Păsăreanu, Corina S., Mangal, Ravi, Gopinath, Divya et al. (3 more authors) (2023) Closed-loop Analysis of Vision-based Autonomous Systems:A Case Study. In: Enea, C. and Lal, A., (eds.) Computer Aided Verification. CAV 2023. Lecture Notes in Computer Science . Springer , pp. 289-303.
Abstract
Deep neural networks (DNNs) are increasingly used in safety-critical autonomous systems as perception components processing high-dimensional image data. Formal analysis of these systems is particularly challenging due to the complexity of the perception DNNs, the sensors (cameras), and the environment conditions. We present a case study applying formal probabilistic analysis techniques to an experimental autonomous system that guides airplanes on taxiways using a perception DNN. We address the above challenges by replacing the camera and the network with a compact probabilistic abstraction built from the confusion matrices computed for the DNN on a representative image data set. We also show how to leverage local, DNN-specific analyses as run-time guards to increase the safety of the overall system. Our findings are applicable to other autonomous systems that use complex DNNs for perception.
Metadata
Item Type: | Proceedings Paper |
---|---|
Authors/Creators: |
|
Editors: |
|
Copyright, Publisher and Additional Information: | © The Author(s) 2023 |
Dates: |
|
Institution: | The University of York |
Academic Units: | The University of York > Faculty of Sciences (York) > Computer Science (York) |
Depositing User: | Pure (York) |
Date Deposited: | 21 Jul 2023 13:30 |
Last Modified: | 23 Nov 2024 00:19 |
Published Version: | https://doi.org/10.1007/978-3-031-37706-8_15 |
Status: | Published |
Publisher: | Springer |
Series Name: | Lecture Notes in Computer Science |
Identification Number: | 10.1007/978-3-031-37706-8_15 |
Open Archives Initiative ID (OAI ID): | oai:eprints.whiterose.ac.uk:201797 |
Download
Filename: 978_3_031_37706_8_15.pdf
Description: Closed-Loop Analysis of Vision-Based Autonomous Systems: A Case Study
Licence: CC-BY 2.5