[1]ZHANG Yi,CHEN Qi,LUO Yuan.Three dimensional visual SLAM for mobile robots in indoor environments[J].CAAI Transactions on Intelligent Systems,2015,10(4):615-619.[doi:10.3969/j.issn.1673-4785.201504003]
Copy

Three dimensional visual SLAM for mobile robots in indoor environments

CAAI Transactions on Intelligent Systems[ISSN 1673-4785/CN 23-1538/TP] Volume: 10 Number of periods: 2015 4 Page number: 615-619 Column: 学术论文—机器感知与模式识别 Public date: 2015-08-25
Title:
Three dimensional visual SLAM for mobile robots in indoor environments
Author(s):
ZHANG Yi1;  CHEN Qi1;  LUO Yuan2
1. Automation College, Chongqing University of Posts and Telecommunications, Chongqing 400065, China;
2. College of Electroning Engineering College, Chongqing University of Posts and Telecommunications, Chongqing 400065, China
Keywords:
mobile robot; Kinect camera; SLAM; point cloud registration; trajectory tracking; robot navigation; robustness
CLC:
TP24
DOI:
10.3969/j.issn.1673-4785.201504003
Abstract:
In this paper, it aiming at the problems of large matching error and inefficiency in the process of point cloud registration in mobile robots 3D visual SLAM, a hierarchical point cloud registration strategy is proposed. It completes the initial registration by eliminating possible false matching points by RANSAC algorithm and then estimates the robot adjacent pose using the least square algorithm of interior points. Meanwhile, accurate registration is completed by the improved ICP algorithm and finally the mobile robot pose is optimized by the g20 optimization method. Addressing the problem of too much repeated points and hole existing in point cloud splicing results, a matching algorithm based on volume space fusion is introduced to fill the hole. Experimental results obtained demonstrated that the proposed method can accurately reconstruct the 3D model and estimate the trajectory of the mobile robot, and can effectively remove the repeated points and fill the hole.
References:
[1] RYDE J, HU H S. 3D mapping with multi-resolution occupied voxel lists[J]. Autonomous Robots, 2010, 28(2):169-185.
[2] KOPPILA H S, ANAND A. Semantic labeling of 3D point clouds for indoor scenes[C]//25th Annual Conference on Neural Information Processing Systems. New York, USA:Curran Associates Inc., 2011.
[3] HERRERA C D, KANNALA J, HEIKKILA J. Joint depth and color camera calibration with distortion correction[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2012, 34(10):2058-2064.
[4] 杨扬,曹其新,朱笑笑.面向机器人手眼协调抓取的3 维建模方法[J].机器人,2013,35(2): 151-155.YANG Yang,CAO Qixin,ZHU Xiaoxiao. A 3D modeling method for robot’s hand-eye coordinated grasping[J]. Robot,2013,35(2):151-155.
[5] HENRY P, KRAININ M, HERBST E, et al. RGB-D mapping: Using Kinect-style depth cameras for dense 3D modeling of indoor environments[J]. International Journal of Robotics Research, 2012, 31(5): 647-663.
[6] HARRIS C, STEPHENS M. A combined corner and edge detector[C]//Proc. Alvey Vis. Conf.,1988: 147-151.
[7] LOWE D G. Object recognition from local scale-invariant features [C]//International Conference on Computer Vision. Kerkyra,Corfu,Greece,1999:1150-1157.
[8] BAY H, ESS A, TUYTELAARS T, et al. Speeded-up robust features (SURF) [J].Comput. Vis. Image Understanding, 2008,110:346-359.
[9] KUMMERLE R, GRISETTI G, STRASDAT H, et al. G2o: A general framework for graph optimization [C]//IEEE International Conference on Robotics and Automation. Piscataway: IEEE,2011: 3607-3613.
[10] JAN S, MICHAL J, TOMAS P.3D with Kinect [C]//2011 IEEE International Conference on Computer Vision Workshops. Barcelona: Institute of Electrical and Electronics Engineers Inc,2011: 1154-1160.
[11] TYKKALA T,AUDRAS C, Comport A I. Direct iterative closest point for real-time visual odometry[C]//ICCV Workshops. IEEE,Barcelona, Spain,2011:2050-2056.
Similar References:

Memo

-

Last Update: 2015-08-28

Copyright © CAAI Transactions on Intelligent Systems