融合深度学习的贝叶斯滤波综述

张文安; 林安迪; 杨旭升; 俞立; 杨小牛

doi:10.16383/j.aas.c230457

融合深度学习的贝叶斯滤波综述

doi: 10.16383/j.aas.c230457

张文安^{1, 2,},
林安迪^{1, 2,},
杨旭升^{1, 2,},
俞立^{1, 2,},
杨小牛^{1, 3,}

1.
浙江工业大学信息工程学院杭州 310023
2.
浙江省嵌入式系统联合重点实验室杭州 310023
3.
电磁空间安全全国重点实验室嘉兴 314033

基金项目: 国家自然科学基金(62173305), 浙江省"尖兵""领雁"研发攻关计划(2022C03114), 浙江省科技计划项目(2023C04032)资助

详细信息

作者简介:
张文安：浙江工业大学信息工程学院教授. 主要研究方向为多源信息融合估计和网络化系统. E-mail: wazhang@zjut.edu.cn

林安迪：浙江工业大学信息工程学院博士研究生. 主要研究方向为多源信息融合估计. E-mail: 201706061126@zjut.edu.cn

杨旭升：浙江工业大学信息工程学院副教授. 主要研究方向为多源信息融合估计和目标定位. 本文通信作者. E-mail: xsyang@zjut.edu.cn

俞立：浙江工业大学信息工程学院教授. 主要研究方向为鲁棒控制, 网络化系统感知与控制. E-mail: lyu@zjut.edu.cn

杨小牛：中国工程院院士, 电磁空间安全全国重点实验室首席科学家. 主要研究方向为软件无线电和智能信号处理. E-mail: yxn2117@126.com

计量
- 文章访问数: 198
- HTML全文浏览量: 91
- 被引次数: 0
出版历程
- 收稿日期: 2023-07-25
- 录用日期: 2023-12-21
- 网络出版日期: 2024-04-11

A Survey on Bayesian Filtering with Deep Learning

ZHANG Wen-An^{1, 2
,},
LIN An-Di^{1, 2
,},
YANG Xu-Sheng^{1, 2
,},
YU Li^{1, 2
,},
YANG Xiao-Niu^{1, 3
,}

1.
College of Information Engineering, Zhejiang University of Technology, Hangzhou 310023
2.
Zhejiang Provincial United Key Laboratory of Embedded Systems, Hangzhou 310023
3.
National Key Laboratory of Electromagnetic Space Security, Jiaxing 314033

Funds: Supported by National Natural Science Foundation of China (62173305), and “Pioneer”, “Leading Goose” R&D Program of Zhejiang Project (2022C03114), and Development Program of Zhejiang Province (2023C04032)

More Information

Author Bio:
ZHANG Wen-An　Professor at the College of Information Engineering, Zhejiang University of Technology. His research interest covers multi-sensor information fusion estimation and networked systems

LIN An-Di　Ph. D. candidate at the College of Information Engineering, Zhejiang University of Technology. His research interest covers multi-sensor information fusion estimation

YANG Xu-Sheng　Associate professor at the College of Information Engineering, Zhejiang University of Technology. His research interest covers multi-sensor information fusion estimation and target positioning. Corresponding author of this paper

YU Li　Professor at the College of Information Engineering, Zhejiang University of Technology. His research interest covers robust control and perception and control of networked systems

YANG Xiao-Niu　Academician of Chinese Academy of Engineering, chief scientist at the National Key Laboratory of Electromagnetic Space Security. His research interest covers software radio and intelligent signal processing

摘要

摘要: 当前动态系统呈现大型化、复杂化的趋势, 基于贝叶斯滤波的动态系统状态估计遇到了一系列新的挑战. 随着深度学习在特征提取与模式识别等方面的优势与潜力不断显现, 深度学习与传统贝叶斯滤波相结合的研究也随之兴起. 为此, 本文梳理了不同领域融合深度学习的贝叶斯滤波方法的应用案例, 从中剖析不同类型动态系统下贝叶斯滤波存在的局限性和共性难题. 在此基础上, 总结了当前贝叶斯滤波存在的几类不确定性问题, 以深度学习的视角将这些问题归纳为特征提取和参数辨识两大基本问题, 进而介绍深度学习为贝叶斯滤波所提供的解决方案. 其次, 归纳整理了两类深度学习与贝叶斯滤波结合的具体方法, 着重介绍了深度卡尔曼滤波和融合深度学习的自适应卡尔曼滤波. 最后, 综合考虑深度学习方法和贝叶斯滤波方法的优势, 讨论了融合深度学习的贝叶斯滤波方法的开放问题和未来研究方向.
- 深度学习 /
- 贝叶斯滤波 /
- 卡尔曼滤波 /
- 状态估计 /
- 状态空间模型
Abstract: As dynamic systems continue to exhibit a trend towards increased scale and complexity, the Bayesian filtering based state estimation for dynamic systems faces a series of challenges. With the increasing prominence and potential of deep learning in areas such as feature extraction and pattern recognition, research on combination of deep learning and classical Bayesian filtering is emerging. In this paper, we present a systematic review of application cases of Bayesian filtering methods that integrate deep learning in different domains, aiming to analyze the limitations and common challenges of Bayesian filtering in various types of dynamic systems. In view of this, we summarize several categories of uncertainty problems in the existing Bayesian filtering. From the perspective of deep learning, these problems are classified into feature extraction and parameter identification. Furthermore, we introduce the solutions provided by deep learning for Bayesian filtering. Additionally, we categorize and organize two specific approaches that combine Bayesian filtering with deep learning, that is, deep Kalman filtering and adaptive Kalman filtering with deep learning. Finally, by considering the advantages of both deep learning and Bayesian filtering methods, we discuss open questions and future research directions for Bayesian filtering with deep learning.
- Deep learning /
- bayesian filtering /
- kalman filtering /
- state estimation /
- state-space model

