Unmanned aerial vehicle battery replacement method and device and unmanned aerial vehicle hangar

Abstract

The embodiment of the invention provides an unmanned aerial vehicle battery replacement method and device and an unmanned aerial vehicle hangar. The method comprises the steps that current battery box position information of an unmanned aerial vehicle is obtained; wherein an unmanned aerial vehicle power battery is contained in the battery box; determining a battery box offset parameter according to the battery box position information and preset calibration battery box position information; according to the deviation parameters, the movement path of a mechanical arm connected with a battery replacing gripper is determined, the mechanical arm is controlled to move to the grabbing position according to the movement path, and the battery of the unmanned aerial vehicle is replaced. The battery box deviation parameter is obtained, the movement path of the mechanical arm is generated according to the battery box deviation parameter, the mechanical arm is controlled to replace the battery according to the movement path, and the battery replacement accuracy and efficiency are improved.

Description

Technical Field

[0001] The present application relates to the technical field of unmanned aerial vehicles, and more specifically, to a method and device for replacing batteries in unmanned aerial vehicles and an unmanned aerial vehicle hangar. Background Art

[0002] With the rapid development of drone technology, drones are increasingly used in civil, commercial and military fields. They are used in many scenarios such as aerial photography, agricultural plant protection, power inspection, logistics distribution, environmental monitoring, etc. After the drone is done working, the battery power of the drone will decrease. Therefore, the battery of the drone needs to be replaced in the drone hangar. However, the drone is currently manually controlled to stop at the battery replacement position based on experience. In this way, there will be displacement errors, and the battery cannot be replaced accurately. It needs to be adjusted multiple times, and the replacement efficiency is low. Therefore, how to improve the efficiency of drone battery replacement is an urgent problem to be solved. Summary of the invention

[0003] The present application provides a method, device and hangar for replacing batteries of a UAV. Through the technical solution of the present application, the current battery box position information of the UAV is obtained; wherein the battery box contains the power battery of the UAV; the battery box offset parameters are determined according to the battery box position information and the preset calibrated battery box position information; wherein the battery box offset parameters at least include an angle offset and a position offset; according to the battery box offset parameters, the motion path of a mechanical arm connected to a battery replacement gripper is determined, and the mechanical arm is controlled to move to a gripping position according to the motion path to replace the battery of the UAV. The present application proposes a method for extracting feature points of a battery box gripping hole and calculating a battery box offset parameter to improve the accuracy of the battery box position deviation, and then generate a motion path of the mechanical arm according to the battery box offset parameter, control the mechanical arm to replace the battery according to the motion path, and improve the accuracy and efficiency of battery replacement.

[0004] In a first aspect, the present application provides a method for replacing a drone battery, the method comprising: Get the current battery box location information of the drone; the battery box contains the drone power battery; Determine a battery box offset parameter according to the battery box position information and the preset calibrated battery box position information; wherein the battery box offset parameter at least includes an angle offset and a position offset; According to the battery box offset parameter, the movement path of the mechanical arm connected to the battery replacement gripper is determined, and the mechanical arm is controlled to move according to the movement path to reach the grasping position to replace the battery of the drone.

[0005] The present application obtains the location information of the drone where the battery needs to be replaced, and compares it with the preset calibrated battery box position information to obtain the battery box offset parameters, and then generates the motion path of the robotic arm according to the battery box offset parameters, controls the robotic arm to replace the battery according to the motion path, and improves the accuracy and efficiency of battery replacement.

[0006] Optionally, the preset calibrated battery box position information is obtained in the following manner: Acquire a first image of the drone, wherein the first image is obtained when the drone is located at a battery calibration position; Analyzing the first image to obtain first acquisition point information corresponding to the first image; According to a preset geometric algorithm, first origin coordinate information and first angle information corresponding to the first collection point information are determined.

[0007] In the present application, a visual camera is used in the drone hangar to obtain an image of the drone at the battery calibration position, and the obtained image is analyzed to obtain the first acquisition point information at the preset position in the image, and then a preset geometric algorithm is used to obtain the coordinate information and angle information in the information of each acquisition point in the image, which is used to calibrate the subsequently collected drone position information.

