A RGBD SLAM algorithm combining ORB with PROSAC for indoor mobile robot

In order to enhance the instantaneity of SLAM for indoor mobile robot, a RGBD SLAM method based on Kinect was proposed. In the method, oriented FAST and rotated BRIEF(ORB) algorithm was combined with progressive sample consensus(PROSAC) algorithm to execute feature extracting and matching. More specifically, ORB algorithm which has better property than many other feature descriptors was used for extracting feature. At the same time, ICP algorithm was adopted for coarse registration of the point clouds, and PROSAC algorithm which is superior than RANSAC in outlier removal was employed to eliminate incorrect matching. To make the result more accurate, pose-graph optimization was achieved based on g2o framework. In the end, a 3D volumetric map which can be directly used to the navigation of robots was created.

[1]  Hugh F. Durrant-Whyte,et al.  Simultaneous localization and mapping: part I , 2006, IEEE Robotics & Automation Magazine.

[2]  Gamini Dissanayake,et al.  A robust RGB-D SLAM algorithm , 2012, 2012 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[3]  Wolfram Burgard,et al.  OctoMap: an efficient probabilistic 3D mapping framework based on octrees , 2013, Autonomous Robots.

[4]  Vincent Lepetit,et al.  BRIEF: Binary Robust Independent Elementary Features , 2010, ECCV.

[5]  José Ruíz Ascencio,et al.  Visual simultaneous localization and mapping: a survey , 2012, Artificial Intelligence Review.

[6]  Cyrill Stachniss,et al.  Robotic Mapping and Exploration , 2009, Springer Tracts in Advanced Robotics.

[7]  Jie Zhang,et al.  3D visual SLAM for an assistive robot in indoor environments using RGB-D cameras , 2014, 2014 9th International Conference on Computer Science & Education.

[8]  Ju Shen,et al.  A robust RGB-D SLAM system for 3D environment with planar surfaces , 2013, 2013 IEEE International Conference on Image Processing.

[9]  Wolfram Burgard,et al.  3-D Mapping With an RGB-D Camera , 2014, IEEE Transactions on Robotics.

[10]  Jiri Matas,et al.  Matching with PROSAC - progressive sample consensus , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[11]  Gary R. Bradski,et al.  ORB: An efficient alternative to SIFT or SURF , 2011, 2011 International Conference on Computer Vision.

[12]  Wolfram Burgard,et al.  G2o: A general framework for graph optimization , 2011, 2011 IEEE International Conference on Robotics and Automation.

[13]  Dieter Fox,et al.  RGB-D Mapping: Using Depth Cameras for Dense 3D Modeling of Indoor Environments , 2010, ISER.

[14]  Tom Drummond,et al.  Machine Learning for High-Speed Corner Detection , 2006, ECCV.