Cross-scene navigation method, device and storage medium

Abstract

The invention discloses a cross-scenario navigation method, device and storage medium. By acquiring the current position of the robot and the target position that the robot will arrive at which is not in the same application scene as the current position; searching the created git navigation map, Obtain the decision chain in the git navigation map corresponding to the current location to the target location, and based on the decision chain, obtain the decision-making route in the application scenario corresponding to the decision chain, and obtain the corresponding cross-scenario navigation path; according to the acquired In the cross-scene navigation path, the robot navigates from the current position to the target position across scenes; it solves the problems in the prior art that the cross-scene map has no navigation error correction function during the application process and the management of map data is chaotic. Further, the efficiency of cross-scene navigation and the accuracy of navigation routes are improved.

Description

technical field [0001] The present invention relates to the technical field of robots, in particular to a cross-scene navigation method, device and storage medium. Background technique [0002] With more and more application scenarios of autonomous mobile robots, the requirements for cross-scenario navigation of autonomous mobile robots are also getting higher and higher. In the navigation process of an autonomous mobile robot, the cross-scenario navigation requirement makes the robot need to read the corresponding map data in different application scenarios, and navigate according to the map data of this scene. Therefore, how to manage and maintain the maps of different scenarios and How to quickly find the map required by the robot is a problem that the robot needs to pay attention to and solve when navigating across scenes. [0003] At present, in the prior art, there are mainly the following two solutions to the above problems. One is: store all the scenes where the rob...

AI Technical Summary

Problems solved by technology

However, this processing method is not convenient for maintaining the map of a single scene

The other is: save a map for each scene of the robot, and go to the scene where the robot goes to find it; the disadvantage is that it cannot reflect the sequence relationship of the robot's decision-making, and there is no error correction function for navigation, such as the robot from the warehouse. When the scene comes out, it should actually go to the factory park scene, but the search result is the home scene. At this time, the robot cannot find this error.

In addition, you can also choose to maintain the current state machine of the robot in the server or robot body software. When the perception moves out of a scene, switch this state and search in the map server in turn to get the corresponding map. The time efficiency is low, and it is impossible to realize the macro-route derivation of robot navigation and the management of navigation map data for the decision-making chain. In addition, it is impossible to display the macro-scene path map

Images