面向多元未知环境的基于深度高斯过程组合导航轨迹预测方法

doi:10.12305/j.issn.1001-506X.2023.11.31

摘要/Abstract

摘要：

传统惯导/卫导组合导航在多元复杂环境下易受干扰, 从而导致观测量异常影响导航性能。以无人驾驶车辆为研究对象, 展开提升组合导航系统导航精度的研究。采用深度高斯过程(deep Gaussian process, DGP)辅助估计位置的方法减小组合导航误差, 提高定位性能。基于DGP的辅助导航方法不仅可以预测无人驾驶车辆的标称轨迹, 同时可以预测各时刻位置可信区间的概率分布, 为基于深度学习模型的数据融合预测方法提供了严格的理论解释性。真实历史数据下的多重对比实验表明, 该算法较传统深度神经网络算法具有更高的精度和可靠性。基于DGP的辅助导航方式能有效提高全球卫星定位系统信号失锁时的导航模型性能, 实验表明相对于纯惯性导航系统(integral navigation system, INS)解算和长短期记忆(long and short term memory, LSTM)进行导航信号补偿定位精度分别提高了97.32%和52.13%。

关键词: 无人驾驶车辆, 深度高斯过程, 导航定位, 信息融合

Abstract:

The traditional inertial navigation and satellite navigation integrated is prone to interfered in complex multi-element and hybrid environment, which affects navigation performance and leads to abnormal observations. We take unmanned ground vehicle as the object and carry out the research on improving the accuracy of the integrated navigation system. A deep Gaussian process (DGP) assisting location estimation method is used to reduce the integrated navigation error and improve the positioning performance. The assisted navigation method based on DGP can not only predict the trajectory of the unmanned vehicle, but also can estimate the probability distribution of the position confidence interval at every time, which provides strict theoretical interpretation for the data fusion prediction method based on deep learning model. Multiple comparison experiments with real historical data show that the proposed framework achieves higher accuracy and reliability than deep neural network algorithms. The DGP-based auxiliary navigation can effectively improve the performance of the navigation model when the global positioning system (GPS) signal is out of lock, and the experiments show that the navigation signal compensation positioning accuracy is improved by 97.32% and 52.13% respectively compared with pure integral navigation system (INS) and long and short term memory (LSTM).

Key words: unmanned ground vehicle, deep Gaussian process (DGP), navigation and location, information fusion

中图分类号:

TN967.2

杨璐宁, 刘正华, 温暖. 面向多元未知环境的基于深度高斯过程组合导航轨迹预测方法[J]. 系统工程与电子技术, 2023, 45(11): 3632-3639.

Luning YANG, Zhenghua LIU, Nuan WEN. Integrated navigation trajectory prediction method based on deep Gaussian process for multiple unknown environments[J]. Systems Engineering and Electronics, 2023, 45(11): 3632-3639.

