Bian Junjian

TL;DR: In this article, an RGB-D camera large-scale 3D scene construction method and system is described, which comprises the following steps: obtaining a depth image and a color image of an RGBD camera, generating a 3D point cloud, and registering the point cloud to a laser radar reference system; acquiring robot attitude data and scanning point data of the laser radar, and processing the data by using a local optimization algorithm of a Cartographerd algorithm to generate a subgraph and robot odometer information; and binding the generated sub-graphs with the corresponding point clouds according

TL;DR: In this article, a real-time SLAM scene map constructing system, a navigation system and a method are disclosed, which overcomes the difficult problem of realtime map constructing for SLAM navigation systems when scene changes are large, such that a robot can obtain accurate positioning information in a changed scene.

TL;DR: In this paper, a multi-robot map construction method and system is presented, which comprises the steps of: scanning environment information by each robot through laser radar and uploading the environment information to a local server to generate a raster map of the robot; recognizing two-dimensional code information in the environment by a visual sensor so as to obtain a unique ID of each twodimensional code and a pose of each robot relative to the 2D code, and sending the unique ID and the pose to the local server; and processing the raster maps constructed by all the robots and the

TL;DR: In this article, an open loop optimization method and system based on SLAM mapping is presented, which comprises the steps that map information of a local environment where mapping needing equipment islocated is acquired, and mapping is carried out based on the map of the local environment.