An Integral-Enhanced Adaptive Gradient Neural Network for k WTA and Multirobot Coordination
- 12 January 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cybernetics
- Vol. 56 (6) , 3165-3176
Abstract
Existing computational methods for the $k$ -winners-take-all ( $k$ WTA) operations often suffer from limitations in eliminating lagging errors, high computational complexity, and weak robustness. To deal with these challenges, we propose an integral-enhanced adaptive gradient neural network (IAGNN) for $k$ WTA. We demonstrate that the IAGNN integrates an adaptive coefficient to eliminate lagging errors while retaining an $O(n^{2})$ computational complexity. We proved the Lyapunov stability and robustness of the IAGNN. We provide a numerical simulation, and the results demonstrate the stability and robustness of the IAGNN. Furthermore, we implement the IAGNN in a multirobot tracking system for competitive allocation coordination, and the results demonstrate the operational feasibility and noise resistance of the IAGNN.Keywords
Funding Information
- National Natural Science Foundation of China (62595800)
- National Natural Science Foundation of China (625B2074)
- National Key Research and Development Program of China (2021ZD0201300)
- Innovation Group Project of the National Natural Science Foundation of China (61821003)
- National Natural Science Foundation of China (B18024)
This publication has 50 references indexed in Scilit:
- A class of finite-time dual neural networks for solving quadratic programming problems and its -winners-take-all applicationNeural Networks, 2013
- Convergence Properties Analysis of Gradient Neural Network for Solving Online Linear EquationsActa Automatica Sinica, 2009
- A new k-winners-take-all neural network2006
- Synthesis of a k-winners-take-all neural network using linear programming with bounded variables2004
- An automata network for performing combinatorial optimizationNeurocomputing, 2002
- Another K-winners-take-all analog neural networkIEEE Transactions on Neural Networks, 2000
- Winner-takes-all and action selectionBehavioral and Brain Sciences, 1999
- A CMOS K-winners-take-all circuit with O(n) complexityIEEE Transactions on Circuits and Systems II: Analog and Digital Signal Processing, 1999
- A new k-winners-take-all neural network and its array architectureIEEE Transactions on Neural Networks, 1998
- K-winners-take-all circuit with O(N) complexityIEEE Transactions on Neural Networks, 1995