Implementation and optimization of ORB-SLAM2 algorithm based on ROS on mobile robots

Abstract

ORB-SLAM2 based on depth camera cannot run directly in ROS operating system, and when the algorithm is implemented through PC, it does not efficiently carry computer resources, and reduces the flexibility of mobile robots. By building a ROS operating system in the embedded system, porting the ORB-SLAM2 algorithm in the system, optimizing the algorithm, adjusting the CPU usage of the algorithm operation, and using a mobile robot based on depth camera for mapping. The results show that the grid map generated by the ROS operating system can meet the needs of robot autonomous navigation, the SLAM effect is more intuitive, the system is more flexible, and the cost and hardware configuration requirements are greatly reduced. It is proved that the optimized algorithm is closer to the actual usage requirements.