基于优化RTAB-Map的室内巡检机器人视觉导航方法  

Autonomous navigation method of indoor inspection robot based on optimized RTAB-Map

作　　者：周加超 葛动元 丛佩超 吕昆峰 ZHOU Jiachao;GE Dongyuan;CONG Peichao;LYU Kunfeng(School of Mechanical and Automotive Engineering,Guangxi University of Science and Technology,Liuzhou 545616,China)

机构地区：[1]广西科技大学机械与汽车工程学院,广西柳州545616

出　　处：《广西科技大学学报》2023年第1期79-84,共6页Journal of Guangxi University of Science and Technology

基　　金：中央引导地方科技发展专项资金项目(桂科ZY19183003);广西重点研发计划项目(桂科AB20058001);广西科技基地和人才专项(桂科AD19110021)资助。

摘　　要：巡检机器人对室内场景进行自主导航监测时,采用视觉同时定位与地图构建(simultaneous localization and mapping,SLAM)方法构建的三维深度地图存在实时性不高、定位精度下降的问题。对此,提出了一种基于RGB-D相机和优化RTAB-Map(real time appearance based mapping)算法的巡检机器人视觉导航方法。首先,通过重新配置RTAB-Map点云更新频率,实现算法优化,构建稠密的点云地图后;采用启发式A*算法、动态窗口法(dynamic window approach,DWA)分别制定全局与局部巡检路径,通过自适应蒙特卡罗定位(adaptive Monte Carlo localization,AMCL)方法更新机器人的实时位姿信息,再将搭建好的实体巡检机器人在软件、硬件平台上完成视觉导航测试实验。结果表明:优化后的RTAB-Map算法运行时的内存占比稍有增加,但获得与真实环境一致性更高的三维深度地图,在一定程度上提高视觉导航的准确性与实用性。Aiming at the problem of low real-time performance and poor positioning accuracy when using visual simultaneous localization and mapping(SLAM)method to build three-dimensional depth map when patrol robots conduct autonomous navigation and monitoring of indoor scenes.In this paper,a visual navigation method for inspection robot based on RGB-D camera and optimized real time appearance based mapping(RTAB-Map)is proposed.Firstly,by reconfiguring the update frequency of RTAB-Map point cloud,the algorithm is optimized and a dense point cloud map is constructed.Then,the heuristic A*algorithm and the dynamic window approach(DWA)are used to formulate the global and local inspection paths respectively,and the real-time pose information of the robot is updated by the adaptive Monte Carlo localization(AMCL)method.Finally,the visual navigation test experiment is completed on the built hardware and software platform of the physical inspection robot.The results show that the optimized RTAB-Map algorithm slightly increases the memory ratio when it runs,but it can obtain a 3D depth map that is more consistent with the real environment,which improves the accuracy and practicality of visual navigation to a certain extent.

关 键 词：巡检机器人 自主导航 RGB-D相机 视觉SLAM RTAB-Map算法 

分 类 号：TH165[机械工程—机械制造及自动化]