A robot automatic aiming method, system and robot

Abstract

The present application provides a robot automatic aiming method, system and robot, which are applicable to the field of robot technology. The method includes: determining candidate armor plates according to the image information of the enemy robot; determining the candidate armor plate closest to itself according to the spatial position information of each candidate armor plate relative to itself; when the distance difference between the candidate armor plate closest to itself and the target armor plate relative to itself is less than a preset distance switching threshold, switching the target armor plate to the candidate armor plate closest to itself; performing Kalman filter fusion processing on the rotation angle information of the target armor plate relative to itself to obtain the target rotation angle information, so as to aim at the target armor plate according to the target rotation angle information. The present application can stably identify the target in the case of the high-speed movement of the robot itself and the target, and avoid the frequent vibration caused by the frequent switching of the strike target in the case of multiple targets, thereby improving the strike efficiency.

Description

Technical Field

[0001] This application belongs to the technical field of robots, and particularly relates to a robot automatic aiming method, system and robot. Background Art

[0002] With the development of artificial intelligence technology, related research in the field of robots has become a current hotspot. Among them, related technologies in the field of robots include environmental perception, autonomous positioning and navigation, path planning and intelligent decision-making, etc.

[0003] Robot shooting confrontation competition is an important competition form in the field of robots. In the battlefield environment of robot shooting confrontation competition, robots need to automatically identify target robots and achieve precise strikes, which requires testing the comprehensive performance of robots in environmental perception, predictive strike, real-time positioning, autonomous decision-making, motion planning, etc. There are high requirements for the intelligence of robots in the battlefield environment.

[0004] However, since both robots are in a moving state, how to accurately aim at and strike the enemy robot is a major difficulty at present. In the prior art, when the robot itself and the target are moving at high speeds, due to the high similarity of the features of different target robots, there is no mature algorithm for decision-making when multiple targets appear in the field of view, resulting in the problem of low strike efficiency. Summary of the Invention

[0005] In view of this, the embodiments of this application provide a robot automatic aiming method, which can solve the problem of low strike efficiency existing in existing robots when the robot itself and the target are moving at high speeds.

[0006] The first aspect of the embodiments of this application provides a robot automatic aiming method, including:

[0007] Including:

[0008] Obtain the image information of the enemy robot;

[0009] Determine candidate armor plates according to the image information of the enemy robot;

[0010] Calculate the spatial position information and rotation angle information of each candidate armor plate relative to itself;

[0011] Determine the candidate armor plate closest to itself according to the spatial position information of each candidate armor plate relative to itself;

[0012] When the distance difference between the candidate armor plate closest to itself and the target armor plate relative to itself is less than the preset distance switching threshold, switch the target armor plate to the candidate armor plate closest to itself;

[0013] Perform Kalman filter fusion processing on the rotation angle information of the target armor plate relative to itself to obtain the target rotation angle information, so as to aim at the target armor plate according to the target rotation angle information.

[0014] The second aspect of the embodiments of the present application provides a robot automatic aiming system, including:

[0015] An image information acquisition module, configured to acquire image information of an enemy robot;

[0016] A first candidate armor plate determination module, configured to determine a candidate armor plate according to the image information of the enemy robot;

[0017] A pose calculation module, configured to calculate the spatial position information and rotation angle information of each of the candidate armor plates relative to itself;

[0018] A second candidate armor plate determination module, configured to determine the candidate armor plate closest to itself according to the spatial position information of each of the candidate armor plates relative to itself;

[0019] A target armor plate determination module, configured to switch the target armor plate to the candidate armor plate closest to itself when the distance difference between the candidate armor plate closest to itself and the target armor plate relative to itself is less than a preset distance switching threshold; and

[0020] A target armor plate aiming module, configured to perform Kalman filter fusion processing on the rotation angle information of the target armor plate relative to itself to obtain the target rotation angle information, so as to aim at the target armor plate according to the target rotation angle information.

[0021] The third aspect of the embodiments of the present application provides a robot, and the robot includes the robot automatic aiming device as described in the second aspect above.

