A journal of IEEE and CAA , publishes high-quality papers in English on original theoretical/experimental research and development in all areas of automation
Volume 9 Issue 8
Aug.  2022

IEEE/CAA Journal of Automatica Sinica

  • JCR Impact Factor: 7.847, Top 10% (SCI Q1)
    CiteScore: 13.0, Top 5% (Q1)
    Google Scholar h5-index: 64, TOP 7
Turn off MathJax
Article Contents
M. Liu, X. Y. Zhang, M. S. Shang, and  L. Jin,  “Gradient-based differential kWTA network with application to competitive coordination of multiple robots,” IEEE/CAA J. Autom. Sinica, vol. 9, no. 8, pp. 1452–1463, Aug. 2022. doi: 10.1109/JAS.2022.105731
Citation: M. Liu, X. Y. Zhang, M. S. Shang, and  L. Jin,  “Gradient-based differential kWTA network with application to competitive coordination of multiple robots,” IEEE/CAA J. Autom. Sinica, vol. 9, no. 8, pp. 1452–1463, Aug. 2022. doi: 10.1109/JAS.2022.105731

Gradient-Based Differential kWTA Network With Application to Competitive Coordination of Multiple Robots

doi: 10.1109/JAS.2022.105731
Funds:  This work was supported in part by the National Natural Science Foundation of China (62176109), the Natural Science Foundation of Gansu Province (21JR7RA531), the Tibetan Information Processing and Machine Translation Key Laboratory of Qinghai Province (2021-Z-003), the CAS “Light of West China” Program, the Natural Science Foundation of Chongqing (China) (cstc2020jcyjzdxmX0028), the Chongqing Entrepreneurship and Innovation Support Program for Overseas Returnees (CX2021100), the Supercomputing Center of Lanzhou University, and the Science and Technology Project of Chengguan District of Lanzhou (2021JSCX0014), and the Education Department of Gansu Province: Excellent Graduate Student “Innovation Star” Project (2021CXZX-122)
More Information
  • Aiming at the k-winners-take-all (kWTA) operation, this paper proposes a gradient-based differential kWTA (GD-kWTA) network. After obtaining the network, theorems and related proofs are provided to guarantee the exponential convergence and noise resistance of the proposed GD-kWTA network. Then, numerical simulations are conducted to substantiate the preferable performance of the proposed network as compared with the traditional ones. Finally, the GD-kWTA network, backed with a consensus filter, is utilized as a robust control scheme for modeling the competition behavior in the multi-robot coordination, thereby further demonstrating its effectiveness and feasibility.


