| A FUSION OF WI-FI LOCALIZATION AND VISUAL ODOMETRY WITH EKF FOR THE INDOOR LOCALIZATION OF A SIX WHEELS ROBOT |
| Paper ID : 1330-SMPR |
| Authors: |
|
mojtaba akhoundi *1, Ali Hosseininaveh2, Mohammad Javad Valadan Zouj3, mohammad hosein azimi4 1photogrammetry,geomatics, K.N. Toosi University of technology,Tehran,Iran 2Department of Photogrammetry and Remote Sensing Faculty of Geodesy and Geomatics Engineering K. N. Toosi University of Technology 3Department of Photogrammetry and Remote Sensing Faculty of Geodesy and Geomatics Engineering K. N. Toosi University of technology 4geographic information system,geomatics, K. N. Toosi university of technology, Tehran, Iran |
| Abstract: |
| While GNSS is a powerful tool for outdoor localization, there is no such technique for indoor environment. Most of indoor localization methods are not satisfying both accuracy and reliability. Improving methods of indoor localization is a hot topic for researchers due to its vast applications. This paper aims to develop a near real-time indoor localization method for MOOR surveying robot. The proposed method uses a Wi-Fi localization technique to determine the initial position of robot. A correction term is used to improve the quality of localization with Wi-Fi. By using Visual Odometry (VO) and Extended Kalman Filter (EKF), it can predict its own trajectory and correct the produced errors. Fusion of these methods would result in overcoming kidnap problem for indoor localization of the robot. At last, to determine the accuracy of the localization, the position of some points in the point cloud is measured using another technique and compared to the results of the proposed method. |
| Keywords: |
| INDOOR LOCALIZATION, VISUAL ODOMETRY, WI-FI LOCALIZATION, EXTENDED KALMAN FILTER, ROBOT MAPPING, ROBOT LOCALIZATION |
| Status : Paper Accepted (Oral Presentation) |