[0008] Optionally, the first acquisition point information includes at least first feature point coordinate data, second feature point coordinate data, third feature point coordinate data and fourth feature point coordinate data; The determining, according to a preset geometric algorithm, first origin coordinate information and first angle information corresponding to the first acquisition point information includes: Determine a first connecting line according to the first feature point coordinate data and the third feature point coordinate data; Determine a second connecting line according to the second feature point coordinate data and the fourth feature point coordinate data; Determine the coordinate information of the first origin of the battery box coordinate system according to the intersection of the first connecting line and the second connecting line; The first angle information is determined according to the first connecting line and the coordinate axes of the battery box coordinate system.

[0009] In the present application, by connecting two points on the diagonal line, the intersection of the two connecting lines is obtained, and then the origin coordinate information and angle information of the battery box coordinate system are obtained.

[0010] Optionally, obtaining the current battery box position information of the drone includes: Acquire a second image from the drone; parsing the second image to obtain second acquisition point information corresponding to the second image; According to a preset geometric algorithm, second origin coordinate information and second angle information corresponding to the second acquisition point information are determined.

[0011] Optionally, determining the battery box offset parameter according to the battery box position information and preset calibrated battery box position information includes: Determine the position offset in the battery box coordinate system according to the first origin coordinate information and the second origin coordinate information; The angle offset in the battery box coordinate system is determined according to the first angle information and the second angle information.

[0012] In the present application, multiple coordinate systems are pre-stored, and the multiple coordinate systems are associated to obtain a coordinate system conversion relationship. The battery box offset parameters in the battery box coordinate system are converted to the battery box offset parameters in the global coordinate system, which can control the robotic arm more accurately.

[0013] Optionally, determining the motion path of a robot arm connected to a battery replacement gripper according to the battery box offset parameter includes: According to a preset coordinate system conversion relationship, the position offset in the battery box coordinate system is converted into the position offset in the global coordinate system; the angle offset in the battery box coordinate system is converted into the angle offset in the global coordinate system; The motion path of the robotic arm connected to the battery replacement gripper is determined according to the position offset in the global coordinate system and the angle offset in the global coordinate system.

[0014] In this application, based on the battery box offset parameters in the global coordinate system, the motion path of the robotic arm connected to the battery replacement gripper is determined to improve the control accuracy of the robotic arm.

[0015] In a second aspect, the present application provides a drone battery replacement device, the device comprising: The acquisition module is used to obtain the current battery box position information of the drone; wherein the battery box contains the drone power battery; A determination module, used to determine a battery box offset parameter according to the battery box position information and preset calibration battery box position information; wherein the battery box offset parameter at least includes an angle offset and a position offset; The replacement module is used to determine the movement path of a mechanical arm connected to a battery replacement gripper according to the battery box offset parameters, and control the mechanical arm to move to a gripping position according to the movement path to replace the battery of the drone.

[0016] The present application obtains the location information of the drone where the battery needs to be replaced, and compares it with the preset calibrated battery box position information to obtain the battery box offset parameters, and then generates the motion path of the robotic arm according to the battery box offset parameters, controls the robotic arm to replace the battery according to the motion path, and improves the accuracy and efficiency of battery replacement.

[0017] Optionally, the device further comprises an establishing module, wherein the establishing module is configured to: Acquire a first image of the drone, wherein the first image is obtained when the drone is located at a battery calibration position; Analyzing the first image to obtain first acquisition point information corresponding to the first image; According to a preset geometric algorithm, first origin coordinate information and first angle information corresponding to the first collection point information are determined.

[0018] In the present application, a visual camera is used in the drone hangar to obtain an image of the drone at the battery calibration position, and the obtained image is analyzed to obtain the first collection point information at the preset position in the image, and then a preset set algorithm is used to obtain the coordinate information and angle information in the information of each collection point in the image, which is used to calibrate the subsequently collected drone position information.

[0019] Optionally, the first acquisition point information includes at least first feature point coordinate data, second feature point coordinate data, third feature point coordinate data and fourth feature point coordinate data; The establishment module is used to: Determine a first connecting line according to the first feature point coordinate data and the third feature point coordinate data; Determine a second connecting line according to the second feature point coordinate data and the fourth feature point coordinate data; Determine the first origin coordinate information of the battery box coordinate system according to the intersection of the first connecting line and the second connecting line; The first angle information is determined according to the first connecting line and the coordinate axes of the battery box coordinate system.

