CN-121995940-A - Unmanned aerial vehicle control method, device, equipment and storage medium

Abstract

The invention relates to the technical field of unmanned aerial vehicle control, and discloses an unmanned aerial vehicle control method, device, equipment and storage medium, which comprise the steps of acquiring a target flight scene, and acquiring scene data of the target flight scene to obtain a scene data set; the method comprises the steps of carrying out three-dimensional modeling based on a scene data set to obtain a three-dimensional scene model, generating a preliminary flight path based on the three-dimensional scene model and a preset obstacle avoidance constraint condition, carrying out paragraph division on the preliminary flight path to obtain paragraph characteristic parameters, generating preliminary control parameters based on the paragraph characteristic parameters, integrating the preliminary flight path and the preliminary control parameters into flight control instructions, and generating the flight control instructions adapting to actual flight requirements based on complete flows of scene perception, three-dimensional modeling, path generation, paragraph characteristic extraction and parameter matching to instruction integration.

Inventors

• CHEN FENG

Assignees

• 广东蜂群航空科技有限公司

Dates

Publication Date

20260508

Application Date

20260303

Claims (10)

1. 1. The unmanned aerial vehicle control method is characterized by comprising the following steps of: acquiring a target flight scene, and acquiring scene data of the target flight scene to obtain a scene data set; performing three-dimensional modeling based on the scene data set to obtain a three-dimensional scene model; generating a preliminary flight path based on the three-dimensional scene model and a preset obstacle avoidance constraint condition; performing paragraph division on the preliminary flight path to obtain paragraph characteristic parameters; Generating preliminary control parameters based on paragraph feature parameters; And integrating the preliminary flight path and the preliminary control parameters into flight control instructions.
2. 2. The unmanned aerial vehicle control method of claim 1, wherein the acquiring the target flight scene and performing scene data acquisition on the target flight scene to obtain the scene data set comprises: Acquiring a target flight scene, and determining a start point and an end point of a flight task based on the target flight scene to define a data acquisition range; Acquiring static environment data based on the data acquisition range to obtain topographic data and obstacle data; Dynamic constraint data acquisition is carried out based on the data acquisition range so as to obtain airspace constraint data and wind speed baseline data; the terrain data, obstacle data, airspace constraint data, and wind speed baseline data are integrated into a scene data set.
3. 3. The unmanned aerial vehicle control method of claim 2, wherein the three-dimensional modeling based on the scene dataset to obtain a three-dimensional scene model comprises: extracting terrain data, obstacle data, airspace constraint data, and wind speed baseline data from the scene dataset; constructing a terrain layer, an obstacle layer and an airspace layer based on the terrain data, the obstacle data and the airspace constraint data respectively; The terrain layer, the barrier layer and the airspace layer are aligned and overlapped according to space coordinates to generate a three-dimensional basic model; and labeling wind speed parameters for each space region in the three-dimensional basic model by using the wind speed baseline data so as to obtain a three-dimensional scene model.
4. 4. The unmanned aerial vehicle control method of claim 1, wherein the generating a preliminary flight path based on the three-dimensional scene model and the preset obstacle avoidance constraints comprises: Determining a space boundary for constructing path search based on the three-dimensional scene model; generating a path feasible region based on a preset obstacle avoidance constraint condition and a space boundary; A path search is performed within the path feasible domain to generate a preliminary flight path.
5. 5. The unmanned aerial vehicle control method of claim 1, wherein the sectioning the preliminary flight path to obtain the section feature parameters comprises: Segmenting the preliminary flight path based on a preset segmentation rule to obtain a plurality of flight paragraphs; Identifying the average gradient, the path curvature and the obstacle distance of each flight paragraph to obtain the characteristic parameters of each flight paragraph; and integrating the characteristic parameters of each flight paragraph into paragraph characteristic parameters according to the sequence of the flight paragraphs.
6. 6. The unmanned aerial vehicle control method of claim 1, wherein the generating preliminary control parameters based on paragraph feature parameters comprises: mapping paragraph characteristic parameters into initial control parameters based on a preset mapping rule; And acquiring performance threshold parameters of the unmanned aerial vehicle, and carrying out numerical correction on an overrun part in the initial control parameters based on the performance threshold parameters to obtain the initial control parameters.
7. 7. The unmanned aerial vehicle control method of claim 1, wherein integrating the preliminary flight path with the preliminary control parameters into flight control instructions comprises: Binding the preliminary control parameters of each paragraph with the preliminary flight path by taking the flight paragraph as a unit, calculating the parameter difference value of the adjacent paragraphs, and performing gradient compensation of the speed and the steering angle on the paragraphs with the difference value exceeding a preset threshold value to obtain a path parameter set; and performing instruction conversion based on the path parameter set to obtain a flight control instruction.
8. 8. An unmanned aerial vehicle control device, characterized by comprising: The data acquisition module is used for acquiring a target flight scene and acquiring scene data of the target flight scene to obtain a scene data set; The model construction module is used for carrying out three-dimensional modeling based on the scene data set so as to obtain a three-dimensional scene model; The path generation module is used for generating a preliminary flight path based on the three-dimensional scene model and a preset obstacle avoidance constraint condition; The paragraph dividing module is used for dividing the paragraphs of the preliminary flight path to obtain paragraph characteristic parameters; The parameter generation module is used for generating preliminary control parameters based on paragraph characteristic parameters; and the instruction generation module is used for integrating the preliminary flight path and the preliminary control parameters into flight control instructions.
9. 9. The unmanned aerial vehicle control device is characterized by comprising a memory and at least one processor, wherein the memory stores instructions; at least one of the processors invokes the instructions in the memory to cause the drone control apparatus to perform the steps of the drone control method of any one of claims 1-7.
10. 10. A computer readable storage medium having instructions stored thereon, which when executed by a processor, implement the steps of the drone control method of any one of claims 1-7.

