There is a lack of approaches to derive accident scenarios automatically for the testing of Autonomous Drive systems. Current approaches that generate test scenarios do not scale due to the manual work required. Machine learning provides the possibility to automate such tasks. In this paper, an automated approach based on Recurrent Neural Networks to generate accident scenarios is presented. Based on a prototype, our approach is evaluated on temporal data from simulated in-vehicle and V2X data to automatically generate new accident scenarios. The results confirm that generated scenarios resemble the accidents that took place in an exclusive test set.
Accident Scenario Generation with Recurrent Neural Networks
01.11.2018
1291068 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Accident Scenario Generation using Driver Behavior Model
IEEE | 2024
|Kraftfahrwesen | 2005
|Hazard/Accident Scenario Evaluation Criteria
British Library Conference Proceedings | 2006
|Hazard/Accident Scenario Evaluation Criteria
British Library Conference Proceedings | 2002
|Traffic accident severity prediction method based on recurrent neural network
Europäisches Patentamt | 2024
|