A journal of IEEE and CAA , publishes high-quality papers in English on original theoretical/experimental research and development in all areas of automation
Advanced Search
Volume 7 Issue 6
Oct.  2020

IEEE/CAA Journal of Automatica Sinica

  • JCR Impact Factor: 11.8, Top 4% (SCI Q1)
    CiteScore: 17.6, Top 3% (Q1)
    Google Scholar h5-index: 77， TOP 5
Turn off MathJax
Article Contents
Article Navigation >  IEEE/CAA Journal of Automatica Sinica  > 2020  >  7(6): 1489-1497
Tongle Zhou, Mou Chen and Jie Zou, "Reinforcement Learning Based Data Fusion Method for Multi-Sensors," IEEE/CAA J. Autom. Sinica, vol. 7, no. 6, pp. 1489-1497, Nov. 2020. doi: 10.1109/JAS.2020.1003180
Citation: Tongle Zhou, Mou Chen and Jie Zou, "Reinforcement Learning Based Data Fusion Method for Multi-Sensors," IEEE/CAA J. Autom. Sinica, vol. 7, no. 6, pp. 1489-1497, Nov. 2020. doi: 10.1109/JAS.2020.1003180
shu

Reinforcement Learning Based Data Fusion Method for Multi-Sensors

doi: 10.1109/JAS.2020.1003180
Funds:  This work was supported in part by the Major Projects for Science and Technology Innovation 2030 (2018AA0100800), the Equipment Pre-research Foundation of Laboratory (61425040104), the Joint Fund of China Electronics Technology for Equipment Preresearch (6141B08231110a), and the Funding for Short Visit Program of Nanjing University of Aeronautics and Astronautics (NUAA) (190915DF03)
More Information
    Abstract
  • In order to improve detection system robustness and reliability, multi-sensors fusion is used in modern air combat. In this paper, a data fusion method based on reinforcement learning is developed for multi-sensors. Initially, the cubic B-spline interpolation is used to solve time alignment problems of multi-source data. Then, the reinforcement learning based data fusion (RLBDF) method is proposed to obtain the fusion results. With the case that the priori knowledge of target is obtained, the fusion accuracy reinforcement is realized by the error between fused value and actual value. Furthermore, the Fisher information is instead used as the reward if the priori knowledge is unable to be obtained. Simulations results verify that the developed method is feasible and effective for the multi-sensors data fusion in air combat.

     