[0020] In this application, based on the battery box coordinate system, the coordinate data at the feature point is obtained for calibrating the position information. By connecting the two points on the diagonal line, the intersection of the two connecting lines is obtained, and then the origin coordinate information and angle information of the battery box coordinate system are obtained.

[0021] Optionally, the acquisition module is used to: Acquire a second image from the drone; parsing the second image to obtain second acquisition point information corresponding to the second image; According to a preset geometric algorithm, second origin coordinate information and second angle information corresponding to the second acquisition point information are determined.

[0022] Optionally, the determining module is used to: Determine the position offset in the battery box coordinate system according to the first origin coordinate information and the second origin coordinate information; The angle offset in the battery box coordinate system is determined according to the first angle information and the second angle information.

[0023] In the present application, multiple coordinate systems are pre-stored, and the multiple coordinate systems are associated to obtain a coordinate system conversion relationship. The battery box offset parameters in the battery box coordinate system are converted to the battery box offset parameters in the global coordinate system, which can control the robotic arm more accurately.

[0024] Optionally, the replacement module is used to: According to a preset coordinate system conversion relationship, the position offset in the battery box coordinate system is converted into the position offset in the global coordinate system; the angle offset in the battery box coordinate system is converted into the angle offset in the global coordinate system; The motion path of the robotic arm connected to the battery replacement gripper is determined according to the position offset in the global coordinate system and the angle offset in the global coordinate system.

[0025] In this application, based on the battery box offset parameters in the global coordinate system, the motion path of the robotic arm connected to the battery replacement gripper is determined to improve the control accuracy of the robotic arm.

[0026] In a third aspect, the present application provides a drone, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the drone battery replacement method as described in any embodiment of the first aspect can be implemented. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] In order to more clearly illustrate the technical solutions of some embodiments of the present application, the drawings required for use in some embodiments of the present application will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0028] Figure 1 A schematic diagram of a flow chart of a method for replacing a drone battery provided in an embodiment of the present application; Figure 2 A schematic diagram of the structure of a drone hangar provided in an embodiment of the present application; Figure 3 A schematic diagram of a visual calibration process provided in an embodiment of the present application; Figure 4 A schematic diagram of a calibration image provided in an embodiment of the present application; Figure 5 A schematic diagram of a flow chart of another method for replacing a drone battery provided in an embodiment of the present application; Figure 6 A schematic diagram of the structure of a drone battery replacement device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0029] The technical solutions in some embodiments of the present application will be described below in conjunction with the drawings in some embodiments of the present application.

[0030] It should be noted that similar reference numerals and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings. At the same time, in the description of this application, the terms "first", "second", etc. are only used to distinguish the description and cannot be understood as indicating or implying relative importance.

[0031] With the rapid development of drone technology, drones are increasingly used in civil, commercial and military fields. They are used in many scenarios such as aerial photography, agricultural plant protection, power inspection, logistics distribution, environmental monitoring, etc. After the drone is done working, the battery power of the drone will decrease. Therefore, the battery of the drone needs to be replaced in the drone hangar. However, the drone is currently manually controlled to stop at the battery replacement position based on experience. In this way, there will be displacement errors, and the battery cannot be replaced accurately. It needs to be adjusted multiple times, and the replacement efficiency is low. Therefore, how to improve the efficiency of drone battery replacement is an urgent problem to be solved. In view of this, some embodiments of the present application provide a method for replacing batteries of a drone, by obtaining the current battery box position information of the drone; wherein the battery box contains a power battery for the drone; according to the battery box position information and the preset calibrated battery box position information, determining the battery box offset parameters; wherein the battery box offset parameters at least include an angle offset and a position offset; according to the battery box offset parameters, determining the motion path of a robotic arm connected to a battery replacement gripper, and controlling the robotic arm to move to a gripping position according to the motion path to replace the battery of the drone. The present application proposes a method for extracting feature points of a battery box gripping hole and calculating a battery box offset parameter to improve the accuracy of the battery box position deviation, and then generating the motion path of the robotic arm according to the battery box offset parameters, controlling the robotic arm to replace the battery according to the motion path, and improving the accuracy and efficiency of battery replacement.

