Method and system for mobile robot pose estimation based on multi-sensor tight coupling

Abstract

The invention discloses a method and system for estimating the pose of a mobile robot based on multi-sensor tight coupling, which belongs to the field of robot positioning technology, wherein the method includes: performing the current frame RGB-D image and the previous frame RGB-D image collected by the camera Feature matching, calculating the visual reprojection error of the matching process; integrating the data measured by the IMU to construct the IMU integral residual; extracting edge feature points and plane feature points from the point cloud collected by the lidar, and calculating the edge feature points to the edge line and the distance from the plane feature point to the plane to construct the geometric residual of the laser point cloud; aiming at the minimum visual reprojection error, IMU integral residual and laser point cloud geometric residual, the pose estimation is performed to obtain the local pose; After using the local pose to update the laser point cloud map, perform global optimization on the laser point cloud map to obtain the global pose. The invention improves the positioning accuracy and robustness of the mobile robot in complex motion and complex environment.

Description

technical field [0001] The invention belongs to the technical field of robot positioning, and more particularly relates to a mobile robot pose estimation method and system based on multi-sensor tight coupling. Background technique [0002] In the field of mobile robots, the fusion of one or more of visual sensors, IMUs, and lidars is often used as the actual SLAM application algorithm. The visual SLAM method using a camera (monocular, binocular or depth) as a single sensor is greatly affected by ambient lighting, and it is difficult to detect effective features in an environment with sparse textures, resulting in missing positioning. The laser SLAM method using lidar (2D or 3D) as a single sensor has a low measurement frequency, and the lidar has motion distortion that is difficult to correct when the motion speed changes greatly. The IMU sensor performs motion estimation based on acceleration and angular velocity integration, and can provide more accurate motion estimation...

AI Technical Summary

Problems solved by technology

[0005] In view of the above defects or improvement needs of the prior art, the present invention provides a mobile robot pose estimation method and system based on multi-sensor tight coupling, thereby solving the problem of existing robot positioning technology in fast movement and different complex environments. Technical issues of low precision and poor robustness

Images