基于DBSCAN聚类和LSTM网络的装甲车辆集群轨迹预测方法

doi:10.12382/bgxb.2023.1064

摘要/Abstract

摘要：

针对装甲车辆运动状态复杂性、战场态势不确定性、战术迷惑和欺骗性导致装甲车辆集群运动轨迹难以准确预测的问题,提出一种基于密度的空间聚类应用(Density-Based Spatial Clustering of Applications with Noise,DBSCAN)和长短时记忆(Long Short Term Memory,LSTM)神经网络的装甲车辆集群轨迹预测方法。根据装甲车辆的斜坡上行驶、转向和车-车交互行驶状态,建立运动学模型。选取机动特征、环境特征和车-车交互特征等轨迹特征信息,基于双层LSTM网络预测单个装甲车辆的轨迹。基于DBSCAN算法将多条单装预测轨迹进行分段、相似度计算和聚类,获得集群代表轨迹作为装甲车辆集群的预测轨迹。仿真结果表明,所提方法能够有效预测装甲车辆集群轨迹,实现料敌于先、谋敌于前。

关键词: 装甲车辆, 集群轨迹预测, 基于密度的空间聚类应用, 长短时记忆网络, 轨迹预测系统

Abstract:

It is difficult to accurately predict the movement trajectory of armored vehicle cluster due to the complexity of armored vehicle motion states, the uncertainty of battlefield situations, and the tactical confusion and deception. This paper proposes a trajectory prediction method for armored vehicle cluster based on density-based spatial clustering of applications with noise (DBSCAN) clustering algorithm and long short-term memory (LSTM) network. Firstly, a kinematic model of armored vehicles is established based on the states of armored vehicles driving on slopes, turning and interacting with other vehicles. And then the trajectory characteristics such as maneuver features, environmental features and vehicle-to-vehicle interaction features are selected, and the trajectory of an individual armored vehicle is predicted using a dual-layer LSTM network. Finally, the DBSCAN algorithm is utilized to segment the multiple single-vehicle predicted trajectories, calculate the similarities among them, and cluster them to obtain a representative trajectory for the cluster, as the predicted trajectory for the armored vehicle cluster. Simulated results demonstrate that the proposed method can effectively predict the trajectories of armored vehicle clusters.

Key words: armored vehicle, cluster trajectory prediction, density-based spatial clustering of applications with noise, long short-term memory network, trajectory prediction system

中图分类号:

TJ810.1

陈刚, 王国新, 明振军, 陈旺, 商曦文, 阎艳. 基于DBSCAN聚类和LSTM网络的装甲车辆集群轨迹预测方法[J]. 兵工学报, 2024, 45(12): 4295-4310.

CHEN Gang, WANG Guoxin, MING Zhenjun, CHEN Wang, SHANG Xiwen, YAN Yan. Armored Vehicle Cluster Trajectory Prediction Method Based on DBSCAN Clustering Algorithm and LSTM Network[J]. Acta Armamentarii, 2024, 45(12): 4295-4310.

