基于稀疏直接法和图优化的移动机器人SLAM  

SLAM based on sparse direct method and graph optimization for mobile robot

作　　者：吴玉香[1] 王超[1] 冼颖宪 Wu Yuxiang;Wang Chao;Xian Yingxian(College of Automation Science and Engineering, South China University of Technology, Guangzhou 510641, China)

机构地区：[1]华南理工大学自动化科学与工程学院

出　　处：《仪器仪表学报》2018年第4期257-263,共7页Chinese Journal of Scientific Instrument

基　　金：广东省科技计划(2015B010133002,2017B090910011)项目资助

摘　　要：针对目前移动机器人同时定位和三维稠密地图构建算法中存在的计算复杂、实时性差的问题,提出一种基于RGB-D数据的实时的同时定位与地图构建（SLAM）算法。首先提取RGB图像中的FAST特征点,并计算特征点的3D位置,接着采用直接法最小化光度误差来估计相机的位姿变换,然后根据位姿变换的大小提取关键帧。为了减小移动机器人运动过程中的累积误差,提出基于词袋模型的闭环检测方法,并采用通用图优化（g2o）框架进行位姿图优化。实验结果表明,所提算法能够大大提高SLAM系统的实时性,并构建稠密化的三维环境地图。To deal with the problem of complex computation and poor real-time performance of mobile robot simultaneous localization and3 D dense mapping,a real-time SLAM algorithm is proposed based on RGB-D data. Firstly,the FAST feature points in RGB image are extracted. The 3 D position of the feature points is calculated. Then,the direct method is used to minimize the photometric error to estimate the pose transform of the camera. The key frames are extracted according to the size of the pose transform. Finally,to reduce the accumulated error occurred during the movement of mobile robot,a closed-loop detection method based on the bag-of-words model is proposed. The g2 o framework is adopted to optimize the pose graph. Experimental results show that the proposed algorithm can effectively improve the real-time performance of SLAM system and build a dense three-dimensional environment map.

关 键 词：移动机器人 同时定位与地图构建 稀疏直接法 图优化 

分 类 号：TP242.6[自动化与计算机技术—检测技术与自动化装置] TH74[自动化与计算机技术—控制科学与工程]