A Method of Road Data Aided Inertial Navigation by Using Learning to Rank and ICCP Algorithm

doi:10.11947/j.JGGS.2021.0407

Abstract

Abstract:

As an independent navigation method, inertial navigation system(INS) has played a huge advantage in a lot of special conditions. But its positioning error will accumulate with time, so it is difficult to work independently for a long time. The vehicle loaded with the inertial navigation system usually drives on the road, so the high precision road data based on geographic information system(GIS) can be used as a bind of auxiliary information, which could correct INS errors by the correlation matching algorithm. The existing road matching methods rely on mathematical models, mostly for global positioning system(GPS) trajectory data, and are limited to model parameters. Therefore, based on the features of inertial navigation trajectory and road, this paper proposes a road data aided vehicle inertial navigation method based on the learning to rank and iterative closest contour point(ICCP) algorithm. Firstly, according to the geometric and directional features of inertial navigation trajectory and road, the combined feature vector is constructed as the input value; Furthermore, the scoring function and RankNet neural network based on the features of vehicle trajectory data and road data are constructed, which can learn and extract the features; Then, the nearest point of each track point and its corresponding road data set to be matched is calculated. The average translation between the two data sets is calculated by using the position relationship between each group of track points to be matched and road points; Finally, the trajectory data set is iteratively translated according to the translation amount, and the matching track point set is obtained when the trajectory error converges to complete the matching. During experiments, it is compared with other algorithms including the hidden Markov model(HMM) matching method. The experimental results show that the algorithm can effectively suppress the divergence of trajectory error. The matching accuracy is close to HMM algorithm, and the computational efficiency can meet the requirements of the traditional matching algorithm.

Key words: ICCP algorithm; vehicle trajectory data; features; road matching; pairwise learning

Xiang LI,Yixin HUA,Wenbing LIU. A Method of Road Data Aided Inertial Navigation by Using Learning to Rank and ICCP Algorithm[J]. Journal of Geodesy and Geoinformation Science, 2021, 4(4): 84-96.

