CN-121979235-A - Mobile device control method, electronic device and readable storage medium

CN121979235ACN 121979235 ACN121979235 ACN 121979235ACN-121979235-A

Abstract

The embodiment of the application provides a control method of mobile equipment, electronic equipment and a readable storage medium, relates to the field of unmanned aerial vehicle inspection, and can improve the safety of autonomous flight of an unmanned aerial vehicle along a power transmission line. The method comprises the steps of obtaining two-dimensional perception information and three-dimensional perception information of a pipeline network under the same spatial reference through mobile equipment, determining a current reliability quantization value of perception capability of the mobile equipment based on the two-dimensional perception information, the three-dimensional perception information and uniqueness judgment results of three-dimensional feature points, wherein different reliability quantization values correspond to different flight distance constraint conditions, the flight distance constraint conditions are used for constraining the mobile equipment to detect the transverse and longitudinal flight distances of the pipeline, and determining a target control instruction of the mobile equipment based on a target flight distance constraint condition corresponding to the current reliability quantization value and the available pipeline length corresponding to the pipeline network.

Inventors

FAN SHUAIFANG
YOU ZHIYUAN
XU YULONG
SONG QIJUN
XIN RONGHUAN
CAI MINGHUI
ZHAO YASHUAI

Assignees

中国联合网络通信集团有限公司
中讯邮电咨询设计院有限公司

Dates

Publication Date: 20260505
Application Date: 20260107

Claims (20)

