficTechnologyToday.com direct to your inbox every Thursday


Supplier Spotlight
  • Norbit ASA
    Norbit ASA
Our Social Channels
  • Twitter
  • YouTube
  • LinkedIn
Getting in Touch
  • Free Email Newsletters
  • Contact Us
  • Meet the Editors
  • Supplier Spotlight

Upcoming Events

Jan 7
7th January 2024 - 11th January 2024

TRB Annual Meeting

Jan 9
9th January 2024 - 12th January 2024

CES 2024

Apr 16
16th April 2024 - 19th April 2024

Intertraffic Amsterdam

View Calendar
© 2023 Mark Allen Group Ltd | All Rights Reserved
  • Cookie Policy
  • Privacy Policy
  • Terms & Conditions

Type above and press Enter to search. Press Esc to cancel.