图/表 25

参考文献 30

[1]	杜志岐, 唐镜. 基于系统工程的装甲车辆总体设计[J]. 兵工学报, 2022, 43(增刊1): 1-10.
	DU Z Q, TANG J. Overall design of armored vehicles based on system engineering[J]. Acta Armamentarii, 2022, 43(S1): 1-10. (in Chinese) doi: 10.12382/bgxb.2022.A016
[2]	陈刚, 姚丽亚, 王国新, 等. 面向鲁棒决策的战场态势评估人机共识形成方法[J]. 兵工学报, 2022, 43(11): 2953-2964. doi: 10.12382/bgxb.2021.0557
	CHEN G, YAO L Y, WANG G X, et al. A human-machine consensus formation method for robust decision making in battlefield situation assessment[J]. Acta Armamentarii, 2022, 43(11): 2953-2964. (in Chinese) doi: 10.12382/bgxb.2021.0557
[3]	张堃, 杜睿怡, 时昊天, 等. 基于Mogrifier-BiGRU的飞行器轨迹预测[J]. 兵工学报, 2024, 45(2):373-384. doi: 10.12382/bgxb.2022.0750
	ZHANG K, DU R Y, SHI H T, et al. Prediction of aircraft trajectory based on Mogrifier-BiGRU[J]. Acta Armamentarii, 2024, 45(2):373-384. (in Chinese) doi: 10.12382/bgxb.2022.0750
[4]	万宜春, 陈志龙, 何昌其, 等. 基于时空和作战编组的兵棋推演系统轨迹聚类算法[J]. 指挥控制与仿真, 2023, 45(1): 108-118. doi: 10.3969/j.issn.1673-3819.2023.01.018
	WAN Y C, CHEN Z L, HE C Q, et al. Trajectory clustering algorithm of wargaming system based on space-time and combat grouping[J]. Command Control & Simulation, 2023, 45(1): 108-118. (in Chinese)
[5]	乔少杰, 韩楠, 朱新文, 等. 基于卡尔曼滤波的动态轨迹预测算法[J]. 电子学报, 2018, 46(2): 418-423. doi: 10.3969/j.issn.0372-2112.2018.02.022
	QIAO S J, HAN N, ZHU X W, et al. A dynamic trajectory prediction algorithm based on Kalman filter[J]. Acta Electronica Sinica, 2018, 46(2): 418-423. (in Chinese)
[12]	唐上钦, 魏政磊, 谢磊, 等. 基于机动单元库的TSO-GRU-Ada机动轨迹预测[J]. 兵工学报, 2022, 43(8): 1913-1925.
	TANG S Q, WEI Z L, XIE L, et al. TSO-GRU-Ada maneuver trajectory prediction based on maneuver unit library[J]. Acta Armamentarii, 2022, 43(8): 1913-1925. (in Chinese) doi: 10.12382/bgxb.2021.0417
[13]	CAPOBIANCO S, MILLEFIORI L M, FORTI N, et al. Deep learning methods for vessel trajectory prediction based on recurrent neural networks[J]. IEEE Transactions on Aerospace and Electronic Systems, 2021, 57(6): 4329-4346.
[14]	张百川, 毕文豪, 张安, 等. 基于Transformer模型的空战飞行器轨迹预测误差补偿方法[J]. 航空学报, 2023, 44(9): 291-304.
	ZHANG B C, BI W H, ZHANG A, et al. Transformer-based error compensation method for air combat aircraft trajectory prediction[J]. Acta Aeronautica et Astronautica Sinica, 2023, 44(9): 291-304. (in Chinese)
[15]	张永梅, 赖裕平, 马健喆, 等. 基于视频的装甲车和飞机检测跟踪及轨迹预测算法[J]. 兵工学报, 2021, 42(3):545-554. doi: 10.3969/j.issn.1000-1093.2021.03.010
	ZHANG Y M, LAI Y P, MA J Z, et al. A video-based prediction algorithm for armored vehicle and aircraft detection/tracking and trajectory[J]. Acta Armamentarii, 2021, 42(3): 545-554. (in Chinese) doi: 10.3969/j.issn.1000-1093.2021.03.010
[16]	ZENG J C, GOU F F, WU J. Task offloading scheme combining deep reinforcement learning and convolutional neural networks for vehicle trajectory prediction in smart cities[J]. Computer Communications, 2023, 208: 29-43.
