基于LGSVL/ Apollo的网络延迟攻击下自动驾驶车辆定位估算

doi:10.3969/j.issn.1674-8484.2021.01.006

汽车安全与节能学报 ›› 2021, Vol. 12 ›› Issue (1): 62-69.DOI: 10.3969/j.issn.1674-8484.2021.01.006

基于LGSVL/ Apollo的网络延迟攻击下自动驾驶车辆定位估算

冯敏健¹(), 张辉¹^,^*(), 巨志扬¹, 许庆²

1.北京航空航天大学交通科学与工程学院,北京 100191,中国
2.汽车安全与节能国家重点实验室,清华大学,北京 100084,中国

收稿日期:2021-02-02 出版日期:2021-03-31 发布日期:2021-04-02
通讯作者: 张辉
作者简介:*张辉(1984—),男(汉),江西,教授。E-mail： huizhang285@buaa.edu.cn。
冯敏健(1997—)，男( 汉)，山西，硕士研究生。E-mail: mjfeng444@buaa.edu.cn。
基金资助:
汽车安全与节能国家重点实验室开放基金(KF1806)

Localization estimation algorithm under cyber delay attack for autonomous vehicle based on LGSVL/Apollo

FENG Minjian¹(), ZHANG Hui¹^,^*(), JU Zhiyang¹, XU Qing²

1. School of Transportation Science and Engineering, Beihang University, Beijing 100191, China
2. State Key Lab of Automotive Safety and Energy, Tsinghua University, Beijing 100084, China

Received:2021-02-02 Online:2021-03-31 Published:2021-04-02
Contact: ZHANG Hui

摘要/Abstract

摘要：

为提高网络延迟攻击下自动驾驶车辆定位估计算法的精确度,研究了延迟模型下自动驾驶车辆定位的无偏差有限脉冲响应（UFIR）估计器设计方法, 并仿真实验。搭建延迟攻击下的车辆运动学模型,拓展模型至有限长度的时间窗口,推导UFIR算法按批处理式与迭代式表达形式,分析Apollo系统各功能模块的数据流动,基于LG开源自动驾驶仿真器（LGSVL）与Apollo系统,搭建联合仿真测试平台并开展实验。结果表明：与Kalman滤波器（KF）相比,该算法估计精确度更高;当延迟数据出现较大变化时,算法响应速度更快,波动幅值更小,鲁棒性更强。当数据延迟时间小于等于1 s时,估计效果良好。因而,验证了基于LGSVL与Apollo系统进行自动驾驶仿真实验的可行性。

关键词: 自动驾驶车辆, 定位估算, Apollo系统, LGSVL模拟器, 无偏差有限脉冲响应（UFIR）, 网络攻击, 延迟攻击

Abstract:

An unbiased finite impulse response filter (UFIR) under delay model was proposed to improve the accuracy of autonomous vehicle location estimation algorithm under delayed attack. A vehicle kinematics model under delayed attack was established and extended to a finite length time window. A batch and iterative forms of UFIR algorithms were derived. The embedding position of the algorithm was selected by analyzing the data flow of Apollo functional modules. A co-simulation test platform was built based on LG Silicon Valley Lab (LGSVL) Simulator and Apollo system, and conducted experiments. The results show that compared with the Kalman filter (KF), the algorithm has higher estimation accuracy, faster response speed, smaller fluctuation amplitude, and stronger robustness when the delay data changes greatly. The estimation effect is great when the data delay time is less than or equal to 1 s. Therefore, the result verifies the feasibility of the autonomous driving simulation experiment based on LGSVL and Apollo system.

Key words: autonomous vehicle, location estimation algorithm, Apollo system, LGSVL (LG Silicon Valley Lab) simulator, unbiased finite impulse response (UFIR), cyber-attack, delay attack

中图分类号:

U46
TN92

冯敏健, 张辉, 巨志扬, 许庆. 基于LGSVL/ Apollo的网络延迟攻击下自动驾驶车辆定位估算[J]. 汽车安全与节能学报, 2021, 12(1): 62-69.