[0032] like Figure 1As shown, an embodiment of the present application provides a method for replacing a drone battery, the method comprising: S101, obtaining the current battery box position information of the drone; wherein the battery box contains the drone power battery; Specifically, a drone landing platform, a visual camera, a robotic arm controller and a robotic arm are provided in the drone hangar. When the drone lands in the drone hangar, the drone landing platform will leave the hangar. After the drone lands, the drone landing platform will be retracted into the hangar with the drone. At this time, the drone image is collected by the visual camera in the hangar, and the feature points of the drone image are identified to obtain the current battery box position information of the drone; the battery box contains the drone power battery, and the visual camera sends the battery position information of the drone to the robotic arm controller. S102, determining a battery box offset parameter according to the battery box position information and the preset calibrated battery box position information; wherein the battery box offset parameter at least includes an angle offset and a position offset; Specifically, preset calibrated battery box position information is pre-stored on the robotic arm controller, and the preset calibrated battery box position information is the accurate position for replacing the battery of the drone. After obtaining the current battery box position information of the drone, the current battery box position information of the drone is compared with the preset calibrated battery box position information to obtain the battery box offset parameters of the drone, wherein the battery box offset parameters include at least an angle offset and a position offset.

[0033] S103: Determine a motion path of a robotic arm connected to a battery replacement gripper according to the battery box offset parameter, and control the robotic arm to move to a gripping position according to the motion path to replace the battery of the drone.

[0034] Specifically, the robotic arm controller determines the movement path of the robotic arm connected to the battery replacement gripper based on the obtained offset parameters of the battery box, that is, determines the movement path of the robotic arm connected to the battery replacement gripper based on the angle offset and the position offset, and then controls the robotic arm to move according to the movement path, and replaces the battery when the robotic arm moves to the battery box position of the drone.

[0035] A battery box is set in the drone hangar, and replaceable batteries are stored in the battery box. When the drone enters the drone hangar, the robotic arm is controlled to move according to the motion path based on the grasping position. When the robotic arm moves to the battery box position of the drone, the battery in the drone is taken out, and then the robotic arm is controlled to put the taken out battery into the battery box. Any replaceable battery that meets the requirements is grabbed from the battery box and installed in the drone body.

[0036] In the embodiment of the present application, the visual camera will feed back the acquired battery position information of the drone to the three-axis module robotic arm control end (i.e., the robotic arm controller). The robotic arm controller will compare the received battery position information of the drone with the calibrated battery position information (i.e., the preset calibrated battery box position information), calculate the deviation of the current drone battery box position, and obtain the current drone battery replacement position in the global coordinate system through matrix transformation and vector translation. The three-axis module robotic arm control end drives the robotic arm to perform motion planning through this position, so that the robotic arm can accurately pick up and place the batteries in the drone battery box.

[0037] The embodiment of the present application integrates positioning through a visual camera and a three-axis module robotic arm, and uses a geometric algorithm to determine the material posture. Under the premise of meeting the accuracy requirements, it not only saves the space of the mechanical structure but also greatly reduces the hardware cost.

[0038] The embodiment of the present application obtains the position information of the drone where the battery needs to be replaced, and compares it with the preset calibrated battery box position information to obtain the battery box offset parameters, and then generates the motion path of the robotic arm according to the battery box offset parameters, controls the robotic arm to replace the battery according to the motion path, and improves the accuracy and efficiency of battery replacement.

[0039] Another embodiment of the present application further supplements the drone battery replacement method provided in the above embodiment.

[0040] like Figure 2 As shown, the UAV battery replacement hangar provided in the embodiment of the present application mainly includes: a hangar shell 100, a UAV 200, a UAV landing platform 300, a battery charging station 400, a battery 500, a battery replacement system 600, a three-axis module robotic arm 601, a gripper 602, a visual camera bracket 603, and a visual camera 604. The hangar shell provides storage space for the UAV.

[0041] The drone landing platform provides a landing site for the drone. When the drone lands, the landing platform will leave the hangar. After the drone lands, the drone landing platform will be retracted into the hangar with the drone. The battery box is placed on the battery charging table for battery charging. The battery replacement system includes a three-axis module robot arm, a gripper, a visual camera bracket and a visual camera. The visual camera is fixed to the visual camera bracket with screws. The visual camera bracket and the gripper are fixed to the hangar with screws and are located above the drone battery box. The visual camera and the drone battery box remain relatively vertical.

[0042] like Figure 3As shown, firstly, the characteristic points and coordinate system information of the drone battery box are calibrated through vision and recorded in the system; when the drone landing platform recovers the drone, the three-axis module robot arm control end (PLC) triggers the visual camera to take pictures of the drone battery replacement calibration position, obtain the characteristic points of the current drone battery box, and convert them through the algorithm in the visual camera to obtain the coordinate information of the current drone battery replacement position.

