CN115220046A - Control method and system for landing and positioning of unmanned aerial vehicle equipment based on laser recognition - Google Patents

Control method and system for landing and positioning of unmanned aerial vehicle equipment based on laser recognition Download PDF

Info

Publication number
CN115220046A
CN115220046A CN202210623063.7A CN202210623063A CN115220046A CN 115220046 A CN115220046 A CN 115220046A CN 202210623063 A CN202210623063 A CN 202210623063A CN 115220046 A CN115220046 A CN 115220046A
Authority
CN
China
Prior art keywords
laser
aerial vehicle
unmanned aerial
landing
vehicle equipment
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202210623063.7A
Other languages
Chinese (zh)
Inventor
陆海博
何哲
李拥祺
李胜全
张卫东
唐辉平
张玉梅
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Peng Cheng Laboratory
Original Assignee
Peng Cheng Laboratory
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Peng Cheng Laboratory filed Critical Peng Cheng Laboratory
Priority to CN202210623063.7A priority Critical patent/CN115220046A/en
Publication of CN115220046A publication Critical patent/CN115220046A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S17/00—Systems using the reflection or reradiation of electromagnetic waves other than radio waves, e.g. lidar systems
    • G01S17/02—Systems using the reflection of electromagnetic waves other than radio waves
    • G01S17/06—Systems determining position data of a target
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/10—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 by using measurements of speed or acceleration
    • G01C21/12—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 by using measurements of speed or acceleration executed aboard the object being navigated; Dead reckoning
    • G01C21/16—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 by using measurements of speed or acceleration executed aboard the object being navigated; Dead reckoning by integrating acceleration or speed, i.e. inertial navigation
    • G01C21/165—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 by using measurements of speed or acceleration executed aboard the object being navigated; Dead reckoning by integrating acceleration or speed, i.e. inertial navigation combined with non-inertial navigation instruments
    • G01C21/1652—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 by using measurements of speed or acceleration executed aboard the object being navigated; Dead reckoning by integrating acceleration or speed, i.e. inertial navigation combined with non-inertial navigation instruments with ranging devices, e.g. LIDAR or RADAR
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/20—Image preprocessing
    • G06V10/24—Aligning, centring, orientation detection or correction of the image
    • G06V10/243—Aligning, centring, orientation detection or correction of the image by compensating for image skew or non-uniform image deformations
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/762—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using clustering, e.g. of similar faces in social networks

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Remote Sensing (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Electromagnetism (AREA)
  • Multimedia (AREA)
  • Artificial Intelligence (AREA)
  • Health & Medical Sciences (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Computing Systems (AREA)
  • Databases & Information Systems (AREA)
  • Evolutionary Computation (AREA)
  • General Health & Medical Sciences (AREA)
  • Medical Informatics (AREA)
  • Software Systems (AREA)
  • Automation & Control Theory (AREA)
  • Length Measuring Devices By Optical Means (AREA)

Abstract

The invention discloses a control method and a system for landing and positioning of unmanned aerial vehicle equipment based on laser identification, wherein the method comprises the following steps: acquiring environmental laser point cloud data based on a laser radar, and identifying a preset laser identifier based on the environmental laser point cloud data; determining first position information of the unmanned aerial vehicle equipment relative to the landing platform according to the identified laser identifier, and controlling the unmanned aerial vehicle equipment to approach the landing platform according to the first position information; in the process that the unmanned aerial vehicle device approaches the landing platform, the distance between the unmanned aerial vehicle device and the landing platform is obtained, and when the distance is smaller than a distance threshold value, a positioning mark in the laser mark is identified; and determining second position information of the unmanned aerial vehicle equipment relative to the landing platform according to the positioning identifier, and controlling the unmanned aerial vehicle equipment to continuously approach the landing platform according to the second position information until landing is finished. The invention realizes positioning by identifying the specific landing identifier by using the laser radar, so that the unmanned aerial vehicle equipment can realize full-time accurate autonomous landing under various complex illumination conditions.

