Patrol robot simultaneous localization and mapping method in underground space based on depth-inertial odometer

Abstract

A patrol robot simultaneous localization and mapping (SLAM) method in an underground space based on a depth-inertial odometer. The method comprises loosely coupling a depth camera and an inertial measurement unit, acquiring point cloud information through a depth map acquired by the depth camera, and extracting a plane feature; converting an RGB image acquired by the depth camera into a grayscalemap to be fused with the plane feature, using an iterative closest point algorithm for optimization; loosely coupling the data subjected to the iterative closest point optimization and the data of theinertial measurement unit, using loop detection to improve the accuracy of a pose image and to obtain the trajectories of the patrol robot, a point cloud map, and a tree skip list map so as to achieve an indoor SLAM effect of the patrol robot. The method improves the simultaneous localization accuracy and robustness of the patrol robot in the underground space, and has a SLAM effect of the patrolrobot in the underground space. When the patrol robot operates in the underground space, the method has good robustness under a strong rotating environment.

Description

technical field [0001] The invention relates to the field of simultaneous positioning of inspection robots, in particular to a method for simultaneous positioning and map construction of an inspection robot in underground space based on a depth inertial odometer. Background technique [0002] With the advancement of science and technology, inspection robots are more and more widely used in industrial, military and other fields. In many cases, the information of the workspace of the inspection robot is complex and unknown. If the inspection robot wants to realize indoor autonomous navigation, target recognition, automatic obstacle avoidance and other functions, its precise and simultaneous positioning is particularly important. Most of the traditional simultaneous positioning methods are based on the simultaneous positioning of global satellites such as GPS and Beidou, but the simultaneous positioning accuracy of ordinary GPS sensors is low, which cannot meet the precise sim...

AI Technical Summary

Problems solved by technology

Although the method of using a separate sensor has a small amount of calculation, the positioning accuracy is not high and the robustness is not strong

Simultaneous localization and mapping methods using fusion of multiple sensors have become mainstream in development, and efficient simultaneous localization and mapping of depth camera and inertial measurement unit fusion are lacking.

Images