HTML全文

图 1 结构及主要内容

Fig. 1 The structure and main contents

下载: 全尺寸图片幻灯片

图 2 不确定性问题

Fig. 2 The uncertainty issues

下载: 全尺寸图片幻灯片

图 3 使用神经网络学习系统状态转移过程

Fig. 3 Learning state transition with neural networks

下载: 全尺寸图片幻灯片

图 4 Backprop KF的动态结构图

Fig. 4 Backprop KF block diagram

下载: 全尺寸图片幻灯片

图 5 基于深度状态空间模型的卡尔曼滤波框架

Fig. 5 Framework of Kalman filtering based on deep state space model

下载: 全尺寸图片幻灯片

图 6 KalmanNet中的卡尔曼增益计算流程

Fig. 6 The Kalman gain computation process in KalmanNet

下载: 全尺寸图片幻灯片

图 7 使用深度神经网络估计噪声统计特性

Fig. 7 Estimating noise statistical characteristics with deep neural networks

下载: 全尺寸图片幻灯片

图 8 基于深度学习的多模型自适应卡尔曼滤波的两类思路

Fig. 8 Two types of ideas for deep learning based multi model adaptive Kalman filtering

下载: 全尺寸图片幻灯片

参考文献(134)

[1]	孙旭, 李晓光, 李嘉锋, 卓力. 基于深度学习的图像超分辨率复原研究进展. 自动化学报, 2017, 43(5): 697−709 Sun Xu, Li Xiao-Guang, Li Jia-Feng, Zhuo Li. Review on deep learning based image super-resolution restoration algorithms. Acta Automatica Sinica, 2017, 43(5): 697−709
[2]	刘小波, 刘鹏, 蔡之华, 乔禹霖, 王凌, 汪敏. 基于深度学习的光学遥感图像目标检测研究进展. 自动化学报, 2021, 47(9): 2078−2089 Liu Xiao-Bo, Liu Peng, Cai Zhi-Hua, Qiao Yu-Lin, Wang Ling, Wang Min. Research progress of optical remote sensing image object detection based on deep learning. Acta Automatica Sinica, 2021, 47(9): 2078−2089
[3]	张号逵, 李映, 姜晔楠. 深度学习在高光谱图像分类领域的研究现状与展望. 自动化学报, 2018, 44(6): 961−977 Zhang Hao-Kui, Li Ying, Jiang Ye-Nan. Deep learning for hyperspectral imagery classification: the state of the art and prospects. Acta Automatica Sinica, 2018, 44(6): 961−977
[4]	刘文举, 聂帅, 梁山, 张学良. 基于深度学习语音分离技术的研究现状与进展. 自动化学报, 2016, 42(6): 819−833 Liu Wen-Ju, Nie Shuai, Liang Shan, Zhang Xue-Liang. Deep learning based speech separation technology and its developments. Acta Automatica Sinica, 2016, 42(6): 819−833
[5]	袁文浩, 孙文珠, 夏斌, 欧世峰. 利用深度卷积神经网络提高未知噪声下的语音增强性能. 自动化学报, 2018, 44(4): 751−759 Yuan Wen-Hao, Sun Wen-Zhu, Xia Bin, Ou Shi-Feng. Improving speech enhancement in unseen noise using deep convolutional neural network. Acta Automatica Sinica, 2018, 44(4): 751−759
[6]	鹿智, 秦世引, 李连伟, 张鼎豪. 智能人机交互中第一视角手势表达的一次性学习分类识别. 自动化学报, 2021, 47(6): 1284−1301 Lu Zhi, Qin Shi-Yin, Li Lian-Wei, Zhang Ding-Hao. One-shot learning classification and recognition of gesture expression from the egocentric viewpoint in intelligent human-computer interaction. Acta Automatica Sinica, 2021, 47(6): 1284−1301
[7]	段艳杰, 吕宜生, 张杰, 赵学亮, 王飞跃. 深度学习在控制领域的研究现状与展望. 自动化学报, 2016, 42(5): 643−654 Duan Yan-Jie, Lv Yi-Sheng, Zhang Jie, Zhao Xue-Liang, Wang Fei-Yue. Deep learning for control: the state of the art and prospects. Acta Automatica Sinica, 2016, 42(5): 643−654
[8]	Jin Z H, Si W Y, Liu A D, Zhang W A, Yu L, Yang C G. Learning a flexible neural energy function with a unique minimum for globally stable and accurate demonstration learning. IEEE Transactions on Robotics, 2023, 39(6): 4520−4538 doi: 10.1109/TRO.2023.3303011
[9]	任浩, 屈剑锋, 柴毅, 唐秋, 叶欣. 深度学习在故障诊断领域中的研究现状与挑战. 控制与决策, 2017, 32(8): 1345−1358 Ren Hao, Qu Jian-Feng, Chai Yi, Tang Qiu, Ye Xin. Deep learning for fault diagnosis: The state of the art and challenge. Control And Decision, 2017, 32(8): 1345−1358
[10]	Huang D J, Zhang W A, Guo F H, Liu W J, Shi X M. Wavelet packet decomposition-based multiscale CNN for fault diagnosis of wind turbine gearbox. IEEE Transactions on Cybernetics, 2023, 53(1): 443−453 doi: 10.1109/TCYB.2021.3123667
[11]	田娟秀, 刘国才, 谷珊珊, 鞠忠建, 刘劲光, 顾冬冬. 医学图像分析深度学习方法研究与挑战. 自动化学报, 2018, 44(3): 401−424 Tian Juan-Xiu, Liu Guo-Cai, Gu Shan-Shan, Ju Zhong-Jian, Liu Jin-Guang, Gu Dong-Dong. Deep learning in medical image analysis and its challenges. Acta Automatica Sinica, 2018, 44(3): 401−424
[12]	Jin Y Q, Wei N W, Fu M L, L H M, Zhang W A. Beyond learning: back to geometric essence of visual odometry via fusion-based paradigm. IEEE Transactions on Instrumentation and Measurement, 2021, 70: 1−15
[13]	Kalman R E. A new approach to linear filtering and prediction problems. Journal of Basic Engineering, 1960, 82(1): 35−45 doi: 10.1115/1.3662552
[14]	Bebis G, Georgiopoulos M. Feed-forward neural networks. IEEE Potentials, 1994, 13(4): 27−31 doi: 10.1109/45.329294
[15]	Elman J L. Finding structure in time. Cognitive science, 1990, 14(2): 179−211 doi: 10.1207/s15516709cog1402_1
[16]	Lecun Y, Bottou L, Bengio Y, Haffner P. Gradient-based learning applied to document recognition. Proceedings of the IEEE, 1998, 86(11): 2278−2324 doi: 10.1109/5.726791
