• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>IEEE transactions on industrial informatics >ReinforcedRimJump: Tangent-Based Shortest-Path Planning for Two-Dimensional Maps
【24h】

ReinforcedRimJump: Tangent-Based Shortest-Path Planning for Two-Dimensional Maps

机译：ReinforcedRimjump：基于切线的二维地图的最短路径规划

获取原文
获取原文并翻译 | 示例
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Path planning under two-dimensional maps is a fundamental problem in mobile robotics and other real-world applications (unmanned vehicles, navigation applications for mobile phones, and so forth). However, traditional algorithms (graph searching, artificial potential field, genetic, and so forth) rely on grid-by-grid searching. Thus, these methods generally do not find the global optimal path, and as the map scale increases, their time cost increase sharply, except artificial potential field. A few algorithms that do not rely on grid-by-grid searching (rapidly-exploring random tree, visibility graph, and tangent graph) have special requirements for maps. Considering that the shortest path is composed of tangents between obstacles, in this paper, we propose a method called ReinforcedRimJump (RRJ) that does not rely on the point-by-point traversal but rather obtains the shortest path by finding the tangent multiple times between obstacles. The first improvement of this method is the precomputation of tangents, which causes the method to have a lower time cost than traditional methods. The second improvement of RRJ is edge segmentation, which allows RRJ to be used when the target is in the depression of the obstacle. To verify the theoretical advantages of RRJ, some comparative experiments under various maps are performed. The experimental results show that RRJ can always find the shortest path in the shortest time. Furthermore, the time cost of RRJ is insensitive to the map size compared to other methods. The experimental results presented herein demonstrate that RRJ meets the theoretical expectations.
机译：二维地图下的路径规划是移动机器人和其他现实世界应用的根本问题（无人驾驶车辆，手机的导航应用等）。然而，传统算法（图表搜索，人工势域，遗传等）依赖于网格搜索。因此，这些方法通常没有找到全局最优路径，随着地图比例的增加，它们的时间成本急剧增加，除了人工势域。一些不依赖于网格搜索的算法（快速探索随机树，可见性图形和切线图）对地图具有特殊要求。考虑到最短路径由障碍物之间的切线组成，在本文中，我们提出了一种称为钢筋（RRJ）的方法，该方法不依赖于点横向遍历，而是通过在多次之间找到切线来获得最短路径障碍。该方法的第一次改进是切线的预测，导致该方法具有比传统方法的较低时间成本。 RRJ的第二种改进是边缘分割，允许在目标处于障碍物的凹陷时使用RRJ。为了验证RRJ的理论优势，执行各种地图下的一些比较实验。实验结果表明，RRJ总能在最短的时间内找到最短的路径。此外，与其他方法相比，RRJ的时间成本对地图尺寸不敏感。这里提出的实验结果表明RRJ符合理论期望。

著录项

  • 来源
    《IEEE transactions on industrial informatics》 |2020年第2期|949-958|共10页
  • 作者

    Yao Zhuo; Zhang Weimin; Shi Yongliang; Li Mingzhu; Liang Zhenshuo; Huang Qiang;

  • 作者单位

    Minist Educ Key Lab Biomimet Robots & Syst Beijing Adv Innovat Ctr Intelligent Robots & Syst Dept Mechatron Beijing Inst Technol Beijing 100081 Peoples R China;

    Minist Educ Key Lab Biomimet Robots & Syst Beijing Adv Innovat Ctr Intelligent Robots & Syst Dept Mechatron Beijing Inst Technol Beijing 100081 Peoples R China;

    Minist Educ Key Lab Biomimet Robots & Syst Beijing Adv Innovat Ctr Intelligent Robots & Syst Dept Mechatron Beijing Inst Technol Beijing 100081 Peoples R China;

    Minist Educ Key Lab Biomimet Robots & Syst Beijing Adv Innovat Ctr Intelligent Robots & Syst Dept Mechatron Beijing Inst Technol Beijing 100081 Peoples R China;

    Minist Educ Key Lab Biomimet Robots & Syst Beijing Adv Innovat Ctr Intelligent Robots & Syst Dept Mechatron Beijing Inst Technol Beijing 100081 Peoples R China;

    Minist Educ Key Lab Biomimet Robots & Syst Beijing Adv Innovat Ctr Intelligent Robots & Syst Dept Mechatron Beijing Inst Technol Beijing 100081 Peoples R China;

  • 收录信息
  • 原文格式 PDF
  • 正文语种 eng
  • 中图分类
  • 关键词

    Path planning; subedge; tangent;

    机译：路径规划;子确ch;切线;

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