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 Plus annual

Presents the access of premium content as premium feature

Premium Content

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 Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Automated driving vehicles~(ADV) promise to enhance driving efficiency andsafety, yet they face intricate challenges in safety-critical scenarios. As aresult, validating ADV within generated safety-critical scenarios is essentialfor both development and performance evaluations. This paper investigates thecomplexities of employing two major scenario-generation solutions: data-drivenand knowledge-driven methods. Data-driven methods derive scenarios fromrecorded datasets, efficiently generating scenarios by altering the existingbehavior or trajectories of traffic participants but often falling short inconsidering ADV perception; knowledge-driven methods provide effective coveragethrough expert-designed rules, but they may lead to inefficiency in generatingsafety-critical scenarios within that coverage. To overcome these challenges,we introduce BridgeGen, a safety-critical scenario generation framework,designed to bridge the benefits of both methodologies. Specifically, byutilizing ontology-based techniques, BridgeGen models the five scenario layersin the operational design domain (ODD) from knowledge-driven methods, ensuringbroad coverage, and incorporating data-driven strategies to efficientlygenerate safety-critical scenarios. An optimized scenario generation toolkit isdeveloped within BridgeGen. This expedites the crafting of safety-criticalscenarios through a combination of traditional optimization and reinforcementlearning schemes. Extensive experiments conducted using Carla simulatordemonstrate the effectiveness of BridgeGen in generating diversesafety-critical scenarios.

Bridging Data-Driven and Knowledge-Driven Approaches for Safety-Critical Scenario Generation in Automated Vehicle Validation