[17]	Stubberud S C, Lobbia R N, Owen M. An adaptive extended Kalman filter using artificial neural networks. In: Proceedings of the 34th IEEE Conference on Decision and Control(CDC). New Orleans, USA: IEEE, 1995. 1852−1856
[18]	Choi M, Sakthivel R, Chung W K. Neural network-aided extended Kalman filter for SLAM problem. In: Proceedings of the 2007 IEEE International Conference on Robotics and Automation(ICRA). Rome, Italy: IEEE, 2007. 1686−1690
[19]	Owen M W, Stubberud A R. A neural extended kalman filter multiple model tracker. In: Proceedings of the Oceans 2003. Celebrating the Past... Teaming Toward the Future. San Diego, USA: IEEE, 2003. 4: 2111−2119
[20]	Li Y, Liu J Y, Jiang Y Q, Liu Y, Lei B Y. Virtual adversarial training-based deep feature aggregation network from dynamic effective connectivity for MCI identification. IEEE Transactions on Medical Imaging, 2022, 41(1): 237−251 doi: 10.1109/TMI.2021.3110829
[21]	Huang H F, Liu Q, Jiang Y Q, Yang Q Y, Zhu X F, Li Y. Deep spatio-temporal attention-based recurrent network from dynamic adaptive functional connectivity for MCI identification. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2022, 30: 2600−2612 doi: 10.1109/TNSRE.2022.3202713
[22]	Zhao Z, Särkkä S, Rad A B. Kalman-based spectro-temporal ecg analysis using deep convolutional networks for atrial fibrillation detection. Journal of Signal Processing Systems, 2020, 92: 621−636 doi: 10.1007/s11265-020-01531-4
[23]	Lee M H, O’Hara N, Sonoda M, Kuroda N, Juhasz C, Asano E, Dong M, Jeong J W. Novel deep learning network analysis of electrical stimulation mapping-driven diffusion mri tractography to improve preoperative evaluation of pediatric epilepsy. IEEE Transactions on Biomedical Engineering, 2020, 67(11): 3151−3162 doi: 10.1109/TBME.2020.2977531
[24]	Xu K, Jiang X Y, Lin S J, Dai C Y, Chen W. Stochastic modeling based nonlinear bayesian filtering for photoplethysmography denoising in wearable devices. IEEE Transactions on Industrial Informatics, 2020, 16(11): 7219−7230 doi: 10.1109/TII.2020.2988097
[25]	Dai C S, Shan G Q, Liu X J, Ru C H, Xin L M, Sun Y. Automated orientation control of motile deformable cells. IEEE Transactions on Automation Science and Engineering, 20221−9
[26]	Perafan-Villota J C, Mondragon O H, Mayor-Toro W M. Fast and precise: parallel processing of vehicle traffic videos using big data analytics. IEEE Transactions on Intelligent Transportation Systems, 2022, 23(8): 12064−12073 doi: 10.1109/TITS.2021.3109625
[27]	Maha Vishnu V C, Rajalakshmi M, Nedunchezhian R[C]. telligent traffic video surveillance and accident detection system with dynamic traffic signal control. Cluster Computing, 2018, 21: 135−147 doi: 10.1007/s10586-017-0974-5
[28]	Abdelali H A, Derrouz H, Zennayi Y, Thami R O H, Bourzeix F. Multiple hypothesis detection and tracking using deep learning for video traffic surveillance. IEEE Access, 2021, 9: 164282−164291 doi: 10.1109/ACCESS.2021.3133529
[29]	Chen Y R, Xie X Y, Yu B, Li Y, Lin K H. Multitarget vehicle tracking and motion state estimation using a novel driving environment perception system of intelligent vehicles. Journal of Advanced Transportation, 2021, 2021: 1−16
[30]	Sudha D, Priyadarshini J. An intelligent multiple vehicle detection and tracking using modified vibe algorithm and deep learning algorithm. Soft Computing, 2020, 24: 17417−17429 doi: 10.1007/s00500-020-05042-z
[31]	Zhu D, Song R, Chen H, Klette R, Xu Y Y. Moment-based multi-lane detection and tracking. Signal Processing: Image Communication, 2021, 95: 116230 doi: 10.1016/j.image.2021.116230
[32]	Wyk F, Wang Y Y, Khojandi A, Masoud N. Real-Time sensor anomaly detection and identification in automated vehicles. IEEE Transactions on Intelligent Transportation Systems, 2020, 21(3): 1264−1276 doi: 10.1109/TITS.2019.2906038
[33]	Jin Y Q, Zhang W A, Sun H, Yu L. Learning-aided inertial odometry with nonlinear state estimator on manifold. IEEE Transactions on Intelligent Transportation Systems, 2023, 24(9): 9792−9803 doi: 10.1109/TITS.2023.3273391
[34]	Piga N A, Onyshchuk Y, Pasquale G, Pattacini U, Natale L. ROFT: real-time optical flow-aided 6D object pose and velocity tracking. IEEE Robotics and Automation Letters, 2022, 7(1): 159−166 doi: 10.1109/LRA.2021.3119379
