Combining Runtime Monitoring and Machine Learning with Human Feedback

Conference Paper (2023)
Author(s)

A. Lukina (TU Delft - Algorithmics)

Research Group
Algorithmics
Copyright
© 2023 A. Lukina
DOI related publication
https://doi.org/10.1609/aaai.v37i13.26815
More Info
expand_more
Publication Year
2023
Language
English
Copyright
© 2023 A. Lukina
Research Group
Algorithmics
Pages (from-to)
15448-15448
ISBN (electronic)
9781577358800
Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Abstract

State-of-the-art machine-learned controllers for autonomous systems demonstrate unbeatable performance in scenarios known from training. However, in evolving environments-changing weather or unexpected anomalies-, safety and interpretability remain the greatest challenges for autonomous systems to be reliable and are the urgent scientific challenges. Existing machine-learning approaches focus on recovering lost performance but leave the system open to potential safety violations. Formal methods address this problem by rigorously analysing a smaller representation of the system but they rarely prioritize performance of the controller. We propose to combine insights from formal verification and runtime monitoring with interpretable machine-learning design for guaranteeing reliability of autonomous systems.

Files

26815_Article_Text_30878_1_2_2... (pdf)
(pdf | 0.2 Mb)
- Embargo expired in 05-02-2024
License info not available