Description

Control method and system for landing and positioning of unmanned aerial vehicle equipment based on laser recognition
Technical Field
The invention relates to the technical field of unmanned aerial vehicle equipment positioning, in particular to a control method and a system for landing positioning of unmanned aerial vehicle equipment based on laser identification.
Background
The unmanned aerial vehicle equipment is an aerial robot which is rapidly developed in recent years, has the advantages of low cost, multiple functions, convenience in use and the like, can be widely applied to task scenes such as security inspection, search and rescue, material transportation, pesticide spraying, data acquisition, map construction and the like, and has outstanding application value. In the actual task in-process of carrying out long period, because the time of endurance of unmanned aerial vehicle equipment is limited at present, especially with the many rotor unmanned aerial vehicle equipment of battery as power source (the time of endurance of generally working is 15 ~ 30 minutes), therefore unmanned aerial vehicle equipment need constantly descend to carry out independently charging on mobile station or the ground basic station, need realize through accurate independently descending. In addition, high requirements are also provided for accurate and autonomous landing of the unmanned aerial vehicle equipment on the landing platform in an actual task scene, and the unmanned aerial vehicle equipment needs to be autonomously and accurately landed on an unmanned aerial vehicle equipment hangar platform after a task is completed, such as in security inspection; in the material transportation, need drop to the platform in warehouse and unload the goods, in the pesticide sprays, need drop to take off and land and carry out medicine filling etc. on the platform.
At present unmanned aerial vehicle equipment independently descends in-process mainly through the aircraft optics camera discernment artificial identification such as two-dimensional code to navigate the location, have better location effect under the suitable condition of illumination condition daytime, however the optics camera is through gathering the object reflection visible light and converting into digital signal and image, it is sensitive to ambient light, the success rate of discerning artificial identification under complicated illumination condition (daytime highlight, strong reflection of light, illumination violent change and night etc.) is showing and is descending, can lead to unmanned aerial vehicle equipment can't descend and even crash. In many actual full-time tasks, the unmanned aerial vehicle equipment needs to accurately land under complex illumination conditions of strong light, strong reflection, severe illumination change, night and the like, and the existing method for identifying the artificial identification based on the airborne optical camera is far from meeting the positioning requirement of landing under the complex illumination conditions.
Thus, there is a need for improvements and enhancements in the art.
Disclosure of Invention
The invention aims to solve the technical problem that a control method and a control system for landing and positioning of unmanned aerial vehicle equipment based on laser recognition are provided aiming at the defects in the prior art, and the problem that the method for recognizing artificial identification based on an airborne optical camera in the prior art cannot meet the positioning requirement of accurate landing under complex illumination conditions is solved.
In order to solve the technical problems, the technical scheme adopted by the invention is as follows:
in a first aspect, the invention provides a control method for landing and positioning of unmanned aerial vehicle equipment based on laser recognition, wherein the method comprises the following steps:
acquiring environmental laser point cloud data based on a laser radar, and identifying a preset laser identifier based on the environmental laser point cloud data, wherein the laser identifier is arranged above a landing platform;
according to the recognized laser mark, determining first position information of the unmanned aerial vehicle device relative to a landing platform, and controlling the unmanned aerial vehicle device to be close to the landing platform according to the first position information;
in the process that the unmanned aerial vehicle device approaches the landing platform, the distance between the unmanned aerial vehicle device and the landing platform is obtained, and when the distance is smaller than a distance threshold value, a positioning mark in the laser mark is identified;
and determining second position information of the unmanned aerial vehicle equipment relative to the landing platform according to the positioning identification, and controlling the unmanned aerial vehicle equipment to continuously approach the landing platform according to the second position information until landing is completed.
In one implementation, the identifying a preset laser identifier based on the environmental laser point cloud data includes:
carrying out distortion correction processing on the environmental laser point cloud data, and extracting characteristic points from the environmental laser point cloud data subjected to the distortion correction processing;
clustering the feature points to obtain feature point clusters, and screening the feature point clusters to obtain screened feature point clusters;
and determining the laser mark according to the screened feature point cluster.
In one implementation, the performing distortion correction processing on the environmental laser point cloud data includes:
acquiring an intensity value corresponding to the environmental laser point cloud data, and filtering the environmental laser point cloud data according to the intensity value to obtain filtered environmental laser point cloud data;
acquiring high-frequency attitude transformation data of the unmanned aerial vehicle equipment through a preset high-frequency inertial measurement sensor, wherein the high-frequency inertial measurement sensor is fixedly connected with the laser radar;
and carrying out interpolation processing on the filtered environment laser point cloud data according to the high-frequency attitude transformation data, and unifying laser point coordinates corresponding to the filtered environment laser point cloud data so as to realize distortion correction processing on the filtered environment laser point cloud data.
In one implementation, the filtering the environmental laser point cloud data according to the intensity value to obtain filtered environmental laser point cloud data includes:
comparing the intensity value with a preset intensity threshold value;
and if the intensity value is smaller than the intensity threshold value, eliminating the environmental laser point cloud data with the intensity value smaller than the intensity threshold value.
In one implementation, the extracting feature points from the environmental laser point cloud data after the distortion correction processing includes:
determining the curvature corresponding to each laser point according to the environmental laser point cloud data after the distortion correction treatment;
and if the curvature is larger than a preset curvature threshold, taking the laser point cloud with the curvature larger than the curvature threshold as the characteristic point.
In an implementation manner, the screening the feature point clusters to obtain screened feature point clusters includes:
acquiring the number of laser points in each feature point cluster, and screening out the feature point clusters of which the number of laser points does not meet a first preset formula if the number of laser points does not meet the first formula;
determining the intensity value gradient of the laser points on the boundary belonging to the laser identifier in the feature point cluster based on a preset second formula, and screening out the feature point cluster corresponding to the laser points of which the intensity value gradient is smaller than or equal to a preset gradient threshold if the intensity value gradient is smaller than or equal to the preset gradient threshold;
acquiring the number of the feature points on the boundary belonging to the laser mark in the feature point cluster, and if the number of the feature points does not meet a preset third formula, screening out the feature point cluster of which the number of the feature points does not meet the third formula;
performing plane fitting on the rest feature point clusters, and acquiring outliers corresponding to each feature point cluster subjected to the plane fitting;
and if the outlier exceeds a preset proportion, screening out the characteristic point clusters corresponding to the outlier exceeding the preset proportion.
In one implementation, the determining first position information of the drone device relative to the landing platform according to the identified laser identifier includes:
decoding the effective coding region in the laser identification to obtain a square matrix composed of different numbers;
determining a first relative attitude change of the unmanned aerial vehicle device relative to the landing level in an auxiliary manner according to the numerical arrangement sequence in the square matrix;
and acquiring a first three-dimensional coordinate at the laser identification center, and determining the first position information according to the first three-dimensional coordinate and the first relative attitude change.
In one implementation manner, the laser marker is composed of black and white squares, a white frame composed of white squares is arranged at the outermost periphery of the laser marker, a black frame composed of a plurality of black squares is arranged at the inner side of the white boundary, and an effective coding region composed of a plurality of black squares and a plurality of white squares is arranged inside the black frame.
