The New Trend of State Estimation: From Model-Driven to Hybrid-Driven Methods
Open accessThe DOI matches its Crossref record; 113 of the 113 references it cites were found in a registry or an index.
Abstract
State estimation is widely used in various automated systems, including IoT systems, unmanned systems, robots, etc. In traditional state estimation, measurement data are instantaneous and processed in real time. With modern systems’ development, sensors can obtain more and more signals and store them. Therefore, how to use these measurement big data to improve the performance of state estimation has become a hot research issue in this field. This paper reviews the development of state estimation and future development trends. First, we review the model-based state estimation methods, including the Kalman filter, such as the extended Kalman filter (EKF), unscented Kalman filter (UKF), cubature Kalman filter (CKF), etc. Particle filters and Gaussian mixture filters that can handle mixed Gaussian noise are discussed, too. These methods have high requirements for models, while it is not easy to obtain accurate system models in practice. The emergence of robust filters, the interacting multiple model (IMM), and adaptive filters are also mentioned here. Secondly, the current research status of data-driven state estimation methods is introduced based on network learning. Finally, the main research results for hybrid filters obtained in recent years are summarized and discussed, which combine model-based methods and data-driven methods. This paper is based on state estimation research results and provides a more detailed overview of model-driven, data-driven, and hybrid-driven approaches. The main algorithm of each method is provided so that beginners can have a clearer understanding. Additionally, it discusses the future development trends for researchers in state estimation.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Figures






Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Hochreiter, S., & Schmidhuber, J. (1997) · Neural Computation · doi:10.1162/neco.1997.9.8.1735 · Cited by 102,318 · cited 1×
“The emergence of long short-term memory (LSTM) solved the long-term dependence problem of RNNs [84].”
BackgroundA New Approach to Linear Filtering and Prediction Problems
Kalman, R. E. (1960) · Journal of Basic Engineering · doi:10.1115/1.3662552 · Cited by 31,751
Sequence to Sequence Learning with Neural Networks
Sutskever, I., Vinyals, O., & Le, Q. V. (2014) · arXiv · doi:10.48550/arxiv.1409.3215 · Cited by 17,766 · cited 1×
“The other is that the encoder encodes the input data into a context vector and outputs the variable-length sequence as a fixed-length sequence [87].”
MethodA tutorial on particle filters for online nonlinear/non-Gaussian Bayesian tracking
Arulampalam, M. S., Maskell, S., Gordon, N., & Clapp, T. (2002) · IEEE Transactions on Signal Processing · doi:10.1109/78.978374 · Cited by 11,502 · cited 1×
“Two reviews provide details about particle filters, [42,43].”
BackgroundEffective Approaches to Attention-based Neural Machine Translation
Luong, T., Pham, H., & Manning, C. D. (2015) · Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d15-1166 · Cited by 8,382 · cited 1×
“There are two common attention mechanisms: Bahdanau attention [88] and Luong attention [89], also known as additive attention and multiplicative attention.”
BackgroundExtrapolation, Interpolation, and Smoothing of Stationary Time Series: With Engineering Applications
Wiener, N. (1949) · The MIT Press eBooks · doi:10.7551/mitpress/2946.001.0001 · Cited by 4,826 · cited 1×
“[8] designed the Wiener filter in the frequency domain to achieve linear optimal dynamic estimation in a stationary random process system.”
Method(2011) · Cited by 3,939
A new method for the nonlinear transformation of means and covariances in filters and estimators
Julier, S., Uhlmann, J., & Durrant-Whyte, H. F. (2000) · IEEE Transactions on Automatic Control · doi:10.1109/9.847726 · Cited by 3,735
Attention-Based Models for Speech Recognition
Chorowski, J., Bahdanau, D., Serdyuk, D., Cho, K., & Bengio, Y. (2015) · arXiv · doi:10.48550/arxiv.1506.07503 · Cited by 2,021 · cited 1×
“There are two common attention mechanisms: Bahdanau attention [88] and Luong attention [89], also known as additive attention and multiplicative attention.”
