No/VOL: 09/2022 Page no. 40
Authors: W.H.Mohd Saad , H. Hussin , S.A.M. Junos , M.N.Shah Zainudin , N.M. Yatim , A.S. Jaafar , M.R. Kamarudin , K.M. Saipullah :
Title: VSLAM analysis using various ORBSLAM parameters setting
Abstract: SLAM or simultaneous localization and mapping system, is a system that determines the orientation and position of a robot by creating a detailed map of the environment while simultaneously tracking where the robot is within the environment. This project aims to use the camera as SLAM primary sensor to replace the LiDAR sensor frequently used in autonomous robots. ORBSLAM is used as the main algorithm, and a few settings are being adjusted to get the most accurate results. The Absolute Trajectory Error and Relative Pose Error are used to evaluate the algorithms accuracy. After the most optimized setting is found, the setting is used for real-time mapping in an unknown environment.
Key words: VSLAM; ORBSLAM; Absolute Trajectory Error (ATE); Pose Relative Error (RPE).