贝叶斯雷达余弦:直接估计雷达位置识别中的位置不确定性

IF 1.4 4区 管理学 Q3 ENGINEERING, ELECTRICAL & ELECTRONIC
Suyash Agarwal, Jianhao Yuan, Paul Newman, Daniele De Martini, Matthew Gadd
{"title":"贝叶斯雷达余弦:直接估计雷达位置识别中的位置不确定性","authors":"Suyash Agarwal,&nbsp;Jianhao Yuan,&nbsp;Paul Newman,&nbsp;Daniele De Martini,&nbsp;Matthew Gadd","doi":"10.1049/rsn2.70002","DOIUrl":null,"url":null,"abstract":"<p>Trust and explainability in localisation systems can be greatly helped by estimating a calibrated uncertainty. In this work, we argue for the first time that for this, it is best to express uncertainty in the location estimate <i>directly</i> rather than indirectly in the ‘noisiness’ or ambiguity of the data sample. Therefore, in this work, through a robust classification-based model, we not only identify the most probable place but also provide a measure of confidence or uncertainty associated with the prediction of the place itself—in contrast to existing approaches where uncertainty values are produced with the same dimension as the encoded feature. We specifically prove the utility of this new formulation on <i>CosPlace</i>, a state-of-the-art Geolocalisation system. Uncertainty is learnt by transforming <i>Cosplace</i> into an uncertainty-aware neural network. To validate the effectiveness of our approach, we conduct extensive experiments using the <i>Oxford Radar RobotCar Dataset</i>, where we find that the backbone features learnt in the uncertainty-aware setting result in better place recognition performance than vanilla <i>Cosplace</i>. Furthermore, by using it as a score to reject putative localisation results, we show that our uncertainty is well-calibrated to place recognition accuracy—more so than two existing systems in uncertainty-aware radar place recognition.</p>","PeriodicalId":50377,"journal":{"name":"Iet Radar Sonar and Navigation","volume":"19 1","pages":""},"PeriodicalIF":1.4000,"publicationDate":"2025-03-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1049/rsn2.70002","citationCount":"0","resultStr":"{\"title\":\"Bayesian Radar Cosplace: Directly estimating location uncertainty in radar place recognition\",\"authors\":\"Suyash Agarwal,&nbsp;Jianhao Yuan,&nbsp;Paul Newman,&nbsp;Daniele De Martini,&nbsp;Matthew Gadd\",\"doi\":\"10.1049/rsn2.70002\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p>Trust and explainability in localisation systems can be greatly helped by estimating a calibrated uncertainty. In this work, we argue for the first time that for this, it is best to express uncertainty in the location estimate <i>directly</i> rather than indirectly in the ‘noisiness’ or ambiguity of the data sample. Therefore, in this work, through a robust classification-based model, we not only identify the most probable place but also provide a measure of confidence or uncertainty associated with the prediction of the place itself—in contrast to existing approaches where uncertainty values are produced with the same dimension as the encoded feature. We specifically prove the utility of this new formulation on <i>CosPlace</i>, a state-of-the-art Geolocalisation system. Uncertainty is learnt by transforming <i>Cosplace</i> into an uncertainty-aware neural network. To validate the effectiveness of our approach, we conduct extensive experiments using the <i>Oxford Radar RobotCar Dataset</i>, where we find that the backbone features learnt in the uncertainty-aware setting result in better place recognition performance than vanilla <i>Cosplace</i>. Furthermore, by using it as a score to reject putative localisation results, we show that our uncertainty is well-calibrated to place recognition accuracy—more so than two existing systems in uncertainty-aware radar place recognition.</p>\",\"PeriodicalId\":50377,\"journal\":{\"name\":\"Iet Radar Sonar and Navigation\",\"volume\":\"19 1\",\"pages\":\"\"},\"PeriodicalIF\":1.4000,\"publicationDate\":\"2025-03-04\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://onlinelibrary.wiley.com/doi/epdf/10.1049/rsn2.70002\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Iet Radar Sonar and Navigation\",\"FirstCategoryId\":\"94\",\"ListUrlMain\":\"https://onlinelibrary.wiley.com/doi/10.1049/rsn2.70002\",\"RegionNum\":4,\"RegionCategory\":\"管理学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q3\",\"JCRName\":\"ENGINEERING, ELECTRICAL & ELECTRONIC\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Iet Radar Sonar and Navigation","FirstCategoryId":"94","ListUrlMain":"https://onlinelibrary.wiley.com/doi/10.1049/rsn2.70002","RegionNum":4,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"ENGINEERING, ELECTRICAL & ELECTRONIC","Score":null,"Total":0}
引用次数: 0

摘要

通过估算校准的不确定性,可以极大地帮助本地化系统的信任和可解释性。在这项工作中,我们首次提出,最好直接表达位置估计中的不确定性,而不是间接地表达数据样本的“噪声”或模糊性。因此,在这项工作中,通过稳健的基于分类的模型,我们不仅确定了最可能的位置,而且还提供了与位置本身预测相关的置信度或不确定性的度量,这与现有的方法形成了对比,其中不确定性值与编码特征具有相同的维度。我们特别在最先进的地理定位系统CosPlace上证明了这种新配方的实用性。不确定性是通过将Cosplace转换为不确定性感知神经网络来学习的。为了验证我们方法的有效性,我们使用牛津雷达机器人汽车数据集进行了广泛的实验,我们发现在不确定性感知设置中学习的主干特征比香草Cosplace具有更好的位置识别性能。此外,通过使用它作为一个分数来拒绝假定的定位结果,我们表明,我们的不确定性被很好地校准为位置识别精度,比现有的两个不确定性感知雷达位置识别系统更准确。
本文章由计算机程序翻译,如有差异,请以英文原文为准。

Bayesian Radar Cosplace: Directly estimating location uncertainty in radar place recognition

Bayesian Radar Cosplace: Directly estimating location uncertainty in radar place recognition

Trust and explainability in localisation systems can be greatly helped by estimating a calibrated uncertainty. In this work, we argue for the first time that for this, it is best to express uncertainty in the location estimate directly rather than indirectly in the ‘noisiness’ or ambiguity of the data sample. Therefore, in this work, through a robust classification-based model, we not only identify the most probable place but also provide a measure of confidence or uncertainty associated with the prediction of the place itself—in contrast to existing approaches where uncertainty values are produced with the same dimension as the encoded feature. We specifically prove the utility of this new formulation on CosPlace, a state-of-the-art Geolocalisation system. Uncertainty is learnt by transforming Cosplace into an uncertainty-aware neural network. To validate the effectiveness of our approach, we conduct extensive experiments using the Oxford Radar RobotCar Dataset, where we find that the backbone features learnt in the uncertainty-aware setting result in better place recognition performance than vanilla Cosplace. Furthermore, by using it as a score to reject putative localisation results, we show that our uncertainty is well-calibrated to place recognition accuracy—more so than two existing systems in uncertainty-aware radar place recognition.

求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
Iet Radar Sonar and Navigation
Iet Radar Sonar and Navigation 工程技术-电信学
CiteScore
4.10
自引率
11.80%
发文量
137
审稿时长
3.4 months
期刊介绍: IET Radar, Sonar & Navigation covers the theory and practice of systems and signals for radar, sonar, radiolocation, navigation, and surveillance purposes, in aerospace and terrestrial applications. Examples include advances in waveform design, clutter and detection, electronic warfare, adaptive array and superresolution methods, tracking algorithms, synthetic aperture, and target recognition techniques.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信