[35]	Liu J G, Guo G. Vehicle localization during GPS outages with extended Kalman filter and deep learning. IEEE Transactions on Instrumentation and Measurement, 2021, 70: 1−10
[36]	Shen C, Zhang Y, Guo X T, Ch en, X Y, Cao H L, Tang J, Li J, Liu J. Seamless GPS/inertial navigation system based on self-learning square-root cubature Kalman filter. IEEE Transactions on Industrial Electronics, 2021, 68(1): 499−508 doi: 10.1109/TIE.2020.2967671
[37]	Shu X, Li G, Zhang Y J, Shen S Q, Chen Z, Liu Y G. Stage of charge estimation of lithium-ion battery packs based on improved cubature kalman filter with long short-term memory model. IEEE Transactions on Transportation Electrification, 2021, 7(3): 1271−1284 doi: 10.1109/TTE.2020.3041757
[38]	Surya S, Samanta A, Marcis V, Williamson S. Hybrid electrical circuit model and deep learning-based core temperature estimation of lithium-ion battery cell. IEEE Transactions on Transportation Electrification, 2022, 8(3): 3816−3824 doi: 10.1109/TTE.2022.3170359
[39]	Zhang H F, Yue D, Dou C X, Li K, Hancke G P. Two-step wind power prediction approach with improved complementary ensemble empirical mode decomposition and reinforcement learning. IEEE Systems Journal, 2021, 16(2): 2545−2555
[40]	Lee M S, Shifat T A, Hur J W. Kalman filter assisted deep feature learning for rul prediction of hydraulic gear pump. IEEE Sensors Journal, 2022, 22(11): 11088−11097 doi: 10.1109/JSEN.2022.3167926
[41]	Dantas H, Warren D J, Wendelken S M, Davis T S, Clark G A, Mathews V J. Deep learning movement intent decoders trained with dataset aggregation for prosthetic limb control. IEEE Transactions on Biomedical Engineering, 2019, 66(11): 3192−3203 doi: 10.1109/TBME.2019.2901882
[42]	Baek D, Seo J H, Kim J, Kwon D S. Hysteresis compensator with learning-based hybrid joint angle estimation for flexible surgery robots. IEEE Robotics and Automation Letters, 2020, 5(4): 6837−6844 doi: 10.1109/LRA.2020.2972821
[43]	Rezaee K, Mousavirad S J, Khosravi M R, Moghimi M K, Heidari M. An autonomous UAV-assisted distance-aware crowd sensing platform using deep shufflenet transfer learning. IEEE Transactions on Intelligent Transportation Systems, 2022, 23(7): 9404−9413 doi: 10.1109/TITS.2021.3119855
[44]	Zhang K Y, Jiang C X, Li J H, Yang S, Ma T, Xu C, Gao F. DIDO: deep inertial quadrotor dynamical odometry. IEEE Robotics and Automation Letters, 2022, 7(4): 9083−9090 doi: 10.1109/LRA.2022.3189168
[45]	潘泉, 于昕, 程咏梅, 张洪才. 信息融合理论的基本方法与进展. 自动化学报, 2003, 29(4): 599−615 Pan Quan, Yu Xin, Cheng Yong-Mei, Zhang Hong-Cai. Essential methods and progress of information fusion theory. Acta Automatica Sinica, 2003, 29(4): 599−615
[46]	潘泉, 胡玉梅, 兰华, 孙帅, 王增福, 杨峰. 信息融合理论研究进展: 基于变分贝叶斯的联合优化. 自动化学报, 2019, 45(7): 1207−1223 Pan Quan, Hu Yu-Mei, Lan Hua, Sun Shuai, Wang Zeng-Fu, Yang Feng[C]. formation fusion progress: joint optimization based on variational Bayesian theory. Acta Automatica Sinica, 2019, 45(7): 1207−1223
[47]	Kalman R E, Bucy R S. New results in linear filtering and prediction theory. Journal of Basic Engineering, 1961, 83(1): 95−108 doi: 10.1115/1.3658902
[48]	Julier S J, Uhlmann J K. Unscented filtering and nonlinear estimation. Proceedings of the IEEE, 2004, 92(3): 401−422 doi: 10.1109/JPROC.2003.823141
[49]	Yang X S, Zhang W A, Liu A D, Yu L. Linear fusion estimation for range-only target tracking with nonlinear transformation. IEEE Transactions on Industrial Informatics, 2020, 16(10): 6403−6412 doi: 10.1109/TII.2019.2955931
[50]	Gibbs R G. New Kalman filter and smoother consistency tests. Automatica, 2013, 49(10): 3141−3144 doi: 10.1016/j.automatica.2013.07.013
[51]	杨峰, 王永齐, 梁彦, 潘泉. 基于概率假设密度滤波方法的多目标跟踪技术综述. 自动化学报, 2013, 39(11): 1944−1956 doi: 10.3724/SP.J.1004.2013.01944 Yang Feng, Wang Yong-Qi, Liang Yan, Pan Quan. A survey of PHD filter based multi-target tracking. Acta Automatica Sinica, 2013, 39(11): 1944−1956 doi: 10.3724/SP.J.1004.2013.01944
[52]	Huang Y L, Zhang Y G, Wu Z M, Li N, Chambers J. A novel adaptive Kalman filter with inaccurate process and measurement noise covariance matrices. IEEE Transactions on Automatic Control, 2018, 63(2): 594−601 doi: 10.1109/TAC.2017.2730480
[53]	Hu Y M, Wang X Z, Pan Q, Hu Z T, Moran B. Variational Bayesian Kalman filter using natural gradient. Chinese Journal of Aeronautics, 2022, 35(5): 1−10 doi: 10.1016/j.cja.2021.08.033