1. A method of controlling a mobile device, the method comprising: Acquiring two-dimensional perception information and three-dimensional perception information of a pipeline network under the same spatial reference through mobile equipment, wherein the pipeline network comprises a plurality of detection pipelines, the two-dimensional perception information comprises image sequences of the detection pipelines in the pipeline network, and the three-dimensional perception information comprises a uniqueness judgment result of three-dimensional feature points corresponding to the detection pipelines on the detection pipelines; Determining a current reliability quantization value of the sensing capability of the mobile device based on the two-dimensional sensing information, the three-dimensional sensing information and the uniqueness judgment result of each three-dimensional feature point, wherein different reliability quantization values correspond to different flight distance constraint conditions; And determining a target control instruction of the mobile equipment based on a target flight distance constraint condition corresponding to the current reliability quantization value and an available pipeline length corresponding to the pipeline network.
2. The method of claim 1, wherein the determining a current reliability quantization value for a perceived capability of the mobile device based on the two-dimensional perceived information, the three-dimensional perceived information, and a result of the uniqueness determination of each of the three-dimensional feature points comprises: based on the two-dimensional perception information and the three-dimensional perception information, obtaining a projection superposition ratio; and inputting the projection superposition proportion, the two-dimensional perception information, the three-dimensional perception information and the uniqueness judgment result of each three-dimensional characteristic point into a perception reliability quantization model, and outputting the current reliability quantization value of the perception capability of the mobile equipment.
3. The method of claim 2, wherein the three-dimensional perception information comprises a pipeline centerline of the detection pipeline and a three-dimensional perception range; the obtaining the projection coincidence proportion based on the two-dimensional perception information and the three-dimensional perception information comprises the following steps: fitting the three-dimensional perception information into a three-dimensional wire; Under the same space reference, based on a pipeline central line and a three-dimensional sensing range corresponding to the three-dimensional sensing information, projecting the three-dimensional conducting wire into a two-dimensional sensing range corresponding to the two-dimensional sensing information, and acquiring two-dimensional projection information; And determining a superposition lead based on the two-dimensional projection information and the two-dimensional perception information, and acquiring the projection superposition proportion.
4. A method according to claim 2 or 3, wherein the perceived reliability quantification model comprises a two-dimensional feature extraction network, a three-dimensional feature extraction network, and a fusion network; The step of inputting the projection coincidence proportion, the two-dimensional perception information, the three-dimensional perception information and the uniqueness determination result of each three-dimensional feature point to a perception reliability quantization model, and outputting the current reliability quantization value of the perception capability of the mobile device, comprises the following steps: Inputting the two-dimensional perception information into the two-dimensional feature extraction network to obtain a two-dimensional feature embedded vector corresponding to the two-dimensional perception information; Inputting the three-dimensional perception information into the three-dimensional feature extraction network to obtain a three-dimensional feature embedding vector corresponding to the three-dimensional perception information; Inputting the two-dimensional feature embedded vector, the three-dimensional feature embedded vector, the projection coincidence proportion and the uniqueness judgment result of each three-dimensional feature point into the fusion network to obtain a fusion feature vector; based on the fused feature vector, a current reliability quantization value of a perceptual capability of the mobile device is determined.
5. The method according to claim 4, wherein inputting the two-dimensional feature embedding vector, the three-dimensional feature embedding vector, the projection coincidence ratio, and the result of the determination of the uniqueness of each of the three-dimensional feature points to the fusion network to obtain a fusion feature vector includes: calculating a difference vector between the two-dimensional feature embedding vector and the three-dimensional feature embedding vector; calculating a product vector of the two-dimensional feature embedding vector and the three-dimensional feature embedding vector; And splicing and fusing the difference vector, the product vector, the two-dimensional feature embedding vector, the three-dimensional feature embedding vector, the projection coincidence proportion and the uniqueness judgment result of each three-dimensional feature point to obtain the fusion feature vector.
6. The method according to claim 4 or 5, wherein the perceived reliability quantization model further comprises a decision network; the determining, based on the fused feature vector, a current reliability quantization value for a perceptual capability of the mobile device, comprising: and inputting the fusion feature vector into the judging network, and acquiring a current reliability quantized value of the perception capability of the mobile equipment and an abnormal type corresponding to the current reliability quantized value.
7. The method according to any one of claims 1 to 6, wherein, The lower the current reliability quantization value of the perception capability of the mobile device, the greater the flight distance indicated by the flight distance constraint condition.
8. The method according to any one of claims 2-7, further comprising: If the length of the available pipeline is greater than or equal to a preset length threshold value, and the current reliability quantization value is in a first preset range, keeping a target flight distance constraint condition corresponding to the current reliability quantization value unchanged; And if the length of the available pipeline is smaller than the preset length threshold, and the current reliability quantized value is in a first preset range, reducing the flight distance indicated in the target flight distance constraint condition corresponding to the current reliability quantized value, and obtaining the updated target flight distance constraint condition.
9. The method of claim 8, wherein the method further comprises: determining an adjustment direction and an adjustment amplitude corresponding to the flight distance constraint condition based on the abnormal type corresponding to the current reliability quantization value; And adjusting the flight distance constraint condition based on the adjustment direction and the adjustment amplitude to obtain an updated target flight distance constraint condition.
10. The method of claim 9, wherein the anomaly types include two-dimensional perceptual information anomalies, three-dimensional perceptual information anomalies, and coincidence anomalies; The determining the adjustment direction and the adjustment amplitude corresponding to the flight distance constraint condition based on the abnormal type corresponding to the current reliability quantization value comprises the following steps: If the anomaly type corresponding to the current reliability quantization value is the two-dimensional perception information anomaly, determining that the adjustment direction corresponding to the two-dimensional perception information anomaly is longitudinal, and determining that the adjustment amplitude corresponding to the longitudinal is a preset first longitudinal amplitude; If the abnormal type corresponding to the current reliability quantization value is the three-dimensional perception information abnormality, determining that the adjustment direction corresponding to the three-dimensional perception information abnormality is transverse, and determining that the adjustment amplitude corresponding to the transverse direction is a preset second transverse amplitude; If the type of the abnormality corresponding to the current reliability quantization value is the coincidence abnormality, determining that the adjustment direction corresponding to the coincidence abnormality is transverse and longitudinal, wherein the adjustment amplitude corresponding to the transverse direction is a preset third transverse amplitude, and the adjustment amplitude corresponding to the longitudinal direction is a preset third longitudinal amplitude.
