| 引用本文: | 曹翔,孙长银.栅格地图中多机器人协作搜索目标[J].控制理论与应用,2018,35(3):273~282.[点击复制] |
| CAO Xiang,SUN Chang-yin.Cooperative target search of multi-robot in grid map[J].Control Theory and Technology,2018,35(3):273~282.[点击复制] |
|
| 栅格地图中多机器人协作搜索目标 |
| Cooperative target search of multi-robot in grid map |
| 摘要点击 3064 全文点击 1125 投稿时间：2017-04-10 修订日期：2017-09-27 |
| 查看全文 查看/发表评论 下载PDF阅读器 |
| DOI编号 10.7641/CTA.2017.70242 |
| 2018,35(3):273-282 |
| 中文关键词 多机器人 目标搜索 Dempster-Shafer理论 生物启发神经网络 |
| 英文关键词 multi-robot target search Dempster-Shafer theory biologically inspired neural network |
| 基金项目 国家自然科学基金项目(61520106009, 61773177), 江苏省博士后基金项目(1701076B)资助. |
|
| 中文摘要 |
| 目标搜索是多机器人领域的一个挑战. 本文针对栅格地图中多机器人目标搜索算法进行研究. 首先, 利用
Dempster-Shafer证据理论将声纳传感器获取的环境信息进行融合, 构建搜索环境的栅格地图. 然后,基于栅格地图
建立生物启发神经网络用于表示动态的环境. 在生物启发神经网络中, 目标通过神经元的活性值全局的吸引机器
人. 同时, 障碍物通过神经元活性值局部的排斥机器人, 避免与其相撞. 最后, 机器人根据梯度递减原则自动的规划
出搜索路径. 仿真和实验结果显示本文提及的算法能够实现栅格地图中静态目标和动态目标的搜索. 与其他搜索
算法比较, 本文所提及的目标搜索算法有更高的效率和适用性. |
| 英文摘要 |
| Target search is a challenge in multi-robot exploration. This paper focuses on an effective strategy for
multi-robot target search in grid map. First, the Dempster-Shafer theory of evidence is applied to extract information of
environment from the sonar data to build a grid map of the environments. Then, a topologically organized biologically
inspired neural network based on the grid map is constructed to represent the dynamic environment. The target globally
attracts the robots through the dynamic neural activity landscape of the model, while the obstacles locally push the robots
away to avoid collision. Finally, the robots plan their search path to the targets autonomously by a steepest gradient descent
rule. The proposed algorithm deals with various situations such as static targets search, dynamic targets search in the grid
map. The results of simulation and experiment show that the proposed algorithm is capable of guiding multi-robot to
achieve search task of multiple targets with higher efficiency and adaptability compared with other algorithms. |
|
|
|
|
|