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

Ensuring the safety and robustness of autonomous driving systems (ADSs) isimperative. One of the crucial methods towards this assurance is the meticulousconstruction and execution of test scenarios, a task often regarded as tediousand laborious. In response to this challenge, this paper introduces TARGET, anend-to-end framework designed for the automatic generation of test scenariosgrounded in established traffic rules. Specifically, we design adomain-specific language (DSL) with concise and expressive syntax for scenariodescriptions. To handle the natural language complexity and ambiguity intraffic rule descriptions, we leverage a large language model to automaticallyextract knowledge from traffic rules and convert the traffic rule descriptionsto DSL representations. Based on these representations, TARGET synthesizesexecutable test scenario scripts to render the testing scenarios in asimulator. Comprehensive evaluations of the framework were conducted on fourdistinct ADSs, yielding a total of 217 test scenarios spread across eightdiverse maps. These scenarios identify approximately 700 rule violations,collisions, and other significant issues, including navigation failures.Moreover, for each detected anomaly, TARGET provides detailed scenariorecordings and log reports, significantly easing the process of troubleshootingand root cause analysis. Two of these causes have been confirmed by the ADSdevelopers; one is corroborated by an existing bug report from the ADS, and theother one is attributed to the limited functionality of the ADS.

TARGET: Automated Scenario Generation from Traffic Rules for Testing Autonomous Vehicles