...
  • 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Journal of Advances in Information Fusion >Multi-step Look-Ahead Policy for Autonomous Cooperative Surveillance by UAVs in Hostile Environments
【24h】

Multi-step Look-Ahead Policy for Autonomous Cooperative Surveillance by UAVs in Hostile Environments

机译：敌对环境下无人机自主合作监视的多步预见策略

获取原文
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

In this paper a real-time cooperative path decision algorithmfor UAV surveillance is proposed. The surveillance mission includesmultiple objectives: i) navigate the UAVs safely in a hostile environment;ii) search for new targets in the surveillance region; iii) classifythe detected targets; iv) maintain tracks on the detected targets.To handle these competing objectives, a layered decision frameworkis proposed, in which different objectives are deemed relevant atdifferent decision layers according to their priorities. Compared toprevious work, in which multiple objectives are integrated into asingle global objective function, this layered decision frameworkallows detailed specification of the desired performance for eachobjective and guarantees that an objective with high priority willbe better satisfied by eliminating possible compromises from otherless important ones. In addition, specific path decision strategiesthat are suited to the individual objectives can be used at differentdecision layers. An important objective of the path decision algorithmis to navigate the UAV safely in the hostile environment. Toachieve this, it is shown necessary to increase the time horizon of thepath decisions. In order to overcome the computational explosion ofan optimal multi-step look-ahead path decision strategy, a RolloutPolicy is proposed. This policy has moderate complexity and, whenused in the layered decision framework, it is able to find safe pathseffectively and efficiently. When the number of UAVs is large, theformation of UAV decision groups based on a nearest neighbor ruleis proposed to control the complexity of the path decision algorithm.Further flexibility of assigning different objectives to the UAVs isalso discussed. Simulation results show that the proposed path decisionalgorithm can guide the group of UAVs efficiently and safelyfor the multi-objective surveillance mission.
机译：提出了一种用于无人机监视的实时协同路径决策算法。监视任务包括多个目标：i）在敌对环境中安全地导航无人机; ii）在监视区域中寻找新目标; iii）分类检测到的目标; iv）跟踪检测到的目标。为处理这些相互竞争的目标，提出了一个分层的决策框架，其中根据不同的优先级，将不同目标视为不同决策层的相关目标。与将多个目标集成到单个全局目标功能中的先前工作相比，此分层决策框架允许详细说明每个目标的期望性能，并通过消除其他重要目标的可能折衷来保证更高优先级的目标得到更好的满足。另外，可以在不同的决策层使用适合于各个目标的特定路径决策策略。路径决策算法的一个重要目标是在敌对环境中安全地导航无人机。为此，显示出必须增加路径决策的时间范围。为了克服最优多步超前路径决策策略的计算爆炸性问题，提出了一种RolloutPolicy策略。该策略具有适度的复杂性，并且在分层决策框架中使用时，能够有效，高效地找到安全路径。当无人机数量众多时，提出了基于最近邻规则的无人机决策组的形成，以控制路径决策算法的复杂性。还讨论了为无人机分配不同目标的进一步灵活性。仿真结果表明，所提出的路径决策算法可以有效，安全地指导多目标侦察任务的无人机群。

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