A method to improve visual Graph under complex maps

Abstract

The invention discloses a method of improving Visual Graph in a complicated map, which is thus applicable to a map with a convex polygon obstacle and also applicable to an SLAM map for a general complicated terrain. Visual Graph is a path planning algorithm brought forward in 1979, the characteristic that light travels in a straight line is simulated, the starting point and the ending point are connected with angular points of the convex polygon obstacle to form paths, but Visual Graph is only limited to the convex polygon obstacle. The main idea that light travels in the straight line is still used, light is emitted from the starting point and the ending point of a path, through reflection of the obstacle, a path connecting the starting point and the ending point with the light path as a carrier is finally acquired, a function of path planning is realized, simply using an obstacle vertex connection line as a carrier does not happen, and thus, the method is not limited to a convex polygon obstacle but is also applicable to a general complicated terrain.

Description

technical field [0001] The present invention relates to a path planning algorithm in the field of intelligent robot motion planning, specifically an improvement of the Visual Graph algorithm for maps with complex terrains, so that it can be applied not only to maps with convex polygonal obstacles, but also to complex map. Background technique [0002] At present, the research on robot systems capable of autonomous navigation and obstacle avoidance is extremely hot, and many products have been applied in practice. For example, a service robot in a restaurant has the ability to identify obstacles and plan paths; another example is a home sweeping robot, which also has the ability to plan its own movement path in an open space. In terms of public transportation, the application of drone express delivery has been in full swing, and path planning must also be used in express delivery, so that the drone can reach the destination with the shortest path while avoiding obstacles. C...

AI Technical Summary

Problems solved by technology

[0005] The technology of the present invention solves the problem: it overcomes the rigid requirements of the original Visual Graph on the map, and proposes a method to improve the Visual Graph under complex maps, so that it is no longer limited to maps with convex polygonal obstacles, and under complex SLAM maps can also be run without preprocessing the map, and the node density parameter can be easily adjusted to generate accurate paths

Images