FENG Minjian, ZHANG Hui, JU Zhiyang, XU Qing. Localization estimation algorithm under cyber delay attack for autonomous vehicle based on LGSVL/Apollo[J]. Journal of Automotive Safety and Energy, 2021, 12(1): 62-69.

图/表 12

图1 网络攻击场景

图2 仿真研究框架

图3 仿真平台内部结构

图4 Apollo系统结构

图5 实现路径跟踪的模块数据流

采样时间,τ	10 ms
时间窗口长度,N	65 ms
按批式窗口长度,K	4 ms
行驶速度,v	7 m/s
速度波动值,?v	2 m/s
真实定位测量精度,μ	10 mm

表1 仿真实验参数设定

图6 LGSVL模拟器仿真环境

图7 系统规划行驶轨迹

图8 延迟1 s情况下y方向上4种轨迹数据与估计误差

图9 延迟1 s情况下x方向上4种轨迹数据与估计误差

图10 延迟1 s情况下行驶方向变动时轨迹数据

数据延迟时间/ s	平均估计误差/ m
数据延迟时间/ s	KF	UFIR
0.1	0.198	0.155
0.2	0.216	0.180
0.5	0.418	0.328
1.0	1.383	0.747
1.2	1.957	1.027
1.5	14.905	6.952

表2 不同延迟时间下的估计误差

参考文献 22

[1]	LYU Xiaorong, DING Yulong, YANG Shuanghua. Safety and security risk assessment in cyber-physical systems[J]. IET Cyber-Phys Syst: Theory Appl, 2019,4(3):221-232.
[2]	章军辉, 陈大鹏, 李庆. 自动驾驶技术研究现状及发展趋势[J]. 科学技术与工程, 2020,20(9):3394-3403.
	ZHANG Junhui, CHEN Dapeng, LI Qing. Research status and development trend of technologies for autonomous vehicles[J]. Sci Tech Engi, 2020,20(9):3394-3403. (in Chinese)
[3]	Taeihagh A, Lim H S M. Governing autonomous vehicles: emerging responses for safety, liability, privacy, cybersecurity, and industry risks[J]. Transp Rev, 2019,39(1):103-128.
[4]	YAN Chen, XU Wenyuan, LIU Jianhao. Can you trust autonomous vehicles: Contactless attacks against sensors of self-driving vehicle[J]. DEF CON 24, 2016,24(8):22-45.
[5]	Hubaux J P, Capkun S, LUO Jun. The security and privacy of smart vehicles[J]. IEEE Security & Privacy, 2004,2(3):49-55.
[6]	Sinopoli B, Schenato L, Franceschetti M, et al. Kalman filtering with intermittent observations[J]. IEEE Trans Automatic Control, 2004,49(9):1453-1464.
[7]	Singh A K, Date P, Bhaumik S. A modified Bayesian filter for randomly delayed measurements[J]. IEEE Trans Automatic Control, 2016,62(1):419-424.
[8]	Kwon O K, Kwon W H, Lee K S. FIR filters and recursive forms for discrete-time state-space models[J]. Automatica, 1989,25(5):715-728.
[9]	Kwon W H, Kim P S, Han S H. A receding horizon unbiased FIR filter for discrete-time state space models[J]. Automatica, 2002,38(3):545-551. doi: 10.1016/S0005-1098(01)00242-4 URL
[10]	Shmaliy Y S. Linear optimal FIR estimation of discrete time-invariant state-space models[J]. IEEE Trans Signal Processing, 2010,58(6):3086-3096. doi: 10.1109/TSP.2010.2045422 URL
[11]	Shmaliy Y S. Unbiased FIR filtering of discrete-time polynomial state-space models[J]. IEEE Trans Signal Processing, 2008,57(4):1241-1249. doi: 10.1109/TSP.2008.2010640 URL
[12]	Ramirez-Echeverria F, Sarr A, Shmaliy Y S. Optimal memory for discrete-time FIR filters in state-space[J]. IEEE Trans Signal Processing, 2013,62(3):557-561. doi: 10.1109/TSP.2013.2290504 URL
[13]	QUAN Zhonghua, Han S H, Kwon W H. A robust FIR filter for linear discrete-time state-space signal models with uncertainties[J]. IEEE Signal Processing Letters, 2007,14(8):553-556. doi: 10.1109/LSP.2007.891839 URL
[14]	Kwon W H, Han S H. Receding horizon control: model predictive control for state models[M]. London: Springer Science & Business Media, 2005: 83-148.
[15]	Shmaliy Y S, Khan S H, ZHAO Shunyi, et al. General unbiased FIR filter with applications to GPS-based steering of oscillator frequency[J]. IEEE Trans Contr Syst Tech, 2016,25(3):1141-1148. doi: 10.1109/TCST.87 URL
[16]	Shmaliy Y S, Simon D. Iterative unbiased FIR state estimation: a review of algorithms[J]. EURASIP J Adva Signal Processing, 2013,2013(1):1-16.
[17]	余荣杰, 田野, 孙剑. 高等级自动驾驶汽车虚拟测试: 研究进展与前沿[J]. 中国公路学报, 2020,33(11):125-138.
	YU Rongjie, TIAN Ye, SUN Jian. Highly automated vehicle virtual testing: A review of recent developments and research frontiers[J]. Chin J Highway Transport, 2020,33(11):125-138. (in Chinese)
[18]	孙勇义. Apollo自动驾驶技术与安全设计[J]. 人工智能, 2018(6):48-58.
	SUN Yongyi. Apollo autonomous driving technology and safety design[J]. AI-View, 2018(6):48-58. (in Chinese)
[19]	Kalman R E. A new approach to linear filtering and prediction problems[J]. Trans ASME, J Basic Engineering, 1960,82:35-45. doi: 10.1115/1.3662552 URL
[20]	杨丹. 卡尔曼滤波器设计及其应用研究[D]. 长沙: 湘潭大学, 2014.
	YANG Dan. A research on design and application of Kalman filter[D]. Changsha: Xiangtan University, 2014. (in Chinese)
[21]	Simon D. Optimal state estimation: Kalman, H infinity, and nonlinear approaches[M]. Hoboken: John Wiley & Sons, 2006: 123-129.
[22]	Shmaliy Y S. An iterative Kalman-like algorithm ignoring noise and initial conditions[J]. IEEE Trans Signal Processing, 2011,59(6):2465-2473. doi: 10.1109/TSP.2011.2129516 URL