11. The method according to any one of claims 2-10, further comprising: if the projection coincidence proportion is larger than or equal to a preset coincidence threshold value, taking a preset flight distance constraint condition as the target flight distance constraint condition; And if the projection coincidence proportion is smaller than the preset coincidence threshold value, keeping the target flight distance constraint condition corresponding to the current reliability quantized value unchanged.
12. The method according to any one of claims 1-11, wherein the acquiring, by the mobile device, two-dimensional and three-dimensional awareness information of the pipe network under the same spatial reference comprises: Acquiring initial two-dimensional perception information through two-dimensional perception equipment of the mobile equipment, wherein the two-dimensional perception equipment comprises an image acquisition device, and the initial two-dimensional perception information comprises an image sequence of the pipeline network; Acquiring initial three-dimensional perception information through three-dimensional perception equipment of the mobile equipment, wherein the three-dimensional perception equipment comprises a laser radar device, and the initial three-dimensional perception information comprises point cloud data of the pipeline network; mapping the initial two-dimensional sensing information and the initial three-dimensional sensing information to the same spatial standard, and determining a pipeline center line, a two-dimensional sensing range corresponding to the initial two-dimensional sensing information and a three-dimensional sensing range corresponding to the initial three-dimensional sensing information; Dividing pipeline segments of a detection pipeline in the image sequence based on the pipeline center line and the two-dimensional perception range to obtain a first pipeline segment set, wherein the first pipeline segment set comprises a plurality of image sequence segments; Dividing pipeline segments of detection pipelines in the point cloud data based on the pipeline center line and the three-dimensional perception range to obtain a second pipeline segment set, wherein the second pipeline segment set comprises a plurality of point cloud data segments; Acquiring the two-dimensional perception information based on the first pipeline segment set; And acquiring the three-dimensional perception information based on the second pipeline segment set.
13. The method of claim 12, wherein the two-dimensional perceptual information comprises a direction consistency quantization value, a longest continuous length, a number of breaks, and an inflection point marker; the obtaining the two-dimensional perception information based on the first pipeline segment set includes: based on the direction of the line in the pipeline, acquiring a direction consistency quantized value corresponding to each image sequence fragment in the first pipeline fragment set; Based on the wire pixels of the image sequence fragments along the pipeline centerline direction, acquiring the longest continuous length and the breaking times corresponding to each image sequence fragment of the first pipeline fragment set; Determining inflection marks corresponding to all image sequence fragments of the first pipeline fragment set based on preset inflection point judging conditions; And determining two-dimensional perception information corresponding to the first pipeline fragment set based on the direction consistency quantized value, the longest continuous length, the breaking times and the inflection point markers.
14. The method of claim 13, wherein determining the inflection point label corresponding to each image sequence segment of the first pipeline segment set based on a preset inflection point decision condition comprises: If the direction change rate of the image sequence segments is greater than or equal to a preset direction change rate threshold, determining a shielding section of each image sequence segment in the first pipeline segment set; acquiring the shielding arc length of each image sequence segment in the first pipeline segment set based on the shielding section; and determining inflection point marks corresponding to the image sequence fragments of the first pipeline fragment set based on the shielding arc length.
15. The method of claim 12, wherein the three-dimensional perceptual information comprises a first distribution uniformity quantization value, an echo stability quantization value, and a first fine tuning stability quantization value; the obtaining the three-dimensional perception information based on the second pipeline segment set includes: determining the number of three-dimensional characteristic points of each point cloud data segment in the second pipeline segment set in a preset length based on the direction of the pipeline center line, and obtaining a first distribution uniformity quantization value of each point cloud data segment in the second pipeline segment set; determining an echo stability quantization value of each point cloud data segment in the second pipeline segment set based on the echo intensity of each point cloud data segment in the second pipeline segment set; acquiring a first fine tuning stability quantized value of each point cloud data segment in the second pipeline segment set based on a preset fine tuning amplitude and the three-dimensional perception range of the point cloud data segment; And determining three-dimensional perception information corresponding to the second pipeline segment set based on the first distribution uniformity quantized value, the echo stability quantized value and the first fine tuning stability quantized value.
16. The method according to any one of claims 1-15, further comprising: acquiring a second distributed uniform quantized value and a second fine tuning stability quantized value of each point cloud data segment in the second pipeline segment set after offset based on a preset offset pipeline center line parallel to the pipeline center line; Based on the first distribution uniformity quantized value, the first fine tuning stability quantized value, the second distribution uniformity quantized value and the second fine tuning stability quantized value, acquiring a uniqueness judgment result of each point cloud data segment in the second pipeline segment set through a preset uniqueness quantization formula.
17. The method of claim 16, wherein the method further comprises: If the uniqueness quantization value is larger than or equal to a uniqueness quantization threshold, determining that the uniqueness judgment result of each point cloud data fragment in the second pipeline fragment set is yes, wherein the uniqueness judgment result is used for representing that the reliability of each point cloud data fragment in the second pipeline fragment set is high; and if the uniqueness quantization value is smaller than the uniqueness quantization threshold, determining whether the uniqueness judgment result of each point cloud data segment in the second pipeline segment set is negative, and determining whether the uniqueness judgment result represents that the reliability of each point cloud data segment in the second pipeline segment set is low.
18. The method according to any one of claims 1-17, further comprising: And if the current reliability quantization value is in the second preset range, the projection coincidence proportion is larger than or equal to the preset coincidence threshold value, and the uniqueness judgment result is that the available pipeline length corresponding to the pipeline network is determined.
19. An electronic device comprising a processor, a communication interface and a memory, wherein the memory has stored therein at least one computer program, at least one of which is loaded and executed by the processor to implement the method of controlling a mobile device according to any of claims 1 to 18.
20. A computer readable storage medium, characterized in that at least one computer program is stored in the computer readable storage medium, the at least one computer program being loaded and executed by a processor to implement a method of controlling a mobile device according to any of claims 1 to 18.

