Automated Vehicle Safety Consortium releases Best Practice for Developing ADS Safety Performance Thresholds Based on Human Driving Behavior

Document addresses leveraging human driving data to establish safety performance targets for ADS-DV behaviors

https://avsc.sae-itc.org/
https://avsc.sae-itc.org/
SAE MOBILUS

The Automated Vehicle Safety Consortium (AVSC), a program of SAE Industry Technologies Consortia (SAE ITC), just announced the availability of their 12th best practice, titled Developing ADS Safety Performance Thresholds Based on Human Driving Behavior. This best practice outlines a process for leveraging human driving data to establish safety performance targets for automated driving system-dedicated vehicles (ADS-DV) behaviors. The targets within the specific use-case exemplified in this best practice are based on naturalistic driving data from manually driven vehicles in the hope of aiding understanding from a broad audience of stakeholders.

Automated driving system (ADS) developers need a way to describe safe and competent driving for ADS-DVs in a way that is relatable to how stakeholders interpret safe driving today. Metrics informed by competent and safe human behavior could improve understanding and confidence in ADS-DVs. One way to make ADS safety performance relatable to stakeholders is to adopt an intuitive comparison to behaviors displayed on the road by human drivers.

“We're excited because this best practice provides guidelines for developers to use data from human driving studies to establish measurable performance reference values and build evidence that supports the safety of their systems.” says Darcyne Foldenauer, Director of the AVSC.

The safety performance of some ADS behaviors can be measured and compared to naturalistic driving studies data from human drivers to help characterize the socially acceptable balance between safety, lawful driving, efficiency, and comfort. For instance, developers can utilize human-driver data to determine an appropriate minimum passing distance when vulnerable road users are present. This process enables them to enhance the safety performance of ADS fleets by aligning it with human-relative benchmarks and considerations.

“It's one way to make performance data relatable to various stakeholders and furthers our mission to build trust in AV systems,” adds Foldenauer.

To download the paper, click HERE.