Orb-slam Performance for Indoor Environment Using Jackal Mobile Robot
Abstract
Computer vision is a hot topic these days. It has many applications such as object recognitions and navigation. Robot learning is the key ingredient for the future of autonomous robots. Recent trends in robot learning are to use Simultaneous Localization and Mapping (SLAM) technique. The traditional SLAM utilizes IMU, radar and other sensors to find the location and map the environment. In visual SLAM, the camera is the only sensor used and information extracted from the images. This thesis explains how Oriented FAST and rotated BRIEF SLAM (ORB-SLAM), one of the best visual SLAM solutions, works indoor and evaluates the technique performance for three different cameras: monocular camera, stereo camera and RGB-D camera. Three experiments are designed to find the limitation of the algorithm. From the experiments, the RGB-D SLAM gives the most accurate result for the indoor environment. The monocular SLAM performs better than stereo SLAM on our platform due to limited computation power. It is expected that stereo SLAM provides better results by increasing the experimental platform computational power. The ORBSLAM results demonstrate the applicability of the approach for the autonomous navigation and future autonomous cars.
Degree
M.Sc.
Advisors
Houshangi, Purdue University.
Subject Area
Applied Mathematics|Mathematics|Robotics
Off-Campus Purdue Users:
To access this dissertation, please log in to our
proxy server.