Skip to main content
U.S. flag

An official website of the United States government

Official websites use .gov
A .gov website belongs to an official government organization in the United States.

Secure .gov websites use HTTPS
A lock ( ) or https:// means you’ve safely connected to the .gov website. Share sensitive information only on official, secure websites.

NIST Researchers Publish Report on Assessing Autonomous Vehicle Performance

NIST Researchers Publish Report on Assessing Autonomous Vehicle Performance
Credit: Ctl

NIST researchers released a publication, NIST Internal Report (IR) 8534 "Feature Description for Assessing Autonomous Vehicle Performance," which introduces a structured framework for describing and evaluating the performance of autonomous vehicle (AV) features. The framework aims to ensure that AV features are described and tested consistently, with precise specifications for the intended functionality of the feature, the desired behaviors or on-road performance, and the different factors that influence vehicle performance.

The framework introduces key components for assessing AV feature performance, including established elements like SAE levels of driving automation, operational design domains (ODD), and behaviors. It also includes new concepts such as the NIST-developed Operating Envelope Specification (OES) and behavior specifications, which are measurable specifications of the feature’s driving environment and intended function that can be used for performance assessment. Together, these components provide a systematic approach to defining, measuring, and validating how AV features perform under various conditions. The report uses the Automatic Emergency Braking (AEB) feature as a use case to demonstrate how the framework can be applied to describe and test AV features.

The methodology described in this report is an important step for developing more robust test procedures for emerging autonomous vehicle technologies, ensuring that AV features are safe when deployed on our roads. This work was conducted as part of the NIST automated vehicles research program.

Released October 1, 2024, Updated November 29, 2024