  • loading
  • [1]
    S. Li, M. Zhou, X. Luo, and Z. You, “Distributed winner-take-all in dynamic networks,” IEEE Trans. Automat. Contr., vol. 62, no. 2, pp. 577–589, Feb. 2017. doi: 10.1109/TAC.2016.2578645
    Y. Zhang, S. Xiang, X. Guo, A. Wen, and Y. Hao, “The winner-take-all mechanism for all-optical systems of pattern recognition and max-pooling operation,” J. Lightwave Technol., vol. 38, no. 18, pp. 5071–5077, Sept. 2020. doi: 10.1109/JLT.2020.3000670
    R. Lippmann, “An introduction to computing with neural nets,” IEEE ASSP Mag., vol. 4, no. 2, pp. 4–22, Apr. 1987. doi: 10.1109/MASSP.1987.1165576
    J. Lazzaro, S. Ryckebusch, M. A. Mahowald, and C. A. Mead, “Winner-take-all networks of O(N) complexity,” in Advances in Neural Inform. Processing Syst., D. S. Touretzky, Ed. Los Altos, CA: Morgan Kaufmann, 1989, pp. 703–711.
    E. Hernández-García, C. López, S. Pigolotti, and K. Andersen, “Species competition: Coexistence, exclusion and clustering,” Philosoph. Trans. R. Soc. A: Math.,Phys. Eng. Sci., vol. 367, no. 1901, pp. 3183–3195, Sept. 2009.
    P. Tien, “A new discrete-time multi-constrained K-winner-take-all recurrent network and its application to prioritized scheduling,” IEEE Trans. Neural Netw. Learn. Syst., vol. 28, no. 11, pp. 2674–2685, Nov. 2017. doi: 10.1109/TNNLS.2016.2600410
    Y. Zhang, S. Li, B. Xu, and Y. Yang, “Analysis and design of a distributed k-winners-take-all model,” Automatica, vol. 115, p. 108868, May 2020.
    K. Simone, A. Deutscher, J. M. Crook, F. W. Ohl, E. Budinger, C. K. Moeller, and H. Schulze, “Auditory cortical contrast enhancing by global winner-take-all inhibitory interactions,” PLoS ONE, vol. 3, no. 3, p. 12, Feb. 2008.
    Z. Guo and J. Wang, “Information retrieval from large data sets via multiple-winners-take-all,” in Proc. IEEE Int. Symp. Circuits Syst., Rio de Janeiro, Brazil, 2011, pp. 2669–2672.
    M. Liu, S. Li, and L. Jin, “Modeling and analysis of Matthew effect under switching social networks via distributed competition,” IEEE/CAA J. Autom. Sinica, vol. 9, no. 7, pp. 1311–1314, 2022. doi: 10.1109/JAS.2022.105527
    X. Zhao, Q. Zong, B. Tian, and M. You, “Finite-time dynamic allocation and control in multiagent coordination for target tracking,” IEEE Trans. Cybern.
    L. Su, C. J. Chang, and N. Lynch, “Spike-based winner-take-all computation: Fundamental limits and order-optimal circuits,” Neural Comput., vol. 31, no. 12, pp. 2523–2561, Dec. 2019. doi: 10.1162/neco_a_01242
    W. Lu, C.-S. Leung, J. Sum, and Y. Xiao, “DNN-kWTA with bounded random offset voltage drifts in threshold logic units,” IEEE Trans. Neural Netw. Learn. Syst..
    L. Jin, X. Zheng, and X. Luo, “Neural dynamics for distributed collaborative control of manipulators with time delays,” IEEE/CAA J. Autom. Sinica, vol. 9, no. 5, pp. 854–863, May 2022.
    W. J. Wolfe, D. Mathis, C. Anderson, J. Rothman, M. Gottler, G. Brady, R. Walker, G. Duane, and G. Alaghband, “K-winner networks,” IEEE Trans. Neural Netw., vol. 2, no. 2, pp. 310–315, Mar. 1991. doi: 10.1109/72.80342
    W. Maass, “On the computational power of winner-take-all,” Neural Comput., vol. 12, no. 11, pp. 2519–2535, Nov. 2000. doi: 10.1162/089976600300014827
    P. V. Tymoshchuk and D. C. Wunsch, “Design of a K-winners-take-all model with a binary spike train,” IEEE Trans. Cybern., vol. 49, no. 8, pp. 3131–3140, Aug. 2019. doi: 10.1109/TCYB.2018.2839691
    Z. Xu, H. Jin, K. Leung, Y. Leung, and C. Wong, “An automata network for performing combinatorial optimization,” Neurocomput., vol. 47, no. 14, pp. 59–83, Aug. 2002.
    L. V. Ferreira, E. Kaszkurewicz, and A. Bhaya, “Synthesis of a k-winners-take-all neural network using linear programming with bounded variables,” in Proc. Int. Joint Conf. Neural Netw, Portland, USA, 2003, vol. 3, pp. 2360–2365.
    S. Li, Y. Li, and Z. Wang, “A class of finite-time dual neural networks for solving quadratic programming problems and its k-winners-take-all application,” Neural Netw., vol. 39, pp. 27–39, 2013. doi: 10.1016/j.neunet.2012.12.009
    Q. Liu, C. Dang, and J. Cao, “A novel recurrent neural network with one neuron and finite-time convergence for k-winners-take-all operation,” IEEE Trans. Neural Netw., vol. 21, no. 7, pp. 1140–1148, Jul. 2010. doi: 10.1109/TNN.2010.2050781
    L. Jin, J. Yan, X. Du, X. Xiao, and D. Fu, “RNN for solving time-variant generalized Sylvester equation with applications to robots and acoustic source localization,” IEEE Trans. Ind. Inform., vol. 16, no. 10, pp. 6359–6369, Oct. 2020. doi: 10.1109/TII.2020.2964817
    X. Luo, W. Qin, A. Dong, K. Sedraoui, and M. Zhou, “Efficient and high-quality recommendations via momentum-incorporated parallel stochastic gradient descent-based learning,” IEEE/CAA J. Autom. Sinica, vol. 8, no. 2, pp. 402–411, Feb. 2021. doi: 10.1109/JAS.2020.1003396