[54]	He Y, Song Q, Dong Y L, Yang J. Adaptive tracking algorithm based on modified strong tracking filter. In: Proceedings of the 2006 CIE International Conference on Radar. Shanghai, China: IEEE, 2006. 1−4
[55]	Yang X S, Zhang W A, Yu L, Xing K X. Multi-rate distributed fusion estimation for sensor network-based target tracking. IEEE Sensors Journal, 2016, 16(5): 1233−1242 doi: 10.1109/JSEN.2015.2497464
[56]	Gordon N J, Salmond D J, Smith A FM. Novel approach to nonlinear/non-Gaussian Bayesian state estimation. IEE Proceedings F (Radar and Signal Processing), 1993, 140(2): 107−113 doi: 10.1049/ip-f-2.1993.0015
[57]	Liu J S, Chen R. Sequential Monte Carlo methods for dynamic systems. Journal of the American Statistical Association, 1998, 93(443): 1032−1044 doi: 10.1080/01621459.1998.10473765
[58]	Kingma D P, Welling M. Auto-encoding variational bayes. arXiv: 1312.6114, 2013.
[59]	Krishnan R G, Shalit U, Sontag D. Deep Kalman filters. arXiv: 1511.05121, 2015.
[60]	Karl M, Soelch M, Bayer J, Smagt P v d. Deep variational bayes filters: unsupervised learning of state space models from raw data. In: Proceedings of the 5th International Conference on Learning Representations Virtual (ICLR). Toulon, France, 2017.
[61]	Liu W, Lai Z L, Bacsa K, Chatzi E. Neural extended Kalman filters for learning and predicting dynamics of structural systems. arXiv: 2210.04165, 2022.
[62]	杨旭升, 张文安, 俞立. 适用于事件触发的分布式随机目标跟踪方法. 自动化学报, 2017, 43(8): 1393−1401 Yang Xu-Sheng, Zhang Wen-An, Yu Li. Distributed tracking method for maneuvering targets with event-triggered mechanism. Acta Automatica Sinica, 2017, 43(8): 1393−1401
[63]	Gedon D, Wahlström N, Schön T B, Ljung L. Deep state space models for nonlinear system identification. IFAC-PapersOnLine, 2021, 54(7): 481−486 doi: 10.1016/j.ifacol.2021.08.406
[64]	Li L Y, Yan J C, Yang X K, Jin Y H. Learning interpretable deep state space model for probabilistic time series forecasting. In: Proceedings of the 28th International Joint Conference on Artificial Intelligence (IJCAI). Macao, China: ACM, 2019. 2901−2908
[65]	Millidge B, Tschantz A, Seth A K, Buckley C L. Neural Kalman filtering. arXiv: 2102.10021.
[66]	Zhao C, Sun L, Yan Z, Neumann G, Duckett T, Stolkin R. Learning Kalman network: a deep monocular visual odometry for on-road driving. Robotics and Autonomous Systems, 2019, 121: 103234 doi: 10.1016/j.robot.2019.07.004
[67]	杨旭升, 王雪儿, 张文安, 汪鹏君. 基于渐进无迹卡尔曼滤波网络的人体肢体运动估计. 自动化学报, 2023, 49(8): 1723−1731 Yang Xu-Sheng, Wang Xue-Er, Zhang Wen-An, Wang Peng-Jun. Estimation of human limb motion based on progressive unscented Kalman filter network. Acta Automatica Sinica, 2023, 49(8): 1723−1731
[68]	Rangapuram S S, Seeger M, Gasthaus J, Stella L, Wang Y Y, Januschowski T. Deep state space models for time series forecasting. In: Proceedings of the 32nd International Conference on Neural Information Processing Systems (NIPS). Montreal, Canada: Curran Associates, 2018. 7796−7805
[69]	Bao T Z, Zhao Y H, Zaidi S A R, Xie S Q, Yang P F, Zhang Z Q. A deep Kalman filter network for hand kinematics estimation using sEMG. Pattern Recognition Letters, 2021, 143: 88−94 doi: 10.1016/j.patrec.2021.01.001
[70]	Zheng X, Zaheer M, Ahmed A, Wang Y, Smola A J, Xing E. State space LSTM models with particle MCMC inference. arXiv: 1711.11179, 2017.
[71]	Hochreiter S, Schmidhuber J. Long short-term memory. Neural Computation, 1997, 9(8): 1735−1780 doi: 10.1162/neco.1997.9.8.1735
[72]	尹宏鹏, 陈波, 柴毅, 刘兆栋. 基于视觉的目标检测与跟踪综述. 自动化学报, 2016, 42(10): 1466−1489 Yin Hong-Peng, Chen Bo, Chai Yi, Liu Zhao-Dong. Vision-based object detection and tracking: a review. Acta Automatica Sinica, 2016, 42(10): 1466−1489
[73]	孟琭, 杨旭. 目标跟踪算法综述. 自动化学报, 2019, 45(7): 1244−1260 Meng Lu, Yang Xu. A survey of object tracking algorithms. Acta Automatica Sinica, 2019, 45(7): 1244−1260
[74]	Lin W Y, Ren X Y, Hu J J, He Y Z, Li Z, Tong M S. Fast, robust and accurate posture detection algorithm based on Kalman filter and SSD for AGV. Neurocomputing, 2018, 316: 306−312 doi: 10.1016/j.neucom.2018.08.006
[75]	Ozaki R, Kuroda Y. EKF-based real-time self-attitude estimation with camera DNN learning landscape regularities. IEEE Robotics and Automation Letters, 2021, 6(2): 1737−1744 doi: 10.1109/LRA.2021.3060442
[76]	Tian J P, Xiong R, Shen W X, Lu J H. State-of-charge estimation of LiFePO4 batteries in electric vehicles: A deep-learning enabled approach. Applied Energy, 2021, 291: 116812 doi: 10.1016/j.apenergy.2021.116812
