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

Corner case scenarios are an essential tool for testing and validating thesafety of autonomous vehicles (AVs). As these scenarios are ofteninsufficiently present in naturalistic driving datasets, augmenting the datawith synthetic corner cases greatly enhances the safe operation of AVs inunique situations. However, the generation of synthetic, yet realistic, cornercases poses a significant challenge. In this work, we introduce a novelapproach based on Heterogeneous Graph Neural Networks (HGNNs) to transformregular driving scenarios into corner cases. To achieve this, we first generateconcise representations of regular driving scenes as scene graphs, minimallymanipulating their structure and properties. Our model then learns to perturbthose graphs to generate corner cases using attention and triple embeddings.The input and perturbed graphs are then imported back into the simulation togenerate corner case scenarios. Our model successfully learned to producecorner cases from input scene graphs, achieving 89.9% prediction accuracy onour testing dataset. We further validate the generated scenarios on baselineautonomous driving methods, demonstrating our model's ability to effectivelycreate critical situations for the baselines.

CC-SGG: Corner Case Scenario Generation using Learned Scene Graphs