Development of a Data Fusion method using Extended Kalman Filter for Collaborative Robots

Murad Omarov, Elgun Jabrayilzade

Abstract


The article considers the development of a Data Fusion method using the Extended Kalman Filter (EKF) to enhance the efficiency of collaborative robots operating in Industry 5.0 production scenarios, where the key task is to ensure adaptability, safety, and accuracy of human–machine interaction. The object of the study is the process of processing signals from heterogeneous sensors - the OV5647 camera, the HC-SR04 ultrasonic sensor, the MPU6050 inertial module, and odometry - which together form a multisensor information system of a mobile manipulator robot. The subject of the research includes models, methods, and algorithmic support for data integration aimed at creating a consistent and unified representation of the robot’s state and its surrounding environment. The goal is to develop a robust and adaptive information fusion method that compensates for measurement errors, reduces noise impact, and improves the consistency of sensor readings under dynamically changing environmental conditions. Within the study, an implementation of the EKF is proposed, in which the system state is predicted using a physical motion model, and subsequent updates are performed for each sensor considering their frequency and signal delays. The mathematical formulation of the method includes nonlinear process and measurement models, covariance matrices, Jacobian derivatives, and innovation estimation, which together ensure the filter’s stability even in the presence of stochastic disturbances and measurement noise. Numerical simulations have shown that the “raw” sensor data are characterized by different mean values and dispersions (for example, HC-SR04 – 100 cm with ±20 cm deviation, camera – 50 cm with ±5 cm deviation), whereas the fused data demonstrate a smoothed trajectory with an average of about 68–70 cm and reduced variance to 8–10 cm. This indicates effective noise suppression and improved localization accuracy. The developed algorithm also provides robustness against temporary sensor signal loss, enables real-time state estimation, and supports asynchronous processing of multi-frequency data streams. The use of the Mahalanobis distance metric for measurement association improves the accuracy of relevant data selection, minimizes the influence of false observations, and enhances the safety of human–robot interaction. The results confirm that applying the Extended Kalman Filter in the Data Fusion process significantly improves distance estimation quality, navigation accuracy, motion smoothness, and control reliability under conditions of incomplete information. The conclusions emphasize that the proposed method is universal, scalable, and suitable for integration into adaptive control systems of next-generation collaborative robots operating in complex and uncertain environments within the framework of the Industry 5.0 concept.

Keywords


Data Fusion, Extended Kalman Filter, collaborative robots, sensor integration, Industry 5.0, mobile platform, adaptive control, navigation, sensors

Full Text:

PDF

References


Nevliudov, I., Yevsieiev, V., Maksymova, S., Gopejenko, V., & Kosenko, V. (2025). Development of mathematical support for adaptive control for the intelligent gripper of the collaborative robot manipulator. Advanced Information Systems, 9(3), 57-65. https://doi.org/10.20998/2522-9052.2025.3.07.

Chouridis, I., Mansour, G., Papageorgiou, V., Mansour, M. T., & Tsagaris, A. (2025). Four-Dimensional Path Planning Methodology for Collaborative Robots Application in Industry 5.0. Robotics, 14(4), 48. https://doi.org/10.3390/robotics14040048.

Xia, G., Ghrairi, Z., Heuermann, A., & Thoben, K. D. (2025). Enhancing sustainability of human-robot collaboration in industry 5.0: Context-and interaction-aware human motion prediction for proactive robot control. Journal of Manufacturing Systems, 82, 376-388. https://doi.org/10.1016/j.jmsy.2025.06.022.

Cohen, Y., Biton, A., & Shoval, S. (2025). Fusion of Computer Vision and AI in Collaborative Robotics: A Review and Future Prospects. Applied Sciences, 15(14), 7905. https://doi.org/10.3390/app15147905.

Masalskyi, V., Dzedzickis, A., Korobiichuk, I., & Bučinskas, V. (2025). Hybrid mode sensor fusion for accurate robot positioning. Sensors, 25(10), 3008. https://doi.org/10.3390/s25103008.

Yevsieiev, V., Maksymova, S., Gurin, D., & Alkhalaileh, A. (2024). Data Fusion Research for Collaborative Robots-Manipulators within Industry 5.0. ACUMEN: International journal of multidisciplinary research, 1(4), 125-137. Retrieved from https://inlibrary.uz/index.php/aijmr/article/view/63482.

Yevsieiv V. Using the Dempster-Shafer theory in Data Fusion solutions for collaborative robotic manipulators within Industry 5.0 / V. Yevsieiv // Manufacturing & Mechatronic Systems 2024 : Proceedings of VIII st International Conference, October 25-26, 2024. - Kharkiv, 2024. - P. 99-101. https://openarchive.nure.ua/handle/document/28949.

