| 基于自组织与LVQ神经网络的足球机器人协作策略学习 |
| |
| 引用本文： | 胡明慧,陈震,黎明.基于自组织与LVQ神经网络的足球机器人协作策略学习[J].南昌航空工业学院学报,2004,18(3):16-20. |
| |
| 作者姓名： | 胡明慧 陈震 黎明 |
| |
| 作者单位： | 南昌航空工业学院人工智能和图像处理研究中心,江西南昌330034 |
| |
| 摘 要： | 足球机器人系统目前已成为人工智能应用技术研究的重要实验平台，系统的核心部分就是决策子系统。本文主要研究机器人足球比赛中协作策略的学习问题，采用了自组织与学习向量量化（LVQ）神经网络算法实现了两个足球机器人的传球学习。提出了一种协作策略学习的改进算法。该算法通过对网络权值矩阵进行改进，可以显著提高网络的训练质量。仿真和实验结果表明了该方法的可行性与有效性。
|
| 关 键 词： | 自组织与LVQ神经网络 足球机器人 协作策略 角色分配 |
| 文章编号： | 1001-4926(2004)03-0016-05 |
| 收稿时间： | 2004-09-15 |
| 修稿时间： | 2004年9月15日 |
Coordination strategies learning of soccer robot based on self-organizing and LVQ NN |
| |
| HU Ming-hui, CHEN Zhen, LI Ming.Coordination strategies learning of soccer robot based on self-organizing and LVQ NN[J].Journal of Nanchang Institute of Aeronautical Technology(Natural Science Edition),2004,18(3):16-20. |
| |
| Authors: | HU Ming-hui CHEN Zhen LI Ming |
| |
| Institution: | The Center of Artificial Intelligence and Image Processing, Nanchang Institute of Aeronautical Technology, Nanchang, Jiangxi 330034 |
| |
| Abstract: | Soccer-robot system now has been an important exp eriment platform for artificial intelligence application technology. The key point of the system is t he decision-making subsystem. This paper focuses on coordination strategies lea rning in robot soccer, s+elf-organizing and learning vector quantization neural networks. A new improved method of coordination strategies is presented in this paper. It is obvious to improve the quality of network training by reforming the NN weight-matrix. The result of simulation experiment indicates that the propo sed method is suitable and effective. |
| |
| Keywords: | Self-organizing and LVQ NN Soccer robot Coordination strategy Role assignment |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