[17]	连静, 丁荣琪, 李琳辉, 等. 基于图模型和注意力机制的车辆轨迹预测方法[J]. 兵工学报, 2023, 44(7): 2162-2170. doi: 10.12382/bgxb.2022.0117
	LIAN J, DING R Q, LI L H, et al. Vehicle trajectory prediction method based on graph models and attention mechanism[J]. Acta Armamentarii, 2023, 44(7): 2162-2170. (in Chinese) doi: 10.12382/bgxb.2022.0117
[18]	杨春伟, 刘炳琪, 王继平, 等. 基于注意力机制的高超声速飞行器LSTM智能轨迹预测[J]. 兵工学报, 2022, 43(增刊2):78-86.
	YANG C W, LIU B Q, WANG J P, et al. LSTM intelligent trajectory prediction for hypersonic vehicles based on attention mechanism[J]. Acta Armamentarii, 2022, 43(S2): 78-86. (in Chinese) doi: 10.12382/bgxb.2022.B002
[19]	郭立威, 王权, 高克斌, 等. 基于虚拟现实的装甲车辆运动仿真研究[J]. 计算机系统应用, 2019, 28(6):221-227.
	GUO L W, WANG Q, GAO K B, et al. Research on armored vehicle motion simulation based on virtual reality[J]. Computer Systems & Applications, 2019, 28(6):221-227. (in Chinese)
[20]	刘妤, 谢铌, 张拓, 等. 履带车辆软坡地面力学建模及行驶性能分析[J]. 机械设计, 2021, 38 (3): 110-118.
	LIU Y, XIE N, ZHANG T, et al. Ground mechanic modeling and analysis on driving performance of tracked vehicles on the soft slope road[J]. Journal of Machine Design, 2021, 38 (3): 110-118. (in Chinese)
[21]	宋波涛, 许广亮. 基于LSTM与1DCNN的导弹轨迹预测方法[J]. 系统工程与电子技术, 2023, 45(2): 504-512. doi: 10.12305/j.issn.1001-506X.2023.02.22
	SONG B T, XU G L. Missile trajectory prediction method based on LSTM and 1DCNN[J]. Systems Engineering and Electronics, 2023, 45(2): 504-512. (in Chinese) doi: 10.12305/j.issn.1001-506X.2023.02.22
[22]	LEE J G, HAN J, WHANG K Y. Trajectory clustering: a partition-and-group framework[C]// Proceedings of the 2007 ACM SIGMOD international conference on Management of data. New York, NY, US: Association for Computing Machinery, 2007: 593-604.
[23]	CONDE R M M, DELAURA R, HANSMAN R J, et al. Trajectory clustering and classification for characterization of air traffic flows[C]//Proceedings of the 16th AIAA Aviation Technology, Integration, and Operations Conference.Washington, DC, US:AIAA, 2016: 1172-1186.
[24]	刘钰, 彭鹏菲. 基于改进DBSCAN的船舶轨迹聚类方法研究[J]. 舰船电子工程, 2022, 42(12): 57-63.
	LIU Y, PENG P F. Research on clustering method of vessel trajectory based on improved DBSCAN[J]. Ship Electronic Engineering, 2022, 42(12): 57-63. (in Chinese)
[25]	韩萍, 张启, 石庆研, 等. 基于DBSCAN-GRU算法的终端区4D航迹预测[J]. 信号处理, 2023, 39(3):439-449.
	HAN P, ZHANG Q, SHI Q Y, et al. 4D trajectory prediction of terminal area based on DBSCAN-GRU algorithm[J]. Journal of Signal Processing, 2023, 39(3):439-449. (in Chinese)
[26]	杨任农, 岳龙飞, 宋敏, 等. 基于Bi-LSTM的无人机轨迹预测模型及仿真[J]. 航空工程进展, 2020, 11(1):77-84.
	YANG R N, YUE L F, SONG M, et al. UVA trajectory prediction model and simulation based on Bi-LSTM[J]. Advances in Aeronautical Science and Engineering, 2020, 11(1): 77-84. (in Chinese)