图/表 8

图1

表1

图2

图3

图4

图5

图6

表2

参考文献 31

1	GAO B B , HU G G , GAO S S , et al. Multi-sensor optimal data fusion for INS/GNSS/CNS integration based on unscented Kalman filter[J]. International Journal of Control, Automation and Systems, 2018, 16, 129- 140. doi: 10.1007/s12555-016-0801-4
2	LI X , CHEN W , CHAN C Y , et al. Multi-sensor fusion metho-dology for enhanced land vehicle positioning[J]. Information Fusion, 2019, 46, 51- 62. doi: 10.1016/j.inffus.2018.04.006
3	HAVYARIMAN V , HANYURWIMFURA D , NSENGIYUMVA P , et al. A novel hybrid approach based-SRG model for vehicle position prediction in multi-GPS outage conditions[J]. Information Fusion, 2018, 41, 1- 8. doi: 10.1016/j.inffus.2017.07.002
4	孟阳, 高社生, 王维. 基于高斯过程回归的平方根UPF算法[J]. 系统工程与电子技术, 2015, 37 (12): 2817- 2822. doi: 10.3969/j.issn.1001-506X.2015.12.23
	MENG Y , GAO S S , WANG W . Square root UPF algorithm based on Gaussian process regression[J]. Systems Engineering and Electronics, 2015, 37 (12): 2817- 2822. doi: 10.3969/j.issn.1001-506X.2015.12.23
5	COSTANZI R , FANELLI F , MELI E , et al. UKF-based navigation system for AUVs: online experimental validation[J]. IEEE Journal of Oceanic Engineering, 2018, 44 (3): 633- 641.
6	CUTARJAR K, BONILLA E V, MICHIARDI P, et al. Random feature expansions for deep Gaussian processes[C]//Proc. of the International Conference on Machine Learning, 2017: 884-893.
7	LI Y , LU X Y , WANG J , et al. Pedestrian trajectory prediction combining probabilistic reasoning and sequence learning[J]. IEEE Trans.on Intelligent Vehicles, 2020, 5 (3): 461- 474. doi: 10.1109/TIV.2020.2966117
8	HABIBI G , HOW J P . Human trajectory prediction using similarity-based multi-model fusion[J]. IEEE Robotics and Automation Letters, 2021, 6 (2): 715- 722. doi: 10.1109/LRA.2020.3048652
9	翟翠红, 汪建均, 冯泽彪. 基于高斯过程模型的多响应稳健参数设计[J]. 系统工程与电子技术, 2021, 43 (12): 3683- 3693.
	ZHAI C H , WANG J J , FENG Z B . Multi-response robust parameter design based on Gaussian Process model[J]. Systems Engineering and Electronics, 2021, 6 (2): 715- 722.
10	LIU Y , FAN X , LYU C , et al. An innovative information fusion method with adaptive Kalman filter for integrated INS/GPS navigation of autonomous vehicles[J]. Mechanical Systems and Signal Processing, 2018, 100, 605- 616. doi: 10.1016/j.ymssp.2017.07.051
11	GEIGER A , LENZ P , STILLER C , et al. Vision meets robo-tics: the kitti dataset[J]. The International Journal of Robotics Research, 2013, 32 (11): 1231- 1237. doi: 10.1177/0278364913491297
12	YUE X Z , LI H W . A hybrid intelligent algorithm DGP-MLP for GNSS/INS integration during GNSS outages[J]. Journal of Navigation, 2019, 72 (2): 375- 388. doi: 10.1017/S0373463318000760
13	ZHANG Y . A fusion methodology to bridge GPS outages for INS/GPS integrated navigation system[J]. IEEE Access, 2019, 7, 61296- 61306. doi: 10.1109/ACCESS.2019.2911025
14	YOON Y , KIM C , LEE J , et al. Interaction-aware probabilistic trajectory prediction of cut-in vehicles using Gaussian process for proactive control of autonomous vehicles[J]. IEEE Access, 2021, 9, 63440- 63455. doi: 10.1109/ACCESS.2021.3075677
15	MU X K , HE B , ZHANG X , et al. End-to-end navigation for autonomous underwater vehicle with hybrid recurrent neural networks[J]. Ocean Engineering, 2019, 194, 106602. doi: 10.1016/j.oceaneng.2019.106602
16	FU M Y , ZHANG T , SONG W J , et al. Trajectory prediction-based local spatio-temporal navigation map for autonomous driving in dynamic highway environments[J]. IEEE Trans.on Intelligent Transportation Systems, 2021, 23 (7): 6418- 6429.
17	LIU K L , TANG X P , TEODORESCU R , et al. Future ageing trajectory prediction for lithium-ion battery considering the knee point effect[J]. IEEE Trans.on Energy Conversion, 2021, 37 (2): 1282- 1291.
18	CHEN Z M , GUO D Y , LIN Y . A deep Gaussian process-based flight trajectory prediction approach and its application on conflict detection[J]. Algorithms, 2020, 13 (11): 293. doi: 10.3390/a13110293
19	BROOKS J , BAROOAH P . Consumer-aware distributed demand-side contingency service in the power grid[J]. IEEE Trans.on Control of Network Systems, 2017, 5 (4): 1987- 1997.
20	郑天宇. 基于循环神经网络的临近空间高超声速目标航迹估计与预报[D]. 哈尔滨: 哈尔滨工业大学, 2020.
	ZHENG T Y. Near-space hypersonic target track estimation and prediction based on recurrent neural network[D]. Harbin: Harbin Institute of Technology University, 2020.
21	CHEN H M , CHENG X H , WANG H P , et al. Dealing with observation outages within navigation data using Gaussian process regression[J]. The Journal of Navigation, 2014, 67 (4): 603- 615. doi: 10.1017/S0373463314000010
22	孙浩. 考虑交通车辆运动不确定性的轨迹规划方法研究[D]. 长春: 吉林大学, 2017.
	SUN H. Research on trajectory planning method considering the uncertainty of vehicle movement[D]. Changchun: Jilin University, 2017.
23	LYU Z H , LI Y X , FENG H L , et al. Deep learning for secu-rity in digital twins of cooperative intelligent transportation systems[J]. IEEE Trans.on Intelligent Transportation Systems, 2021, 23 (9): 16666- 16675.
24	WANG J M , FLEETl D J , HERTZMANN A . Gaussian process dynamical models for human motion[J]. IEEE Trans.on Pattern Analysis and Machine Intelligence, 2007, 30 (2): 283- 298.
25	ZHOU R Y , CHEN H , CHEN H R , et al. Research on traffic situation analysis for urban road network through spatiotemporal data mining: a case study of Xi'an, China[J]. IEEE Access, 2021, 9, 75553- 75567. doi: 10.1109/ACCESS.2021.3082188
26	CAO D , ZHAO J B , HU W H , et al. Robust deep Gaussian process-based probabilistic electrical load forecasting against anomalous events[J]. IEEE Trans.on Industrial Informatics, 2021, 18 (2): 1142- 1153.
27	KIM Y , CHO J , CHO K , et al. Glass-interposer electromagnetic bandgap structure with defected ground plane for broadband suppression of power/ground noise coupling[J]. IEEE Trans.on Components, Packaging and Manufacturing Technology, 2017, 7 (9): 1493- 1505. doi: 10.1109/TCPMT.2017.2730853
28	PAN X G , ZHAN X H , DAI B , et al. Exploiting deep generative prior for versatile image restoration and manipulation[J]. IEEE Trans.on Pattern Analysis and Machine Intelligence, 2021, 44 (11): 7474- 7489.
29	CHEN Z L , GUO Q , LI T S , et al. Gait prediction and variable admittance control for lower limb exoskeleton with measurement delay and extended-state-observer[J]. IEEE Trans.on Neural Networks and Learning Systems, 2022, doi: 10.1109/TNNLS.2022.3152255
30	MUNOZ-GONZALEZ L , LAZARO-GREDILLA M , FIGUEIRAS-VIDAL A R . Laplace approximation for divisive Gaussian processes for nonstationary regression[J]. IEEE Trans.on Pattern Analysis and Machine Intelligence, 2015, 38 (3): 618- 624.
31	MATHEW V , KURIAN C P , AUGUSTINE N . Optimizing daylight glare and circadian entrainment in a Daylight-Artificial Light Integrated scheme[J]. IEEE Access, 2022, 10, 38174- 38188.

