异构感知神经网络驱动的多智能体分布式协调控制方法
The multi-agent distributed coordination control method driven by heterogeneous perceptual neural networks solves the problems of difficult modeling and high computational complexity in heterogeneous multi-agent systems by traditional methods, and realizes efficient and stable heterogeneous multi-agent coordination control with strong environmental adaptability and real-time performance.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- CHANGCHUN UNIV OF SCI & TECH
- Filing Date
- 2026-04-08
- Publication Date
- 2026-07-17
AI Technical Summary
Traditional control methods cannot effectively handle the differences in capabilities between agents in heterogeneous multi-agent systems, resulting in modeling difficulties and high computational complexity, making it difficult to meet the real-time decision-making and stability requirements in complex dynamic environments.
A multi-agent distributed coordination control method driven by heterogeneous perceptual neural networks is adopted. By establishing a heterogeneous distributed nonlinear system model, dynamically adjusting the neighbor weights, fusing multi-source information, and reconstructing the communication topology, the distributed coordination control of heterogeneous multi-agents is realized.
It achieves adaptive configuration of parameter dimensions, significantly improves computational efficiency, ensures 100% safety constraint satisfaction rate under 30% heterogeneous parameter differences, has strong environmental adaptability and real-time control capabilities, improves inference time by 5 times, reduces formation error by 31.6%, and finally achieves convergence accuracy of 98.6%.
Smart Images
Figure CN121995772B_ABST