一种改进的移动机器人自主室内环境探索方法

吴桐; 郭晨; 许桐; 王召东

doi:10.16411/j.cnki.issn1006-7736.2019.03.009

大连海事大学学报 >

2019 , Vol. 45 >Issue 3: 59 - 65

DOI: https://doi.org/10.16411/j.cnki.issn1006-7736.2019.03.009

控制

一种改进的移动机器人自主室内环境探索方法

吴桐 ,
郭晨 ,
许桐 ,
王召东

展开

(大连海事大学船舶电气工程学院，辽宁大连 116026)

吴桐（1995 — ），男，硕士生，E-mail:m18940841821@163.com.

收稿日期: 2019-03-03

修回日期: 2019-03-27

网络出版日期: 2019-03-27

基金资助

国家自然科学基金资助项目（51879027；51579024）；中央高校基本科研业务费专项资金资助项目（3132016311）.

收起

An improved autonomous exploration method of a mobile robot in indoor environment

WU Tong ,
GUO Chen ,
XU Tong ,
WANG Zhao-dong

Expand

(Marine Electrical Engineering College, Dalian Maritime University, Dalian 116026, China)

Received date: 2019-03-03

Revised date: 2019-03-27

Online published: 2019-03-27

Fold

摘要

针对未知室内环境下移动机器人自主探索与地图构建的问题，提出一种基于八叉树地图的移动机器人自主探索方法.首先，将前沿点分组并提取关键前沿点，用于生成候选点；然后，分别基于关键前沿点和可通行空间提出两种候选点生成方法，用于自主探索的不同阶段；接着，利用信息增益和行驶距离的非线性组合构造效益函数来评价候选点，选取最优候选点作为下一目标点；最后，利用RGB-D信息更新八叉树地图.经仿真实验和实际场景验证了所提出的自主探索方法的有效性.

关键词： 移动机器人; 自主探索; 八叉树地图; 信息增益; 贝叶斯优化; SLAM

本文引用格式

吴桐 , 郭晨 , 许桐 , 王召东 . 一种改进的移动机器人自主室内环境探索方法[J]. 大连海事大学学报, 2019 , 45(3) : 59 -65 . DOI: 10.16411/j.cnki.issn1006-7736.2019.03.009

Abstract

Aiming at the problem of mobile robot autonomous exploration and map building in the unknown indoor environment, a mobile robot autonomous exploration method based on the octree map was proposed. Firstly，the frontier points were grouped and the key frontier points were extracted to generate candidate points. Then, two generation methods of candidate exploration point were proposed respectively based on the key frontier points and the accessible space, which were used for different stages of autonomous exploration.Next,the nonlinear combination of information gain and driving distance was used to construct benefit function to evaluate candidate points, and the optimal candidate point was selected as the next target point.Finally, the octree map was updated by using the RGB-D data. The simulation and physical experiments verify the effectivity of autonomous exploration method.

Key words： mobile robot; autonomous exploration; octree map; information gain; Bayesian optimization; SLAM

参考文献

[1]Perea StroM D，Bogoslavskyi I，Stachniss C．Robust exploration and homing for autonomous robots[J]．Robotics and Autonomous Systems，2016：S0921889016304730．
[2]王东署，段谊海，王佳．未知环境中移动机器人的环境探索与地图构建[J]．郑州大学学报(理学版)，2014，46(03)：96-101．
[3]Tovar B，Murrietacid R，Esteves C．Robot motion planning for map building[C]// IEEE/RSJ International Conference on Intelligent Robots & Systems．IEEE，2002．
[4]吕伟新，赵立军，王珂，et al．基于边界约束RRT的未知环境探索方法[J]．华中科技大学学报（自然科学版），2011，39(z2) ：366-369．
[5]Yamauchi B．A frontier-based approach for autonomous exploration[C]．Proc of IEEE Int Symposium on Computational Intelligence in Robotics and Automation． Monterey：IEE Press，1997：146-151．
[6]李秀智，邱欢，贾松敏，龚月．基于动态精简式混合地图的移动机器人自主探索[J]．控制与决策，2017，32(05)：817-822．
[7]于宁波，王石荣，徐昌．一种基于RGB-D的移动机器人未知室内环境自主探索与地图构建方法[J]．机器人，2017(6)．
[8]高翔，张涛， et al．视觉SLAM十四讲[M]．2017．
[9]李秀智，龚月，贾松敏，et al．一种室内移动机器人自主探索方法[J]．控制与决策．
[10]Bai S，Wang J，Chen F，et al．Information-theoretic exploration with Bayesian optimization[C]// 2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (I-ROS)．IEEE， 2016．
[11]Stachniss C，Burgard W．Exploring Unknown Environ-ments with Mobile Robots using Coverage Maps[C]// Inter-national Joint Conference on Artificial Intelligence．Morgan Kaufmann Publishers Inc．2003．
[12]Gonzáles-Baos H，Latombe J．Navigation strategies for exploring indoor environments [J]．International Journal of Robotics Research，2002，21 (10/11)：829-848．
[13]Dirk H，Nicola B，Francesco A． A comparative evaluation of exploration strategies and heuristics to improve them[C]//Pro-ceedings of the European Conference on Mobile Robotics (ECMR) ．Oerebro，2011．
[14]Shahriari B，Swersky K，Wang Z，et al． Taking the Human Out of the Loop：A Review of Bayesian Optimization [J]．Proceedings of the IEEE，2016，104(1)：148-175．
[15]Rasmussen C E，and Williams C K I，Gaussian Processes for Machine Learning，The MIT Press，2006．
[16]Srinivas N，Krause A，Kakade S M，and Seeger M．Gaussian Process Optimization in the Bandit Settin：No Regret and Experimental Design．Proceedings of the 27th International Conference on Machine Learning，2010．
[17]Grisetti G，Stachniss C，Burgard W．Improved Techniques for Grid Mapping With Rao-Blackwellized Particle Filters [J]．IEEE Transactions on Robotics， 2007，23(1)：34-46．
[18]Khoshelham K，Elberink S O．Accuracy and resolution of Kinect depth data for indoor mapping applications[J]． Industrial Technology & Vocational Education，2012，12(2)：1437．
[19]张毅，杜凡宇，罗元，熊艳．一种融合激光和深度视觉传感器的SLAM地图创建方法[J]．计算机应用研究，2016，33(10)：2970-2972+30 06．

Options

文章导航

模态框（Modal）标题

摘要

本文引用格式

Abstract

参考文献