[0022] The fourth aspect of the embodiments of the present application provides a computer device, the computer device includes a memory and a processor, and a computer program capable of running on the processor is stored on the memory, and when the processor executes the computer program, the steps of the robot automatic aiming method as described in the first aspect above are implemented.

[0023] The fifth aspect of the embodiments of the present application provides a computer-readable storage medium, including: storing a computer program, characterized in that when the computer program is executed by a processor, the steps of the robot automatic aiming method as described in any one of the first aspects above are implemented.

[0024] The robot automatic aiming method provided by the embodiment of the present application can, after determining several candidate armor plates to be struck based on the image information of the enemy robot, determine whether the preset target switching requirements are met in real time according to the positional relationship of each candidate armor plate relative to itself, so as to determine the target armor plate from each candidate armor plate for striking. It can stably identify the target when the robot itself and the target are moving at high speed, and can also provide real-time and fast feedback and predict the position and attitude information of the target to implement tracking and firing, avoiding the frequent vibration caused by the frequent switching of the striking target in the case of multiple targets, and greatly improving the striking efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0026] Figure 1 is a schematic structural diagram of the robot provided by the embodiment of the present application;

[0027] Figure 2 is a schematic implementation flowchart of the robot automatic aiming method provided by the embodiment of the present application;

[0028] Figure 3 is a schematic diagram of the surface information of the armor plate provided by the embodiment of the present application;

[0029] Figure 4 is a schematic diagram of the neural network structure provided by the embodiment of the present application;

[0030] Figure 5 is a schematic implementation flowchart of determining the candidate armor plate provided by the embodiment of the present application;

[0031] Figure 6 is a schematic diagram of the robot automatic aiming effect provided by the embodiment of the present application;

[0032] Figure 7 is a schematic structural diagram of the robot automatic aiming system provided by the embodiment of the present application;

[0033] Figure 8 is a schematic diagram of the computer device provided by the embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0034] In the following description, specific details such as specific system structures and technologies are presented for the purpose of illustration rather than limitation, so as to thoroughly understand the embodiments of the present application. However, those skilled in the art should clearly understand that the present application can also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid unnecessary details from interfering with the description of the present application.

[0035] In order to illustrate the technical solutions described in the present application, the following will be described through specific embodiments.

[0036] As Figure 1 shown, an application environment diagram of a robot automatic aiming method provided by an embodiment of the present application is shown, which can also be understood as a schematic structural diagram of a robot applying the robot automatic aiming method. The robot body includes a robot automatic aiming system, a camera, a pan-tilt, and a barrel that communicate with the robot automatic aiming system; the overall shape and structure of the robot body are similar to those of existing robots, and armor plates are provided on the front, back, left, and right. Each armor plate has not only digital features but also texture features; light strips are provided on both sides of the armor plate.

[0037] Referring to Figure 2 , a schematic flow chart of the steps of a robot automatic aiming method provided by an embodiment of the present application is shown, which specifically may include the following steps:

[0038] Step S202, obtain image information of the enemy robot.

[0039] In the embodiment of the present application, the image information of the enemy robot can be collected by a camera. In the prior art, due to the relatively fast moving speed of the robot, blurring will occur during recognition due to exposure, making it difficult to recognize. Therefore, in the present application, the camera adopts a low-exposure mode. Parameters such as the exposure time of the camera have a great impact on the quality of the image. For example, a long exposure time results in a high-brightness image, which is convenient for feature extraction. However, when observing a high-speed moving object with a long exposure time, such as 10 ms, blurring will occur, so features will still be lost. While a short exposure time does not produce blurring, less light will cause the image to be too dark and the features to become less obvious. Therefore, adjusting the exposure time is a tricky matter. In the present application, based on the understanding of the task, since most of the task is completed under high-speed movement, blurring is unacceptable. Therefore, the first priority is that blurring cannot occur, so it is determined to adopt a low-exposure mode. The correction of the image is mainly achieved by adjusting the gamma transformation of the image to appropriately increase the brightness of the low-gray-value part of the image, and adjusting the analog gain of the camera sampling to make the image brightness a little higher, so as to adjust the indicators of the camera exposure time, the gamma value of the look-up table transformation, and the analog gain to a more excellent solution.

