Combining Runtime Monitoring and Machine Learning with Human Feedback
DOI:
https://doi.org/10.1609/aaai.v37i13.26815Keywords:
New Faculty HighlightsAbstract
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.Downloads
Published
2023-09-06
How to Cite
Lukina, A. (2023). Combining Runtime Monitoring and Machine Learning with Human Feedback. Proceedings of the AAAI Conference on Artificial Intelligence, 37(13), 15448-15448. https://doi.org/10.1609/aaai.v37i13.26815
Issue
Section
New Faculty Highlights