    • FullText(HTML)
  • loading
    • References(32)
  • [1]
    D. Hall and J. Llinas, “An introduction to multisensor data fusion,” in Proc. IEEE Int. Symposium on Circuits and Systems, Monterey, USA: IEEE, 1998, vol.6, pp. 537–540.
    [2]
    T. L. Zhou, M. Chen, Y. H. Wang, J. L. He, and C. G. Yang, “Information entropybased intention prediction of aerial targets under uncertain and incomplete information,” Entropy, vol. 22, no. 3, pp. 279, Feb. 2020. doi: 10.3390/e22030279
    [3]
    D. Nada, M. Bousbia-Salah, and M. Bettayeb, “Multi-sensor data fusion for wheelchair position estimation with unscented Kalman filter,” Int. J. Autom. and Computing, vol. 15, no. 2, pp. 207–217, Apr. 2018.
    [4]
    X. S. Yang, W. A. Zhang, M. Z. Q. Chen, and L. Yu, “Hybrid sequential fusion estimation for asynchronous sensor eetwork-based target tracking,” IEEE Trans. Control Systems Technology, vol. 25, no. 2, pp. 669–676, May 2017. doi: 10.1109/TCST.2016.2558632
    [5]
    W. S. Zhang and W. Z. Wan, “Research and application of data fusion technology in smart manager and control platform in sub-station,” Electrical Engineering, vol. 15, no. 2, pp. 48–52, Feb. 2014.
    [6]
    C. Garcia, R. Omar, and O. Aycard, “Multiple sensor fusion and classification for moving object detection and tracking,” IEEE Trans. Intelligent Transportation Systems, vol. 17, no. 2, pp. 1–10, Sept. 2015.
    [7]
    F. Y. Xiao, “Multi-sensor data fusion based on the belief divergence measure of evidences and the belief entropy,” Information Fusion, vol. 46, no. 1, pp. 23–32, Apr. 2018.
    [8]
    T. L. Zhou, M. Chen, and J. Zou. “Data fusion of air combat based on reinforcement learning,” in Proc. 4th IEEE Int. Conf. Advanced Robotics and Mechatronics, Osaka, Japan: IEEE, 2019, pp.492–497.
    [9]
    R. S. Sutton, A. G. Barto. Reinforcement Learning, Cambridge, MA, USA: MIT Press, 2017.
    [10]
    A. Sallab, M. Abdou, E. Perot, and S. Yogamani, “Deep reinforcement learning framework for autonomous driving,” Electronic Imaging, vol. 1, no. 19, pp. 70–76, Jan. 2017.
    [11]
    Z. J. Li, B. Huang, A. Ajoudani, C. G. Yang, C. Y. Su, and A. Bicchi, “Asymmetric bimanual control of dual-arm exoskeletons for human-cooperative manipulations,” IEEE Trans. Robotics, vol. 34, no. 1, pp. 264–271, Nov. 2017.
    [12]
    Z. J. Li, B. Huang, Z. F. Ye, M. D. Deng, and C. G. Yang, “Physical human-robot interaction of a robotic exoskeleton by admittance control,” IEEE Trans. Industrial Electronics, vol. 65, no. 1, pp. 9614–9624, Mar. 2018.
    [13]
    H. Zhu, Y. Cao, W. Wang, T. Jiang, and S. Jin, “Deep reinforcement learning for mobile edge caching: Review, new features, and open issues,” IEEE Network, vol. 32, no. 6, pp. 50–57, Nov. 2018. doi: 10.1109/MNET.2018.1800109
    [14]
    Z. J. Li, C. J. Deng, and K. K. Zhao, “Human cooperative control of a wearable walking exoskeleton for enhancing climbing stair activities,” IEEE Trans. Industrial Electronics, vol. 67, no. 4, pp. 3086–3095, May 2019.
    [15]
    Z. J. Li, J. J. Li, S. N. Zhao, Y. X. Yuan, Y. Kang, and C. L. P. Chen, “Adaptive neural control of a kinematically redundant exoskeleton robot using brain-machine interfaces,” IEEE Trans. Neural Networks and Learning Systems, vol. 30, no. 22, pp. 3558–3571, Oct. 2019.
    [16]
    T. T. Gao, Y. J. Liu, L. Liu, and D. P. Li, “Adaptive neural network-based control for a class of nonlinear pure-feedback systems with time-varying full state constraints,” IEEE/CAA J. Autom. Sinica, vol. 4, no. 5, pp. 41–51, May 2018.
    [17]
    Y. Li, R. X. Cui, Z. J. Li, and D. M. Xu, “Neural network approximation based nearoptimal motion planning with kinodynamic constraints using RRT,” IEEE Trans. Industrial Electronics, vol. 65, no. 11, pp. 8718–8729, Mar. 2018. doi: 10.1109/TIE.2018.2816000
    [18]
    L. Liu, Y. J. Liu, and S. C. Tong, “Neural networks-based adaptive finite-time fault-tolerant control for a class of strict-feedback switched nonlinear systems,” IEEE Trans. Cybernetics, vol. 49, no. 7, pp. 2536–2545, May 2018.