[0040] In the embodiments of the present application, the identification of enemy robots and friendly robots is mainly determined by the number information and color information of the robots. Among them, the number information refers to the digital information on the armor plate, generally the number 1 or 2. For example, Figure 3 As shown, for the extraction of the numbers on the armor plate, since the low-exposure image is relatively dim, adaptive threshold segmentation can be used to distinguish the panoramic numbers on the armor plate from the black background. The basic idea of adaptive threshold segmentation is to divide the image into several blocks, then count the pixel values in each block, and calculate the mean, median, and Gaussian weighted average (Gaussian filtering) of a certain neighborhood (local) to determine the threshold. Since there are only robots numbered 1 and 2 in this competition, the inclination rate of the middle part of the number can be further used to identify the numbers 1 and 2, because the middle part of the number 1 is vertical, while the middle part of the number 2 has an inclination of approximately 60 degrees.

[0041] Step S204: Determine the candidate armor plate according to the image information of the enemy robot.

[0042] In the embodiments of the present application, since the feature similarities of different targets are relatively high and there is interference from the shaded triangles in digital recognition, for the candidate armor plate, a neural network can be independently designed through the armor plate light strip features and detailed texture features. For example, Figure 4 As shown in the neural network structure, the function of the neural network is to classify different armor plates, such as giving armor plates with different texture features (the triangles in the shading have different orientations). The input image is the front view of a 30*30 armor plate, and the output is the category of the armor plate. Among them, the category of the armor plate is divided into 9 categories, including the front, back, left, and right of the robot numbered 1 and 2, and the pretend deck (such as the shadow on the glass screened out in traditional OpenCV). The neural network structure used is mainly a convolutional neural network, without using a fully connected structure, which can appropriately reduce the computational amount while achieving good accuracy; the activation function used is Relu. The final 1*1 convolution does not use ConV2d for convolution, but uses matrix multiplication of GEMM twice to accelerate the operation and achieve the purpose of dimensionality reduction, finally converting the 1*1*96 channels into 1*1*9 results, which exactly correspond to the 9 types of armor plate categories in the recognition task.

[0043] In a preferred embodiment of the present application, as Figure 5 shown, the step S204 includes the following steps:

[0044] Step S502: Perform channel threshold segmentation processing on the image information of the enemy robot after channel subtraction processing to obtain a first image.

[0045] Step S504: Perform brightness threshold segmentation processing on the image information of the enemy robot to obtain a second image.

[0046] Step S506: Perform binary bit processing on the first image and the second image to obtain a grayscale image.

[0047] In the embodiment of the present application, by performing morphological processing on the image information of the enemy robot, that is, subtracting the BGR channels of the original image and then performing threshold segmentation to obtain the first image; performing brightness threshold segmentation on the original image to obtain the second image; and then performing an "AND" operation on the first image and the second image to obtain the final grayscale image.

[0048] Step S508: Perform rotated rectangle fitting processing on the grayscale image to obtain a preliminary light bar.

[0049] Step S510: Obtain the geometric information of the preliminary light bar, and determine the preliminary armor plate and the geometric information of the preliminary armor plate according to the geometric information of the preliminary light bar.

[0050] In the embodiment of the present application, rotated rectangle fitting processing is performed on the grayscale image to screen the light bars, and a preliminary light bar is obtained; then the geometric information on the preliminary light bar, such as the inclination angle and aspect ratio of the light bar, is obtained, and abnormal light bars, such as light bars with too large an inclination angle and light bars with abnormal aspect ratios, are removed. Specifically, for light bars with too large an inclination angle, due to the particularity of the scene, there is no uphill or downhill but only flat ground, so the target robot will not roll over, and thus the light bars of the armor plate are basically vertical. From different perspectives, the light bars of the armor plate will not lie flat or be close to horizontal, so the light bars with too small an angle with the horizontal plane are removed; for light bars with abnormal aspect ratios, because the light bars are rigid and basically will not undergo drastic changes, and the height of the own perspective will not change during the competition, the length and width of the light bars basically maintain the original ratio, so those selected bar-shaped objects close to a square will be considered not to be light bars.