[77]	Youn W, Lim H, Choi H S, Rhudy M B, Ryu H, Kim S, Myung H. State estimation for HALE UAVs with deep-learning-aided virtual AOA/SSA sensors for analytical redundancy. IEEE Robotics and Automation Letters, 2021, 6(3): 5276−5283 doi: 10.1109/LRA.2021.3074084
[78]	Haarnoja T, Ajay A, Levine S, Abbeel P. Backprop KF: learning discriminative deterministic state estimators. In: Proceedings of the 30th International Conference on Neural Information Processing Systems (NIPS). Barcelona, Spain: Curran Associates, 2016, 29
[79]	Bharadwaj S, Prasad S, Almekkawy M. An upgraded siamese neural network for motion tracking in ultrasound image sequences. IEEE Transactions on Ultrasonics, Ferroelectrics, and Frequency Control, 2021, 68(12): 3515−3527 doi: 10.1109/TUFFC.2021.3095299
[80]	Xiao B, Xiao H R, Wang J W, Chen Y. Vision-based method for tracking workers by integrating deep learning instance segmentation in off-site construction. Automation in Construction, 2022, 136: 104148 doi: 10.1016/j.autcon.2022.104148
[81]	Lim H, Ryu H, Rhudy M B, Lee D J, Jang D J, Lee C, Park Y, Youn W, Myung H. Deep learning-aided synthetic airspeed estimation of UAVs for analytical redundancy with a temporal convolutional network. IEEE Robotics and Automation Letters, 2022, 7(1): 17−24 doi: 10.1109/LRA.2021.3117021
[82]	Ju C, Wang Z, Long C, Zhang X Y, Chang D E. Interaction-aware Kalman neural networks for trajectory prediction. In: Proceedings of the 2020 IEEE Intelligent Vehicles Symposium (IV). Las Vegas, USA: IEEE, 2020: 1793−1800
[83]	Yin H, Chen R J, Wang Y, Xiong R. RaLL: End-to-end radar localization on lidar map using differentiable measurement model. IEEE Transactions on Intelligent Transportation Systems, 2022, 23(7): 6737−6750 doi: 10.1109/TITS.2021.3061165
[84]	Li Y J, Yin G D, Zhuang W C, Zhang N, Wang J X, Geng K K. Compensating delays and noises in motion control of autonomous electric vehicles by using deep learning and unscented kalman predictor. IEEE Transactions on Systems, Man, and Cybernetics: Systems, 2020, 50(11): 4326−4338 doi: 10.1109/TSMC.2018.2850367
[85]	Lu G, Zhang X Y, Ouyang W, Xu D, Chen L, Gao Z Y. Deep non-local Kalman network for video compression artifact reduction. IEEE Transactions on Image Processing, 2020, 29: 1725−1737 doi: 10.1109/TIP.2019.2943214
[86]	Tariq M, Ali M, Naeem F, Poor H V. Vulnerability assessment of 6G-enabled smart grid cyber–physical systems. IEEE Internet of Things Journal, 2021, 8(7): 5468−5475 doi: 10.1109/JIOT.2020.3042090
[87]	Li D H, Zhou J, Liu Y Y. Recurrent-neural-network-based unscented Kalman filter for estimating and compensating the random drift of MEMS gyroscopes in real time. Mechanical Systems and Signal Processing, 2021, 147: 107057 doi: 10.1016/j.ymssp.2020.107057
[88]	Coskun H, Achilles F, DiPietro R, Navab N, Tombari F. Long short-term memory Kalman filters: recurrent neural estimators for pose regularization. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV). Venice, Italy: IEEE, 2017. 5524−5532
[89]	Chen C H, Lu C X X, Wang B, Trigoni N, Markham A. DynaNet: neural Kalman dynamical model for motion estimation and prediction. IEEE Transactions on Neural Networks and Learning Systems, 2021, 32(12): 5479−5491 doi: 10.1109/TNNLS.2021.3112460
[90]	Cui Y Q, He Y, Tang T T, Liu Y. A new target tracking filter based on deep learning. Chinese Journal of Aeronautics, 2022, 35(5): 11−24 doi: 10.1016/j.cja.2021.10.023
[91]	Revach G, Shlezinger N, Ni X Y, Escoriza A L, van Sloun R J G, Eldar Y C. KalmanNet: neural network aided Kalman filtering for partially known dynamics. IEEE Transactions on Signal Processing, 2022, 70: 1532−1547 doi: 10.1109/TSP.2022.3158588
[92]	Klein I, Revach G, Shlezinger N, Mehr J E, van Sloun R J G, Eldar Y C. Uncertainty in data-driven Kalman filtering for partially known state-space models. In: Proceedings of the 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Singapore, Singapore: IEEE, 2022. 3194−3198
[93]	Revach G, Shlezinger N, Locher T, Ni X Y, van Sloun R J G, Eldar Y C. Unsupervised learned Kalman filtering. In: Proceedings of the 30th European Signal Processing Conference (EUSIPCO). Belgrade, Serbia: IEEE, 2022. 1571−1575