BackgroundThe scaled unscented transformation
Julier, S. J. (2002) · Proceedings of the 2002 American Control Conference (IEEE Cat. No.CH37301) · doi:10.1109/acc.2002.1025369 · Cited by 1,114 · cited 1×
“In 2002, Julier proposed the UKF method and selected sampling points as the unscented transformation [32].”
Method
Research works printed but not linked: 7
- Xin, 2019, Multi-UAV Cooperative Target Tracking Control Based on Nonlinear Guidance, Command. Inf. Syst. Technol., 10, 47
- Ma, 2019, State estimation of AC and DC distribution network under three-phase unbalance, Autom. Electr. Power Syst., 43, 65
- Sorenson, H.W. (1985). Kalman Filtering: Theory and Application, IEEE Press.
- Qin, Y.Y., Zhang, H.Y., and Wang, S.H. (1998). Principles of Kalman Filtering and Integrated Navigation, Northwestern Polytechnical University Press.
- Fu, M., Deng, Z.H., and Zhang, J.W. (2010). Kalman Filtering Theory and Its Application in Navigation System, Science Press.
- Julier, S.J., and Uhlmann, J.K. (1995, January 21–23). A new approach for filtering nonlinear system. Proceedings of the 1995 American Control Conference, Seattle, WA, USA.
- 1996, Non Linear Filtering: Interacting Particle Solution, Markov Process. Relat. Fields, 2, 555
Cited by
Items 101–148 of 148
Extended target tracking using neural network and Gaussian process
Wang, H., & Song, L. (2025) · Electronics Letters · doi:10.1049/ell2.70151 · Cited by 1
Yadav, P., Piri, J., Sengupta, A., & Sengupta, M. (2025) · International Journal of Adaptive Control and Signal Processing · doi:10.1002/acs.4056 · Cited by 1
State Estimation of Environmental Temperature Based on Deep Learning and Unscented Kalman Filtering
Yu, Y., Ma, S., Wang, C., Wu, X., & Xu, C. (2025) · IEEE Sensors Journal · doi:10.1109/jsen.2025.3626674 · Cited by 1
“In complex nonlinear environments and under non-Gaussian noise interference in industrial settings, the estimation performance of these methods can be substantially degraded [15].”
Zhang, Y., Yang, M., Zeng, Y., Chen, H., Zhang, L., & Huang, J. X. (2025) · International Conference on Big Data and Information Analytics (BigDIA) · doi:10.1109/bigdia68682.2025.11383169 · Cited by 1
Abbas, N., & Karimpour, H. (2026) · European Journal of Control · doi:10.1016/j.ejcon.2026.101510 · Cited by 1
Hu, J., Zhao, M., Bai, S., Ren, Y., Fang, R., Zhu, X., & Yin, G. (2026) · Mechatronics · doi:10.1016/j.mechatronics.2026.103530 · Cited by 1
Kalman Filter-based Path Following Control Design for Unmanned Surface Vehicles
Sun, T., Yang, Z., Shao, M., Song, L., Liu, X., & Feng, S. (2026) · Journal of Marine Science and Application · doi:10.1007/s11804-026-00892-9 · Cited by 1
Gargouri, S., Mansouri, M. M., Kahloul, A. A., Kermani, M., & Sakly, A. (2026) · Energies · doi:10.3390/en19143301 · Cited by 1
Tolerance-Dependent Multilayer Robust Estimation of Power System States
Shahriar, M. S. (2022) · Arabian Journal for Science and Engineering · doi:10.1007/s13369-022-06707-7 · Cited by 1
Thiruselvan, D., & Ananth, J. P. (2023) · Cybernetics & Systems · doi:10.1080/01969722.2023.2175142 · Cited by 1
“Underwater surveillance is the primary component of national defense and economic development (Yu et al. 2020; Luo, Han, and Fan 2018; Jin et al. 2021).”