[0043] Specifically, the preset calibration battery box position information is obtained in the following manner: Acquire a first image of the drone, wherein the first image is obtained when the drone is located at a battery calibration position; Analyze the first image to obtain first acquisition point information corresponding to the first image; According to a preset geometric algorithm, first origin coordinate information and first angle information corresponding to the first acquisition point information are determined.

[0044] In the present application, a visual camera is used in the drone hangar to obtain an image of the drone at the battery calibration position, and the obtained image is analyzed to obtain the first acquisition point information at the preset position in the image, and then a preset geometric algorithm is used to obtain the coordinate information and angle information in the information of each acquisition point in the image, which is used to calibrate the subsequently collected drone position information.

[0045] Optionally, the first acquisition point information includes at least first feature point coordinate data, second feature point coordinate data, third feature point coordinate data and fourth feature point coordinate data; Determining first origin coordinate information and first angle information corresponding to the first acquisition point information according to a preset geometric algorithm includes: Determine a first connecting line according to the first feature point coordinate data and the third feature point coordinate data; Determine a second connecting line according to the second feature point coordinate data and the fourth feature point coordinate data; Determine the coordinate information of the first origin of the battery box coordinate system according to the intersection of the first connecting line and the second connecting line; The first angle information is determined according to the first connecting line and the coordinate axis of the battery box coordinate system.

[0046] That is, the calibration process includes: 1. Confirm the calibration position of the drone; 2. The battery box location of the visual camera drone; 3. The visual camera obtains the coordinates O0 and angle of the calibration point 0; 4. Write to the three-axis module controller.

[0047] In the present application, by connecting two points on the diagonal line, the intersection of the two connecting lines is obtained, and then the origin coordinate information and angle information of the battery box coordinate system are obtained.

[0048] Optionally, obtaining the current battery box position information of the drone; wherein the battery box contains the drone power battery, including: Acquire a second image from the drone; Analyzing the second image to obtain second acquisition point information corresponding to the second image; According to a preset geometric algorithm, second origin coordinate information and second angle information corresponding to the second acquisition point information are determined.

[0049] Optionally, determining the battery box offset parameter according to the battery box position information and the preset calibrated battery box position information includes: Determine the position offset in the battery box coordinate system according to the first origin coordinate information and the second origin coordinate information; The angle offset in the battery box coordinate system is determined according to the first angle information and the second angle information.

[0050] Optionally, determining a motion path of a robot arm connected to a battery replacement gripper according to the battery box offset parameter includes: According to the preset coordinate system conversion relationship, the position offset in the battery box coordinate system is converted into the position offset in the global coordinate system; the angle offset in the battery box coordinate system is converted into the angle offset in the global coordinate system; The motion path of the robotic arm connected to the battery replacement gripper is determined based on the position offset in the global coordinate system and the angle offset in the global coordinate system.

[0051] The battery exchange system in the embodiment of the present application includes a global coordinate system, a workpiece coordinate system, a gripper tool coordinate system, a camera coordinate system and a battery box coordinate system. The global coordinate system is the reference coordinate system of the entire battery exchange system in space, which can determine the relationship between different systems and components. The workpiece coordinate system is the battery box coordinate system, which is established with a certain point on the battery as the origin. The tool coordinate system is the gripper tool coordinate system, which is established with the gripper center as the origin. The camera coordinate system is established with the camera center as the origin.

[0052] The robot arm controller pre-associates the global coordinate system, workpiece coordinate system, gripper tool coordinate system, camera coordinate system and drone battery box coordinate system. During the battery replacement process, the data of any coordinate system can be converted to other coordinate systems. For example, the coordinate system can be converted through matrix transformation and translation vector.

[0053] In the present application, multiple coordinate systems are pre-stored, and the multiple coordinate systems are associated to obtain a coordinate system conversion relationship. The battery box offset parameters in the battery box coordinate system are converted to the battery box offset parameters in the global coordinate system, which can control the robotic arm more accurately.

