Improved RGB-D vision SLAM algorithm for mobile robot

Simultaneous localization and mapping (SLAM) is one of the most challenging problems of mobile robots. An improved RGB-D visual SLAM algorithm is proposed in this paper, which based on the wheeled mobile robot to solve the problem of accumulative position error and large computation existed in the traditional algorithm. In order to overcome the error caused by the superposition of frames, a semi-random loop closures detection method is introduced at the backend of the graph optimization process. In this paper, we use the FR1/room data packet for experiments, and the experimental results show that the improved RGB-D visual SLAM algorithm saves computation time and enhances the real-time performance of the algorithm.