    L. Jin, L. Wei, and S. Li, “Gradient-based differential neural-solution to time-dependent nonlinear optimization,” IEEE Trans. Automat. Contr.
    Z. Li, L. Gao, W. Chen, and Y. Xu, “Distributed adaptive cooperative tracking of uncertain nonlinear fractional-order multi-agent systems,” IEEE/CAA J. Autom. Sinica, vol. 7, no. 1, pp. 292–300, Jan. 2020. doi: 10.1109/JAS.2019.1911858
    Y. Yang, L. Liao, H. Yang, and S. Li, “An optimal control strategy for multi-UAVs target tracking and cooperative competition,” IEEE/CAA J. Autom. Sinica, vol. 8, no. 12, pp. 1931–1947, Dec. 2021. doi: 10.1109/JAS.2020.1003012
    Y. Ju, D. Ding, X. He, Q.-L. Han, and G. Wei, “Consensus control of multi-agent systems using fault-estimation-in-the-loop: Dynamic event-triggered case,” IEEE/CAA J. Autom. Sinica. DOI: 110.1109/JAS.2021.1004386.
    L. Ma, Y.-L. Wang, and Q.-L. Han, “Cooperative target tracking of multiple autonomous surface vehicles under switching interaction topologies,” IEEE/CAA J. Autom. Sinica. DOI: 10.1109/JAS.2022.105509.
    Z. Zhou, J. Liu, and J. Yu, “A survey of underwater multi-robot systems,” IEEE/CAA J. Autom. Sinica, vol. 9, no. 1, pp. 1–18, Jan. 2022. doi: 10.1109/JAS.2021.1004269
    X. Ge, Q.-L. Han, J. Wang, and X.-M. Zhang, “A scalable adaptive approach to multi-vehicle formation control with obstacle avoidance,” IEEE/CAA J. Autom. Sinica., vol. 9, no. 6, pp. 990–1004, 2022. doi: 10.1109/JAS.2021.1004263
    Y. Qi, L. Jin, X. Luo, Y. Shi, and M. Liu, “Robust k-WTA network generation, analysis, and applications to multiagent coordination,” IEEE Trans. Cybern. DOI: 10.1109/TCYB.2021.3079457.
    I. Ahmad, X. Ge, and Q.-L. Han, “Decentralized dynamic event-triggered communication and active suspension control of in-wheel motor driven electric vehicles with dynamic damping,” IEEE/CAA J. Autom. Sinica, vol. 8, no. 5, pp. 971–986, May 2021. doi: 10.1109/JAS.2021.1003967
    H. Zhang, J. Sun, and Z. Wang, “Distributed control of nonholonomic robots without global position measurements subject to unknown slippage constraints,” IEEE/CAA J. Autom. Sinica, vol. 9, no. 2, pp. 354–364, Feb. 2022. doi: 10.1109/JAS.2021.1004329
    L. Jin, S. Li, H. M. La, X. Zhang, and B. Hu, “Dynamic task allocation in multi-robot coordination for moving target tracking: A distributed approach,” Automatica, vol. 100, pp. 75–81, Feb. 2019. doi: 10.1016/j.automatica.2018.11.001
    S. Li, Y. Wang, J. Yu, and B. Liu, “A nonlinear model to generate the winner-take-all competition,” Commun. Nonlinear Sci. Numer. Simul., vol. 18, no. 3, pp. 435–442, Mar. 2013. doi: 10.1016/j.cnsns.2012.07.021
    Y. Zhang, K. Chen, and H. Tan, “Performance analysis of gradient neural network exploited for online time-varying matrix inversion,” IEEE Trans. Automat. Contr., vol. 54, no. 8, pp. 1940–1945, Aug. 2009. doi: 10.1109/TAC.2009.2023779
    A. Nazemi, “A neural network model for solving convex quadratic programming problems with some applications,” Eng. Appl. Artif. Intel., vol. 32, pp. 54–62, 2014. doi: 10.1016/j.engappai.2014.02.014
    A. Nazemi, “A capable neural network framework for solving degenerate quadratic optimization problems with an application in image fusion,” Neural Process. Lett., vol. 47, no. 1, pp. 167–192, 2018. doi: 10.1007/s11063-017-9640-4
    W. Li, X. Ma, J. Luo, and L. Jin, “A strictly predefined-time convergent neural solution to equality-constrained and inequality-constrained time-variant quadratic programming,” IEEE Trans. Syst. Man Cybern., vol. 51, no. 7, pp. 4028–4039, Jul. 2021. doi: 10.1109/TSMC.2019.2930763
    X. Zhang, L. Chen, S. Li, Stanimirovic, J. Zhang, and L. Jin, “Design and analysis of recurrent neural network models with non-linear activation functions for solving time-varying quadratic programming problems,” CAAI Trans. Intell. Technol., vol. 6, no. 4, pp. 394–404, Dec. 2021. doi: 10.1049/cit2.12019
    X. Wang, D. Ding, X. Ge, and Q.-L. Han, “Neural-network-based control for discrete-time nonlinear systems with denial-of-service attack: The adaptive event-triggered case,” Int. J. Robust Nonlinear Control, vol. 32, no. 5, pp. 2760–2779, 2022. doi: 10.1002/rnc.5831
    H. Song, D. Ding, H. Dong, and X. Yi, “Distributed filtering based on Cauchy-kernel-based maximum correntropy subject to randomly occurring cyber-attacks,” Automatica.


    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(9)  / Tables(1)

    Article Metrics

    Article views (1437) PDF downloads(28) Cited by()


    • A novel GD-kWTA network is designed, which is equipped with improved accuracy and enhanced robustness in tackling kWTA operations
    • Theorems on the convergence and robustness of the proposed network and numerical simulations in cases with or without noises are presented
    • Aided with the constructed GD-kWTA network for describing the competitive behavior, an application on the multirobot system for conducting the tracking task is provided


    DownLoad:  Full-Size Img  PowerPoint