AmbieGen at the SBFT 2024 Tool Competition - CPS-UAV Track

Simulation based testing of autonomous systems prior to their deployment in the real world is of big importance. AmbieGen is a tool for automatic generation of virtual test cases for autonomous cyber-physical systems (CPS). In the context of SBFT 2024 CPS-UAV tool competition, we adopted it to the g...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	2024 IEEE/ACM International Workshop on Search-Based and Fuzz Testing (SBFT) S. 69 - 70
Hauptverfasser:	Humeniuk, Dmytro, Khomh, Foutse
Format:	Tagungsbericht
Sprache:	Englisch
Veröffentlicht:	ACM 14.04.2024
Schlagworte:	Autonomous aerial vehicles Autonomous systems Collision avoidance Computing methodologies → Search methodologies Conferences Cyber-physical systems Fuzzing Genetic algorithms Path planning Software Software and its engineering → Software verification and validation Testing
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Beschreibung
Zusammenfassung:	Simulation based testing of autonomous systems prior to their deployment in the real world is of big importance. AmbieGen is a tool for automatic generation of virtual test cases for autonomous cyber-physical systems (CPS). In the context of SBFT 2024 CPS-UAV tool competition, we adopted it to the generation of scenes with obstacles for testing an unmanned aerial vehicle (UAV) obstacle avoidance system. AmbieGen leverages a genetic algorithm guided by a path planner to prioritize test scenarios to be evaluated in the simulation. It could reveal some critical failures in all the 6 use cases considered in the competition.
DOI:	10.1145/3643659.3648552