Safety Monitoring for Learning-Enabled Cyber-Physical Systems in Out-of-Distribution Scenarios

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Lin, Vivian, Kaur, Ramneet, Yang, Yahan, Dutta, Souradeep, Kantaros, Yiannis, Roy, Anirban, Jha, Susmit, Sokolsky, Oleg, Lee, Insup
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866910913994424320
author Lin, Vivian
Kaur, Ramneet
Yang, Yahan
Dutta, Souradeep
Kantaros, Yiannis
Roy, Anirban
Jha, Susmit
Sokolsky, Oleg
Lee, Insup
author_facet Lin, Vivian
Kaur, Ramneet
Yang, Yahan
Dutta, Souradeep
Kantaros, Yiannis
Roy, Anirban
Jha, Susmit
Sokolsky, Oleg
Lee, Insup
contents The safety of learning-enabled cyber-physical systems is compromised by the well-known vulnerabilities of deep neural networks to out-of-distribution (OOD) inputs. Existing literature has sought to monitor the safety of such systems by detecting OOD data. However, such approaches have limited utility, as the presence of an OOD input does not necessarily imply the violation of a desired safety property. We instead propose to directly monitor safety in a manner that is itself robust to OOD data. To this end, we predict violations of signal temporal logic safety specifications based on predicted future trajectories. Our safety monitor additionally uses a novel combination of adaptive conformal prediction and incremental learning. The former obtains probabilistic prediction guarantees even on OOD data, and the latter prevents overly conservative predictions. We evaluate the efficacy of the proposed approach in two case studies on safety monitoring: 1) predicting collisions of an F1Tenth car with static obstacles, and 2) predicting collisions of a race car with multiple dynamic obstacles. We find that adaptive conformal prediction obtains theoretical guarantees where other uncertainty quantification methods fail to do so. Additionally, combining adaptive conformal prediction and incremental learning for safety monitoring achieves high recall and timeliness while reducing loss in precision. We achieve these results even in OOD settings and outperform alternative methods.
format Preprint
id arxiv_https___arxiv_org_abs_2504_13478
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Safety Monitoring for Learning-Enabled Cyber-Physical Systems in Out-of-Distribution Scenarios
Lin, Vivian
Kaur, Ramneet
Yang, Yahan
Dutta, Souradeep
Kantaros, Yiannis
Roy, Anirban
Jha, Susmit
Sokolsky, Oleg
Lee, Insup
Machine Learning
The safety of learning-enabled cyber-physical systems is compromised by the well-known vulnerabilities of deep neural networks to out-of-distribution (OOD) inputs. Existing literature has sought to monitor the safety of such systems by detecting OOD data. However, such approaches have limited utility, as the presence of an OOD input does not necessarily imply the violation of a desired safety property. We instead propose to directly monitor safety in a manner that is itself robust to OOD data. To this end, we predict violations of signal temporal logic safety specifications based on predicted future trajectories. Our safety monitor additionally uses a novel combination of adaptive conformal prediction and incremental learning. The former obtains probabilistic prediction guarantees even on OOD data, and the latter prevents overly conservative predictions. We evaluate the efficacy of the proposed approach in two case studies on safety monitoring: 1) predicting collisions of an F1Tenth car with static obstacles, and 2) predicting collisions of a race car with multiple dynamic obstacles. We find that adaptive conformal prediction obtains theoretical guarantees where other uncertainty quantification methods fail to do so. Additionally, combining adaptive conformal prediction and incremental learning for safety monitoring achieves high recall and timeliness while reducing loss in precision. We achieve these results even in OOD settings and outperform alternative methods.
title Safety Monitoring for Learning-Enabled Cyber-Physical Systems in Out-of-Distribution Scenarios
topic Machine Learning
url https://arxiv.org/abs/2504.13478