• Skip to primary navigation
  • Skip to main content
  • Skip to footer
Logo for the Department of Civil and Environmental Engineering at the University of Michigan
  • Strategic Directions
  • News and Events
  • Contact

  • About
    • History
    • Strategic Directions
    • Diversity, Equity and Inclusion
      • CEE DEI Committee
      • DEI Resources
      • Have a concern?
    • Alumni
      • CEE Friends Association
        • CEEFA Board
      • Award Winners
    • Giving
      • Giving Legacy
    • Leadership and Governance
    • Faculty Search
      • Faculty Position in Environmental Engineering
      • Faculty Position in Intelligent Systems
    • Contact
      • Student Services Contacts
      • Master’s Advising Contacts
      • Undergraduate Advising Contacts
  • Undergraduate Studies
    • BSE Degree in Civil Engineering
    • BSE Degree in Environmental Engineering
    • Minor in Civil Engineering
    • Minor in Environmental Engineering
    • FocusCEE
      • Community Policy and Planning
      • Smart Cities
      • Sustainability
    • Undergraduate Opportunities
      • Undergraduate Externship
      • Student Research and Employment
        • CEE SURE/SROP Projects 2023
    • Schedule an Advising Appointment
    • Declare Your Major
    • Careers in CEE
      • What is a Civil or Environmental Engineer?
      • Career Pathways
      • Employers of CEE Graduates
      • How to Recruit CEE Graduates
    • Undergraduate Student Advisory Council
    • Student Life
  • Graduate Studies
    • Master’s Programs
    • PhD Programs
      • PhD Mentoring Framework
      • PhD Candidate Roster
    • Pelham Scholars Program
    • Online Learning
      • Construction Engineering and Management MasterTrack™
    • Admissions Information
      • International Applicants
      • Sequential Undergraduate/Graduate Studies (SUGS) Applicants
    • Graduate Handbook
    • Graduate Student Advisory Council
    • Student Life
  • People
    • Faculty
      • Affiliated Faculty
      • Core Faculty
      • Emeritus Faculty
    • Postdocs
    • Researchers
    • Staff
      • Administrative
      • Finance
      • Human Resources
      • IT & Web
      • Laboratory Technicians
      • Purchasing
      • Student Services
  • Research
    • New Grants
    • Civil Infrastructure Systems
      • Construction Engineering and Management
      • Geotechnical Engineering
      • Intelligent Systems
      • Next Generation Transportation Systems
      • Structural and Materials Engineering
    • Environment and Water Resources
      • Ecohydrology and Hydraulic Engineering
      • Energy and Clean Technology
      • Environmental Chemistry and Soil Physics
      • Environmental Microbiology and Biotechnology
    • Smart Infrastructure Finance
    • Urban Collaboratory
    • Facilities
      • Advanced Materials Research
      • Cementitious Composites
      • Center of Excellence in Bridges and Structures
      • Computational Community Resilience
      • Computational Structural Simulation
      • Construction Engineering Lab
      • Geotechnical Engineering Labs
      • Intelligent Structural Technology
      • Next Generation Infrastructure
      • Next Generation Transportation Systems Research Facilities
      • Pavement Research Center of Excellence
      • Structural Engineering Lab
  • Resources
    • Shipping
    • Purchasing
      • Purchasing Frequently Asked Questions
    • Reimbursement
    • IT Resources
    • Lab Safety
      • Lab Safety Basics
      • Minimum Training Requirements
    • Lab Requests and Procedures
    • Room Requests
    • Faculty Intranet
    • Strategic Directions
    • News and Events
    • Contact

Simulated terrible drivers cut the time and cost of AV testing by a factor of one thousand

New virtual testing environment breaks the 'curse of rarity' for autonomous vehicle emergency decision-making.

Written by: Jim Lynch

March 22, 2023

The push toward truly autonomous vehicles has been hindered by the cost and time associated with safety testing, but a new system developed at the University of Michigan shows that artificial intelligence can reduce the testing miles required by 99.99%.

It could kick off a paradigm shift that enables manufacturers to more quickly verify whether their autonomous vehicle technology can save lives and reduce crashes. In a simulated environment, vehicles trained by artificial intelligence perform perilous maneuvers, forcing the AV to make decisions that confront drivers only rarely on the road but are needed to better train the vehicles.

To repeatedly encounter those kinds of situations for data collection, real world test vehicles need to drive for hundreds of millions to hundreds of billions of miles.

