Robust k-WTA Network Generation, Analysis, and Applications to Multiagent Coordination.

Journal: IEEE transactions on cybernetics
Published Date:

Abstract

In this article, a robust k -winner-take-all ( k -WTA) neural network employing the saturation-allowed activation functions is designed and investigated to perform a k -WTA operation, and is shown to possess enhanced robustness to disturbance compared to existing k -WTA neural networks. Global convergence and robustness of the proposed k -WTA neural network are demonstrated through analysis and simulations. An application studied in detail is competitive multiagent coordination and dynamic task allocation, in which k active agents [among ] are allocated to execute a tracking task with the static m-k ones. This is implemented by adopting a distributed k -WTA network with limited communication, aided with a consensus filter. Simulation results demonstrating the system's efficacy and feasibility are presented.

Authors

  • Yimeng Qi
  • Long Jin
  • Xin Luo
    Department of Pharmacology, The Basic Medical Sciences College of Xinjiang Medical University Urumqi 830054, China.
  • Yang Shi
  • Mei Liu
    Department of Internal Medicine, Division of Medical Informatics, University of Kansas Medical Center, Kansas City, Missouri, USA.