RCUKF: Data-Driven Modeling Meets Bayesian Estimation
Anurag, K. A., Azizi, K., Sorrentino, F., & Wan, W. (2025) · IFAC-PapersOnLine · doi:10.1016/j.ifacol.2025.12.251 · Cited by 1
“On the other hand, data-driven methods, such as deep black-box networks, have become popular for capturing vehicle dynamics when first–principles models are unreliable (Rai and Sahu (2020); Jin et al. (2021); Zhang et al. (2023)).”
Hybrid State Estimation of Uncertain Nonlinear Dynamics Using Neural ProcessesPreprint
Hunter, D., & Enyioha, C. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2509.12522 · Cited by 1
“Factors such as stochastic environmental perturbations, modeling errors, and sensor limitations often introduce modeling inaccuracies that can severely degrade estimation performance [12, 13].”
Deep Fusion Predictive Modeling Based on Noise Analysis
Jin, X., Zhang, J., Su, T., Kong, J., & Bai, Y. (2021) · International Conference on Control, Automation and Information Sciences (ICCAIS) · doi:10.1109/iccais52680.2021.9624540
Self-citationKosović, I. N., Mastelić, T., Sokol, D., & Kuražić, D. Š. (2022) · Journal of Communications Software and Systems · doi:10.24138/jcomss-2022-0092
“There are two approaches when creating the models: a model-driven and data-driven approach [5].”
MethodRajendra, K., Subramanian, S., Karthik, N., Kaliyan, N., & Ganesan, S. (2023) · International Journal on Recent and Innovation Trends in Computing and Communication · doi:10.17762/ijritcc.v11i4s.6530
Dai, Q., Lu, F., & Xu, J. (2023) · Applied Sciences · doi:10.3390/app131910705
Hybrid Intelligent Model Fusing Brain Imaging and Cognition Scale Information for AD Diagnosis
Lin, X., Wang, H., Zhu, T., & Zhu, Q. (2023) · International Conference on Electronic Information Engineering and Computer Science (EIECS) · doi:10.1109/eiecs59936.2023.10435610
“To assess the impact of removing expert knowledge structure on the model's learning of sample features in a more comprehensible manner [10], we generated a bar chart combining scale information for the classification task.”
MethodАлиагаев, А. Р., Ажмухамедов, И. М., & Владимировна, Х. Т. (2024) · Modelirovanie, optimizaciâ i informacionnye tehnologii. · doi:10.26102/2310-6018/2024.46.3.029
“Существуют также нелинейные расширения фильтров Калмана для оценки нелинейных систем, такие как C ubature Kalman Filter ( CKF) и U nscented Kalman filter (UKF) [37].”
Zárate-Castrejón, J. L., Pérez, P. A. L., López-López, M., Núñez-Colín, C. A., Veloz-García, R. A., Mukhtar, H., & Peña-Caballero, V. (2024) · Mathematics · doi:10.3390/math12243996
Towards reliable data in the scope of unmanned aircraft systems
Lohre, K., Baier, H., Hardi, L., & Attenberger, A. (2025) · Forensic Science International Digital Investigation · doi:10.1016/j.fsidi.2025.301914
Towards Optimum Drones Track-to-Track Adaptive Fusion Using LSTM
Fares, S., Barbaresco, F., Seghrouchni, A. E. F., & Zitar, R. A. (2024) · International Radar Conference (RADAR) · doi:10.1109/radar58436.2024.10993807
“Please see reference [7] for more details.”
Enhance Parameter Identification Accuracy for State-of-Charge Optimization in Lithium-Ion Batteries
Shanaq, A. A., & Zohdy, M. A. (2025) · Transactions on Engineering and Computing Sciences · doi:10.14738/tmlai.1301.18254
Design and Experimental Test of Datatic Approximate Optimal Filter in Nonlinear Dynamic Systems
He, W., He, Z., Cao, W., Gao, H., Liu, T., Shuai, B., Liu, C., & Li, S. E. (2025) · International Conference on Control and Automation · doi:10.1109/icca65672.2025.11129724
Liu, Y., Zhao, H., & Li, Y. (2025) · Chinese Control Conference (CCC) · doi:10.23919/ccc64809.2025.11179129
“In recent years, propelled by rapid advancements in big data and deep learning technologies, data-driven approaches for vehicle state prediction have made remarkable progress [7-9].”
