English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

This paper describes Waymo's Collision Avoidance Testing (CAT) methodology: ascenario-based testing method that evaluates the safety of the Waymo DriverAutomated Driving Systems' (ADS) intended functionality in conflict situationsinitiated by other road users that require urgent evasive maneuvers. BecauseSAE Level 4 ADS are responsible for the dynamic driving task (DDT), whenengaged, without immediate human intervention, evaluating a Level 4 ADS usingscenario-based testing is difficult due to the potentially infinite number ofoperational scenarios in which hazardous situations may unfold. To that end, inthis paper we first describe the safety test objectives for the CATmethodology, including the collision and serious injury metrics and thereference behavior model representing a non-impaired eyes on conflict humandriver used to form an acceptance criterion. Afterward, we introduce theprocess for identifying potentially hazardous situations from a combination ofhuman data, ADS testing data, and expert knowledge about the product design andassociated Operational Design Domain (ODD). The test allocation and executionstrategy is presented next, which exclusively utilize simulations constructedfrom sensor data collected on a test track, real-world driving, or fromsimulated sensor data. The paper concludes with the presentation of resultsfrom applying CAT to the fully autonomous ride-hailing service that Waymooperates in San Francisco, California and Phoenix, Arizona. The iterativenature of scenario identification, combined with over ten years of experienceof on-road testing, results in a scenario database that converges to arepresentative set of responder role scenarios for a given ODD. Using Waymo'svirtual test platform, which is calibrated to data collected as part of manyyears of ADS development, the CAT methodology provides a robust and scalablesafety evaluation.

Collision Avoidance Testing of the Waymo Automated Driving System