In view of the complexity, the low precision and the interference of the EKF-SLAM algorithm of mobile robot, an improved simultaneous localization and mapping (SLAM) algorithm based on the optimal smoothing filtering theory is proposed. The improvement process of the algorithm is introduced in detail, and the position tracking error and standard deviation of the position tracking software are simulated and analyzed by MATLAB software to verify the superiority of the improved algorithm. Finally, an experimental platform based on robot operating system (ROS) system is designed and SLAM experiment is carried out in the indoor corridor to test the effect of the improved algorithm. The results show that the improved SLAM algorithm has high precision and strong anti-interference ability, and it can realize simultaneous localization and map building of mobile robot. At the same time, the software platform based on ROS system simplifies the difficulty of development and improves the intelligence of mobile robot.