In one implementation, the valid encoding region consists of 4*4 squares, and the positioning identifier is disposed at the center of the valid encoding region.
In one implementation, the determining second position information of the drone device relative to the landing platform according to the location identifier includes:
acquiring a second three-dimensional coordinate at the center of the positioning identifier;
acquiring second relative attitude change of the unmanned aerial vehicle equipment relative to the landing platform in real time;
and determining the second position information according to the second three-dimensional coordinate and the second relative posture change.
In one implementation, the location indicia are geometric blocks of high reflectivity material.
In a second aspect, an embodiment of the present invention further provides a control system for landing and positioning of an unmanned aerial vehicle device based on laser recognition, where the system includes:
the laser identification recognition module is used for acquiring environmental laser point cloud data based on a laser radar and recognizing a preset laser identification based on the environmental laser point cloud data, wherein the laser identification is arranged above the landing platform;
the first position information determining module is used for determining first position information of the unmanned aerial vehicle equipment relative to a landing platform according to the identified laser identifier and controlling the unmanned aerial vehicle equipment to be close to the landing platform according to the first position information;
the positioning identifier recognition module is used for acquiring the distance between the unmanned aerial vehicle equipment and the landing platform in the process that the unmanned aerial vehicle equipment approaches the landing platform, and recognizing the positioning identifier in the laser identifier when the distance is smaller than a distance threshold value;
and the second position information determining module is used for determining second position information of the unmanned aerial vehicle equipment relative to the landing platform according to the positioning identifier, and controlling the unmanned aerial vehicle equipment to continuously approach the landing platform according to the second position information until landing is finished.
In a third aspect, an embodiment of the present invention further provides an unmanned aerial vehicle device, where the unmanned aerial vehicle device includes the control system for landing and positioning of the unmanned aerial vehicle device based on laser recognition in the foregoing scheme; the unmanned aerial vehicle device further comprises: the system comprises a laser radar connected with the control system and a high-frequency inertial measurement sensor fixedly connected with the laser radar.
Has the advantages that: compared with the prior art, the invention provides a control method for landing and positioning of unmanned aerial vehicle equipment based on laser identification. Then, according to the recognized laser mark, first position information of the unmanned aerial vehicle device relative to the landing platform is determined, and the unmanned aerial vehicle device is controlled to be close to the landing platform according to the first position information. And then, in the process that the unmanned aerial vehicle equipment is close to the landing platform, acquiring the distance between the unmanned aerial vehicle equipment and the landing platform, and identifying the positioning identifier in the laser identifier when the distance is smaller than a distance threshold value. And finally, according to the positioning identification, determining second position information of the unmanned aerial vehicle equipment relative to the landing platform, and controlling the unmanned aerial vehicle equipment to continuously approach the landing platform according to the second position information until landing is finished. The invention realizes positioning by utilizing the airborne laser radar to identify the specific landing identifier (namely the laser identifier and the positioning identifier), so that the unmanned aerial vehicle equipment can realize full-time accurate autonomous landing under various complex illumination conditions. In addition, compared with a landing positioning control method based on traditional optical vision recognition in the prior art, in the control method for realizing positioning based on the laser radar, the laser radar has a ranging function and does not need an additional ranging sensor for height measurement, so that important technology and method support are provided for solving the key problem that the unmanned aerial vehicle cannot land effectively under complex illumination conditions and in a specific working period.
Drawings
Fig. 1 is a flowchart of a specific implementation of a method for controlling landing and positioning of an unmanned aerial vehicle device based on laser recognition according to an embodiment of the present invention.
Fig. 2 is a schematic diagram of laser identifier recognition in the control method for landing and positioning of unmanned aerial vehicle equipment based on laser recognition according to the embodiment of the present invention.
Fig. 3 is a schematic diagram of identifying a positioning identifier in the control method for landing positioning of the unmanned aerial vehicle device based on laser identification according to the embodiment of the present invention.
Fig. 4 is a schematic diagram of laser identification in the control method for landing and positioning of the unmanned aerial vehicle device based on laser recognition according to the embodiment of the present invention.
Fig. 5 is a schematic diagram illustrating placement of laser markers in the control method for landing and positioning of the unmanned aerial vehicle device based on laser recognition according to the embodiment of the present invention.
Fig. 6 is a functional schematic block diagram of a control system for landing and positioning of an unmanned aerial vehicle device based on laser recognition according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and effects of the present invention clearer and clearer, the present invention is further described in detail below with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
The embodiment provides a control method for landing and positioning of unmanned aerial vehicle equipment based on laser recognition, and according to the control method of the embodiment, the unmanned aerial vehicle equipment can realize full-time accurate autonomous landing under various complex illumination conditions. During specific implementation, the embodiment firstly acquires environmental laser point cloud data based on a laser radar, and identifies a preset laser identifier based on the environmental laser point cloud data, wherein the laser identifier is arranged above the landing platform. Then, according to the recognized laser mark, first position information of the unmanned aerial vehicle device relative to the landing platform is determined, and the unmanned aerial vehicle device is controlled to be close to the landing platform according to the first position information. And then, in the process that the unmanned aerial vehicle equipment is close to the landing platform, acquiring the distance between the unmanned aerial vehicle equipment and the landing platform, and identifying the positioning identifier in the laser identifier when the distance is smaller than a distance threshold value. And finally, according to the positioning identification, determining second position information of the unmanned aerial vehicle equipment relative to the landing platform, and controlling the unmanned aerial vehicle equipment to continuously approach the landing platform according to the second position information until landing is finished. It is thus clear that this embodiment utilizes the specific descending sign of airborne laser radar discernment (laser identification and location sign promptly) to realize the location for unmanned aerial vehicle equipment can realize accurate independently descending in the whole period at various complicated illumination conditions. In addition, compare with the landing location control method based on traditional optical vision discernment among the prior art, among the control method based on laser radar realizes the location in this embodiment, laser radar itself possesses the range finding function, no longer needs extra range finding sensor to carry out the height measurement, consequently, this embodiment will provide important technique and method support for solving the key problem that unmanned aerial vehicle equipment can't effectively land in complicated illumination condition and specific work period.
Exemplary method
The control method for landing and positioning of the unmanned aerial vehicle equipment based on laser identification of the embodiment can be applied to the unmanned aerial vehicle equipment, wherein an onboard computer is arranged on the unmanned aerial vehicle equipment, and the onboard computer carries a control system, specifically, as shown in fig. 1, the method comprises the following steps:
s100, acquiring environmental laser point cloud data based on a laser radar, and identifying a preset laser identifier based on the environmental laser point cloud data, wherein the laser identifier is arranged above a landing platform.
