首页> 外文会议>Intelligent autonomous systems(IAS-5) >Training mobile agent to solve cellular maze problem: an ANN based approach
【24h】

Training mobile agent to solve cellular maze problem: an ANN based approach

机译:训练移动代理解决蜂窝迷宫问题:一种基于ANN的方法

获取原文
获取原文并翻译 | 示例

摘要

The path-planning problem is one of the navigation problems. We adopt ANN to acquire the behavior for an agent in order to solve the problems. We set the problem space on cellular mazes. Recurrent Cascade Correlation (RCC) is implemented for ANN. Genetic Algorithms (GA) and Evolutionary Programming (EP) are applied to train the networks. For Artificial Intelligence (AI), we adopted depth-first search and A~* algorithms. We computed for four different types of mazes and each planning path will be shown as the results.
机译:路径规划问题是导航问题之一。为了解决问题,我们采用人工神经网络来获取代理的行为。我们在蜂窝迷宫上设置问题空间。递归级联相关(RCC)为ANN实现。遗传算法(GA)和进化规划(EP)用于训练网络。对于人工智能(AI),我们采用了深度优先搜索和A〜*算法。我们针对四种不同类型的迷宫进行了计算,每个规划路径都将显示为结果。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号