Description

Unmanned aerial vehicle control method, device, equipment and storage medium Technical Field The present invention relates to the field of unmanned aerial vehicle control technologies, and in particular, to an unmanned aerial vehicle control method, apparatus, device, and storage medium. Background In the existing unmanned aerial vehicle control method, most of flight path planning and control parameter generation are independent and separated, parameter generation is not carried out by fully combining with actual environment characteristics of a target flight scene, so that generated control parameters and path suitability are poor, the problems of unstable flight, insufficient obstacle avoidance precision and the like are easy to occur, and the requirement of unmanned aerial vehicle accurate flight under a complex scene cannot be met. Disclosure of Invention In order to overcome the defects in the prior art, the invention aims to provide an unmanned aerial vehicle control method, an unmanned aerial vehicle control device, unmanned aerial vehicle control equipment and a storage medium; according to the invention, based on complete flow of scene perception, three-dimensional modeling, path generation, paragraph feature extraction and parameter matching to instruction integration, the flight control instruction adapting to actual flight requirements is generated, the problem of poor adaptability of the flight path and control parameters in the prior art is solved, and the flight stability and accuracy of the unmanned aerial vehicle are improved. The first aspect of the invention provides an unmanned aerial vehicle control method, which comprises the steps of obtaining a target flight scene, collecting scene data of the target flight scene to obtain a scene data set, carrying out three-dimensional modeling on the basis of the scene data set to obtain a three-dimensional scene model, generating a preliminary flight path on the basis of the three-dimensional scene model and preset obstacle avoidance constraint conditions, carrying out paragraph division on the preliminary flight path to obtain paragraph characteristic parameters, generating preliminary control parameters on the basis of the paragraph characteristic parameters, and integrating the preliminary flight path and the preliminary control parameters into flight control instructions. Optionally, in a first implementation manner of the first aspect of the present invention, the acquiring the target flight scene and performing scene data acquisition on the target flight scene to obtain the scene data set includes acquiring the target flight scene, determining a start point and an end point of a flight mission based on the target flight scene to define a data acquisition range, performing static environment data acquisition based on the data acquisition range to obtain terrain data and obstacle data, performing dynamic constraint data acquisition based on the data acquisition range to obtain airspace constraint data and wind speed baseline data, and integrating the terrain data, the obstacle data, the airspace constraint data and the wind speed baseline data into the scene data set. Optionally, in a second implementation manner of the first aspect of the present invention, the three-dimensional modeling is performed based on the scene data set to obtain the three-dimensional scene model, which includes extracting terrain data, obstacle data, airspace constraint data and wind speed baseline data from the scene data set, constructing a terrain layer, an obstacle layer and an airspace layer based on the terrain data, the obstacle data and the airspace constraint data respectively, aligning and superposing the terrain layer, the obstacle layer and the airspace layer according to space coordinates to generate the three-dimensional basic model, and labeling wind speed parameters for each space region in the three-dimensional basic model by using the wind speed baseline data to obtain the three-dimensional scene model. Optionally, in a third implementation manner of the first aspect of the present invention, the generating the preliminary flight path based on the three-dimensional scene model and the preset obstacle avoidance constraint condition includes determining a spatial boundary for constructing a path search based on the three-dimensional scene model, generating a path feasible region based on the preset obstacle avoidance constraint condition and the spatial boundary, and executing the path search in the path feasible region to generate the preliminary flight path. Optionally, in a fourth implementation manner of the first aspect of the present invention, the step of dividing the preliminary flight path to obtain the paragraph feature parameters includes dividing the preliminary flight path based on a preset division rule to obtain a plurality of flight paragraphs, identifying an average gradient, a path curvature and an obstacle distance of each flight