SML4ADS: An Open DSML for Autonomous Driving Scenario Representation and Generation

Bo Li, Dehui Du*, Sicong Chen, Minjun Wei, Chenghang Zheng, Xinyuan Zhang

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

1 Scopus citations

Abstract

Autonomous Driving Systems(ADS) require extensive evaluation of safety before they can come onto the market. However, since relying solely on field testing is practically infeasible due to the impossibility to cover sufficient distances to ensure adequate safety, the focus shifted to scenario-based testing. The challenge is to generate scenarios flexibly. We proposed Scenario Modeling Language for ADS (SML4ADS) as a Domain-Specific Modeling Language (DSML) for scenario representation and generation. Compared to other existing works, our approach simplifies the description of scenarios in a non-programming, user-friendly manner, allows modeling stochastic behavior of vehicles and generating executable scenario in CARLA. We apply SML4ADS in numerous typical scenarios to preliminarily demonstrate the effectiveness and feasibility of our approach in modeling and generating executable scenarios.

Original languageEnglish
Title of host publication37th IEEE/ACM International Conference on Automated Software Engineering, ASE 2022
EditorsMario Aehnelt, Thomas Kirste
PublisherAssociation for Computing Machinery
ISBN (Electronic)9781450396240
DOIs
StatePublished - 19 Sep 2022
Event37th IEEE/ACM International Conference on Automated Software Engineering, ASE 2022 - Rochester, United States
Duration: 10 Oct 202214 Oct 2022

Publication series

NameACM International Conference Proceeding Series

Conference

Conference37th IEEE/ACM International Conference on Automated Software Engineering, ASE 2022
Country/TerritoryUnited States
CityRochester
Period10/10/2214/10/22

Keywords

  • ADS
  • DSML
  • scenario modeling
  • scenario simulation

Fingerprint

Dive into the research topics of 'SML4ADS: An Open DSML for Autonomous Driving Scenario Representation and Generation'. Together they form a unique fingerprint.

Cite this