Safety-Violation Scenarios Search for ADS via Multi-Objective Genetic Algorithm

Haoxin Zong, Zhonglin Hou, Hong Liu

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

Abstract

Simulation testing of Autonomous Driving Systems (ADS) has become prominent, but prevalent techniques often miss bugs due to insufficient cross-layer integration and employ simplistic participant models, leading to a mismatch with real-world complexities and flawed ADS evaluation. The paper presents a Multi-Objective Genetic Algorithm (MOGA)-based method for creating scenarios that lead to safety violations by the ego vehicle. It considers complex conditions with various actor types and behaviors, using Behavior Trees for actor trajectories. The method includes a multi-dimensional metric to optimize MOGA for critical scenarios and reduce irrelevant ones, considering the ego vehicle's performance and the environment. Tests show the method produced 1, 5 5 2 scenarios in 24 hours, identifying 53 that led to 1 0 different safety violations, proving the effectiveness of behavior tree actors in increasing complexity. It also outperforms traditional methods in identifying a wider range of violations faster and triples the occurrence of critical safety scenarios.

Original languageEnglish
Title of host publicationProceedings - 2024 IEEE Smart World Congress, SWC 2024 - 2024 IEEE Ubiquitous Intelligence and Computing, Autonomous and Trusted Computing, Digital Twin, Metaverse, Privacy Computing and Data Security, Scalable Computing and Communications
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1961-1966
Number of pages6
ISBN (Electronic)9798331520861
DOIs
StatePublished - 2024
Event10th IEEE Smart World Congress, SWC 2024 - Nadi, Fiji
Duration: 2 Dec 20247 Dec 2024

Publication series

NameProceedings - 2024 IEEE Smart World Congress, SWC 2024 - 2024 IEEE Ubiquitous Intelligence and Computing, Autonomous and Trusted Computing, Digital Twin, Metaverse, Privacy Computing and Data Security, Scalable Computing and Communications

Conference

Conference10th IEEE Smart World Congress, SWC 2024
Country/TerritoryFiji
CityNadi
Period2/12/247/12/24

Keywords

  • Autonomous Driving System
  • Evolutionary Strategy
  • Multi-Objective Genetic Algorithm
  • Test Scenario Generation

Fingerprint

Dive into the research topics of 'Safety-Violation Scenarios Search for ADS via Multi-Objective Genetic Algorithm'. Together they form a unique fingerprint.

Cite this