机器人信息增益RRT环境认知算法
作者:
作者单位:

北京工业大学

作者简介:

通讯作者:

中图分类号:

TP273

基金项目:

国家自然科学基金项目(面上项目,重点项目,重大项目)


Robot RRT based on Information Divergence for Environment Recognition
Author:
Affiliation:

Beijing University of Technology

Fund Project:

  • 摘要
  • |
  • 图/表
  • |
  • 访问统计
  • |
  • 参考文献
  • |
  • 相似文献
  • |
  • 引证文献
  • |
  • 资源附件
  • |
  • 文章评论
    摘要:

    由于传统RRT(Rapidly-exploring Random Trees)路径规划算法固有的盲目探索的问题,在机器人到达目标点时,除起始点扩展到目标点的路径之外还会生成其他与结果无关的分支路径与节点。为使这些分支路径得到利用并且减少探索的盲目性,提出基于信息增益与RRT思想相结合的机器人环境认知策略。该方法对未知环境中的节点进行信息估计,选取具有最大信息增益的节点作为采样节点且每次都会生成最大信息增益的新节点进行扩展,该策略使机器人能完成对未知环境的探索,还可以降低传统RRT算法固有的盲目性。仿真实验结果表明,所提出的方法能够有效快速地帮助机器人探索未知环境,实现环境认知。

    Abstract:

    Traditional RRT(Rapidly-exploring Random Trees) algorithms typically tend to explore the environment blindly, which possibly causes the decrease in efficiency. For example, in traditional RRT methods, besides the path from the start point to the goal point, other branch paths unrelated to the result are also generated. In order to take advantage of these branch paths and reduce the blindness of exploration, a robot environment exploration strategy based on the combination of information gain and RRT was proposed.This method estimates the information of the nodes in the unknown environment, selects the nodes with the maximum information gain as the sampling nodes and generates the new nodes with the maximum information gain every time for expansion. This strategy enables the robot to explore the unknown environment autonomously, and also reduces the inherent blindness of the traditional RRT algorithm. The simulation results show that the proposed method can effectively and quickly help the robot explore the unknown environment and realize environmental exploration.

    参考文献
    相似文献
    引证文献
引用本文
分享
文章指标
  • 点击次数:
  • 下载次数:
  • HTML阅读次数:
  • 引用次数:
历史
  • 收稿日期:2020-07-21
  • 最后修改日期:2020-09-24
  • 录用日期:2020-09-25
  • 在线发布日期:
  • 出版日期: