SLAM-based robot navigation method and robot

Abstract

The invention discloses an SLAM-based robot navigation method comprising a pose determination step, a sub-map construction step, a sub-map splicing step and a global map optimization step. According to the SLAM-based robot navigation method disclosed by the invention, sub maps are constructed and splicing is carried out to assist a robot in acquiring complete map information of an ambient environment. When the method is used for carrying out navigation for the robot, the high accuracy of the sensor data is ensured; and on the basis of multiple optimization strategies, the advantages of the laser SLAM navigation method can be realized to the greatest extent. In addition, the invention also discloses a robot using the method for navigation; and the own pose information and feature information of the ambient environment can be obtained, so that the high safety in the robot marching process is guaranteed.

Description

technical field [0001] The invention relates to the field of laser navigation, more specifically, to a SLAM-based robot navigation method and a robot. Background technique [0002] SLAM (Simultaneous Localization and Mapping, real-time positioning and map construction) navigation method is a widely used real-time positioning and navigation method in the field of robots. The data adjusts the robot's travel route in real time. The current SLAM navigation methods mainly have two implementation methods: vision and laser. Among them, the SLAM navigation method implemented by laser technology has the advantages of cost and reliability, and has been relatively mature in most robot products. [0003] However, the existing laser SLAM navigation method also has defects. On the one hand, if the robot is moved from its original position during operation, it needs to re-scan the surrounding environmental feature information, and compare the scanned environmental feature information with...

AI Technical Summary

Problems solved by technology

[0003] However, the existing laser SLAM navigation method also has defects. On the one hand, if the robot is moved from its original position during operation, it needs to re-scan the surrounding environmental feature information, and compare the scanned environmental feature information with the original constructed one. Only by matching the environmental feature information in the complete map can we re-determine our own position. Since the matching process of the environmental feature information is carried out in the complete map, a large amount of data needs to be searched and matched, and the process of completing the relocation takes several days. minutes, thus affecting the work efficiency and user experience of the robot

On the other hand, the existing laser SLAM navigation method needs to obtain odometer data, inertial navigation data and laser data to know the pose state of the robot. Inertial navigation data is optimally calibrated, and the scanned environmental feature information is continuously incorporated into the constructed map to directly build a complete map. Since the process of optimal calibration is continuous, the odometer and inertial navigation system obtained The data will drift as the time of use increases, resulting in less and less accurate odometer data and inertial navigation data used for optimal calibration, which directly affects the accuracy of SLAM navigation methods

Images