The unmanned aerial vehicle equipment in this embodiment is last to be provided with laser radar, and this laser radar is connected with control system to as discernment sensor, be used for discerning predetermined specific mark, in order to realize the location. The laser radar can be solid laser radar or mechanical laser radar. This embodiment uses solid-state laser radar, and during specific application, this embodiment is installed solid-state laser radar in unmanned aerial vehicle equipment bottom and is made the transmitting plane of radar downwards to specific sign is discerned more easily. Specifically, the laser radar can acquire environmental laser point cloud data, wherein the environmental laser point cloud data is acquired by the laser radar during landing based on the identification of the outline and the pattern of the preset laser identification, and therefore the preset laser identification can be identified by analyzing the environmental laser point cloud data. In this embodiment, the laser marker is preset above the landing platform and is used as a reference object for identifying and positioning the landing platform. Specifically as shown in fig. 2, 1 in fig. 2 is unmanned aerial vehicle equipment, 2 is lidar, 3 is laser marking, 4 is the location sign, and 5 is the effective coding region, and the dotted line represents lidar's identification range. In this embodiment, unmanned aerial vehicle equipment slowly descends and is close to the landing platform, and the top of landing platform sets up laser marking, therefore laser radar discerns laser marking's profile at first.
In one implementation manner, when identifying the laser identifier, the embodiment includes the following steps:
s101, performing distortion correction processing on the environmental laser point cloud data, and extracting feature points from the environmental laser point cloud data subjected to the distortion correction processing;
step S102, clustering the feature points to obtain feature point clusters, and screening the feature point clusters to obtain screened feature point clusters;
and S103, determining the laser identifier according to the screened feature point clusters.
During specific implementation, the laser radar of this embodiment passes through net twine or USB and connects unmanned aerial vehicle equipment's airborne computer, then installs the drive that laser radar corresponds on airborne computer, starts this drive just can acquire laser point cloud data through laser radar after that. During specific application, the laser radar is driven by the ROS drive package, then the topics of the environmental laser point cloud data are obtained based on the laser radar, and the topics comprise three-dimensional coordinates and intensity values of laser points in the environmental laser point cloud data.
In order to reduce invalid point cloud data and improve calculation efficiency, in combination with a practical application scenario, the embodiment needs to filter the environmental laser point cloud data. Specifically, in this embodiment, after the intensity value corresponding to the environmental laser point cloud data is obtained, the intensity value is compared with a preset intensity threshold. And if the intensity value is smaller than the intensity threshold value, removing the environmental laser point cloud data with the intensity value smaller than the intensity threshold value. For example, if the actual application scene is sea area monitoring, the sea surface points need to be removed, because the absorption rate of the sea water to the laser is high, and the high absorption rate means that the reflectivity is low, that is, the intensity value is small, the laser points with the intensity value lower than the intensity threshold value need to be removed in this embodiment; ground points can be culled in the same manner if other scenarios are to be used.
Because laser radar is mechanical rotation type mostly, therefore in a frame of environment laser point cloud data that laser radar scanning circle was obtained, the time of every laser point acquireed is different, if unmanned aerial vehicle equipment is the motion, that means that the position of unmanned aerial vehicle equipment is different when every laser point acquireed, leads to the reference system of laser point coordinate to be inconsistent, if still regard these laser point's coordinate as under same reference system, the error will produce. To this end, the utility modelThe embodiment needs to carry out distortion correction processing on environmental laser point cloud data. Specifically, this embodiment obtains the high frequency attitude transformation data of unmanned aerial vehicle equipment through preset high frequency inertial measurement unit, in this embodiment, high frequency Inertial Measurement Unit (IMU) with laser radar fixed connection. And then carrying out interpolation processing on the filtered environment laser point cloud data according to the high-frequency attitude transformation data, and unifying laser point coordinates corresponding to the filtered environment laser point cloud data so as to realize distortion correction processing on the filtered environment laser point cloud data. For example, in this embodiment, the pose transformation data output by the high-frequency inertial measurement sensor is used to calculate the high-frequency pose transformation data (i.e., the pose of the drone device corresponding to each frame of IMU data timestamp), and then the high-frequency pose transformation data is interpolated by a time sequence to obtain the pose T of the drone device corresponding to the ith laser point i Let the i-th laser spot coordinate be P i Then, the coordinates of all laser points can be unified into the coordinate system corresponding to the first laser point, P i '＝T i ·P i Laser point coordinates P after using a unified coordinate system i ' subsequent calculation is carried out, so that the error is greatly reduced, and the recognition success rate is greatly improved.
After the distortion correction processing is performed, the present embodiment extracts feature points from the environmental laser point cloud data after the distortion correction processing. Specifically, in this embodiment, the curvature corresponding to each laser point is determined according to the environmental laser point cloud data after the distortion correction processing. And if the curvature is larger than a preset curvature threshold, taking the laser point cloud with the curvature larger than the curvature threshold as the characteristic point. In specific application, the curvature conv of the ith laser point of the jth frame is calculated by the following formula i,j ：
curv i,j ＝||p i+1,j -p i,j || 2 -||p i-1,j -p i,j || 2
Wherein p is i,j Coordinates representing the ith laser point of the jth frame, if the curvature curv i,j If the curvature is larger than the preset curvature threshold value, the curvature is considered to be larger than the preset curvature threshold valueThe laser spot is a characteristic spot.
After the feature points are extracted, the embodiment clusters the feature points to obtain feature point clusters. And then, screening the feature point clusters to obtain screened feature point clusters. Specifically, after the feature points are extracted, the feature points are clustered by the following formula:
Figure BDA0003677611950000111
Figure BDA0003677611950000112
Figure BDA0003677611950000113
wherein:
Figure BDA0003677611950000114
representing the coordinates, intensity value and wiring harness of the jth point;
Figure BDA0003677611950000115
coordinates, intensity values, and pencil representing points in the ith cluster;
min (-) represents the minimum value in a set, and max (-) represents the maximum value in a set;
γ represents a threshold value of error between the values set to be classified into one class of points.
That is to say, after clustering all the feature points, the respective condition of each feature point can be determined, that is, a plurality of feature point clusters can be obtained. After the feature point clusters are obtained, the feature point clusters can be screened, and the specific screening process is as follows:
first, the present embodiment obtains the number of laser points in each feature point cluster, and if the number of laser points does not satisfy a preset first formula, screens out the feature point clusters whose number of laser points does not satisfy the first formula. In specific application, the first formula is as follows:
Figure BDA0003677611950000116
wherein n is bit_points Representing the minimum number of laser points in each cell that make up the identity; n is a radical of an alkyl radical bit The number of small squares contained in each edge of the mark is shown, and the parameter in the mark is 4; n is r Indicating the number of laser beams striking the mark; s represents the side length of the mark; d represents the distance between the laser and the marking plate; θ represents the angular resolution of the single laser. If the laser point number does not satisfy the first formula, the feature point cluster of which the laser point number does not satisfy the first formula is determined not to be the laser mark, and therefore the feature point cluster of which the laser point number does not satisfy the first formula is screened out.
Then, in this embodiment, based on a preset second formula, an intensity value gradient of the laser point on the boundary belonging to the laser identifier in the feature point cluster is determined, and if the intensity value gradient is less than or equal to a preset gradient threshold, the feature point cluster corresponding to the laser point whose intensity value gradient is less than or equal to the gradient threshold is screened out. In specific application, the second formula is as follows:
η I ＝|I i+1,j -I i,j |-|I i-1,j -I i,j i, wherein I i,j Representing the intensity value of the ith laser spot of the jth beam.
The intensity value gradient eta of each laser point on the boundary of the laser mark can be calculated by the second formula I If the intensity value gradient η I If the intensity value gradient is smaller than or equal to the preset gradient threshold, determining that the feature point cluster corresponding to the laser point with the intensity value gradient smaller than or equal to the gradient threshold is not the laser identifier, and screening out the feature point cluster corresponding to the laser point with the intensity value gradient smaller than or equal to the gradient threshold。