[0051] Step S512: Determine the candidate armor plates from the preliminary armor plates according to the geometric information of the preliminary armor plates and the central position relationship between the preliminary armor plates.

[0052] In the embodiments of the present application, geometric information such as the inclination angle and aspect ratio of the preliminary armor plate are obtained according to the fitting of two preliminary light bars (the armor plate is actually a rectangle formed by fitting two light bars), and the abnormal preliminary armor plates are removed; then, according to the central position relationship of each preliminary armor plate, the ground reflection armor plates are removed to obtain candidate armor plates. Among them, the screening of the inclination angle and aspect ratio of the preliminary armor plate is basically the same as the above-mentioned light bar screening principle; in addition, the positions of the centers of different armor plates in the image are different. Because of the design of the reflection area in the competition scene, a same armor plate may be reflected below the real target armor plate. However, according to geometric knowledge, the center position of the reflected armor plate and the center of the original armor plate are located on the same vertical line. Therefore, in the image, it is reflected that the x values of the coordinates of the two center points are the same. Then, the coordinates of the center points of the candidate armor plates are compared one by one. If the x values in the coordinates of the center points of two armor plates are the same, it is considered that the armor plate located below is the ground reflection armor plate.

[0053] Step S206, calculate the spatial position information and rotation angle information of each of the candidate armor plates relative to itself.

[0054] In the embodiments of the present application, the rotation angle information includes yaw angle information and pitch angle information.

[0055] In a preferred embodiment of the present application, the position coordinates and attitude angles of the armor plate in the camera coordinate system are solved by combining the corner point information of the candidate armor plate with perspective transformation; the step of calculating the spatial position information and rotation angle information of each of the candidate armor plates relative to itself includes: obtaining the corner point position information of each of the candidate armor plates; according to the corner point position information of each of the candidate armor plates, calculate the spatial position information and rotation angle information of each of the candidate armor plates relative to itself. Specifically, according to the two-dimensional coordinate information of the four corner points of each candidate armor plate, the three-dimensional coordinate point positions of each candidate armor plate and its rotation vector relative to itself are obtained, and the yaw angle and pitch angle can be further calculated through the rotation vector.

[0056] Step S208, determine the candidate armor plate closest to itself according to the spatial position information of each of the candidate armor plates relative to itself.

[0057] In the embodiments of the present application, the distance value between each candidate armor plate and itself is calculated according to the three-dimensional coordinate point position of each candidate armor plate, and the candidate armor plate closest to itself is determined therefrom.

[0058] Step S210, determine whether the distance difference between the candidate armor plate closest to itself and the target armor plate relative to itself is less than a preset distance switching threshold; if so, enter step S212; if not, enter step S214.

[0059] Step S212: Switch the target armor plate to the candidate armor plate closest to itself.

[0060] Step S214: Keep the target armor plate unchanged.

[0061] In the embodiment of the present application, if the principle is to give priority to hitting the closest one, when there are two candidate armor plate targets for the robot itself, for example, the previous one is 50 cm away from itself and the latter one is 60 cm away from itself, and the two are very close, the previous one is preferentially selected as the target armor plate; if the previous one runs to the back and becomes 70 cm away from itself, the target armor plate has to be switched to the other armor plate 60 cm away. At this time, when the distance between the target armor plate and the robot itself is repeatedly adjusted, it will cause the robot itself to frequently switch targets, which in turn drives the robot to turn and generates inertia. This not only reduces the shooting force, but also takes a certain amount of time for turning. Inertia will cause the bullet direction to be difficult to control and the accuracy to decrease. Therefore, in the case where the priority changes within a small range of distances in the present application, the original target armor plate is maintained, and the target armor plate is only switched after reaching a certain large range. As Figure 6 shown in the robot automatic aiming effect diagram, the upper left figure is the image segmented by the RGB blue channel threshold, the lower left figure is the image segmented by the brightness threshold, the lower right figure is the candidate armor plate before screening, and the upper right figure is the finally selected target armor plate.