Description

Mobile device control method, electronic device and readable storage medium Technical Field The present application relates to the field of unmanned aerial vehicle inspection, and in particular, to a control method for a mobile device, an electronic device, and a readable storage medium. Background In the prior art, unmanned aerial vehicle realizes autonomous flight along the transmission line through the continuous perception result of the transmission line in a complex outdoor environment, thereby realizing inspection of the transmission line. However, the continuous sensing result of the existing unmanned aerial vehicle is influenced by complex and severe environments and complex power transmission lines, the problem of low reliability exists, and the unmanned aerial vehicle has low safety in autonomous flight along the power transmission lines. Disclosure of Invention The application provides a control method of mobile equipment, electronic equipment and a readable storage medium, which can improve the safety of autonomous flight of an unmanned aerial vehicle along a power transmission line. In order to achieve the above purpose, the application adopts the following technical scheme: in a first aspect, the present application provides a control method of a mobile device, the method including: The method comprises the steps of obtaining two-dimensional perception information and three-dimensional perception information of a pipeline network under the same spatial reference through mobile equipment, wherein the pipeline network comprises a plurality of detection pipelines, the two-dimensional perception information comprises an image sequence of the detection pipelines in the pipeline network, and the three-dimensional perception information comprises a unique judgment result of three-dimensional feature points corresponding to the detection pipelines on the detection pipelines. And determining a current reliability quantized value of the sensing capability of the mobile device based on the two-dimensional sensing information, the three-dimensional sensing information and the uniqueness judgment result of each three-dimensional feature point, wherein different reliability quantized values correspond to different flight distance constraint conditions, the flight distance constraint conditions are used for constraining the transverse and longitudinal flight distances of the mobile device to the detection pipeline, and a target control instruction of the mobile device is determined based on a target flight distance constraint condition corresponding to the current reliability quantized value and the available pipeline length corresponding to the pipeline network. Based on the first aspect, the two-dimensional perception information can represent two-dimensional image information related to pipeline conditions and surrounding environments of detection pipelines of the pipeline network, the three-dimensional perception information can represent three-dimensional information related to pipeline conditions and surrounding environments of detection pipelines of the pipeline network, and the uniqueness judgment result of the detection pipelines contained in the three-dimensional perception information can represent the probability that each three-dimensional feature point in the three-dimensional perception information can represent information of the same target detection pipeline. By combining the two-dimensional sensing information and the three-dimensional sensing information, the actual sensing condition (namely, the reliability quantization value of the sensing capability) of the detection pipeline can be obtained more accurately, and the flight distance constraint condition of the mobile device determined based on the more accurate actual sensing condition is also more accurate. Further, the available pipe length refers to the length of the effective detection pipe composition, the effective detection pipe refers to the detection pipe without shielding, the mobile device detects in the available pipe length, and the mobile device does not detect for non-available pipes, i.e. for other pipes due to bad environmental influence or shielding. When the mobile equipment moves to other pipelines, the flight distance of the mobile equipment from other pipelines is far, so that the influence of complex and severe environments and complex pipeline networks on the aspects of the flight of the mobile equipment, the acquisition of perception data and the like can be avoided. In addition, instructions generated based on the more accurate flight distance constraints and the available pipe lengths are also more accurate. Therefore, the mobile equipment can realize more accurate and reliable control in the flight process along the detection pipeline, so that the safety and the continuity of autonomous flight of the mobile equipment are improved. In one possible implementation manner, the determining the current reliability