Chen, W., Jing, Y., Zhao, S., Yan, L., Liu, Q., & He, Z. (2025). A Distributed Collaborative Navigation Strategy Based on Adaptive Extended Kalman Filter Integrated Positioning and Model Predictive Control for Global Navigation Satellite System/Inertial Navigation System Dual-Robot. Remote Sensing, 17(4), 721. https://doi.org/10.3390/rs17040721.

Keshvarparast, A., Battini, D., Battaia, O., & Pirayesh, A. (2024). Collaborative robots in manufacturing and assembly systems: literature review and future research agenda. Journal of Intelligent Manufacturing, 35(5), 2065-2118. https://doi.org/10.1007/s10845-023-02137-w.

Rahman, M. M., Khatun, F., Jahan, I., Devnath, R., & Bhuiyan, M. A. A. (2024). Cobotics: the evolving roles and prospects of next‐generation collaborative robots in Industry 5.0. Journal of Robotics, 2024(1), 2918089. https://doi.org/10.1155/2024/2918089.

Guerra-Zubiaga, D. A., Aksu, M., Richards, G., & Kuts, V. (2025). Integrating Digital Twin Software Solutions with Collaborative Industrial Systems: A Comprehensive Review for Operational Efficiency. Applied Sciences, 15(13), 7049. https://doi.org/10.3390/app15137049.

Urrea, C., & Kern, J. (2025). Recent Advances and Challenges in Industrial Robotics: A Systematic Review of Technological Trends and Emerging Applications. Processes, 13(3), 832. https://doi.org/10.3390/pr13030832.

Soudani, M. L., Nissabouri, S., Ech-Chhibat, M. E. H., Haidoury, M., & Elhirch, I. (2025, May). Industrial Robots and Collaborative Robots: A Comparative Study. In 2025 5th International Conference on Innovative Research in Applied Science, Engineering and Technology (IRASET) (pp. 1-10). IEEE. https://doi.org/10.1109/IRASET64571.2025.11008132.

Attar, H., Abu-Jassar, A. T., Yevsieiev, V., Lyashenko, V., Nevliudov, I., & Luhach, A. K. (2022). Zoomorphic mobile robot development for vertical movement based on the geometrical family caterpillar. Computational intelligence and neuroscience, 2022(1), 3046116. https://doi.org/10.1155/2022/3046116.

Nevlyudov, I. Sh., Yevsyeyev, V. V., & Gurin, D. V. (2025). Model development of dynamic representation a model description parameters for the environment of a collaborative robot manipulator within the industry 5.0 framework. Sistemi upravlinnya, navigaciyi ta zv’yazku. Zbirnik naukovih prac, 1(79), 42-48. https://doi.org/10.26906/SUNZ.2025.1.42-48

Chen, B., Tong, X., Wan, J., Wang, L., Duan, X., Wang, Z., & Xia, X. (2025). Knowledge sharing-enabled low-code program for collaborative robots in mix-model assembly. Journal of Industrial Information Integration, 45, 100824. https://doi.org/10.1016/j.jii.2025.100824.

Liu, C., Wang, T., Li, Z., Li, S., & Tian, P. (2025). A Novel Loosely Coupled Collaborative Localization Method Utilizing Integrated IMU-Aided Cameras for Multiple Autonomous Robots. Sensors, 25(10), 3086. https://doi.org/10.3390/s25103086.

Joon, A., Kowalczyk, W., & Herman, P. (2025). Control of Multiple Mobile Robots Based on Data Fusion from Proprioceptive and Actuated Exteroceptive Onboard Sensors. Electronics, 14(4), 776. https://doi.org/10.3390/electronics14040776.

Nevliudov I. Features of Using Data Fusion With Extended Kalman Filter in Industry 5.0 Concepts / I. Nevliudov, V. Yevsieiev, Elgun Jabrayilzade // International Scientific Conference “Intellectual Resource of Today: Scientific Tasks, Development and Questions”, collection of scientific papers with materials of the V International Scientific Conference, August 29, 2025. — Vinnytsia : LLC “UKRLOGOS Group, 2025. — P. 195-199. - DOI : https://doi.org/10.62731/mcnd-29.08.2025.

Yevsieiev V. Using Multi-Agent Systems in the Management of Collaborative Robots / V. Yevsieiev // Computer-integrated technologies, automation and robotics 2025 : Thesises of Reports of II st All-Ukrainian Conference, May 16-17, 2025. - Kharkiv, 2025. - P. 13-17. https://openarchive.nure.ua/handle/document/30230.

Hesar, H. D., & Hesar, A. D. (2025). Adaptive dual augmented extended Kalman filtering of ECG signals. Measurement, 239, 115457. https://doi.org/10.1016/j.measurement.2024.115457.