[0062] In a preferred embodiment of the present application, according to the spatial position information of each candidate armor plate relative to itself, determine the target weight value of each candidate armor plate; determine the candidate armor plate with the largest target weight value from the candidate armor plates; when the weight difference between the candidate armor plate with the largest target weight value and the target armor plate is greater than the preset weight switching threshold, switch the target armor plate to the candidate armor plate with the largest target weight value.

[0063] Specifically, according to the weight calculation formula W = -e dis , where dis refers to the distance value between the candidate armor plate and itself, and e is the natural constant, calculate the weight value W of each screened candidate armor plate. The larger the weight value, the higher the hitting priority of the candidate armor plate; further find the target armor plate A in the previous frame and the optimal hitting candidate armor plate B sorted according to the weight value; calculate the weight difference between the weight value of the candidate armor plate B and the weight value of the target armor plate A. If the weight difference is greater than the preset weight switching threshold, then switch the target armor plate to the candidate armor plate B; otherwise, still hit the target armor plate A.

[0064] In the embodiment of the present application, the switching threshold is mainly set according to the performance of the robot itself.

[0065] Step S216, perform Kalman filter fusion processing on the rotation angle information of the target armor plate relative to itself to obtain the target rotation angle information, and aim at the target armor plate according to the target rotation angle information.

[0066] In the embodiment of the present application, performing Kalman filter fusion processing on the rotation angle information of the target armor plate relative to itself can well predict a target rotation angle with less noise and higher accuracy, enabling real-time tracking of self-aiming.

[0067] In the embodiment of the present application, the designed Kalman filter is as follows:

[0068] Kalman Filter use Singer model

[0069] state update:

[0070]

[0071]

[0072]

[0073]

[0074]

[0075] q 12 =[1+e -2αT -2e -αT +2αTe -αT -2αT+2α 2 T 2 / 2α 4

[0076] q 13 =[1-e -2αT +2αTe -αT / 2α 3

[0077] q 22 =[4e -αT -3-e -2αT +2αT] / 2α 3

[0078] q 23 =[1+e -αT -e -2αT / 2α 2

[0079] q 33 =[1-e -2αT / 2α

[0080] measurement update

[0081] z k =Cx k

[0082]

[0083]

[0084]

[0085] C=[1 0 0]

[0086]

[0087] where

[0088] measurement noise

[0089] process noise

[0090] α: maneuvering frequency

[0091] T:computation cycle

[0092] in, is a priori estimate, is the prior covariance matrix, Q is the process noise, x k 、z k is the measurement result of the yaw angle or pitch angle, R is the measurement noise, K k is the Kalman gain, It is the posterior estimate, that is, the prediction result of the final yaw angle or pitch angle.

[0093] In an embodiment of the present application, the step of performing Kalman filter fusion processing on the rotation angle information of the target armor plate relative to itself to obtain the target rotation angle information includes: initializing the state transfer matrix parameters of the Kalman filter; determining the prior estimate value based on the last a posteriori estimate value and the state transfer matrix parameters; determining the prior covariance matrix parameters based on the last covariance matrix parameters and process noise; determining the posterior covariance matrix parameters based on the prior covariance matrix parameters and measurement noise; determining the Kalman gain parameters based on the posterior covariance matrix parameters and measurement noise; determining the target rotation angle information based on the rotation angle information of the target armor plate relative to itself, the prior estimate value and the Kalman gain parameters.

[0094] Specifically: 1. Initialize parameters and the model: Select a motion model such as uniformly accelerated motion or uniform motion, which is reflected in the state transition matrix A. The parameters in the process noise Q and the measurement noise R are appropriate values obtained through a large number of experiments. 2. Obtain the prior estimate and the prior covariance matrix: Substitute the previous posterior estimate into the motion equation (i.e., multiply it by the state transition matrix A) to obtain the current prior estimate, and then use the formula to calculate the prior covariance matrix 3. Update the measurement value and the posterior covariance matrix to obtain the measurement value x k Convert it to the form of z k and then use the formula to calculate the posterior covariance matrix. 4. Calculate the Kalman gain and perform data fusion: Use the formula to calculate the Kalman gain K k , and then perform data fusion Fuse the prior estimate and the current measurement value to obtain a posterior estimate with a smaller variance as the result.

