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

Modern AI techniques open up ever-increasing possibilities for autonomousvehicles, but how to appropriately verify the reliability of such systemsremains unclear. A common approach is to conduct safety validation based on apredefined Operational Design Domain (ODD) describing specific conditions underwhich a system under test is required to operate properly. However, collectingsufficient realistic test cases to ensure comprehensive ODD coverage ischallenging. In this paper, we report our practical experiences regarding theutility of data simulation with deep generative models for scenario-based ODDvalidation. We consider the specific use case of a camera-based rail-scenesegmentation system designed to support autonomous train operation. Wedemonstrate the capabilities of semantically editing railway scenes with deepgenerative models to make a limited amount of test data more representative. Wealso show how our approach helps to analyze the degree to which a systemcomplies with typical ODD requirements. Specifically, we focus on evaluatingproper operation under different lighting and weather conditions as well aswhile transitioning between them.

Towards Scenario-based Safety Validation for Autonomous Trains with Deep Generative Models