论文部分内容阅读
对复杂环境对象进行决策时,多agent合作可以融合各agent的知识经验,提高决策结果的可靠性.针对环境对象的辨识空间中多假设同时成立的决策问题,本文提出了一种基于证据理论的多agent合作决策算法,详细描述与分析了多agent合作决策的原理.为提高系统决策的可靠性,降低了合成计算的复杂度,在多agent合作决策系统中引入正确的训练案例进行学习.本文提出的算法应用于蔬菜的病害判别,实验结果验证了本文提出的多agent合作决策算法的有效性.
When making decisions on complex environment objects, the multi-agent cooperation can fuse the knowledge experience of each agent and improve the reliability of the decision-making results.Aiming at the decision-making problem of multi-assumptions in environment object recognition space, a new method based on evidence theory Multi-agent cooperative decision-making algorithm, the principle of multi-agent cooperative decision-making is described and analyzed in detail.In order to improve the reliability of system decision-making and reduce the complexity of synthetic calculation, the paper introduces the correct training case to study in multi-agent cooperative decision-making system. The proposed algorithm is applied to vegetable disease identification. The experimental results verify the effectiveness of the proposed multi-agent cooperative decision making algorithm.