Addressing the IEEE AV Test Challenge with Scenic and VerifAI

Kesav Viswanadha, Francis Indaheng, Justin Wong, Edward Kim, Ellen Kalvan, Yash Pant, Daniel J. Fremont, and Sanjit A. Seshia. Addressing the IEEE AV Test Challenge with Scenic and VerifAI. In IEEE International Conference on Artificial Intelligence Testing (AITest), pp. 136–142, IEEE, 2021.

Download

[HTML] 

Abstract

This paper summarizes our formal approach to testing autonomous vehicles (AVs) in simulation for the IEEE AV Test Challenge. We demonstrate a systematic testing framework leveraging our previous work on formally-driven simulation for intelligent cyber-physical systems. First, to model and generate interactive scenarios involving multiple agents, we used Scenic, a probabilistic programming language for specifying scenarios. A Scenic program defines an abstract scenario as a distribution over configurations of physical objects and their behaviors over time. Sampling from an abstract scenario yields many different concrete scenarios which can be run as test cases for the AV. Starting from a Scenic program encoding an abstract driving scenario, we can use the Verifai toolkit to search within the scenario for failure cases with respect to multiple AV evaluation metrics. We demonstrate the effectiveness of our testing framework by identifying concrete failure scenarios for an open-source autopilot, Apollo, starting from a variety of realistic traffic scenarios.

BibTeX

@inproceedings{viswanadha-aitest21,
  author    = {Kesav Viswanadha and
               Francis Indaheng and
               Justin Wong and
               Edward Kim and
               Ellen Kalvan and
               Yash Pant and
               Daniel J. Fremont and
               Sanjit A. Seshia},
  title     = {Addressing the {IEEE} {AV} Test Challenge with Scenic and VerifAI},
  booktitle = {{IEEE} International Conference on Artificial Intelligence Testing (AITest)},
  pages     = {136--142},
  publisher = {{IEEE}},
  year      = {2021},
  abstract  = {This paper summarizes our formal approach to testing autonomous vehicles (AVs) in simulation for the IEEE AV Test Challenge. We demonstrate a systematic testing framework leveraging our previous work on formally-driven simulation for intelligent cyber-physical systems. First, to model and generate interactive scenarios involving multiple agents, we used Scenic, a probabilistic programming language for specifying scenarios. A Scenic program defines an abstract scenario as a distribution over configurations of physical objects and their behaviors over time. Sampling from an abstract scenario yields many different concrete scenarios which can be run as test cases for the AV. Starting from a Scenic program encoding an abstract driving scenario, we can use the Verifai toolkit to search within the scenario for failure cases with respect to multiple AV evaluation metrics. We demonstrate the effectiveness of our testing framework by identifying concrete failure scenarios for an open-source autopilot, Apollo, starting from a variety of realistic traffic scenarios.},
}