Jiang, W., Fu, Y., Zhao, H., Cai, X., Yang, R., Li, L., & Zhu, J. (2025) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3746252.3761207
Context and intent enhanced target tracking
Vaci, L., Mari, M., Snidaro, L., & Foresti, G. L. (2025) · Digital Signal Processing · doi:10.1016/j.dsp.2025.105836
Observability analysis for structural system identification based on state estimation
Alahmad, A., Solana, R. M., Porras, R., Lozano-Galant, J. A., & Turmo, J. (2023) · e-Archivo (Carlos III University of Madrid)
Classification of organometallic reactions using machine learning
Mahlangu, W. B., Rapulenyane, N., Hungwe, T., & Ncube, S. (2025) · International Journal of Innovative Research and Scientific Studies · doi:10.53894/ijirss.v8i12.11078
UAV Intelligent Control Design : A Flight Control Perspective
Zubair, A., Mir, I., Abbas, M., Masud, J., & Safdar, M. M. (2026) · AIAA SciTech Forum · doi:10.2514/6.2026-0542
Zubair, A., Mir, I., Abbas, M., Masud, J., & Safdar, M. M. (2026) · AIAA SciTech Forum · doi:10.2514/6.2026-0543
Chen, J., Hu, J., Zhang, P., Xu, W., Tang, Y., & Yang, D. (2026) · Mechanical Systems and Signal Processing · doi:10.1016/j.ymssp.2026.113999
Ambuj, Jayraj, P., Basak, A., & Machavaram, R. (2026) · Measurement · doi:10.1016/j.measurement.2026.121033
Dynamic Model Algorithm Based on Interactive Multi-Model Unscented Kalman Filtering
Hu, J., Yu, Z., Hu, Y., Li, H., Meng, G., & Lv, S. (2025) · International Conference on Intelligent Computing and Next Generation Networks (ICNGN) · doi:10.1109/icngn67480.2025.11413750
“While adding more models to match target motion improves state estimation accuracy, this significantly increases computational load and may even degrade tracker performance in many cases [5].”
Macedo, A. M., & Kienitz, K. H. (2026) · IEEE Access · doi:10.1109/access.2026.3680826
“Model-based approaches benefit from prior knowledge of dynamic laws to formulate the state estimation problem, dispensing with the large volumes of labeled data required in purely data-driven methods [3].”
Zhou, H., He, W., Bai, Y., & Guo, F. (2026) · Lecture notes in computer science · doi:10.1007/978-981-92-0369-7_3
Self-citationXi, Y.-A., Dong, X.-H., & Wu, S. (2026) · Sensors · doi:10.3390/s26103260
“…compared with representative deep learning-enhanced filtering methods and model-driven-data-driven hybrid filtering approaches in recent years [27], such as KalmanNet [28] and its recursive extensions [29], Transformer-based state estimation methods [30], and neural network-assisted Kalman…”
Application of an Improved Kalman Filter in Non-Gaussian Noise Sensor Signal Acquisition
Christodoulou, P., Ioannidis, A., & Tsiolis, S. (2026) · Journal of Applied Automation Technologies · doi:10.64972/jaat.2026v4.114
“In this situation, the state estimator may be affected by outliers and slower convergence rates, thereby impacting the reliability and timeliness of its output [19].”
Time-Aware Transformer Based Model for Maneuvering Targets Tracking
Li, Z., & Zhong, W. (2026) · International Conference on Image, Signal Processing and Pattern Recognition (ISPP) · doi:10.1109/ispp69262.2026.11542883
“In recent years, deep learning (DL) models have been widely applied in radar target tracking [3–6] .”
Ali, A., & Qian, R. (2026) · Earth Science Informatics · doi:10.1007/s12145-026-02193-9
“Consequently, researchers have increasingly shifted toward multivariate and data-driven modeling techniques to improve estimation accuracy (Jin et al. 2021).”