[27]	俞庆英, 赵亚军, 叶梓彤, 等. 基于群组与密度的轨迹聚类算法[J]. 计算机工程, 2021, 47(4): 100-107. doi: 10.19678/j.issn.1000-3428.0057425
	YU Q Y, ZHAO Y J, YE Z T, et al. Trajectory clustering algorithm based on group and density[J]. Computer Engineering, 2021, 47(4): 100-107. (in Chinese) doi: 10.19678/j.issn.1000-3428.0057425
[28]	杨家轩, 刘元. 基于DBTCAN算法的船舶轨迹聚类与航路识别[J]. 上海海事大学学报, 2022, 43(3):7-12.
[6]	DING J H, LIU H Z, YANG L T, et al. Multiuser multivariate multiorder Markov-based multimodal user mobility pattern prediction[J]. IEEE Internet of Things Journal, 2020, 7(5): 4519-4531.
[7]	PANG Y T, ZHAO X Y, HAO Y, et al. Data-driven trajectory prediction with weather uncertainties: a Bayesian deep learning approach[J]. Transportation Research Part C:Emerging Technologies, 2021, 130(1): 103326.
[8]	FENG Y Y, YAN X L. Support vector machine based lane-changing behavior recognition and lateral trajectory prediction[J]. Computational Intelligence and Neuroscience, 2022, 2022: 3632333.
[9]	CHEN Y M, YU H L, ZHANG J W, et al. Lane-exchanging driving strategy for autonomous vehicle via trajectory prediction and model predictive control[J]. Chinese Journal of Mechanical Engineering, 2022, 35(1): 71.
[10]	赵梓烨, 刘海鸥, 陈慧岩. 分布式电驱动无人高速履带车辆越野环境轨迹预测方法研究[J]. 兵工学报, 2019, 40(4): 680-688. doi: 10.3969/j.issn.1000-1093.2019.04.002
	ZHAO Z Y, LIU H O, CHEN H Y. Research on trajectory prediction method of distributed high speed electric drive unmanned tracked vehicle in off-road conditions[J]. Acta Armamentarii, 2019, 40(4): 680-688. (in Chinese) doi: 10.3969/j.issn.1000-1093.2019.04.002
[11]	熊光明, 鲁浩, 郭孔辉, 等. 基于滑动参数实时估计的履带车辆运行轨迹预测方法研究[J]. 兵工学报, 2017, 38(3): 600-607. doi: 10.3969/j.issn.1000-1093.2017.03.025
	XIONG G M, LU H, GUO K H, et al. Research on trajectory prediction of tracked vehicles based on real time slip estimation[J]. Acta Armamentarii, 2017, 38(3):600-607. (in Chinese)
[28]	YANG J X, LIU Y. Ship trajectory clustering and route recognition based on DBTCAN algorithm[J]. Journal of Shanghai Maritime University, 2022, 43(3):7-12. (in Chinese)
[29]	李文杰, 闫世强, 蒋莹, 等. 自适应确定DBSCAN算法参数的算法研究[J]. 计算机工程与应用, 2019, 55(5): 1-7,148. doi: 10.3778/j.issn.1002-8331.1809-0018
	LI W J, YAN S Q, JIANG Y, et al. Research on method of self-adaptive determination of DBSCAN algorithm parameters[J]. Computer Engineering and Applications, 2019, 55(5): 1-7,148. (in Chinese) doi: 10.3778/j.issn.1002-8331.1809-0018
[30]	万佳, 胡大裟, 蒋玉明. 多密度自适应确定DBSCAN算法参数的算法研究[J]. 计算机工程与应用, 2022, 58(2): 78-85. doi: 10.3778/j.issn.1002-8331.2012-0476
	WAN J, HU D S, JIANG Y M. Research on method of multi-density self-adaptive determination of DBSCAN algorithm parameters[J]. Computer Engineering and Applications, 2022, 58(2):78-85. (in Chinese) doi: 10.3778/j.issn.1002-8331.2012-0476