[0054] Exemplarily, in the camera coordinate system, an image of the battery box of the drone is acquired, the image in the camera coordinate system is converted to the battery box coordinate system, the battery box offset parameters in the battery box coordinate system are obtained, the battery box offset parameters in the battery box coordinate system are converted to the battery box offset parameters in the global coordinate system, and then the motion path of a robotic arm connected to a battery replacement gripper is determined, and based on the gripper tool coordinate system, the robotic arm is controlled to move according to the motion path to the gripping position to replace the battery of the drone.

[0055] In this application, based on the battery box offset parameters in the global coordinate system, the motion path of the robotic arm connected to the battery replacement gripper is determined to improve the control accuracy of the robotic arm.

[0056] For example, Figure 4 As shown in the figure, the coordinate system of the drone battery box is the coordinate system of the position for taking and placing batteries on the aircraft. There are four clamping holes on the battery box. The geometric center of the clamping hole is used as the feature point. The coordinates are point A0 (x 01 ,y 01 )、B0 point(x 02 ,y 02 )、C0 point(x 03 ,y 03 )、D0 point(x 04 ,y 04 ), by connecting the diagonal lines of the coordinates of the four points, namely A0C0 and B0D0, determine the center coordinates of the object O0 (x 00 ,y 00 ) and the angle information between the diagonal A0C0 and the X-axis 0. The camera obtains the coordinates of the feature points of the battery box during the i-th battery replacement through visual information, and the feature points are identified as A i (x i1 ,y i1 )、Bi(x i2 ,y i2 )、C i (x i3 ,y i3 )、D i Point (x i4 ,y i4 ), calculate the center coordinates O of the object to be identified i Point (x i0 ,y i0 ) and the diagonal A i C i and Bi D i Angle information with respect to the X axis i By comparing the coordinates of the i-th feature point with the calibrated feature point coordinates, the offset data of the battery box in the battery box coordinate system can be obtained.

[0057] in, Figure 4 Points A, B, C, and D in the figure only represent the relative positions of the four points on the battery box, and they represent different values ​​in different calculation processes. That is, in the calibration process, they represent A0, B0, C0, and D0, and in the actual visual camera acquisition, they can represent A i , B i , C i , D i .

[0058] Optionally, four corner points of the edge of the battery box may be used as feature points.

[0059] like Figure 5 As shown, the visual correction method provided by the embodiment of the present application includes: Step 1: After the drone is recovered, it enters the drone hangar.

[0060] Step 2: Use the visual camera to take a photo of the drone battery box location; Step 3: The visual camera calculates the point coordinates Oi and angle of the current drone battery box i; Step 4, the three-axis module controller calculates the deviation value between the current battery box position information and the calibrated position, that is, the preset calibrated battery box position information, that is, the battery box offset parameter; Specifically, by comparing the preset calibrated battery box position with the current battery box position, the translation vector of the battery box, i.e., the position offset O = (x, y), can be calculated. i0- x 00， y = y i0- y 00。 The position translation difference of the battery box from the preset calibrated battery box position to the current battery box position can be calculated.

[0061] The battery box angle offset can be calculated as follows = i - 0, θ is the angle offset of the battery box; Step 5: Convert the calculated battery box offset parameters in the battery box coordinate system into the three-axis module grabbing position coordinates in the global coordinate system; Specifically, the controller calculates the battery box offset parameters in the battery box coordinate system, and then uses the transformation relationship between coordinate systems such as matrix transformation and translation vector to finally obtain the position information of the battery box in the global coordinate system, and feeds this position information back to the robotic arm controller.

[0062] Step 6: The three-axis module controller drives the actuator to pick up and install and unload the batteries in the drone battery box.

[0063] The robot controller plans the robot's motion path through the converted coordinates, controls the robot to grab the battery workpiece, and then places it into the battery box.

[0064] The embodiments of the present application provide a method and system for replacing batteries in a drone hangar based on machine vision, which aims to automatically replace batteries for drones through an intelligent battery replacement method that combines a robotic arm and machine vision, thereby improving the storage and battery replacement efficiency of drones, reducing manual intervention, and improving the uninterrupted operation capability of drones.

[0065] It should be noted that each implementable method in this embodiment may be implemented separately, or may be implemented in combination in any manner without conflict, and this application is not limited thereto.

[0066] Another embodiment of the present application provides a drone battery replacement device, which is used to execute the drone battery replacement method provided in the above embodiment.

