AZTrans
Virtual Visit Request info Apply
MENUMENU
  • Home
    • History
    • Press
    • Mission
    • PSR Region 9
  • Research
    • Program
    • Projects
    • Journal Articles
    • Sponsors
  • Education
    • Undergraduate Courses
    • Graduate Courses
  • People
    • Leadership and Faculty
    • Student Researchers
    • Alumni
  • IN
  • AZTrans
  • The Development of a Cooperative Safety Performance Assessment Framework for Connected and Automated Driving System-Equipped Vehicles

The Development of a Cooperative Safety Performance Assessment Framework for Connected and Automated Driving System-Equipped Vehicles

Posted by nbl42 on November 12, 2019

Sponsor: Institute of Automated Mobility (IAM) through the Arizona Commerce Authority (ACA)

PI: Brendan J Russo

Start Date: August 2019

The rapid development and testing of connected and automated driving system (ADS)-equipped vehicles (CAVs) in our urban communities raises serious concerns for public safety. To address these concerns, the Institute of Automated Mobility (IAM) established by Governor Ducey in Arizona has embarked on an innovative approach to driving safety performance assessment that cooperatively utilizes both infrastructure and vehicle data. Data from sensors and controls (decisions) from infrastructure systems and from vehicle systems are fused to allow for measurements of a rich set of safety performance metrics that include safety envelop violations, conflicts (e.g. post-encroachment time, time to collision, speed differential, etc.), rules-of-the road violations, and ADS-specific performance metrics. In this study, data are collected in the Maricopa County SmartDrive ProgramSM test bed in Anthem, AZ at an intersection that is equipped with video, LIDAR, and RADAR sensors, as well as data from the traffic signal controller (Signal Phase and Timing (SPaT), signal timing plan, etc.). These data are synchronized with data from onboard vehicle sensors including video, LIDAR, and RADAR and vehicle control information (e.g., identified objects, path planning, driving commands (steering, speed, etc.)) and analyzed using a variety of statistical inference and machine learning techniques. The objective is to determine metrics, data capture techniques, and analysis algorithms and methods as a framework for driving safety performance assessment.

Filed Under: AZ_Trans, Past Research, Research

AZTrans Home
Location
Room 114 Building 69
Engineering And Natural Sciences
Flagstaff, AZ 86011
Mailing Address
PO Box: 15600
Flagstaff, AZ 86011
Contact Form
Email
AZTrans@nau.edu
Phone
928-523-1431
Social Media
Facebook LinkedIn