Geographical environmental characteristic map construction and navigation method based on data mining

Abstract

The invention discloses a geographical environmental characteristic map construction and navigation method based on data mining, and belongs to the field of automatic control. The method comprises the following flow: firstly performing processing and matching on a current 3D laser-point cloud of the surrounding environment of a platform and a panoramic picture, to acquire characteristic vectors of each object in the platform surrounding environment; secondly inputting the characteristic vectors of each object into a neural network which classifies the characteristic vectors and outputs a characteristic environmental model; thirdly according to the characteristic environmental model, establishing a current local map or updating an original local map; and finally based on a current position of the platform and a predicted next-moment position, selecting a routine for driving according to the local map. If the platform does not reach a final goal, the flow is repeated; and if the platform reaches the final goal, the flow is finished and the final local map is a global map. The method is applicable to geographical environment map construction and navigation of a ground unmanned mobile platform.

Description

technical field [0001] The invention belongs to the field of automatic control, and in particular relates to a method for constructing and navigating a geographic environment map of a ground unmanned mobile platform. Background technique [0002] The ground unmanned mobile platform is a comprehensive system that integrates various functions such as environmental perception, dynamic decision-making and planning, behavior control and execution. The mobility and intelligence of the ground unmanned mobile platform depends on its autonomous navigation capability, and the accurate and fast autonomous navigation function is based on the precise geographic environment map information. Therefore, the study of advanced geographic environment map construction and navigation methods can enhance the intelligence of the ground unmanned mobile platform and open up a situation for its modern application. [0003] The existing geographic environment map construction and navigation methods b...

AI Technical Summary

Problems solved by technology

When using the SLAM method for positioning, it is necessary to add artificial landmarks. At the same time, when the position is moved, the calculation is complex and the amount of calculation is large

[0007] Based on the above-mentioned existing methods, the accuracy of the ground unmanned mobile platform cannot be guaranteed when performing map construction and navigation. At the same time, complex algorithms and huge calculations cannot meet the requirements of modernization.

Images