[94]	Zhang Y X, Yu M, Zhang H, Yu D, Wang D L. NeuralKalman: a learnable Kalman filter for acoustic echo cancellation. arXiv: 2301.12363, 2023.
[95]	Choi G, Park J, Shlezinger N, Eldar Y C, Lee N. Split-KalmanNet: a robust model-based deep learning approach for state estimation. IEEE Transactions on Vehicular Technology, 20231−6
[96]	Deng H R, Revach G, Morgenstern H, Shlezinger N. KALMANBOT: KalmanNet-aided bollinger bands for pairs trading. In: Proceedings of the 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Rhodes Island, Greece: IEEE, 2023. 1−5
[97]	Buchnik I, Steger D, Revach G, van Sloun R J G, Routtenberg T, Shlezinger N. Latent-KalmanNet: learned Kalman filtering for tracking from high-dimensional signals. arXiv: 2304.07827, 2023.
[98]	郑婷婷, 杨旭升, 张文安, 俞立. 一种高斯渐进滤波框架下的目标跟踪方法. 自动化学报, 2018, 44(12): 2250−2258 Zheng Ting-Ting, Yang Xu-Sheng, Zhang Wen-An, Yu Li. A target tracking method in Gaussian progressive filtering framework. Acta Automatica Sinica, 2018, 44(12): 2250−2258
[99]	Yang X S, Zhang W A, Yu L, Yang F W. Sequential Gaussian approximation filter for target tracking with nonsynchronous measurements. IEEE Transactions on Aerospace and Electronic Systems, 2019, 55(1): 407−418 doi: 10.1109/TAES.2018.2852398
[100]	Yuen K V, Hoi K I, Mok K M. Selection of noise parameters for Kalman filter. Earthquake Engineering and Engineering Vibration, 2007, 60(1): 49−56
[101]	Yuen K V, Liang P F, Kuok S C. Online estimation of noise parameters for Kalman filter. Structural Engineering and Mechanics, 2013, 47(3): 361−381 doi: 10.12989/sem.2013.47.3.361
[102]	Li P, Zhang W A, Zhang J H. HMM based adaptive Kalman filter for orientation estimation. IEEE Sensors Journal, 2022, 22(17): 17065−17074 doi: 10.1109/JSEN.2022.3193000
[103]	Jouaber S, Bonnabel S, Velasco-Forere S, PiltéM. NNAKF: a neural network adapted Kalman filter for target tracking. In: Proceedings of the 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Toronto, Canada: IEEE, 2021. 4075−4079
[104]	Zheng T Y, Yao Y, He F H, Zhang X R. An RNN-based learnable extended Kalman filter design and application. In: Proceedings of the 18th European Control Conference (ECC). Napoli, Italy: IEEE, 2019. 25−28
[105]	Brossard M, Barrau A, Bonnabel S. AI-IMU dead-reckoning. IEEE Transactions on Intelligent Vehicles, 2020, 5(4): 585−595 doi: 10.1109/TIV.2020.2980758
[106]	Xiao Y M, Luo H Y, Zhao F, Wu F, Gao X L, Wang Q, Cui L Z. Residual attention network-based confidence estimation algorithm for non-holonomic constraint in GNSS/INS integrated navigation system. IEEE Transactions on Vehicular Technology, 2021, 70(11): 11404−11418 doi: 10.1109/TVT.2021.3113500
[107]	Wu F, Luo H Y, Jia H W, Zhao F, Xiao Y M, Gao X L. Predicting the noise covariance with a multitask learning model for Kalman filter-based GNSS/INS integrated navigation. IEEE Transactions on Instrumentation and Measurement, 2021, 70: 1−13
[108]	Blom H A P, Bar-Shalom Y. The interacting multiple model algorithm for systems with markovian switching coefficients. IEEE Transactions on Automatic Control, 1988, 33(8): 780−783 doi: 10.1109/9.1299
[109]	Yang X S, Zhang W A, Chen M Z Q, Yu L. Hybrid sequential fusion estimation for asynchronous sensor network-based target tracking. IEEE Transactions on Control Systems Technology, 2017, 25(2): 669−676 doi: 10.1109/TCST.2016.2558632
[110]	Fu Q E, Lu K L, Sun C Y. Deep learning aided state estimation for guarded semi-markov switching systems with soft constraints. IEEE Transactions on Signal Processing, 20231−17
[111]	Moon S, Youn W, Bang H. Novel deep-learning-aided multimodal target tracking. IEEE Sensors Journal, 2021, 21(18): 20730−20739 doi: 10.1109/JSEN.2021.3100588
[112]	Deng L C, Li D, Li R F. Improved IMM algorithm based on RNNs. Journal of Physics: Conference Series, 2020, 1518(1): 012055 doi: 10.1088/1742-6596/1518/1/012055
[113]	崔亚奇, 熊伟, 何友. 不确定航迹自适应预测模型. 航空学报, 2019, 40(5): 322557−322557 Cui Ya-Qi, Xiong Wei, He You. Adaptive forecast model for uncertain track. Acta Aeronauticaet Astronautica Sinica, 2019, 40(5): 322557−322557
[114]	纪守领, 李进锋, 杜天宇, 李博. 机器学习模型可解释性方法、应用与安全研究综述. 计算机研究与发展, 2019, 56(10): 2071−2096 Ji Shou-Ling, Li Jin-Feng, Du Tian-Yu, Li Bo. Survey on techniques, applications and security of machine learning interpretability. Journal of Computer Research and Development, 2019, 56(10): 2071−2096
