EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

A Game‐Theoretic Fuzzy‐Parameter Dynamic Neural Network for Competitive Multicriteria Kinematic Control of Redundant Manipulators

Zining Su, Mei Liu

IET Control Theory & Applications · 2026-01 · 20 (1)

DOI: 10.1049/cth2.70156 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IET Control Theory & Applications, online erschienen am 28.07.2026. Verfasst von Zining Su und 1 weiteren Autor:innen. Die Arbeit nennt 63 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In redundant manipulator kinematic control, multiple criteria such as orientation tracking accuracy, physical constraints and motion smoothness inherently compete for limited joint resources. This competitive interaction can be modelled as a non‐cooperative game among virtual agents, each representing a distinct performance index or constraint. In this context, advanced neurodynamic approaches have recently shown strong potential in the adaptive coordination of such multi‐agent systems. Traditional dynamic neural networks (DNNs) with fixed parameters struggle to balance the conflicting objectives of fast convergence and system stability in such a game. To address this, we propose a game‐theoretic fuzzy‐parameter dynamic neural network (FP‐DNN) that recasts the competitive multicriteria kinematic control as a generalized optimization problem. Within the game‐theoretic FP‐DNN framework, individual neurons or nodes act as decision‐makers that adaptively compete and cooperate to optimize their respective criteria through real‐time adjustments of scaling parameters. Specifically, a fuzzy logic system dynamically tunes the convergence scaling factor according to the Karush–Kuhn–Tucker residual, enabling the network to resolve the trade‐off between convergence speed and stability without extra computational burden. Theoretical analysis guarantees global exponential convergence of the proposed a game‐theoretic FP‐DNN to the equilibrium point, that is, the optimal solution of the original constrained optimization. Simulation and experimental results on a Franka Emika Panda manipulator confirm that the game‐theoretic scheme achieves precise orientation tracking under strict constraints, and exhibits superior robustness and practical feasibility compared to fixed‐parameter methods.

Zitieren

APA

Su, Z., & Liu, M. (2026). A Game‐Theoretic Fuzzy‐Parameter Dynamic Neural Network for Competitive Multicriteria Kinematic Control of Redundant Manipulators. IET Control Theory & Applications, 20(1). https://doi.org/10.1049/cth2.70156

Vancouver

Su Z, Liu M. A Game‐Theoretic Fuzzy‐Parameter Dynamic Neural Network for Competitive Multicriteria Kinematic Control of Redundant Manipulators. IET Control Theory & Applications. 2026;20(1). doi:10.1049/cth2.70156

BibTeX
@article{Su2026,
  author = {Su, Zining and Liu, Mei},
  title = {A Game‐Theoretic Fuzzy‐Parameter Dynamic Neural Network for Competitive Multicriteria Kinematic Control of Redundant Manipulators},
  journal = {IET Control Theory & Applications},
  year = {2026},
  volume = {20},
  number = {1},
  doi = {10.1049/cth2.70156}
}
Kostenlos starten →