Driving Safety Performance Metrics for ADS-Equipped Vehicles
What does it mean for an automated vehicle to drive safely? How does it compare to human-driven vehicles? In this three-phase, safety metrics project, IAM aims to define a concise set of metrics to inform an AV driving safety performance assessment. Through IAM’s test network, the team can test the metrics in a real-world intersection.
Phase I: August 2019 - April 2020
The first phases will include the design and validation of metric definitions, a data capture system and a detection and tracking algorithm. The definitions are a mix of existing, adapted and novel metrics. The data capture system is supported by IAM’s test network site operated by the Maricopa County Department of Transportation in Anthem, Arizona. The intersection’s cameras are infused with AI to sense objects, informing detection and tracking algorithms.
This compilation of footage from the IAM Test Network site in Anthem, Arizona features how the IAM team uses MCDOT intersection cameras to test and measure its safety assessment metrics.
IAM published driving safety performance metrics and methods identified in this project’s first phase in the SAE International Journal.
Phase II: May 2020 - December 2020
In this second phase, IAM members will refine and evaluate the safety metrics, as well as the detection and tracking algorithm defined in Phase I. The team will also research assessment methodologies to analyze the driving safety performance of an individual vehicle and the vehicle’s impact on the overall traffic network.
Phase III: January 2021 - December 2022
The third and final phase will establish an assessment network to serve as a test bed for a statewide system deployment of the driving safety performance metrics.