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

Generating safety-critical scenarios, which are crucial yet difficult tocollect, provides an effective way to evaluate the robustness of autonomousdriving systems. However, the diversity of scenarios and efficiency ofgeneration methods are heavily restricted by the rareness and structure ofsafety-critical scenarios. Therefore, existing generative models that onlyestimate distributions from observational data are not satisfying to solve thisproblem. In this paper, we integrate causality as a prior into the scenariogeneration and propose a flow-based generative framework, Causal AutoregressiveFlow (CausalAF). CausalAF encourages the generative model to uncover and followthe causal relationship among generated objects via novel causal maskingoperations instead of searching the sample only from observational data. Bylearning the cause-and-effect mechanism of how the generated scenario causesrisk situations rather than just learning correlations from data, CausalAFsignificantly improves learning efficiency. Extensive experiments on threeheterogeneous traffic scenarios illustrate that CausalAF requires much feweroptimization resources to effectively generate safety-critical scenarios. Wealso show that using generated scenarios as additional training samplesempirically improves the robustness of autonomous driving algorithms.

CausalAF: Causal Autoregressive Flow for Safety-Critical Driving Scenario Generation