Research on RGB-D SLAM Method for Mobile Robot in Subway Station

In recent years, China's subway has developed at an amazing speed, and various service robots with navigation and language communication functions have appeared in subway stations. The subway station scene is characterized by a large number of people and a fast moving target. In such a scenario, the mobile robot must not only achieve real-time navigation, but also avoid hitting fast-moving pedestrians, which places high demands on the movement of the robot. In order to solve this problem, this paper proposes a simultaneous localization and mapping (SLAM) method based on RGB-D for mobile robots in subway station scenes, which provides an effective solution to the problem of moving mobile robots in subway stations. The key point of this method is that the robot needs to update the map in real time through the information collected by RGB-D, and quickly make movement decisions. Our contributions include: i. Propose a mobile robot based on RGB-D SLAM method to adapt to the subway station scenario; ii. Verify the feasibility of this method to construct dense maps in real time and use them for navigation.