[0067] like Figure 6 , which is a schematic diagram of the structure of the drone battery replacement device provided in an embodiment of the present application. The drone battery replacement device at least includes: an acquisition module 701, a determination module 702 and a replacement module 703, wherein: The acquisition module 701 is used to obtain the current battery box position information of the drone; wherein the battery box contains the drone power battery; The determination module 702 is used to determine the battery box offset parameter according to the battery box position information and the preset calibration battery box position information; wherein the battery box offset parameter at least includes an angle offset and a position offset; The replacement module 703 is used to determine the movement path of the robotic arm connected to the battery replacement gripper according to the battery box offset parameters, and control the robotic arm to move to the gripping position according to the movement path to replace the battery of the drone.

[0068] Regarding the device in this embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0069] The present application obtains the location information of the drone where the battery needs to be replaced, and compares it with the preset calibrated battery box position information to obtain the battery box offset parameters, and then generates the motion path of the robotic arm according to the battery box offset parameters, controls the robotic arm to replace the battery according to the motion path, and improves the accuracy and efficiency of battery replacement.

[0070] Another embodiment of the present application further supplements the description of the drone battery replacement device provided in the above embodiment.

[0071] Optionally, the device further comprises an establishing module, the establishing module being configured to: Acquire a first image of the drone, wherein the first image is obtained when the drone is located at a battery calibration position; Analyze the first image to obtain first acquisition point information corresponding to the first image; According to a preset geometric algorithm, first origin coordinate information and first angle information corresponding to the first acquisition point information are determined.

[0072] In the present application, a visual camera is used in the drone hangar to obtain an image of the drone at the battery calibration position, and the obtained image is analyzed to obtain the first collection point information at the preset position in the image, and then a preset set algorithm is used to obtain the coordinate information and angle information in the information of each collection point in the image, which is used to calibrate the subsequently collected drone position information.

[0073] Optionally, the first acquisition point information includes at least first feature point coordinate data, second feature point coordinate data, third feature point coordinate data and fourth feature point coordinate data; The establishment module is used to: Determine a first connecting line according to the first feature point coordinate data and the third feature point coordinate data; Determine a second connecting line according to the second feature point coordinate data and the fourth feature point coordinate data; Determine the first origin coordinate information of the battery box coordinate system according to the intersection of the first connecting line and the second connecting line; The first angle information is determined according to the first connecting line and the coordinate axes of the battery box coordinate system.

[0074] In the present application, by connecting two points on the diagonal line, the intersection of the two connecting lines is obtained, and then the origin coordinate information and angle information of the battery box coordinate system are obtained.

[0075] Optionally, obtain a module for: Acquire a second image from the drone; Analyzing the second image to obtain second acquisition point information corresponding to the second image; According to a preset geometric algorithm, second origin coordinate information and second angle information corresponding to the second acquisition point information are determined.

[0076] Optionally, a module is determined to: Determine the position offset in the battery box coordinate system according to the first origin coordinate information and the second origin coordinate information; Determine an angle offset in a battery box coordinate system according to the first angle information and the second angle information; According to the preset coordinate system conversion relationship, the position offset in the battery box coordinate system is converted into the position offset in the global coordinate system; the angle offset in the battery box coordinate system is converted into the angle offset in the global coordinate system.

[0077] In the present application, multiple coordinate systems are pre-stored, and the multiple coordinate systems are associated to obtain a coordinate system conversion relationship. The battery box offset parameters in the battery box coordinate system are converted to the battery box offset parameters in the global coordinate system, which can control the robotic arm more accurately.

[0078] Optionally, replace the module for: The motion path of the robotic arm connected to the battery replacement gripper is determined based on the position offset in the global coordinate system and the angle offset in the global coordinate system.

[0079] In this application, based on the battery box offset parameters in the global coordinate system, the motion path of the robotic arm connected to the battery replacement gripper is determined to improve the control accuracy of the robotic arm.

[0080] Regarding the device in this embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0081] It should be noted that each implementable method in this embodiment may be implemented separately, or may be implemented in combination in any manner without conflict, and this application is not limited thereto.

[0082] The above are only embodiments of the present application and are not intended to limit the scope of protection of the present application. For those skilled in the art, the present application may have various changes and variations. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application should be included in the scope of protection of the present application. It should be noted that similar reference numerals and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in the subsequent drawings.