Then, the number of feature points on the boundary belonging to the laser identifier in the feature point clusters is obtained, and if the number of feature points does not satisfy a preset third formula, the feature point clusters whose number does not satisfy the third formula are screened out. Specifically, the third formula is:
n edge_pioits ≥2(n bit + 2), wherein n edge_points Indicating the number of feature points on each boundary.
If the number of the feature points does not satisfy the third formula, it is indicated that the feature point clusters whose number of the feature points does not satisfy the third formula at this time are not laser marks, and therefore the feature point clusters whose number of the feature points does not satisfy the third formula are screened out.
Finally, the embodiment performs plane fitting on the remaining feature point clusters, and obtains an outlier corresponding to each feature point cluster subjected to plane fitting. If the outlier exceeds a preset proportion, determining that the feature point cluster corresponding to the outlier exceeding the preset proportion is not the laser mark, and screening out the feature point cluster corresponding to the outlier exceeding the preset proportion. After all screening processes are completed, if the remaining feature point clusters exist, the final remaining feature point clusters can be determined to be laser marks, and therefore the laser marks can be identified.
In the present embodiment, the laser marker is manufactured based on tag No. 5 of 16H5 family of Apriltag (visual reference system), as shown in fig. 4. The laser mark of the embodiment is composed of black and white squares, and a white frame composed of white squares is arranged at the outermost periphery of the laser mark and is used for isolating the laser mark from other objects. And a black frame consisting of a plurality of black squares is arranged on the inner side of the white boundary, and an effective coding region consisting of a plurality of black squares and a plurality of white squares is arranged inside the black frame. The effective coding area is composed of 4*4 squares, and the positioning mark is arranged at the center of the effective coding area (as shown in fig. 2). In order to isolate from other objects, the laser mark of the embodiment needs to be placed at a certain height and cannot be placed by being attached to the plane of the landing platform, and specifically, as shown in fig. 5, the laser mark can be placed on the platform which is raised by the laser mark, so that the laser mark is located above the landing platform.
S200, determining first position information of the unmanned aerial vehicle equipment relative to a landing platform according to the identified laser identifier, and controlling the unmanned aerial vehicle equipment to be close to the landing platform according to the first position information.
After the laser radar identifies the laser identification, the control system can determine first position information of the unmanned aerial vehicle equipment relative to the landing platform according to the identified laser identification. The first position information reflects the height and the orientation of the unmanned aerial vehicle device relative to the landing platform, and based on the first position information, the unmanned aerial vehicle device can be controlled to land towards the landing platform accurately.
In one implementation manner, the embodiment includes the following steps when determining the first position information:
step S201, decoding the effective coding area in the laser mark to obtain a square matrix composed of different numbers;
step S203, assisting to determine a first relative attitude change of the unmanned aerial vehicle equipment relative to the landing level according to the numerical arrangement sequence in the square matrix;
step S204, a first three-dimensional coordinate at the laser mark center is obtained, and the first position information is determined according to the first three-dimensional coordinate and the first relative posture change.
Specifically, as shown in fig. 4, since the laser marker is provided with an effective coding area composed of a plurality of black squares and a plurality of white squares, the effective coding area carries the coded information of the laser marker. Therefore, after the laser identifier is identified, the present embodiment may perform decoding processing on the effective coding area of the laser identifier to obtain coded information, where the coded information is a square matrix composed of different numbers, that is, a square matrix composed of 4*4 different numbers. The first relative attitude change of the unmanned aerial vehicle equipment relative to the laser identification is judged in an auxiliary mode according to the number arrangement sequence in the square matrix, and the attitude change information of the unmanned aerial vehicle equipment relative to the laser identification in the landing process is reflected by the first relative attitude change. Then, a control system acquires a first three-dimensional coordinate at the laser mark center, and then determines the first position information according to the first three-dimensional coordinate and the first relative attitude change. After the first position information is determined, the control system can control the unmanned aerial vehicle equipment to land close to the laser identifier (namely close to the landing platform) according to the first position information.
S300, in the process that the unmanned aerial vehicle equipment is close to the landing platform, the distance between the unmanned aerial vehicle equipment and the landing platform is obtained, and when the distance is smaller than a distance threshold value, a positioning mark in the laser mark is identified.
Control unmanned aerial vehicle equipment and be close to the in-process of descending the platform, laser radar can acquire the distance between unmanned aerial vehicle equipment and the descending platform in real time to after laser radar acquires the distance at every turn, all can compare the distance that measures with predetermined distance threshold value, this distance threshold value indicates that laser radar can't discern the distance that laser marking's whole profile is exactly completely. Therefore, if the measured distance is smaller than the distance threshold, it indicates that the laser radar at this time cannot identify the profile of the complete laser marker, and the laser radar starts to identify the positioning marker in the laser marker at this time, as shown in fig. 3. Laser radar can further discern the predetermined location sign this moment to confirm the position of unmanned aerial vehicle equipment for descending the platform more accurately, so that realize accurate descending.
And S400, determining second position information of the unmanned aerial vehicle equipment relative to the landing platform according to the positioning identifier, and controlling the unmanned aerial vehicle equipment to continuously approach the landing platform according to the second position information until landing is finished.
In this embodiment, after the positioning identifier is identified, the present embodiment may obtain a second three-dimensional coordinate at the center of the positioning identifier; when the unmanned aerial vehicle equipment is close to the landing platform, the laser radar acquires the second relative attitude change of the unmanned aerial vehicle equipment relative to the landing platform in real time, and the second relative attitude change reflects the attitude change information of the unmanned aerial vehicle equipment relative to the positioning identification in the landing process. And then determining the second position information according to the second three-dimensional coordinate and the second relative attitude change. After determining first position information, control system can be close to the location sign (be close to and descend the platform promptly) and descend according to first position information control unmanned aerial vehicle equipment, just can realize the accurate of unmanned aerial vehicle equipment this moment and descend. In this embodiment, the positioning mark is a geometric block made of a high-reflectivity material, and is more easily recognized by a laser radar, so that accurate landing under a complex illumination condition is facilitated. It is thus clear that this embodiment divide into two stages at the in-process of the accurate descending of control unmanned aerial vehicle equipment, and the first stage is based on laser radar discernment laser marking's profile, then control unmanned aerial vehicle equipment is close to the laser marking and descends, and the second stage is when laser radar can't complete discernment laser marking's profile, begins the location sign among the discernment laser marking, then control unmanned aerial vehicle equipment is close to the location sign and descends to make unmanned aerial vehicle equipment descend accurately on descending platform.
Exemplary devices