Figures/Tables 13

Fig.1

Fig.2

Fig.3

Fig.4

Fig.5

Fig.6

Fig.7

Fig.8

Fig.9

Fig.10

Fig.11

Tab.1

Fig.12

References 31

[1]	LI Xiang. Research on technology and method of vector road data aided inertial navigation[J]. Acta Geodaetica et Cartographica Sinica, 2018, 47(5):692. DOI: 10.11947/j.AGCS.2018.20170454. doi: 10.11947/j.AGCS.2018.20170454
[2]	LI Bowen, YAO Danya. Low-cost MEMS IMU navigation positioning method for land vehicle[J]. Journal of Chinese Inertial Technology, 2014, 22(6):719-723.
[3]	ZHOU Jingmei, ZHAO Xiangmo, CHENG Xin, et al. Vehicle ego-localization based on streetscape image database under blind area of global positioning system[J]. Journal of Shanghai Jiaotong University(Science), 2019, 24(1):122-129.
[4]	GUO Li, LI Hongwei, ZHANG Zejian, et al. Geometry matching method for transportation road network data based on projection[J]. Geomatics and Information Science of Wuhan University, 2013, 38(9):1113-1117.
[5]	MOHAMED R, ALY H, YOUSSEF M. Accurate real-time map matching for challenging environments[J]. IEEE Transactions on Intelligent Transportation Systems, 2017, 18(4):847-857. doi: 10.1109/TITS.2016.2591958
[6]	LUO Hao, DENG Zhihong, FU Mengyin, et al. A map matching algorithm for inertial navigation systems based on the adaptive projection method[C]// Proceedings of the Seventh International Symposium on Computational Intelligence and Design. Hangzhou, China:IEEE, 2014.
[7]	AI Guo. Map-matching aided RLG inertial navigation system with curve matching[J]. Optics & Optoelectronic Technology, 2018, 16(4):92-98.
[8]	IMPRIALOU M I M, QUDDUS M, PITFIELD D E. High accuracy crash mapping using fuzzy logic[J]. Transportation Research Part C: Emerging Technologies, 2014, 42:107-120. doi: 10.1016/j.trc.2014.03.002
[9]	CHE Mingliang, WANG Yingli, ZHANG Chi, et al. An enhanced hidden Markov map matching model for floating car data[J]. Sensors, 2018, 18(6):1758. doi: 10.3390/s18061758
[10]	ZHAO Dongbao, LIU Xueme, GUO Li. Real time map matching algorithm of floating car in support of spatial grid index[J]. Journal of Computer-Aided Design & Computer Graphics, 2014, 26(9):1550-1556.
[11]	ZHANG Shuyou, GU Ye, YI Guodong, et al. A knowledge matching approach based on multi-classification radial basis function neural network for knowledge push system[J]. Frontiers of Information Technology & Electronic Engineering, 2020, 21(7):981-994.
[12]	GUO Ningning, SHENG Yehua, LV Haiyang, et al. Automated matching road networks utilized RBF neural network[J]. Science of Surveying and Mapping, 2018, 43(3):45-50.
[13]	LU Jiapin, LUO Yuetong, HUANG Zhaosong, et al. An information fusion map matching method based on ranking learning[J]. Journal of Zhejiang University (Science Edition), 2020, 47(1):27-35, 66.
[14]	KAMGAR-PARSIB, KAMGAR-PARSIB. Vehicle localization on gravity maps[C]// Proceedings of SPIE 3693. Orlando FL: SPIE, 1999: 182-191.
[15]	LIU Fanming, SUN Feng, CHENG Yi. Gravity localization based on ICCP algorithm and its generalization[J]. Journal of Chinese Inertial Technology, 2004, 12(5):36-39.
[16]	WANG Zhigang, BIAN Shaofeng. ICCP algorithm for gravity aided inertial navigation[J]. Acta Geodaetica et Cartographica Sinica, 2008, 37(2):147-151, 157.
[17]	YAN Li, CUI Chenfeng, XIE Hong. The application of ICCP algorithm to gravity matching[J]. Remote Sensing Information, 2009(1):16-19.
[18]	XIAO Jing, DUAN Xiusheng, QI Xiaohui, et al. An improved ICCP matching algorithm for use in an interference environment during geomagnetic navigation[J]. TheJournal of Navigation, 2020, 73(1):56-74.
[19]	SONG Zhongguo, ZHANG Jinsheng, ZHU Wenqi, et al. The vector matching method in geomagnetic aiding navigation[J]. Sensors, 2016, 16(7):1120. doi: 10.3390/s16071120
[20]	LIU Rui, ZHANG Jiangshui, LI Xiang. The research on the improvement of ICCP algorithm for the route-matching of initial navigation vehicles in road network[J]. Journal of Geomatics Science and Technology, 2016, 33(1):82-87.
[21]	LI Xiang. Research and implementation on aided inertial navigation positioning algorithm based on road networks feature[D]. Zhengzhou: Information Engineering University, 2013.
[22]	SOBREIRA H, COSTA C M, SOUSA I, et al. Map-matching algorithms for robot self-localization: a comparison between perfect match, iterative closest point and normal distributions transform[J]. Journal of Intelligent & Robotic Systems, 2019, 93(3):533-546.
[23]	LIU Fei, BALAZADEGAN Y, GAO Yang. Tight integration of INS/Stereo VO/Digital map for land vehicle navigation[J]. Photogrammetric Engineering & Remote Sensing, 2018, 84(1):15-23.
[24]	WANG Xianglei, SU Mudan, LIU Peigen, et al. Application of improved ICCP algorithm in gravity matching aided navigation[J]. Science of Surveying and Mapping, 2013, 38(1):36-39, 50.
[25]	SUN Yongrong, HUANG Bin, WANG Lina, et al. Vector map matching navigation method with anti-scale transformation[J]. Journal of Chinese Inertial Technology, 2013, 21(1):89-92, 111.
[26]	LI Xiang, ZHANG Jiangshui, YANG Baixin, et al. An extraction algorithm of track features based on trend set of heading angle variable[J]. Journal of Geo-information Science, 2015, 17(10):1172-1178.
[27]	SHEN Jian, ZHANG Jingyuan, ZHA Feng. Improved ICCP algorithm for underwater terrain matching method[J]. Journal of Huazhong University of Science and Technology (Natural Science Edition), 2012, 40(10):63-67.
[28]	BURGES C, SHAKED T, RENSHAW E, et al. Learning to rank using gradient descent[C]// Proceedings of the 22nd International Conference on Machine Learning. Bonn: Association for Computing Machinery, 2005: 89-96.
[29]	LI Xiang, ZHANG Jiangshui, GE Shihao, et al. An assistant navigation positioning algorithm based on the road curve feature and inertial navigation data[J]. Journal of Geomatics Science and Technology, 2013, 30(2):210-213.
[30]	LI Xiang, HUA Yixin, ZHANG Hong, et al. Positioning correction algorithm of vector road aided inertial navigation based on the rough/fine matching method[J]. Acta Geodaetica et Cartographica Sinica, 2017, 46(8):1034-1046. DOI: 10.11947/j.AGCS.2017.20160469. doi: 10.11947/j.AGCS.2017.20160469
[31]	DOURIEZ M. A new real-time map-matching algorithm at lyft[EB/OL]. [2021-02-16]. https://zhuanlan.zhihu.com/p/258508760.

Algorithm	Evaluation standard	Track No.
Algorithm	Evaluation standard	1	2	3	4	5	Average
Projection algorithm	Accuracy rate/(%)	76.4	80.7	78.9	80.1	77.9	79.4
	Time/s	5.8	1.5	2.3	1.0	4.2	3.0
	Deviation/(×10^-4)	1.19362	1.22047	1.22275	1.22352	1.21267	1.21461
ICCP algorithm only	Accuracy rate/(%)	87.9	86.1	83.6	89.1	85.8	86.5
	Time/s	9.8	2.6	3.8	1.7	7.1	5.0
	Deviation/(×10^-4)	0.88416	0.90405	0.90574	0.90631	0.89827	0.89971
HMM algorithm	Accuracy rate/(%)	96.2	92.5	94.8	90.8	95.2	93.9
	Time/s	12.9	3.4	5.0	2.2	9.4	6.6
	Deviation/(×10^-4)	0.93766	0.95874	0.96054	0.96114	0.95261	0.95414
Algorithm at Lyft^[31]	Accuracy rate/(%)	97.1	92.3	94.8	91.3	95.4	94.2
	Time/s	13.8	3.6	5.4	2.4	10.1	7.1
	Deviation/(×10^-4)	0.93300	0.95397	0.95576	0.95636	0.94787	0.94939
Our algorithm	Accuracy rate/(%)	94.6	90.0	92.2	88.3	92.6	91.5
	Time/s	7.5	2.7	3.5	2.1	5.7	4.3
	Deviation/(×10^-4)	0.92837	0.94925	0.95103	0.95163	0.94318	0.94470
Number of track points		3660	862	1148	521	2560	1750