Driver anomaly quantification for intelligent vehicles: a contrastive learning approach with representation clustering

Simple item page
dc.contributor.authorHu, Zhongxu
dc.contributor.authorXing, Yang
dc.contributor.authorGu, Weihao
dc.contributor.authorCao, Dongpu
dc.contributor.authorLv, Chen
dc.date.accessioned2022-04-08T12:50:39Z
dc.date.available2022-04-08T12:50:39Z
dc.date.issued2022-03-30
dc.description.abstractDriver anomaly quantification is a fundamental capability to support human-centric driving systems of intelligent vehicles. Existing studies usually treat it as a classification task and obtain discrete levels for abnormalities. Meanwhile, the existing data-driven approaches depend on the quality of dataset and provide limited recognition capability for unknown activities. To overcome these challenges, this paper proposes a contrastive learning approach with the aim of building a model that can quantify driver anomalies with a continuous variable. In addition, a novel clustering supervised contrastive loss is proposed to optimize the distribution of the extracted representation vectors to improve the model performance. Compared with the typical contrastive loss, the proposed loss can better cluster normal representations while separating abnormal ones. The abnormality of driver activity can be quantified by calculating the distance to a set of representations of normal activities rather than being produced as the direct output of the model. The experiment results with datasets under different modes demonstrate that the proposed approach is more accurate and robust than existing ones in terms of recognition and quantification of unknown abnormal activities.en_UK
dc.identifier.citationHu Z, Xing Y, Gu W, et al., (2023) Driver anomaly quantification for intelligent vehicles: a contrastive learning approach with representation clustering. IEEE Transactions on Intelligent Vehicles, Volume 8, Issue 1, January 2023, pp. 37-47en_UK
dc.identifier.issn2379-8858
dc.identifier.urihttps://doi.org/10.1109/TIV.2022.3163458
dc.identifier.urihttps://dspace.lib.cranfield.ac.uk/handle/1826/17756
dc.language.isoenen_UK
dc.publisherIEEEen_UK
dc.rightsAttribution-NonCommercial 4.0 International*
dc.rights.urihttp://creativecommons.org/licenses/by-nc/4.0/*
dc.subjectDriver anomalyen_UK
dc.subjectonline quantificationen_UK
dc.subjectcontinuous variableen_UK
dc.subjectcontrastive learningen_UK
dc.subjectrepresentation clusteringen_UK
dc.titleDriver anomaly quantification for intelligent vehicles: a contrastive learning approach with representation clusteringen_UK
dc.typeArticleen_UK

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Driver_anomaly_quantification_for_intelligent_vehicles-2022.pdf
Size:
2.45 MB
Format:
Adobe Portable Document Format
Description:
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.63 KB
Format:
Item-specific license agreed upon to submission
Description:
Download

Collections

Staff publications (SATM)