首页> 外文会议>International Conference on Information Technology - New Generations >Use of Intelligent Water Drops (IWD) for Intelligent Autonomous Force Deployment
【24h】

Use of Intelligent Water Drops (IWD) for Intelligent Autonomous Force Deployment

机译:使用智能水滴(IWD)进行智能自主力部署

获取原文

摘要

This paper presents a decentralized method for autonomously directing the movement of troops or battlefield robots from areas where their capabilities are being underutilized to areas where they are needed. This technique, which relies on limited message passing, does not require a centralized controller and is thus well suited to the battlefield environment where natural or deliberately created conditions may limit communications or render a centralized controller inaccessible. The Colonel Blotto Game (simulation scenario) is extended to provide a testing framework for Intelligent Water Drops (IWD)-derivative methods. The performance of the conventional approach to the Colonel Blotto Game is characterized in application to this extended scenario. Then, an IWD approach is presented and its performance is compared to the conventional method. The IWD approach is shown to outperform the conventional approach, from a gameplay perspective, while having significantly greater processing costs. Finally, the performance of an extended approach, which plays out possibilities for the remainder of the game multiple times before making a decision, is compared with an approach based on making the best decision in the short term without extended network information. The gameplay utility of this extended solver is not demonstrated, despite it having significantly higher computational costs.
机译:本文提出了一种分散的方法,用于自主地指导部队或战场机器人从其能力未低于所需地区的地区移动的方法。这种依赖于有限消息传递的技术不需要集中控制器,因此非常适合于战地环境,其中自然或故意创建的条件可以限制通信或渲染集中式控制器无法访问。延长上校Blotto游戏(模拟方案),为智能水滴(IWD)的测试框架提供了一个测试框架。传统方法对上校Blotto游戏的性能的特征在于应用于这种扩展场景。然后,提出了IWD方法,并将其性能与传统方法进行了比较。从游戏角度来看,IWD方法显示出常规方法,同时具有明显更大的处理成本。最后,在作出决定之前,将延长方法的性能发挥了剩余的游戏的可能性,与基于在短期内的最佳决定的方法进行比较,而无需扩展网络信息。尽管它具有显着提高的计算成本,但不证明该扩展求解器的游戏实用程序。

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