Introduction - If you have any usage issues, please Google them yourself
In this paper, based on multi-sensor integrated navigation method of SLAM, since the mobile robot can not pass through a single
Sensors give reliable information, the use of multi-sensor integrated navigation method can solve this problem. In this paper, single
CCD camera and odometer combination SLAM research and get more accurate information on pose. Firstly SIFT
Different algorithms for image feature extraction and matching, to obtain essential matrix, it is decomposed to obtain the rotation of the robot
Matrix and translation vector (and the actual difference a scale factor). Then, combine it with the odometer information to give the robot
Pose. On this basis, the three-dimensional coordinates of the feature point can be obtained in the current camera coordinate system, the map feature is created.
Experimental results show that this method can reduce the cumulative error odometer, improve positioning accuracy.