A.Anthoniammal, Prasad, D. A., Bhuvaneswari, G., Rajakumar, P. T. V., Vinothkumar, S., & Sudha, D. S. (2026) · International Academic Journal of Innovative Research · doi:10.71086/iajir/v13i2/iajir1329
Huang, L., Liu, Y., Fang, X., Liu, J., & Mei, J. (2026) · Electric Power Systems Research · doi:10.1016/j.epsr.2026.113962
Zhang, W., Huang, H., Wei, S., Han, N., Ren, P., Xu, Y., Zhang, L., & Zhou, Q. (2026) · IEEE Sensors Journal · doi:10.1109/jsen.2026.3722321
“These approaches are fundamentally reliant on understanding and modeling the underlying dynamics of the target model [39].”
Hybrid DNN and EnKF framework for dynamic state estimation in power systems
Zhang, T., Li, X., & Yang, J. (2026) · Engineering Research Express · doi:10.1088/2631-8695/aea3a8
“Another direction combines learning models with Kalman-type filtering [22–24].”
Credibility State Estimation Fusion Driven by Deep Learning for Low-Altitude Target Tracking
Ge, Q., Cao, Y., Lin, K., Liu, Y., & Huang, Y. (2026) · IEEE Transactions on Automation Science and Engineering · doi:10.1109/tase.2026.3736440
“Data-driven approaches, in contrast, are critically dependent on the quality of sensor measurements, including signal fidelity, temporal consistency, and measurement accuracy [7], [8], [9].”
A Graph based Kolmogorov-Arnold Hybrid Network for Distribution System State Estimation
Xu, T., Yang, N., & Wang, R. (2026) · IEEE Power Engineering Society General Meeting · doi:10.1109/pesgm58988.2026.11693799
“With the recent development of machine learning studies, data-driven state estimation methods have emerged as effective tools to address the increasing complexity and uncertainties of modern DNs [4].”
Roshni Rajan, K., & Shijoh, V. (2026) · International Conference on Innovations in Engineering and Technology (ICIET) · doi:10.1109/iciet70550.2026.11712855
A Literature Review on the Sensor Network Design Problem Applied to Chemical Processes
Silva, J. D. S., de Sá, M. C. C., da Silva, R. B., Manhães, B. C., Neves, D. M., Campos, L. F. D. O., Anzai, T. K., Diehl, F. C., & Pinto, J. C. (2026) · Processes · doi:10.3390/pr14203318
Metadata
- Authors
- Jin, X.-B., Robert Jeremiah, R. J., Su, T.-L., Bai, Y.-T., & Kong, J.-L.
- Affiliations
- Artificial Intelligence College, Beijing Technology and Business University, Beijing 100048, China
- School of Food and Health, Beijing Technology and Business University, Beijing 100048, China
- Venue
- Sensors
- Publisher
- MDPI AG
- Published
- 2021-03-16
- Volume
- 21
- Issue
- 6
- Pages
- 2085
- ISSN
- 1424-8220 (ISSN-L)
- PMC
- PMC8002332
- OpenAlex
- W3137956598
- Cited by
- 137
- References
- 113
- Citations by year
- 2026: 23 · 2025: 27 · 2024: 20 · 2023: 26 · 2022: 21 · 2021: 20
- FWCI
- 1.57
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- Sensors (publishedVersion, cc-by)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Funders
- National Natural Science Foundation of China (61903009)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Target Tracking and Data Fusion in Sensor Networks
- Physical Sciences › Engineering › Aerospace Engineering › Inertial Sensor and Navigation
- Physical Sciences › Engineering › Control and Systems Engineering › Control Systems and Identification
- Keywords
- state estimation, hybrid filter, data-driven estimation, network learning, Kalman filter, extended Kalman filter, unscented Kalman filter, cubature Kalman filter, particle filter, Gaussian mixture filter, robust filtering, interacting multiple model, adaptive filtering, sensor data
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.