An Agency-Directed Approach to Test Generation for Simulation-based Autonomous Vehicle Verification

Greg Chance, Abanoub Ghobrial, Severin Lemaignan, Tony Pipe, Kerstin I Eder

Research output: Contribution to conferenceConference Paperpeer-review

128 Downloads (Pure)


Simulation-based verification is beneficial for assessing otherwise dangerous or costly on-road testing of autonomous vehicles (AV). This paper addresses the challenge of efficiently generating effective tests for simulation-based AV verification using software testing agents. The multi-agent system (MAS) programming paradigm offers rational agency, causality and strategic planning between multiple agents. We exploit these aspects for test generation, focusing in particular on the generation of tests that trigger the precondition of an assertion. On the example of a key assertion we show that, by encoding a variety of different behaviours respondent to the agent’s perceptions of the test environment, the agency-directed approach generates twice as many effective tests than pseudo-random test generation, while being both efficient and robust. Moreover, agents can be encoded to behave naturally without compromising the effectiveness of test generation. Our results suggest that generating tests using agency-directed testing significantly improves upon random and simultaneously provides more realistic driving scenarios.
Original languageEnglish
Number of pages8
Publication statusPublished - 16 Apr 2020
EventAITEST 2020 - Oxford University, Oxford, United Kingdom
Duration: 13 Apr 202016 Apr 2020


ConferenceAITEST 2020
Country/TerritoryUnited Kingdom


  • Test Generation
  • Simulation
  • Autonomous Driving
  • Verification
  • Multi-Agent System
  • Test Agent


Dive into the research topics of 'An Agency-Directed Approach to Test Generation for Simulation-based Autonomous Vehicle Verification'. Together they form a unique fingerprint.

Cite this