[0095] The robot automatic aiming method provided by the embodiment of the present application, after determining several candidate armor plates to be struck through the image information of the enemy robot, determines whether it meets the preset target switching requirements in real time according to the position relationship of each candidate armor plate relative to itself, so as to determine the target armor plate from each candidate armor plate for striking. It can achieve stable target recognition when the robot itself and the target are moving at high speed, and real-time and rapid feedback and prediction of the target position and attitude information for tracking and firing, avoiding the frequent vibration caused by frequent switching of the strike target in the case of multiple targets, and greatly improving the strike efficiency.

[0096] Corresponding to the method in the above embodiment, Figure 7 The structural block diagram of the robot automatic aiming system provided by the embodiment of the present application is shown. For the sake of convenience of description, only the parts related to the embodiment of the present application are shown. Figure 7 The exemplary robot automatic aiming system may be the execution subject of the robot automatic aiming method provided by the foregoing embodiment.

[0097] Referring to Figure 7 , the robot automatic aiming system includes:

[0098] An image information acquisition module 710, configured to acquire the image information of the enemy robot;

[0099] A first candidate armor plate determination module 720, configured to determine candidate armor plates according to the image information of the enemy robot;

[0100] The pose calculation module 730 is configured to calculate the spatial position information and the rotation angle information of each of the candidate armor plates relative to itself;

[0101] The second candidate armor plate determination module 740 is configured to determine the candidate armor plate closest to itself according to the spatial position information of each of the candidate armor plates relative to itself;

[0102] The target armor plate determination module 750 is configured to switch the target armor plate to the candidate armor plate closest to itself when the distance difference between the candidate armor plate closest to itself and the target armor plate relative to itself is less than a preset distance switching threshold; and

[0103] The target armor plate aiming module 760 is configured to perform Kalman filter fusion processing on the rotation angle information of the target armor plate relative to itself to obtain target rotation angle information, so as to aim at the target armor plate according to the target rotation angle information.

[0104] For the process of each module in the robot automatic aiming system provided by the embodiments of the present application to implement its respective functions, reference may be specifically made to the description of the foregoing embodiments, which will not be elaborated herein.

[0105] It should be understood that the magnitudes of the sequence numbers of the steps in the foregoing embodiments do not mean the order of execution. The order of execution of each process should be determined according to its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present application.

[0106] It should be understood that when used in the specification of the present application and the appended claims, the term "comprising" indicates the presence of the described features, wholes, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or their combinations.

[0107] It should also be understood that the term "and / or" as used in the specification of the present application and the appended claims refers to any combination and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0108] As used in the specification of the present application and the appended claims, the term "if" may be interpreted as "when...", "once", "in response to determining", or "in response to detecting" according to the context. Similarly, the phrase "if determined" or "if [the described condition or event] is detected" may be interpreted as meaning "once determined", "in response to determining", "once [the described condition or event] is detected", or "in response to detecting [the described condition or event]" according to the context.

[0109] In addition, in the description of the specification and the appended claims of this application, the terms "first", "second", "third", etc. are only used for distinguishing descriptions and should not be construed as indicating or implying relative importance. It should also be understood that although the terms "first", "second", etc. are used in the text to describe various elements in some embodiments of this application, these elements should not be limited by these terms. These terms are only used to distinguish one element from another. For example, the first table can be named the second table, and similarly, the second table can be named the first table without departing from the scope of the various described embodiments. The first table and the second table are both tables, but they are not the same table.

