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

The simulation-based testing of Autonomous Driving Systems (ADSs) has gainedsignificant attention. However, current approaches often fall short ofaccurately assessing ADSs for two reasons: over-reliance on expert knowledgeand the utilization of simplistic evaluation metrics. That leads todiscrepancies between simulated scenarios and naturalistic drivingenvironments. To address this, we propose the Matrix-Fuzzer, a behaviortree-based testing framework, to automatically generate realisticsafety-critical test scenarios. Our approach involves the $log2BT$ method,which abstracts logged road-users' trajectories to behavior sequences.Furthermore, we vary the properties of behaviors from real-world drivingdistributions and then use an adaptive algorithm to explore the input space.Meanwhile, we design a general evaluation engine that guides the algorithmtoward critical areas, thus reducing the generation of invalid scenarios. Ourapproach is demonstrated in our Matrix Simulator. The experimental results showthat: (1) Our $log2BT$ achieves satisfactory trajectory reconstructions. (2)Our approach is able to find the most types of safety-critical scenarios, butonly generating around 30% of the total scenarios compared with the baselinealgorithm. Specifically, it improves the ratio of the critical violations tototal scenarios and the ratio of the types to total scenarios by at least 10xand 5x, respectively, while reducing the ratio of the invalid scenarios tototal scenarios by at least 58% in two case studies.

Realistic Safety-critical Scenarios Search for Autonomous Driving System via Behavior Tree