Evaluation of false alarm alarms in truck FCW based on calibration of RSS model under different driving scenarios

IF 4.3 Q2 TRANSPORTATION
{"title":"Evaluation of false alarm alarms in truck FCW based on calibration of RSS model under different driving scenarios","authors":"","doi":"10.1016/j.ijtst.2023.07.001","DOIUrl":null,"url":null,"abstract":"<div><div>Advanced driver-assistance systems (ADASs), such as forward collision warning (FCW), are widely used and, in some countries, have been made mandatory for commercial vehicles. In practical applications, however, FCW systems produce many false alarms. Using scenario and driving behavior data collected from naturalistic driving study data of trucks, a variable threshold evaluation method was proposed to determine the factors correlating with false alarms. A total of 450 collision avoidance events were divided based on driving characteristics into three groups with <em>k</em>-means clustering. Responsibility-sensitive safety (RSS) model’s parameters were calibrated with the driving behavior characteristics and scenarios to evaluate the truck FCW system’s alarm accuracy. The evaluation of the results of truck FCW system based on RSS model found 47 false alarm alarms in the 450 events, a false alarm rate of 11.19%. When the following distance was close (&lt;7 m) or far (&gt;20 m), the false alarm rate reached more than 30%. The minimum time to collision (TTC) in the close distance driving clusters (DCs) (5.81 s) was lower than that in long distance DCs (7.68 s and 9.46 s). Braking force in the low-speed DCs (deceleration at −0.16 g and −0.55 g) was lower than in high-speeded DC (deceleration = −1.21 g). The FCW system does not conform to the driver's reaction time and braking characteristics in different scenarios, and is the main reason for false alarms. This is more obviously reflected in low-speed short distance and high-speed long-distance scenarios.</div></div>","PeriodicalId":52282,"journal":{"name":"International Journal of Transportation Science and Technology","volume":null,"pages":null},"PeriodicalIF":4.3000,"publicationDate":"2024-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"International Journal of Transportation Science and Technology","FirstCategoryId":"1085","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S2046043023000655","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"TRANSPORTATION","Score":null,"Total":0}
引用次数: 0

Abstract

Advanced driver-assistance systems (ADASs), such as forward collision warning (FCW), are widely used and, in some countries, have been made mandatory for commercial vehicles. In practical applications, however, FCW systems produce many false alarms. Using scenario and driving behavior data collected from naturalistic driving study data of trucks, a variable threshold evaluation method was proposed to determine the factors correlating with false alarms. A total of 450 collision avoidance events were divided based on driving characteristics into three groups with k-means clustering. Responsibility-sensitive safety (RSS) model’s parameters were calibrated with the driving behavior characteristics and scenarios to evaluate the truck FCW system’s alarm accuracy. The evaluation of the results of truck FCW system based on RSS model found 47 false alarm alarms in the 450 events, a false alarm rate of 11.19%. When the following distance was close (<7 m) or far (>20 m), the false alarm rate reached more than 30%. The minimum time to collision (TTC) in the close distance driving clusters (DCs) (5.81 s) was lower than that in long distance DCs (7.68 s and 9.46 s). Braking force in the low-speed DCs (deceleration at −0.16 g and −0.55 g) was lower than in high-speeded DC (deceleration = −1.21 g). The FCW system does not conform to the driver's reaction time and braking characteristics in different scenarios, and is the main reason for false alarms. This is more obviously reflected in low-speed short distance and high-speed long-distance scenarios.
基于不同驾驶场景下 RSS 模型校准的卡车 FCW 误报警报评估
先进驾驶辅助系统(ADAS),如前撞预警(FCW),已得到广泛应用,在一些国家,商用车辆已强制使用该系统。然而,在实际应用中,FCW 系统会产生许多误报。利用从卡车自然驾驶研究数据中收集的场景和驾驶行为数据,提出了一种可变阈值评估方法,以确定与误报相关的因素。通过 k-means 聚类,根据驾驶特征将总共 450 个避免碰撞事件分为三组。根据驾驶行为特征和场景对责任敏感安全(RSS)模型的参数进行校准,以评估卡车 FCW 系统的报警准确性。基于 RSS 模型的卡车 FCW 系统结果评估发现,在 450 个事件中有 47 个误报,误报率为 11.19%。当跟车距离较近(7 米)或较远(20 米)时,误报率达到 30% 以上。近距离驾驶集群(DCs)的最小碰撞时间(TTC)(5.81 秒)低于远距离驾驶集群(DCs)的最小碰撞时间(7.68 秒和 9.46 秒)。低速行驶集群的制动力(减速度为-0.16 g和-0.55 g)低于高速行驶集群(减速度=-1.21 g)。FCW 系统不符合驾驶员在不同情况下的反应时间和制动特性,是造成误报的主要原因。这一点在低速短距离和高速长距离场景中体现得更为明显。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
International Journal of Transportation Science and Technology
International Journal of Transportation Science and Technology Engineering-Civil and Structural Engineering
CiteScore
7.20
自引率
0.00%
发文量
105
审稿时长
88 days
×
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:481959085
Book学术官方微信