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

Discovering potential failures of an autonomous system is important prior todeployment. Falsification-based methods are often used to assess the safety ofsuch systems, but the cost of running many accurate simulation can be high. Thevalidation can be accelerated by identifying critical failure scenarios for thesystem under test and by reducing the simulation runtime. We propose a Bayesianapproach that integrates meta-learning strategies with a multi-armed banditframework. Our method involves learning distributions over scenario parametersthat are prone to triggering failures in the system under test, as well as adistribution over fidelity settings that enable fast and accurate simulations.In the spirit of meta-learning, we also assess whether the learned fidelitysettings distribution facilitates faster learning of the scenario parameterdistributions for new scenarios. We showcase our methodology using acutting-edge 3D driving simulator, incorporating 16 fidelity settings for anautonomous vehicle stack that includes camera and lidar sensors. We evaluatevarious scenarios based on an autonomous vehicle pre-crash typology. As aresult, our approach achieves a significant speedup, up to 18 times fastercompared to traditional methods that solely rely on a high-fidelity simulator.

SAVME: Efficient Safety Validation for Autonomous Systems Using Meta-Learning