Based on the above embodiment, the present invention further provides a control system for landing and positioning of an unmanned aerial vehicle device based on laser recognition, where the control system in this embodiment is installed in an onboard computer of the unmanned aerial vehicle device, as shown in fig. 6, the system includes: a laser marker recognition module 10, a first location information determination module 20, a location marker recognition module 30, and a second location information determination module. Specifically, the laser identifier recognition module 10 is configured to obtain environmental laser point cloud data based on a laser radar, and recognize a preset laser identifier based on the environmental laser point cloud data, where the laser identifier is disposed above the landing platform. The first position information determining module 20 is configured to determine first position information of the unmanned aerial vehicle device relative to the landing platform according to the identified laser identifier, and control the unmanned aerial vehicle device to approach the landing platform according to the first position information. The positioning identification recognition module 30 is configured to obtain a distance between the unmanned aerial vehicle device and the landing platform in a process that the unmanned aerial vehicle device is close to the landing platform, and recognize the positioning identification in the laser identification when the distance is smaller than a distance threshold. The second position information determining module 40 is configured to determine second position information of the unmanned aerial vehicle device relative to the landing platform according to the positioning identifier, and control the unmanned aerial vehicle device to continue to approach the landing platform according to the second position information until landing is completed.
In one implementation, the laser identification recognition module 10 includes:
the characteristic point extraction unit is used for carrying out distortion correction processing on the environmental laser point cloud data and extracting characteristic points from the environmental laser point cloud data after the distortion correction processing;
the characteristic point cluster screening unit is used for clustering the characteristic points to obtain characteristic point clusters and screening the characteristic point clusters to obtain screened characteristic point clusters;
and the laser identifier determining unit is used for determining the laser identifier according to the screened feature point clusters.
In one implementation, the feature point extraction unit includes:
the point cloud filtering subunit is used for acquiring an intensity value corresponding to the environmental laser point cloud data, and filtering the environmental laser point cloud data according to the intensity value to obtain filtered environmental laser point cloud data;
the attitude transformation data acquisition subunit is used for acquiring high-frequency attitude transformation data of the unmanned aerial vehicle equipment through a preset high-frequency inertial measurement sensor, wherein the high-frequency inertial measurement sensor is fixedly connected with the laser radar;
and the correction processing subunit is used for performing interpolation processing on the filtered environment laser point cloud data according to the high-frequency attitude transformation data and unifying laser point coordinates corresponding to the filtered environment laser point cloud data so as to realize distortion correction processing on the filtered environment laser point cloud data.
In one implementation, the point cloud filtering subunit includes:
the intensity value comparison subunit is used for comparing the intensity value with a preset intensity threshold value;
and the point cloud data removing subunit is used for removing the environmental laser point cloud data with the intensity value smaller than the intensity threshold value if the intensity value is smaller than the intensity threshold value.
In one implementation, the feature point extracting unit further includes:
the curvature analysis subunit is used for determining the curvature corresponding to each laser point according to the environmental laser point cloud data after the distortion correction processing;
and the characteristic point determining subunit is used for taking the laser point cloud with the curvature larger than the curvature threshold value as the characteristic point if the curvature is larger than a preset curvature threshold value.
In one implementation, the feature point cluster screening unit includes:
the first feature point cluster screening subunit is used for acquiring the number of laser points in each feature point cluster, and screening out the feature point clusters of which the number of laser points does not meet a first preset formula if the number of laser points does not meet the first formula;
the second feature point cluster screening subunit is configured to determine, based on a preset second formula, an intensity value gradient of laser points on a boundary belonging to the laser identifier in the feature point cluster, and if the intensity value gradient is smaller than or equal to a preset gradient threshold, screen out the feature point cluster corresponding to the laser point whose intensity value gradient is smaller than or equal to the gradient threshold;
the third feature point cluster screening subunit is configured to obtain the number of feature points on the boundary belonging to the laser identifier in the feature point cluster, and screen out the feature point clusters of which the number does not satisfy a preset third formula if the number of feature points does not satisfy the third formula;
the characteristic point clustering plane fitting subunit is used for carrying out plane fitting on the remaining characteristic point clusters and acquiring outliers corresponding to each characteristic point cluster subjected to plane fitting;
and the fourth feature point cluster screening subunit is configured to screen, if the outlier exceeds a preset ratio, the feature point cluster corresponding to the outlier exceeding the preset ratio.
In one implementation, the first location information determining module 20 includes:
the laser mark decoding unit is used for decoding the effective coding area in the laser mark to obtain a square matrix consisting of different numbers;
a first attitude change determination unit, configured to assist in determining a first relative attitude change of the drone device with respect to the landing level according to a numerical order in the square matrix;
and the first position information determining unit is used for acquiring a first three-dimensional coordinate at the laser mark center and determining the first position information according to the first three-dimensional coordinate and the first relative attitude change.
In this embodiment, the laser marker is composed of black and white squares, a white frame composed of white squares is disposed at the outermost periphery of the laser marker, a black frame composed of a plurality of black squares is disposed at the inner side of the white boundary, and an effective coding region composed of a plurality of black squares and a plurality of white squares is disposed inside the black frame. The effective coding area is composed of 4*4 squares, and the positioning mark is arranged at the center of the effective coding area. The positioning marks are geometric blocks made of high-reflectivity materials.
In one implementation, the fourth location information determining module 40 includes:
a coordinate obtaining unit, configured to obtain a second three-dimensional coordinate at the center of the positioning identifier;
the second attitude change determining unit is used for acquiring a second relative attitude change of the unmanned aerial vehicle equipment relative to the landing platform in real time;
and the second position information determining unit is used for determining the second position information according to the second three-dimensional coordinates and the second relative posture change.
The principle of each module in the control system for landing and positioning of the unmanned aerial vehicle device based on laser recognition in the embodiment is the same as the execution principle of each step in the above method embodiment, and the description is not repeated here.
Based on the above embodiment, the present invention further provides an unmanned aerial vehicle device, which includes the control system for landing and positioning of the unmanned aerial vehicle device based on laser recognition described in the above embodiment. The unmanned aerial vehicle device further comprises: the system comprises a laser radar connected with the control system and a high-frequency inertial measurement sensor fixedly connected with the laser radar. The working principle of the lidar and the high-frequency inertial measurement sensor is the same as that of the method embodiment, and the working principle is not described again here.
In conclusion, the invention discloses a control method and a system for landing and positioning of unmanned aerial vehicle equipment based on laser identification, wherein the method comprises the following steps: acquiring environmental laser point cloud data based on a laser radar, and identifying a preset laser identifier based on the environmental laser point cloud data; determining first position information of the unmanned aerial vehicle equipment relative to the landing platform according to the identified laser identifier, and controlling the unmanned aerial vehicle equipment to approach the landing platform according to the first position information; in the process that the unmanned aerial vehicle device approaches the landing platform, the distance between the unmanned aerial vehicle device and the landing platform is obtained, and when the distance is smaller than a distance threshold value, a positioning mark in the laser mark is identified; and determining second position information of the unmanned aerial vehicle equipment relative to the landing platform according to the positioning identifier, and controlling the unmanned aerial vehicle equipment to continuously approach the landing platform according to the second position information until landing is finished. The invention realizes positioning by identifying the specific landing identifier by using the laser radar, so that the unmanned aerial vehicle equipment can realize full-time accurate autonomous landing under various complex illumination conditions.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, and not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.