“The safety critical events—the accidents, or the near misses—are very rare in the real world, and often time AVs have difficulty handling them,” said Henry Liu, U-M professor of civil engineering and director of both Mcity and the Center for Connected and Automated Transportation, a regional transportation research center funded by the U.S. Department of Transportation.

U-M researchers refer to the problem as the “curse of rarity,” and they’re tackling it by learning from real-world traffic data that contains rare safety-critical events. Testing conducted on test tracks mimicking urban as well as highway driving showed that the AI-trained virtual vehicles can accelerate the testing process by thousands of times. The study appears on the cover of Nature.

Xintao Yan and Haojie Zhu, both civil engineering PhD students, prepare to take one of the autonomous vehicles for a test run at Mcity. Photo: Brenda Ahearn/Michigan Engineering
Xintao Yan and Haojie Zhu, both civil engineering PhD students, prepare to take one of the autonomous vehicles for a test run at Mcity. Photo: Brenda Ahearn/Michigan Engineering

“The AV test vehicles we’re using are real, but we’ve created a mixed reality testing environment. The background vehicles are virtual, which allows us to train them to create challenging scenarios that only happen rarely on the road,” Liu said.

U-M’s team used an approach to train the background vehicles that strips away nonsafety-critical information from the driving data used in the simulation. Basically, it gets rid of the long spans when other drivers and pedestrians behave in responsible, expected ways—but preserves dangerous moments that demand action, such as another driver running a red light. 

By using only safety-critical data to train the neural networks that make maneuver decisions, test vehicles can encounter more of those rare events in a shorter amount of time, making testing much cheaper.

Detail photograph of screens during the virtual reality test run of an autonomous vehicle at Mcity. Photo: Brenda Ahearn/Michigan Engineering

“Dense reinforcement learning will unlock the potential of AI for validating the intelligence of safety-critical autonomous systems such as AVs, medical robotics and aerospace systems,” said Shuo Feng, assistant professor in the Department of Automation at Tsinghua University and former assistant research scientist at the U-M Transportation Research Institute. 

“It also opens the door for accelerated training of safety-critical autonomous systems by leveraging AI-based testing agents, which may create a symbiotic relationship between testing and training, accelerating both fields.” 

And it’s clear that training, along with the time and expense involved, is an impediment. An October Bloomberg article stated that although robotaxi leader Waymo’s vehicles had driven 20 million miles over the previous decade, far more data was needed. 

“That means,” the author wrote, “its cars would have to drive an additional 25 times their total before we’d be able to say, with even a vague sense of certainty, that they cause fewer deaths than bus drivers.”

Testing was conducted at Mcity’s urban environment in Ann Arbor, as well as the highway test track at the American Center for Mobility in Ypsilanti.

Haojie Zhu, a civil engineering PhD student, prepares for a test run of one of the autonomous vehicles at Mcity. Photo: Brenda Ahearn/Michigan Engineering

Launched in 2015, Mcity, was the world’s first purpose-built test environment for connected and autonomous vehicles. With new support from the National Science Foundation, outside researchers will soon be able to run remote, mixed reality tests using both the simulation and physical test track, similar to those reported in this study.

Real-world data sets that support Mcity simulations are collected from smart intersections in Ann Arbor and Detroit, with more intersections to be equipped. Each intersection is fitted with privacy-preserving sensors to capture and categorize each road user, identifying its speed and direction. The research was funded by the Center for Connected and Automated Transportation and the National Science Foundation.

Connect to the Nature story at this link.

Explore: Civil and Environmental Engineering Department Research News Features Mcity Research Transporation Transportation University of Michigan Transportation Research Institute Adaptation Autonomy in Infrastructure Henry Liu

Footer

Logo for Michigan Engineering at the University of Michigan

  • Giving
  • News and Events
  • Contact
  • Sign up for our newsletter
  • U-M Engineering Home
  • Strategic Vision
  • Graduate and Professional
  • Undergraduate
  • U-M Engineering Research News
  • U-M Home

  • Giving
  • News and Events
  • Contact
  • Sign up for our newsletter

© 2023 The Regents of the University of Michigan Ann Arbor, MI 48109 USA Privacy Policy | Non-Discrimination Policy | Campus Safety

  • Facebook
  • Instagram
  • LinkedIn
  • Twitter
  • YouTube