A method of navigation for a robot

Abstract

The invention discloses a navigation method for a robot. Firstly, when the robot is started, a virtual cleaning zone is framed in the working space, and then the boundary feature information of the navigation boundary is marked during the process of cleaning the virtual cleaning zone, and a local boundary map is constructed; The data of the local boundary map is converted to the global coordinate system; after cleaning the virtual cleaning partition, move to the uncleaned area, and frame the next virtual cleaning partition, continue to mark the boundary feature information, and so on. When the entire workspace is cleaned, the loop is exited to complete the construction of the global boundary map; finally, the navigation boundary is selected as the navigation path for navigation. Through the method of constructing the local boundary map and the global boundary map, the present invention realizes fast navigation of the robot under the condition of retaining the characteristic information of the boundary, saves system memory at the same time, and improves the flexibility and efficiency of robot navigation.

Description

technical field [0001] The invention relates to the technical field of indoor navigation and intelligent control of robots, in particular to a method for constructing a global boundary map and a navigation method thereof. Background technique [0002] Robots based on inertial navigation are becoming more and more popular, and the most representative ones are household sweeping and cleaning robots. The sweeping robot combines the data of the gyroscope, acceleration and wheel odometer to realize real-time positioning and mapping of the indoor environment, and then realize positioning and navigation according to the established map. The robot based on inertial navigation navigates back to the charging base based on the global grid map. When implementing gyroscope-based inertial navigation in the actual home environment, because there are various unknown conditions in the relatively complex home environment, the Over time, the errors caused by wheel slippage and gyroscope drift...

AI Technical Summary

Problems solved by technology

[0004] Chinese invention patent CN100449444 proposes a method for simultaneous positioning and map construction of mobile robots in an unknown environment. High-precision positioning and navigation is achieved by constructing a global line segment feature map and a global occupancy grid map, but the matching line segment features and grid map update in the map The algorithm has high requirements on the performance of the processor, and the amount of calculation for line segment feature matching is relatively large; the method of topological map is used in the Chinese patent CN107121142, and the method of combining the current environment characteristics of the robot is used to judge whether to divide the sub-regions and how to divide them, and then fuse the sensor data Path planning is performed, but the division of sub-areas is affected by the detection range of the laser sensor

Images