[0083] The above are only specific implementations of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0084] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

Claims

1. A method for replacing a drone battery, characterized in that: The method comprises: Get the current battery box location information of the drone; the battery box contains the drone power battery; Determine a battery box offset parameter according to the battery box position information and the preset calibrated battery box position information; wherein the battery box offset parameter at least includes an angle offset and a position offset; According to the battery box offset parameter, the movement path of the mechanical arm connected to the battery replacement gripper is determined, and the mechanical arm is controlled to move according to the movement path to reach the grasping position to replace the battery of the drone.

2. The method for replacing a drone battery according to claim 1, characterized in that: The preset calibration battery box position information is obtained in the following manner: Acquire a first image of the drone, wherein the first image is obtained when the drone is located at a battery calibration position; Analyzing the first image to obtain first acquisition point information corresponding to the first image; According to a preset geometric algorithm, first origin coordinate information and first angle information corresponding to the first collection point information are determined.

3. The method for replacing a drone battery according to claim 2, characterized in that: The first collection point information includes at least first feature point coordinate data, second feature point coordinate data, third feature point coordinate data and fourth feature point coordinate data; The determining, according to a preset geometric algorithm, first origin coordinate information and first angle information corresponding to the first acquisition point information includes: Determine a first connecting line according to the first feature point coordinate data and the third feature point coordinate data; Determine a second connecting line according to the second feature point coordinate data and the fourth feature point coordinate data; Determine the coordinate information of the first origin of the battery box coordinate system according to the intersection of the first connecting line and the second connecting line; The first angle information is determined according to the first connecting line and the coordinate axes of the battery box coordinate system.

4. The method for replacing a drone battery according to claim 1, characterized in that: The obtaining of the current battery box position information of the drone includes: Acquire a second image from the drone; parsing the second image to obtain second acquisition point information corresponding to the second image; According to a preset geometric algorithm, second origin coordinate information and second angle information corresponding to the second acquisition point information are determined.

5. The method for replacing a drone battery according to claim 4, characterized in that: The step of determining the battery box offset parameter according to the battery box position information and the preset calibrated battery box position information includes: Determine the position offset in the battery box coordinate system according to the first origin coordinate information and the second origin coordinate information; The angle offset in the battery box coordinate system is determined according to the first angle information and the second angle information.

6. The method for replacing a drone battery according to claim 5, characterized in that: The step of determining the motion path of a robot arm connected to a battery replacement gripper according to the battery box offset parameter includes: According to a preset coordinate system conversion relationship, the position offset in the battery box coordinate system is converted into the position offset in the global coordinate system; the angle offset in the battery box coordinate system is converted into the angle offset in the global coordinate system; The motion path of the robotic arm connected to the battery replacement gripper is determined according to the position offset in the global coordinate system and the angle offset in the global coordinate system.

7. A drone battery replacement device, characterized in that: The device comprises: The acquisition module is used to obtain the current battery box position information of the drone; wherein the battery box contains the drone power battery; A determination module, used to determine a battery box offset parameter according to the battery box position information and preset calibration battery box position information; wherein the battery box offset parameter at least includes an angle offset and a position offset; The replacement module is used to determine the movement path of a mechanical arm connected to a battery replacement gripper according to the battery box offset parameters, and control the mechanical arm to move to a gripping position according to the movement path to replace the battery of the drone.

8. The drone battery replacement device according to claim 7, characterized in that: The device also includes a building module, the building module is used to: Acquire a first image of the drone, wherein the first image is obtained when the drone is located at a battery calibration position; Analyzing the first image to obtain first acquisition point information corresponding to the first image; According to a preset geometric algorithm, first origin coordinate information and first angle information corresponding to the first collection point information are determined.

9. The drone battery replacement device according to claim 8, characterized in that: The first collection point information includes at least first feature point coordinate data, second feature point coordinate data, third feature point coordinate data and fourth feature point coordinate data; The establishment module is used to: Determine a first connecting line according to the first feature point coordinate data and the third feature point coordinate data; Determine a second connecting line according to the second feature point coordinate data and the fourth feature point coordinate data; Determine the coordinate information of the first origin of the battery box coordinate system according to the intersection of the first connecting line and the second connecting line; The first angle information is determined according to the first connecting line and the coordinate axes of the battery box coordinate system.

10. A drone hangar, characterized in that: The invention comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor can implement the method for replacing the battery of the drone as described in any one of claims 1 to 6 when executing the program.

Images