Research of SLAM for Static Environment Based on Kinect

DOI

10.2991/ceie-16.2017.56How to use a DOI?

Keywords

SLAM; Kinect; Loop Closure Detection; Pose Graph Optimization

Abstract

Intelligent mobile robots require autonomous navigation and localization in the environment. In order to realize the function of localization and navigation, the robot often needs to obtain the 3D map of the environment. The basic and key technology to achieve the intelligence is Simultaneous Localization and Mapping (SLAM). In order to solve the problem of localization for mobile robots based on vision, a method of SLAM based on Kinect is proposed. Firstly, the continuous images are obtained by Kinect sensor. Secondly, to find the matching points between the two frames via SIFT feature matching method, then RANSAC algorithm is used to remove the errors of matching, and the relative motion transformations are computed via the PnP algorithm. Thirdly, loop closure detection and global graph optimization are used to eliminate the accumulated robot pose errors and achieve a continuous trajectory. Finally, the 3D map of the environment is obtained. Experimental results show the feasibility and effectiveness of this method.

Copyright

© 2017, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Hongyan Chen
AU  - Yajun Zhang
PY  - 2016/10
DA  - 2016/10
TI  - Research of SLAM for Static Environment Based on Kinect
BT  - Proceedings of the International Conference on Communication and Electronic Information Engineering (CEIE 2016)
PB  - Atlantis Press
SP  - 448
EP  - 454
SN  - 2352-5401
UR  - https://doi.org/10.2991/ceie-16.2017.56
DO  - 10.2991/ceie-16.2017.56
ID  - Chen2016/10
ER  -