Processed RGB-D Slam Using Open-Source Software

摘要

SLAM (Simultaneous Localization and Mapping) of robot is the key to achieve autonomous control of robot, and also a significant topic in the field of mobile robotics. Aiming at 3D modeling of indoor complex environment, this paper presents a fast three-dimensional simultaneous location and mapping (SLAM) method for mobile robots. On the basis of RGB-D SLAM algorithm, the open-source software combining the RGB-D sensor like Kinect with the wheeled mobile robot is used to obtain the odometry data, and then the information of their location is matched through the image feature extraction and in the end the map is constructed. Finally, the feasibility and effectiveness of the proposed method are verified by experiments in indoor environment.