基于LGSVL/ Apollo的网络延迟攻击下自动驾驶车辆定位估算

Localization estimation algorithm under cyber delay attack for autonomous vehicle based on LGSVL/Apollo

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

图/表 12

参考文献 22

相关文章 5

编辑推荐

Metrics

本文评价

期刊信息

在线期刊

作者中心

审稿中心

联系我们

[1]	张平、迟志诚、陈一凡、惠飞. 用于自动驾驶车辆的融合注意力机制多目标跟踪算法[J]. 汽车安全与节能学报, 2021, 12(4): 516-521.
[2]	李耀华、范吉康、刘洋、何杰、李泽田、潘绍飞. 自适应双时域参数MPC的智能车辆路径规划与跟踪控制[J]. 汽车安全与节能学报, 2021, 12(4): 528-539.
[3]	张晨阳，李曙光，李耀华，姚进,祝磊，王敏. 基于驾驶模拟器和 fNIRS 的与晕动病相关脑活动区的差异性[J]. JASE, 2019, 10(4): 433-442.
[4]	戴荣健，丁川，鹿应荣，赵福全. 自动驾驶环境下车辆轨迹及交通信号协同控制[J]. JASE, 2019, 10(4): 531-539.
[5]	王乐一，殷刚，赵广亮，李升波，徐彪，李克强. 自动驾驶汽车控制系统参数辨识与学习（英文）[J]. JASE, 2018, 9(2): 141-148.