Claims (13)

1. A control method for landing and positioning of unmanned aerial vehicle equipment based on laser recognition is characterized by comprising the following steps:
acquiring environmental laser point cloud data based on a laser radar, and identifying a preset laser identifier based on the environmental laser point cloud data, wherein the laser identifier is arranged above a landing platform;
according to the recognized laser mark, determining first position information of the unmanned aerial vehicle device relative to a landing platform, and controlling the unmanned aerial vehicle device to be close to the landing platform according to the first position information;
in the process that the unmanned aerial vehicle device approaches the landing platform, the distance between the unmanned aerial vehicle device and the landing platform is obtained, and when the distance is smaller than a distance threshold value, a positioning mark in the laser mark is identified;
and determining second position information of the unmanned aerial vehicle equipment relative to the landing platform according to the positioning identification, and controlling the unmanned aerial vehicle equipment to continuously approach the landing platform according to the second position information until landing is finished.
2. The method for controlling landing positioning of unmanned aerial vehicle equipment based on laser identification as claimed in claim 1, wherein said identifying a preset laser identifier based on said environmental laser point cloud data comprises:
carrying out distortion correction treatment on the environmental laser point cloud data, and extracting characteristic points from the environmental laser point cloud data subjected to the distortion correction treatment;
clustering the feature points to obtain feature point clusters, and screening the feature point clusters to obtain screened feature point clusters;
and determining the laser mark according to the screened feature point cluster.
3. The laser recognition-based unmanned aerial vehicle device landing positioning control method according to claim 2, wherein the distortion correction processing of the environmental laser point cloud data includes:
acquiring an intensity value corresponding to the environmental laser point cloud data, and filtering the environmental laser point cloud data according to the intensity value to obtain filtered environmental laser point cloud data;
acquiring high-frequency attitude transformation data of the unmanned aerial vehicle equipment through a preset high-frequency inertial measurement sensor, wherein the high-frequency inertial measurement sensor is fixedly connected with the laser radar;
and carrying out interpolation processing on the filtered environment laser point cloud data according to the high-frequency attitude transformation data, and unifying laser point coordinates corresponding to the filtered environment laser point cloud data so as to realize distortion correction processing on the filtered environment laser point cloud data.
4. The laser identification-based unmanned aerial vehicle device landing positioning control method according to claim 3, wherein the filtering of the environmental laser point cloud data according to the intensity value to obtain filtered environmental laser point cloud data comprises:
comparing the intensity value with a preset intensity threshold value;
and if the intensity value is smaller than the intensity threshold value, removing the environmental laser point cloud data with the intensity value smaller than the intensity threshold value.
5. The method for controlling landing and positioning of unmanned aerial vehicle equipment based on laser identification according to claim 2, wherein the extracting of the feature points from the environmental laser point cloud data after distortion correction processing comprises:
determining the curvature corresponding to each laser point according to the environmental laser point cloud data after the distortion correction treatment;
and if the curvature is larger than a preset curvature threshold, taking the laser point cloud with the curvature larger than the curvature threshold as the characteristic point.
6. The laser identification-based unmanned aerial vehicle landing positioning control method according to claim 2, wherein the step of screening the feature point clusters to obtain the screened feature point clusters comprises:
acquiring the number of laser points in each feature point cluster, and screening out the feature point clusters of which the number of laser points does not meet a first preset formula if the number of laser points does not meet the first formula;
determining the intensity value gradient of the laser points on the boundary of the laser mark in the feature point cluster based on a preset second formula, and if the intensity value gradient is less than or equal to a preset gradient threshold, screening out the feature point cluster corresponding to the laser points of which the intensity value gradient is less than or equal to the gradient threshold;
acquiring the number of the feature points on the boundary belonging to the laser identifier in the feature point cluster, and if the number of the feature points does not meet a preset third formula, screening out the feature point cluster of which the number does not meet the third formula;
performing plane fitting on the remaining feature point clusters, and acquiring outliers corresponding to each feature point cluster subjected to the plane fitting;
and if the outlier exceeds a preset proportion, screening out the characteristic point clusters corresponding to the outlier exceeding the preset proportion.
7. The method for controlling landing positioning of unmanned aerial vehicle equipment based on laser identification as claimed in claim 1, wherein said determining first position information of unmanned aerial vehicle equipment relative to the landing platform according to the identified laser identifier comprises:
decoding the effective coding region in the laser identification to obtain a square matrix composed of different numbers;
determining a first relative attitude change of the unmanned aerial vehicle equipment relative to the landing level in an auxiliary manner according to the numerical arrangement sequence in the square matrix;
and acquiring a first three-dimensional coordinate at the laser mark center, and determining the first position information according to the first three-dimensional coordinate and the first relative posture change.
8. The method as claimed in claim 7, wherein the laser marker is composed of black and white blocks, a white border composed of white blocks is disposed at the outermost periphery of the laser marker, a black border composed of a plurality of black blocks is disposed at the inner side of the white border, and an effective coding region composed of a plurality of black blocks and a plurality of white blocks is disposed inside the black border.
9. The method as claimed in claim 8, wherein the effective coding area is 4*4 blocks, and the positioning mark is disposed at the center of the effective coding area.
10. The method for controlling landing positioning of unmanned aerial vehicle equipment based on laser recognition according to claim 1, wherein determining second position information of the unmanned aerial vehicle equipment relative to the landing platform according to the positioning identifier comprises:
acquiring a second three-dimensional coordinate at the center of the positioning identifier;
acquiring second relative attitude change of the unmanned aerial vehicle equipment relative to the landing platform in real time;
and determining the second position information according to the second three-dimensional coordinate and the second relative posture change.
11. The method of claim 1, wherein the positioning indicia are geometric blocks made of a high reflectivity material.
12. A control system of unmanned aerial vehicle equipment landing location based on laser discernment, its characterized in that, the system includes:
the laser identification recognition module is used for acquiring environmental laser point cloud data based on a laser radar and recognizing a preset laser identification based on the environmental laser point cloud data, wherein the laser identification is arranged above the landing platform;
the first position information determining module is used for determining first position information of the unmanned aerial vehicle equipment relative to a landing platform according to the identified laser identifier and controlling the unmanned aerial vehicle equipment to be close to the landing platform according to the first position information;
the positioning identifier recognition module is used for acquiring the distance between the unmanned aerial vehicle equipment and the landing platform in the process that the unmanned aerial vehicle equipment approaches the landing platform, and recognizing the positioning identifier in the laser identifier when the distance is smaller than a distance threshold value;
and the second position information determining module is used for determining second position information of the unmanned aerial vehicle equipment relative to the landing platform according to the positioning identifier, and controlling the unmanned aerial vehicle equipment to continuously approach the landing platform according to the second position information until landing is finished.
13. A drone device, characterized in that it comprises a control system for the landing positioning of drone devices based on laser identification as described in claim 12 above; the unmanned aerial vehicle device further comprises: the system comprises a laser radar connected with the control system and a high-frequency inertial measurement sensor fixedly connected with the laser radar.
CN202210623063.7A 2022-06-02 2022-06-02 Control method and system for landing and positioning of unmanned aerial vehicle equipment based on laser recognition Pending CN115220046A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210623063.7A CN115220046A (en) 2022-06-02 2022-06-02 Control method and system for landing and positioning of unmanned aerial vehicle equipment based on laser recognition

