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

Simulation-based testing of autonomous vehicles (AVs) has become an essentialcomplement to road testing to ensure safety. Consequently, substantial researchhas focused on searching for failure scenarios in simulation. However, afundamental question remains: are AV failure scenarios identified in simulationmeaningful in reality, i.e., are they reproducible on the real system? Due tothe sim-to-real gap arising from discrepancies between simulated and realsensor data, a failure scenario identified in simulation can be either aspurious artifact of the synthetic sensor data or an actual failure thatpersists with real sensor data. An approach to validate simulated failurescenarios is to identify instances of the scenario in a corpus of real data,and check if the failure persists on the real data. To this end, we propose aformal definition of what it means for a labelled data item to match anabstract scenario, encoded as a scenario program using the SCENIC probabilisticprogramming language. Using this definition, we develop a querying algorithmwhich, given a scenario program and a labelled dataset, finds the subset ofdata matching the scenario. Experiments demonstrate that our algorithm isaccurate and efficient on a variety of realistic traffic scenarios, and scalesto a reasonable number of agents.

Querying Labelled Data with Scenario Programs for Sim-to-Real Validation