[115]	成科扬, 王宁, 师文喜, 詹永照. 深度学习可解释性研究进展. 计算机研究与发展, 2020, 57(6): 1208−1217 Cheng Ke-Yang, Wang Ning, Shi Wen-Xi, Zhan Yong-Zhao. Research advances in the interpretability of deep learning. Journal of Computer Research and Development, 2020, 57(6): 1208−1217
[116]	Russell R L, Reale C. Multivariate uncertainty in deep learning. IEEE Transactions on Neural Networks and Learning Systems, 2022, 33(12): 7937−7943 doi: 10.1109/TNNLS.2021.3086757
[117]	武东杰, 仲训昱, 崔晓珍, 彭侠夫, 杨功流. 可在线配置结构的多源融合位姿估计框架. 机器人, 2022, 44(6): 660−671 Wu Dong-Jie, Zhong Xun-Yu, Cui Xiao-Zhen, Peng Xia-Fu, Yang Gong-Liu. Multi-source fusion pose estimation framework with online configurable structure. Robot, 2022, 44(6): 660−671
[118]	Müller S, Hollmann N, Arango S P, Grabocka J, Hutter F. Transformers can do Bayesian inference. In: Proceedings of the 5th International Conference on Learning Representations Virtual (ICLR). Virtual: OpenReview.net, 2022.
[119]	Xue B Y, Yu J W, Xu J H, Liu S S, Hu S K, Ye Z, Geng M Z, Liu X Y, Meng H L. Bayesian transformer language models for speech recognition. In: Proceedings of the 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Toronto, Canada: IEEE, 2021. 7378−7382
[120]	Ansari R F, Ebrahimi M A, Khademi M, Sadoghi Y H. Diffusion-based Kalman iterative thresholding for compressed sampling recovery over network. Signal Processing, 2023, 202: 108750 doi: 10.1016/j.sigpro.2022.108750
[121]	Alcaraz J M L, Strodthoff N. Diffusion-based time series imputation and forecasting with structured state space models. arXiv: 2208.09399, 2022.
[122]	Munir A, Blasch E, Kwon J, Kong J, Aved A. Artificial intelligence and data fusion at the edge. IEEE Aerospace and Electronic Systems Magazine, 2021, 36(7): 62−78 doi: 10.1109/MAES.2020.3043072
[123]	Blasch E, Pham T, Chong C Y, Koch W, Leung H, Braines D, Abdelzaher T. Machine learning/artificial intelligence for sensor data fusion–opportunities and challenges. IEEE Aerospace and Electronic Systems Magazine, 2021, 36(7): 80−93 doi: 10.1109/MAES.2020.3049030
[124]	张鋆豪, 何百岳, 杨旭升, 张文安. 基于可穿戴式惯性传感器的人体运动跟踪方法综述. 自动化学报, 2019, 45(8): 1439−1454 Zhang Jun-Hao, He Bai-Yue, Yang Xu-Sheng, Zhang Wen-An. A review on wearable inertial sensor based human motion tracking. Acta Automatica Sinica, 2019, 45(8): 1439−1454
[125]	Liu Q, Wang X, Rao N S V. Artificial neural networks for estimation and fusion in long-haul sensor networks. In: Proceedings of the 18th International Conference on Information Fusion (Fusion). Washington, USA: IEEE, 2015. 460−467
[126]	Brigham K, Kumar B V K V, Rao N S V. Learning-based approaches to nonlinear multisensor fusion in target tracking. In: Proceedings of the 16th International Conference on Information Fusion (Fusion). Istanbul, Turkey: IEEE, 2013. 1320−1327
[127]	Chowdhury F N. A neural approach to data fusion. In: Proceedings of the 1995 American Control Conference (ACC). Seattle, USA: IEEE, 1995, 3: 1693-1697
[128]	Peng Z X, Li Y, Hao G. The research on distributed fusion estimation based on machine learning. IEEE Access, 2020, 8: 38174−38184 doi: 10.1109/ACCESS.2020.2974039
[129]	Chen Y S, Yan G F. Multi-sensors data tracking fusion based on a neural network filter. In: Proceedings of the 2006 IEEE International Joint Conference on Neural Network Proceedings. Vancouver, Canada: IEEE, 2006. 981−984
[130]	Yang X S, Zhang W A, Yu L. A bank of decentralized extended information filters for target tracking in event-triggered WSNs. IEEE Transactions on Systems, Man, and Cybernetics: Systems, 2020, 50(9): 3281−3289 doi: 10.1109/TSMC.2018.2883706
[131]	Liu P, Wang L Z, Ranjan R, He G J, Zhao L. A survey on active deep learning: from model driven to data driven. ACM Computing Surveys, 2022, 54(10s): 1−34
[132]	Yang X S, Zhang W A, Yu L, Shi L. Performance evaluation of distributed linear regression Kalman filtering fusion. IEEE Transactions on Automatic Control, 2021, 66(6): 2889−2896 doi: 10.1109/TAC.2020.3012638
[133]	Blundell C, Cornebise J, Kavukcuoglu K, Wierstra D. Weight uncertainty in neural network. In: Proceedings of the 32nd International Conference on Machine Learning (ICML). Lille, France: PMLR, 2015. 1613−1622
[134]	Kendall A, Gal Y. What uncertainties do we need in Bayesian deep learning for computer vision? In: Proceedings of the 31st Conference on Neural Information Processing Systems (NIPS). Long Beach, USA: Curran Associates, 2017.