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210623063.7A CN115220046A (en) 2022-06-02 2022-06-02 Control method and system for landing and positioning of unmanned aerial vehicle equipment based on laser recognition

Publications (1)

Publication Number Publication Date
CN115220046A true CN115220046A (en) 2022-10-21

Family

ID=83608519

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210623063.7A Pending CN115220046A (en) 2022-06-02 2022-06-02 Control method and system for landing and positioning of unmanned aerial vehicle equipment based on laser recognition

Country Status (1)

Country Link
CN (1) CN115220046A (en)

Similar Documents

Publication Publication Date Title
US11195011B2 (en) Object detection and avoidance for aerial vehicles
CN110991207B (en) Unmanned aerial vehicle accurate landing method integrating H pattern recognition and Apriltag two-dimensional code recognition
US20200344464A1 (en) Systems and Methods for Improving Performance of a Robotic Vehicle by Managing On-board Camera Defects
CN108873943B (en) Image processing method for centimeter-level accurate landing of unmanned aerial vehicle
CN109823552B (en) Vision-based unmanned aerial vehicle accurate landing method, storage medium, device and system
US20190068829A1 (en) Systems and Methods for Improving Performance of a Robotic Vehicle by Managing On-board Camera Obstructions
CN108153334B (en) Visual autonomous return and landing method and system for unmanned helicopter without cooperative target
CN111989544A (en) System and method for indoor vehicle navigation based on optical targets
CN109460046B (en) Unmanned aerial vehicle natural landmark identification and autonomous landing method
CN111123964B (en) Unmanned aerial vehicle landing method and device and computer readable medium
AU2017223463B2 (en) Automated loading bridge positioning using encoded decals
CN111353522B (en) Method and system for determining road signs in the surroundings of a vehicle
CN106908064B (en) Indoor night vision navigation method based on Kinect2 sensor
CN108710381A (en) A kind of servo-actuated landing method of unmanned plane
CN111221343A (en) Unmanned aerial vehicle landing method based on embedded two-dimensional code
US10908580B2 (en) Devices, systems, and methods for automated loading bridge positioning using shapes associated with a vehicle
CN111191557B (en) Mark identification positioning method, mark identification positioning device and intelligent equipment
CN112700498A (en) Wind driven generator blade tip positioning method and system based on deep learning
CN114815871A (en) Vision-based autonomous landing method for vertical take-off and landing unmanned mobile platform
CN113378701B (en) Ground multi-AGV state monitoring method based on unmanned aerial vehicle
KR20190097350A (en) Precise Landing Method of Drone, Recording Medium for Performing the Method, and Drone Employing the Method
CN112650304A (en) Unmanned aerial vehicle autonomous landing system and method and unmanned aerial vehicle
CN115220046A (en) Control method and system for landing and positioning of unmanned aerial vehicle equipment based on laser recognition
CN114066972A (en) Unmanned aerial vehicle autonomous positioning method based on monocular vision
CN113298044A (en) Obstacle detection method, system, device and storage medium based on positioning compensation

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination