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

With the growing capabilities of autonomous vehicles, there is a higherdemand for sophisticated and pragmatic quality assurance approaches for machinelearning-enabled systems in the automotive AI context. The use ofsimulation-based prototyping platforms provides the possibility for early-stagetesting, enabling inexpensive testing and the ability to capture criticalcorner-case test scenarios. Simulation-based testing properly complementsconventional on-road testing. However, due to the large space of test inputparameters in these systems, the efficient generation of effective testscenarios leading to the unveiling of failures is a challenge. This paperpresents a study on testing pedestrian detection and emergency braking systemof the Baidu Apollo autonomous driving platform within the SVL simulator. Wepropose an evolutionary automated test generation technique that generatesfailure-revealing scenarios for Apollo in the SVL environment. Our approachmodels the input space using a generic and flexible data structure and benefitsa multi-criteria safety-based heuristic for the objective function targeted foroptimization. This paper presents the results of our proposed test generationtechnique in the 2021 IEEE Autonomous Driving AI Test Challenge. In order todemonstrate the efficiency and effectiveness of our approach, we also reportthe results from a baseline random generation technique. Our evaluation showsthat the proposed evolutionary test case generator is more effective atgenerating failure-revealing test cases and provides higher diversity betweenthe generated failures than the random baseline.

Efficient and Effective Generation of Test Cases for Pedestrian Detection -- Search-based Software Testing of Baidu Apollo in SVL