Title | ||
---|---|---|
ML-Based Fault Injection for Autonomous Vehicles: A Case for Bayesian Fault Injection |
Abstract | ||
---|---|---|
The safety and resilience of fully autonomous vehicles (AVs) are of significant concern, as exemplified by several headline-making accidents. While AV development today involves verification, validation, and testing, end-to-end assessment of AV systems under accidental faults in realistic driving scenarios has been largely unexplored. This paper presents DriveFI, a machine learning-based fault injection engine, which can mine situations and faults that maximally impact AV safety, as demonstrated on two industry-grade AV technology stacks (from NVIDIA and Baidu). For example, DriveFI found 561 safety-critical faults in less than 4 hours. In comparison, random injection experiments executed over several weeks could not find any safety-critical faults. |
Year | DOI | Venue |
---|---|---|
2019 | 10.1109/DSN.2019.00025 | 2019 49th Annual IEEE/IFIP International Conference on Dependable Systems and Networks (DSN) |
Keywords | DocType | ISSN |
Autonomous Vehicles,Fault Injection,Machine Learning | Conference | 1530-0889 |
ISBN | Citations | PageRank |
978-1-7281-0058-6 | 9 | 0.54 |
References | Authors | |
9 | 8 |
Name | Order | Citations | PageRank |
---|---|---|---|
Saurabh Jha | 1 | 13 | 2.61 |
Subho S. Banerjee | 2 | 26 | 6.88 |
Timothy K. Tsai | 3 | 647 | 56.27 |
S. K. S. Hari | 4 | 384 | 20.20 |
Michael Sullivan | 5 | 313 | 18.05 |
Zbigniew Kalbarczyk | 6 | 1896 | 159.48 |
Stephen W. Keckler | 7 | 3404 | 201.71 |
Ravishankar K. Iyer | 8 | 3489 | 504.32 |