Youm, D., Oh, H., Choi, S., Kim, H., Jeon, S., & Hwangbo, J. (2025, May). Legged robot state estimation with invariant extended kalman filter using neural measurement network. In 2025 IEEE International Conference on Robotics and Automation (ICRA) (pp. 670-676). IEEE. https://doi.org/10.1109/ICRA55743.2025.11127971.

Hasan, H. S., Kamil, F., & Khudhair, M. R. (2025). Optimization of improved extended Kalman filter for mobile robot Navigation. environment, 15(19), 20. https://doi.org/10.55214/25768484.v9i5.7370.

Sundaram, G., Bose, S., Kandasamy, V. K., & Thandiyappan, B. (2025). Robust and Reliable State Estimation for a Five-Axis Robot Using Adaptive Unscented Kalman Filtering. Engineering Proceedings, 95(1), 1. https://doi.org/10.3390/engproc2025095001.

Meng, W., Wu, T., Yin, H., & Zhang, F. (2025). NuRF: Nudging the Particle Filter in Radiance Fields for Robot Visual Localization. IEEE Transactions on Cognitive and Developmental Systems. https://doi.org/10.1109/TCDS.2025.3553261.

He, P., Zhao, Y., Tan, M., & Liao, B. (2025, February). Path optimization model of manipulator based on dh parameter method and genetic algorithm. In Journal of Physics: Conference Series (Vol. 2964, No. 1, p. 012018). IOP Publishing. https://doi.org/10.1088/1742-6596/2964/1/012018.

Niu, Q., Zhao, J., Liang, L., Xing, J., Li, H., & Wang, Z. (2025). A general framework for the analytical inverse kinematics solution of industrial robots. Proceedings of the Institution of Mechanical Engineers, Part C: Journal of Mechanical Engineering Science, 239(12), 4499-4511. https://doi.org/10.1177/09544062251318236.

Gündoğan, N., & Doğan, C. (2025). Inverse Kinematic Analysis of a 5DOF Gantry Type Welding Robot. Türk Doğa ve Fen Dergisi, 14(2), 195-203. https://doi.org/10.46810/tdfd.1633814.

Kadhim, M. N., Al-Shammary, D., Mahdi, A. M., & Ibaida, A. (2025). Feature selection based on Mahalanobis distance for early Parkinson disease classification. Computer Methods and Programs in Biomedicine Update, 7, 100177. https://doi.org/10.1016/j.cmpbup.2025.100177.

Fan, B., Zhang, L., Cai, S., Du, M., Liu, T., Li, Q., & Shull, P. (2025). Influence of Sampling Rate on Wearable IMU Orientation Estimation Accuracy for Human Movement Analysis. Sensors, 25(7), 1976. https://doi.org/10.3390/s25071976.

Mohd Yusoff, Z., Ismail, N., & Ahmad Sabri, N. A. S. (2025). Formulation of K-nearest neighbor model by varying the distance metrics of mahalanobis, correlation and cosine in discriminating different grades of Aquilaria oil. Journal of Essential Oil Bearing Plants, 28(2), 427-440. https://doi.org/10.1080/0972060X.2025.2469677.

Lee, J., & Kang, J. (2025). Extended Kalman Filter-Based Visual Odometry in Dynamic Environments Using Modified 1-Point RANSAC. Biomimetics. https://doi.org/10.3390/biomimetics10100710.

De Leon, E., Riensche, A., Bevans, B. D., Billings, C., Siddique, Z., & Liu, Y. (2025). A Review of Modeling, Simulation, and Process Qualification of Additively Manufactured Metal Components via the Laser Powder Bed Fusion Method. Journal of Manufacturing and Materials Processing, 9(1), 22. https://doi.org/10.3390/jmmp9010022.

Zheng, Y., Yang, H., Jiang, G., Hu, S., Tao, T., & Mei, X. (2025). Data-mechanism fusion modeling and compensation for the spindle thermal error of machining center based on digital twin. Measurement, 250, 117152. https://doi.org/10.1016/j.measurement.2025.117152.

Biswas, B., Mishra, S., & Balamurugan, S. (2025). Data Analytics and Collaborative Robots in Smart Territory: Research Methodology, Applications, and Open Challenges. Intelligent Robots and Cobots: Industry 5.0 Applications, 291-316. https://doi.org/10.1002/9781394198252.ch14.

Shi, S., Peng, Q., Liu, T., Dai, Y., & Meng, J. (2025). Online estimation of inertia-supporting sustaining power boundary of lithium-ion battery energy storage systems based on model-data fusion method. Applied Energy, 393, 126064. https://doi.org/10.1016/j.apenergy.2025.126064.


Refbacks

  • There are currently no refbacks.