    [19]
    H. Xiao, R. X. Cui, and D. M. Xu, “A sampling-based Bayesian approach for cooperative multiagent online search with Resource constraints,” IEEE Trans. Cybernetics, vol. 48, no. 6, pp. 1773–1785, May 2018. doi: 10.1109/TCYB.2017.2715228
    [20]
    D. P. Li, Y. J. Liu, S. C. Tong, C. L. P. Chen, and D. J. Li, “Neural networks-based adaptive control for nonlinear state constrained systems with input delay,” IEEE Trans. Cybernetics, vol. 49, no. 4, pp. 1249–1258, Feb. 2018.
    [21]
    B. J. Lascara, J. W. Carson, and D. N. Edwards. “A study of primary surveillance radar traffic and its utility via ADS-B uplink,” in Proc. Integrated Communications, Navigation and Surveillance Conf. (ICNS) IEEE, pp.1–11, Jun. 2013.
    [22]
    K. Liang, Q. Pan, G. M. Song, X. G. Zhang, and Z. L. Zhang, “The study of multi-sensor time registration method based on curve fitting,” J. Shaanxi University of Science and Technology, vol. 6, no. 24, pp. 111–114, Dec. 2006.
    [23]
    C. Y. Deng and H. W. Lin, “Progressive and iterative approximation for least squares B-spline curve and surface fitting,” Computer-Aided Design, vol. 47, no. 1, pp. 32–44, Feb. 2014.
    [24]
    J. Chen and G. J. Wang, “Progressive-iterative approximation for triangular bezier surfaces,” Computer-Aided Design, vol. 43, no. 8, pp. 889–895, Dec. 2011. doi: 10.1016/j.cad.2011.03.012
    [25]
    Y. Kineri, M. Morioka, and T. Maekawa, “Point-tangent/point-normal Bspline curve interpolation/approximation algorithms,” Computer-Aided Design, vol. 44, no. 7, pp. 697–708, Jun. 2012. doi: 10.1016/j.cad.2012.02.011
    [26]
    H. P. Liu, F. C. Sun, and X. Y. hang, “Robotic material perception using active multi-modal fusion,” IEEE Trans. Industrial Electronics, vol. 9, no. 9, pp. 1–9, Nov. 2018.
    [27]
    L. Li, Y. S. Lv, and F.-Y. Wang, “Traffic signal timing via deep reinforcement learning,” IEEE/CAA J. Autom. Sinica, vol. 3, no. 3, pp. 247–254, Jul. 2016. doi: 10.1109/JAS.2016.7508798
    [28]
    A. Xi, T. W. Mudiyanselage, D. C. Tao, and C. Chen, “Balance control of a biped robot on a rotating platform based on efficient reinforcement learning,” IEEE/CAA J. Autom. Sinica, vol. 6, no. 4, pp. 938–951, Jul. 2019. doi: 10.1109/JAS.2019.1911567
    [29]
    T. L. Zhou, M. Chen, C. G. Yang, and Z. Q. Nie, “Data fusion using Bayesian theory and reinforcement learning method,” Science China Information Sciences, vol. 63, no.7, DOI: 10.1007/s11432-019-2751-4, 2020.
    [30]
    S. M. Chen, X. L. Chen, Z. K. Pei, X. X. Zhang, and H. J. Fang, “Distributed filtering algorithm based on tunable weights under untrustworthy dynamics,” IEEE/CAA J. Autom. Sinica, vol. 3, no. 2, pp. 225–232, Apr. 2016. doi: 10.1109/JAS.2016.7451110
    [31]
    J. J. Rissanen, “Fisher information and stochastic complexity,” IEEE Trans. Information Theory, vol. 42, no. 1, pp. 40–47, Jun. 1996. doi: 10.1109/18.481776
    [32]
    S. P. Wan, “Method of fusion for multi-sensor data based on fisher information,” Chinese J. Sensors and Actuators, vol. 21, no. 12, pp. 2035–2038, Dec. 2008.
    • Related Articles
    • Supplements(0)

Catalog

    通讯作者: 陈斌, bchen63@163.com
    • 1. 

      沈阳化工大学材料科学与工程学院 沈阳 110142

    1. 本站搜索
    2. 百度学术搜索
    3. 万方数据库搜索
    4. CNKI搜索

    Figures(10)  / Tables(8)

    Get Citation
    PDF
    XML

    Article Metrics

    Article views (1472) PDF downloads(150) Cited by()

    Highlights

    • A data pre-processing method is raised before data fusion, which could solve the time alignment problem.
    • To improve the accuracy of data fusion system, a data fusion approach based on reinforcement learning is designed by multi-sensors weight adjustment.
    • In the case without prior knowledge, the reinforcement learning based data fusion is realized by the Fisher information of observations.

    /

    DownLoad:  Full-Size Img  PowerPoint
    Return
    Return