特征类型	类型特征取值	编码
	平地	100
地形信息	丘陵	010
	高山	001
	湖泊	100
水文信息	沼泽	010
	江河	001

特征类型	类型特征取值	编码
	平地	100
地形信息	丘陵	010
	高山	001
	湖泊	100
水文信息	沼泽	010
	江河	001

样本点	速度/ (km·h^-1)	加速度/ (km·h^-2)	垂直偏转角/ (°)	水平偏转角/ (°)	转向半径/ km	转向角度/ (°)	经度/ (°)	纬度/ (°)	高度/ m	地形信息	水文信息	气温/ ℃	能见度	相对距离/ km	相对高度/ m	速度矢量夹角/ (°)
1	20	0	0	-43.4	0	0	121.28	25.03	85.58	100	000	25.2	2	0	0	0
2	20	0	0	-43.3	0	0	121.28	25.03	85. 89	100	000	25.3	2	0	0	0
3	20	0	0	-43.8	0	0	121.28	25.03	85.07	100	000	25.1	2	0	0	0
︙	︙	︙	︙	︙	︙	︙	︙	︙	︙	︙	︙	︙	︙	︙	︙	︙
1399	36	0.4	15.6	23.4	20	12.2	121.31	25.06	116.01	100	100	25.5	2	4.3	20.8	38.2
1400	36	0.4	15.8	24.6	20	13.5	121.31	25.06	116.44	100	100	24.8	1	4.5	21.5	37.4
1401	36	0.4	15.8	24.6	20	13.5	121.31	25.06	116.51	100	100	24.8	1	4.5	21.9	37.4
︙	︙	︙	︙	︙	︙	︙	︙	︙	︙	︙	︙	︙	︙	︙	︙	︙
2798	40	0.5	10.4	24.8	20	-8.6	121.33	25.09	127.03	001	000	24.9	1	5.9	45.6	15.2
2799	40	0.5	10.6	25.2	20	-8.9	121.33	25.09	127.15	001	000	24.2	2	6.2	45.9	16.8
2800	40	0.5	10.8	25.2	20	-8.9	121.33	25.09	127.27	001	000	24.2	2	6.4	46.8	16.5

样本点	速度/ (km·h^-1)	加速度/ (km·h^-2)	垂直偏转角/ (°)	水平偏转角/ (°)	转向半径/ km	转向角度/ (°)	经度/ (°)	纬度/ (°)	高度/ m	地形信息	水文信息	气温/ ℃	能见度	相对距离/ km	相对高度/ m	速度矢量夹角/ (°)
1	20	0	0	-43.4	0	0	121.28	25.03	85.58	100	000	25.2	2	0	0	0
2	20	0	0	-43.3	0	0	121.28	25.03	85. 89	100	000	25.3	2	0	0	0
3	20	0	0	-43.8	0	0	121.28	25.03	85.07	100	000	25.1	2	0	0	0
︙	︙	︙	︙	︙	︙	︙	︙	︙	︙	︙	︙	︙	︙	︙	︙	︙
1399	36	0.4	15.6	23.4	20	12.2	121.31	25.06	116.01	100	100	25.5	2	4.3	20.8	38.2
1400	36	0.4	15.8	24.6	20	13.5	121.31	25.06	116.44	100	100	24.8	1	4.5	21.5	37.4
1401	36	0.4	15.8	24.6	20	13.5	121.31	25.06	116.51	100	100	24.8	1	4.5	21.9	37.4
︙	︙	︙	︙	︙	︙	︙	︙	︙	︙	︙	︙	︙	︙	︙	︙	︙
2798	40	0.5	10.4	24.8	20	-8.6	121.33	25.09	127.03	001	000	24.9	1	5.9	45.6	15.2
2799	40	0.5	10.6	25.2	20	-8.9	121.33	25.09	127.15	001	000	24.2	2	6.2	45.9	16.8
2800	40	0.5	10.8	25.2	20	-8.9	121.33	25.09	127.27	001	000	24.2	2	6.4	46.8	16.5

数据集	轨迹数量	位置点数量	子轨迹数量	输入向量维度	输出向量维度
训练集	240	2000	474240	20×20	5×3
验证集	240	400	90240	20×20	5×3
测试集	240	400	90240	20×20	5×3