License: 
Creative Commons Attribution 3.0 Unported license (CC BY 3.0)
When quoting this document, please refer to the following
DOI: 10.4230/LIPIcs.ECRTS.2020.7
URN: urn:nbn:de:0030-drops-123704
URL: http://dagstuhl.sunsite.rwth-aachen.de/volltexte/2020/12370/
Agrawal, Kunal ;
Baruah, Sanjoy ;
Burns, Alan
The Safe and Effective Use of Learning-Enabled Components in Safety-Critical Systems
Abstract
Autonomous systems increasingly use components that incorporate machine learning and other AI-based techniques in order to achieve improved performance. The problem of assuring correctness in safety-critical systems that use such components is considered. A model is proposed in which components are characterized according to both their worst-case and their typical behaviors; it is argued that while safety must be assured under all circumstances, it is reasonable to be concerned with providing a high degree of performance for typical behaviors only. The problem of assuring safety while providing such improved performance is formulated as an optimization problem in which performance under typical circumstances is the objective function to be optimized while safety is a hard constraint that must be satisfied. Algorithmic techniques are applied to derive an optimal solution to this optimization problem. This optimal solution is compared with an alternative approach that optimizes for performance under worst-case conditions, as well as some common-sense heuristics, via simulation experiments on synthetically-generated workloads.
BibTeX - Entry
@InProceedings{agrawal_et_al:LIPIcs:2020:12370,
author = {Kunal Agrawal and Sanjoy Baruah and Alan Burns},
title = {{The Safe and Effective Use of Learning-Enabled Components in Safety-Critical Systems}},
booktitle = {32nd Euromicro Conference on Real-Time Systems (ECRTS 2020)},
pages = {7:1--7:20},
series = {Leibniz International Proceedings in Informatics (LIPIcs)},
ISBN = {978-3-95977-152-8},
ISSN = {1868-8969},
year = {2020},
volume = {165},
editor = {Marcus V{\"o}lp},
publisher = {Schloss Dagstuhl--Leibniz-Zentrum f{\"u}r Informatik},
address = {Dagstuhl, Germany},
URL = {https://drops.dagstuhl.de/opus/volltexte/2020/12370},
URN = {urn:nbn:de:0030-drops-123704},
doi = {10.4230/LIPIcs.ECRTS.2020.7},
annote = {Keywords: Learning-enabled components (LECs), Safety-critical systems, Typical analysis, Performance optimization, Run-time monitoring}
}
|
Keywords: |
|
Learning-enabled components (LECs), Safety-critical systems, Typical analysis, Performance optimization, Run-time monitoring |
|
Collection: |
|
32nd Euromicro Conference on Real-Time Systems (ECRTS 2020) |
|
Issue Date: |
|
2020 |
|
Date of publication: |
|
30.06.2020 |
