Map optimization method and system for mobile robot SLAM

Abstract

The invention relates to a map optimization method and system for a mobile robot SLAM. The method comprises the steps: acquiring the environment information collected by a mobile robot, wherein the environment information is obtained by scanning in an environment of a to-be-constructed map by the mobile robot; obtaining a plurality of indexes representing the quality of the environment grid map, wherein the plurality of indexes comprise a grid occupancy rate, an angular point number and a closed area number; taking the plurality of indexes as targets, and performing multi-target iterative optimization according to the environment information and the ranges of the plurality of parameters to be optimized in the SLAM algorithm to obtain an optimal parameter combination in the SLAM algorithm,wherein the SLAM algorithm is used for generating an environment grid map according to the environment information; generating an optimal environment grid map by adopting an SLAM algorithm of the optimal parameter combination according to the environment information, wherein the optimal environment grid map is used for navigation and positioning of the mobile robot. According to the invention, themap construction efficiency and the map quality of the SLAM can be improved.

Description

technical field [0001] The invention relates to the field of mobile robots, in particular to a map optimization method and system for SLAM of a mobile robot. Background technique [0002] In recent years, with the development and breakthrough of science and technology in the field of mobile robots, mobile robots have become more and more widely used in industries, service industries and other fields, effectively reducing manpower and time costs. Simultaneous Localization And Mapping (SLAM) is an important means for robots to achieve autonomous movement, and related algorithms have become key technologies in the field of mobile robot research. The SLAM problem can be described as: in an unknown environment, can the robot establish a corresponding environment map based on this pose while determining its own pose. At present, there are many SLAM algorithms for two-dimensional lasers in the field of mobile robots. These algorithms have many parameters, and the parameter value s...

AI Technical Summary

Problems solved by technology

Through the establishment of mathematical model-style parameter adjustment, the process is cumbersome and complicated, difficult, and the cycle is long, which is not suitable for practical application

Adjust parameters based on experience, limited by the experience of engineers, it is difficult to guarantee the efficiency of parameter adjustment

At present, algorithm tuning is still a challenge for SLAM workers, which leads to low efficiency of SLAM map construction and poor quality of constructed maps

Images