An Adaptive Maneuvering Target Tracking Algorithm Based on Fuzzy Inference

doi:10.16183/j.cnki.jsjtu.2022.314

Abstract

Abstract:

An adaptive maneuvering target tracking algorithm based on fuzzy inference is proposed to deal with the low adaptive capacity of variable structure interacting multi-model algorithms for target maneuver uncertainty and measurement uncertainty in maneuvering target tracking. A two-stage maneuvering discrimination model based on fuzzy inference is designed, which uses the probability of models and residual weighted norm of the main model to infer the reliability of the main model and the possibility of maneuvering discrimination. The two-stage maneuvering discriminant is introduced into the framework of expected-model augmentation based on likely model-set (EMA-LMS). A kind of fuzzy inference-based EMA-LMS algorithm is proposed to adjust the parameter and strategy of model-set adaption online. This algorithm generates an expected model that is closer to the real motion model and makes better choices for model selection. The simulation results show that the proposed algorithm can strengthen the adaptive capacity for the uncertainty of target maneuver and measurement, and improve accuracy.

Key words: maneuvering target tracking, variable structure interacting multiple model, maneuvering discriminant, fuzzy inference

CLC Number:

TP13

HAO Liang, HUANG Yinghao, YAO Lixiu, CAI Yunze. An Adaptive Maneuvering Target Tracking Algorithm Based on Fuzzy Inference[J]. Journal of Shanghai Jiao Tong University, 2024, 58(4): 468-480.

Figures/Tables 13

Fig.1

Tab.1

Fig.2

Fig.3

Tab.2

Fig.4

Fig.5

Tab.3

Fig.6

Fig.7

Fig.8

Tab.4

Fig.9

References 17

[1]	陈晓, 李亚安, 李余兴, 等. 基于距离加权的概率数据关联机动目标跟踪算法[J]. 上海交通大学学报, 2018, 52(4): 474-479. doi: 10.16183/j.cnki.jsjtu.2018.04.013
	CHEN Xiao, LI Ya’an, LI Yuxing, et al. Maneuvering target tracking algorithm based on weighted distance of probability data association[J]. Journal of Shanghai Jiao Tong University, 2018, 52(4): 474-479.
[2]	LI X R, ZHANG Y. Multiple-model estimation with variable structure. V. Likely-model set algorithm[J]. IEEE Transactions on Aerospace and Electronic Systems, 2000, 36(2): 448-466. doi: 10.1109/7.845222 URL
[3]	LI X R, ZHI X, ZHANG Y. Multiple-model estimation with variable structure. III. Model-group switching algorithm[J]. IEEE Transactions on Aerospace and Electronic Systems, 1999, 35(1): 225-241. doi: 10.1109/7.745694 URL
[4]	LI X R, JILKOV V P, RU J. Multiple-model estimation with variable structure—Part VI: Expected-mode augmentation[J]. IEEE Transactions on Aerospace and Electronic Systems, 2005, 41(3): 853-867. doi: 10.1109/TAES.2005.1541435 URL
[5]	JILKOV V P, ANGELOVA D S, SEMERDJIEV T Z A. Design and comparison of mode-set adaptive IMM algorithms for maneuvering target tracking[J]. IEEE Transactions on Aerospace and Electronic Systems, 1999, 35(1): 343-350. doi: 10.1109/7.745704 URL
[6]	王昱淇, 卢宙, 蔡云泽. 基于一致性的分布式变结构多模型方法[J]. 自动化学报, 2021, 47(7): 1548-1557.
	WANG Yuqi, LU Zhou, CAI Yunze. Consensus-based distributed variable structure multiple model[J]. Acta Automatica Sinica, 2021, 47(7): 1548-1557.
[7]	郭志, 董春云, 蔡远利, 等. 时变转移概率IMM-SRCKF机动目标跟踪算法[J]. 系统工程与电子技术, 2015, 37(1): 24-30.
	GUO Zhi, DONG Chunyun, CAI Yuanli, et al. Time-varying transition probability based IMM-SRCKF algorithm for maneuvering target tracking[J]. Systems Engineering and Electronics, 2015, 37(1): 24-30. doi: 10.3969/j.issn.1001-506X.2015.01.05
[8]	游航航, 韩其松, 余敏建, 等. 基于AIGWO-IMMUKF 的目标跟踪算法[J]. 北京航空航天大学学报, 2020, 46(10): 1826-1833.
	YOU Hanghang, HAN Qisong, YU Minjian, et al. Target tracking algorithm based on AIGWO-IMMUKF[J]. Journal of Beijing University of Aeronautics and Astronautics, 2020, 46(10): 1826-1833.
[9]	XIE G, SUN L, WEN T, et al. Adaptive transition probability matrix-based parallel IMM algorithm[J]. IEEE Transactions on Systems, Man, and Cybernetics: Systems, 2019, 51(5): 2980-2989. doi: 10.1109/TSMC.2019.2922305 URL
[10]	潘媚媚. 高速高机动目标自适应跟踪算法研究[D]. 西安: 西安电子科技大学, 2019.
	PAN Meimei. Research on adaptive algorithms for highly maneuvering target tracking[D]. Xi’an: Xi-dian University, 2019.
[11]	EUN Y, JEON D. Fuzzy inference-based dynamic determination of IMM mode transition probability for multi-radar tracking[C]// Proceedings of the 16th International Conference on Information Fusion. Istanbul, Turkey: IEEE, 2013: 1520-1525.
[12]	LI L Q, ZHAO D, LUO C D. A novel interacting TS fuzzy multiple model by using UKF for maneuvering target tracking[C]// 2019 22th International Conference on Information Fusion. Ottawa, Canada: IEEE, 2019: 1-7.
[13]	邵堃, 雷迎科. 基于模糊逻辑和机动检测的AGIMM跟踪算法[J]. 空军工程大学学报(自然科学版), 2020, 21(4): 80-87.
	SHAO Kun, LEI Yingke. AGIMM tracking algorithm based on fuzzy logic and maneuvering detection[J]. Journal of Air Force Engineering University (Natural Science Edition), 2020, 21(4): 80-87.
[14]	CHANG C W, TAO C W. A novel approach to implement Takagi-Sugeno fuzzy models[J]. IEEE Transactions on Cybernetics, 2017, 47(9): 2353-2361. doi: 10.1109/TCYB.2017.2701900 URL
[15]	雷英杰, 路艳丽, 王毅, 等. 模糊逻辑与智能系统[M]. 西安: 西安电子科技大学出版社, 2016.
	LEI Yingjie, LU Yanli, WANG Yi, et al. Fuzzy logic with intelligent systems[M]. Xi’an: Xidian University Press, 2016.
[16]	罗晓勇. 无线传感网络中基于交互式多模型目标跟踪算法研究[D]. 重庆: 重庆邮电大学, 2020.
	LUO Xiaoyong. Research on target tracking algorithm based on interaction multiple model in wireless sensor networks[D]. Chongqing: Chongqing University of Posts and Telecommunications, 2020.
[17]	傅虹景, 于守江, 吉峰, 等. 基于“当前”统计模型的变结构交互多模型算法[J]. 无线电工程, 2020, 50(4): 318-322.
	FU Hongjing, YU Shoujiang, JI Feng, et al. Variable structure interactive multiple model algorithm based on current statistical model[J]. Radio Engineering, 2020, 50(4): 318-322.

