ML-based Fault Injection for Autonomous Vehicles: A Case for Bayesian Fault Injection

Saurabh Jha, Subho S. Banerjee, Timothy Tsai, Siva K. S. Hari, Michael B. Sullivan, Zbigniew T. Kalbarczyk, Stephen W. Keckler, and Ravishankar K. Iyer

DSN 2019


The safety and resilience of fully autonomous vehicles (AVs) is of significant concern, as exemplified by several headline making accidents. While AV development today inherently involves verification, validation and testing, end-to-end assessment of AV systems under accidental faults in realistic driving scenarios is largely unexplored. This paper presents DriveFI, a machine learning-based fault injection engine, which can mine situations and faults that maximally impact AV safety, demonstrated on two industry-grade AV technology stacks (from NVIDIA and Baidu). For example, DriveFI finds 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.

In the News


  author={S. {Jha} and S. {Banerjee} and T. {Tsai} and S. K. S. {Hari} and M. B. {Sullivan} and Z. T. {Kalbarczyk} and S. W. {Keckler} and R. K. {Iyer}},
  booktitle={2019 49th Annual IEEE/IFIP International Conference on Dependable Systems and Networks (DSN)},
  title={ML-Based Fault Injection for Autonomous Vehicles: A Case for Bayesian Fault Injection},
  keywords={Autonomous Vehicles;Fault Injection;Machine Learning},

Related Projects

  • Powered by Hugo
  • Last updated 10/21/2021
  • Feed