模型参数	LSTM	GP	DGP
均值函数	-	Constant_mean	Constant_mean
核函数	-	RBFKernel	RBFKernel
优化器	Adam	Adam	Adam
学习率	0.1	0.1	0.1
诱导点数目	-	-	5
网络层数	2	-	2
隐藏层神经元数目	32	-	-

参数	LSTM-UKF	GP-UKF	DGP-UKF
100 s东向误差/m	0.049	0.046	0.040
200 s东向误差/m	0.298	0.278	0.148
500 s东向误差/m	26.669	22.585	15.915
100 s北向误差/m	0.048	0.047	0.038
200 s北向误差/m	0.288	0.274	0.138
500 s北向误差/m	26.529	22.337	15.868

[1]	任文娟, 杨战鹏, 许光銮, 付琨. 海上动目标身份置信度融合计算模型[J]. 系统工程与电子技术, 2023, 45(4): 1082-1089.
[2]	张晔, 侯毅, 欧阳克威, 周石琳. 单变量序列数据分类方法综述[J]. 系统工程与电子技术, 2023, 45(2): 313-335.
[3]	黄林, 龚立, 姜伟, 王康勃. 基于多源信息融合与HMM的剩余寿命预测[J]. 系统工程与电子技术, 2022, 44(5): 1747-1756.
[4]	薛春岭, 曹菲, 孙庆, 秦建强, 冯晓伟. 基于多特征信息融合的海面微弱目标检测[J]. 系统工程与电子技术, 2022, 44(11): 3338-3345.
[5]	张瑜, 吴凯, 郭杰, 葛志闪, 张宝超. 基于数据质量评估的自适应序贯航迹关联算法[J]. 系统工程与电子技术, 2022, 44(11): 3477-3485.
[6]	关欣, 于昊天, 衣晓. 证据独立性及其对目标识别的影响研究[J]. 系统工程与电子技术, 2022, 44(1): 192-198.
[7]	孙雪, 黄志球, 沈国华, 王金永, 徐恒. 基于本体和BN的无人车行为决策方法[J]. 系统工程与电子技术, 2021, 43(2): 452-465.
[8]	王润, 杨宾峰, 孙欢, 管桦. 基于磁梯度张量的旋转永磁体定位技术[J]. 系统工程与电子技术, 2020, 42(9): 2085-2090.
[9]	赵岩, 吴建峰, 高育鹏. 基于多智能体导航的高超飞行器信息融合方法[J]. 系统工程与电子技术, 2020, 42(2): 405-413.
[10]	李佳炜, 江晶, 刘重阳, 吴卫华. 多星载光学传感器系统误差极大似然配准算法[J]. 系统工程与电子技术, 2020, 42(1): 1-9.
[11]	邵松世, 刘海涛, 张志华. 融合多源先验信息的舰船备件可靠性评估[J]. 系统工程与电子技术, 2019, 41(12): 2905-2910.
[12]	杨乐昌, 郭艳玲. 基于贝叶斯混合概率分布融合的系统可靠性分析与预测方法[J]. 系统工程与电子技术, 2018, 40(7): 1660-1668.
[13]	常天庆, 王全东, 郝娜, 孙皓泽, 孔德鹏. 基于信息融合的目标管理与被动定位方法[J]. 系统工程与电子技术, 2017, 39(9): 1921-1935.
[14]	唐续, 吴骐, 李明晏, 黄大羽. 天波超视距雷达的多路径融合多目标跟踪算法[J]. 系统工程与电子技术, 2017, 39(7): 1493-1499.
[15]	孙璐, 周伟, 姜佰辰, 关键. 一种时空联合约束的多源航迹相似性度量模型[J]. 系统工程与电子技术, 2017, 39(11): 2405-2413.