n	P_max,_k	P_diff,_k	$P n M a i n, k$
1	S	S	0.3P_max,_k
2	S	M	0.3P_max,_k
3	S	B	0.5P_max,_k+0.2P_diff,_k+0.3
4	M	S	0.5P_max,_k+0.2P_diff,_k+0.3
5	M	M	0.5P_max,_k+0.2P_diff,_k+0.3
6	M	B	0.5P_max,_k+0.2P_diff,_k+0.3
7	B	S	0.5P_max,_k+0.2P_diff,_k+0.3
8	B	M	0.3P_max,_k+0.5
9	B	B	0.3P_max,_k+0.5

k/s	场景1		场景2
k/s	a_x/(m·s^-2)	a_y/(m·s^-2)	a_x/(m·s^-2)	a_y/(m·s^-2)
1~50	0	0	0	0
51~100	60	60	30	-20
101~150	100	0	20	-30
151~200	-30	30	-20	-20
201~250	-30	-45	-30	15
251~300	25	40	-45	30
301~350	35	-50	-60	60

算法	匹配阶段			不匹配阶段
算法	ARMSE_p/m	ARMSE_v/(m·s^-1)	ARMSE_a/(m·s^-2)	ARMSE_p/m	ARMSE_v/(m·s^-1)	ARMSE_a/(m·s^-2)
IMM	40.46	22.10	11.71	69.00	69.63	32.69
LMS	41.55	23.44	12.01	71.20	71.53	33.11
EMA	48.38	31.18	15.78	60.16	50.49	25.97
EMA-LMS	51.36	29.75	13.24	64.09	55.39	27.78
CS-AG	63.54	33.77	10.13	85.08	55.91	19.68
模糊推理 EMA-LMS	48.24	28.59	12.73	59.58	43.20	20.05

算法	匹配阶段			不匹配阶段
算法	ARMSE_p/m	ARMSE_v/(m·s^-1)	ARMSE_a(m·s^-2)	ARMSE_p/m	ARMSE_v/(m·s^-1)	ARMSE_a/(m·s^-2)
IMM	37.84	16.85	8.42	71.25	69.90	29.60
LMS	40.29	20.27	9.96	72.08	70.46	29.64
EMA	46.09	25.37	11.55	58.91	45.08	20.55
EMA-LMS	45.93	24.01	10.08	61.95	51.26	23.78
CS-AG	55.42	30.71	9.82	56.95	32.87	10.40
模糊推理 EMA-LMS	46.34	24.09	9.81	57.67	38.53	15.69