[0110] The reference to "one embodiment" or "some embodiments" etc. described in the specification of this application means that a specific feature, structure, or characteristic described in connection with that embodiment is included in one or more embodiments of this application. Thus, the statements "in one embodiment", "in some embodiments", "in other some embodiments", "in still other embodiments", etc. that appear in different places in this specification do not necessarily all refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "comprising", "including", "having" and their variants all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0111] Figure 8 is a schematic structural diagram of a computer device provided by an embodiment of this application. As Figure 8 shown, the computer device 7 of this embodiment includes: at least one processor 70 ( Figure 7 only one is shown in the figure), a memory 71, and a computer program 72 that can run on the processor 70 is stored in the memory 71. When the processor 70 executes the computer program 72, it implements the steps in the above-mentioned embodiments of various robot automatic aiming methods, such as Figure 2 the steps 202 to 216 shown in the figure. Or, when the processor 70 executes the computer program 72, it implements the functions of each module / unit in the above-mentioned device embodiments, such as Figure 7 the functions of the modules 710 to 760 shown in the figure.

[0112] The terminal device may include, but is not limited to, a processor 70 and a memory 71. Those skilled in the art can understand that Figure 7 this is only an example of the terminal device 7 and does not constitute a limitation on the terminal device 7. It may include more or fewer components than shown in the figure, or combine some components, or different components. For example, the terminal device may further include an input and sending device, a network access device, a bus, etc.

[0113] The so-called processor 70 may be a Central Processing Unit (CPU), or may also be other general-purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field-Programmable Gate Arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0114] In some embodiments, the memory 71 may be an internal storage unit of the terminal device 7, such as the hard disk or memory of the terminal device 7. The memory 71 may also be an external storage device of the terminal device 7, such as a plug-in hard disk equipped on the terminal device 7, a Smart Media Card (SMC), a Secure Digital (SD) card, a Flash Card, etc. Further, the memory 71 may also include both the internal storage unit of the terminal device 7 and the external storage device. The memory 71 is used to store an operating system, application programs, a BootLoader, data, and other programs, such as the program code of the computer program. The memory 71 may also be used to temporarily store data that has been sent or will be sent.

[0115] In addition, in each embodiment of the present application, each functional unit may be integrated in one processing unit, or each unit may exist physically alone, or two or more units may be integrated in one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of a software functional unit.

[0116] The embodiment of the present application also provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the steps in the above-mentioned various method embodiments can be implemented.

[0117] The embodiment of the present application provides a computer program product. When the computer program product runs on a computer device, the computer device can implement the steps in the above-mentioned various method embodiments when executed.

[0118] When the integrated module / unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, to implement all or part of the processes in the above-described embodiment methods of this application, it can also be completed by instructing relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, the steps of the above-described method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file, or some intermediate form, etc. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disc, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal, and software distribution medium, etc.

[0119] In the above embodiments, the descriptions of the respective embodiments have their own emphases. For the parts not detailed or recorded in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0120] Those of ordinary skill in the art can realize that the units and algorithm steps of the examples described in conjunction with the embodiments disclosed herein can be implemented by electronic hardware, or by a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. A professional technician can use different methods for each specific application to implement the described functions, but such implementation should not be considered to exceed the scope of this application.

[0121] The unit described as a separate component may or may not be physically separated, and the component shown as a unit may or may not be a physical unit, that is, it may be located in one place, or may be distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0122] The above-described embodiments are only used to illustrate the technical solutions of this application, rather than to limit them; although this application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.

Claims

1. A robot automatic aiming method, characterized in that, Including: Obtain the image information of the enemy robot; Determine candidate armor plates according to the image information of the enemy robot; Calculate the spatial position information and rotation angle information of each candidate armor plate relative to itself; Determine the candidate armor plate closest to itself according to the spatial position information of each candidate armor plate relative to itself; When the distance difference between the candidate armor plate closest to itself and the target armor plate relative to itself is less than the preset distance switching threshold, switch the target armor plate to the candidate armor plate closest to itself; Perform Kalman filter fusion processing on the rotation angle information of the target armor plate relative to itself to obtain the target rotation angle information, so as to aim at the target armor plate according to the target rotation angle information.

2. The robot automatic aiming method according to claim 1, wherein, The step of determining candidate armor plates according to the image information of the enemy robot includes: Perform channel threshold segmentation processing on the image information of the enemy robot after channel subtraction processing to obtain a first image; Perform brightness threshold segmentation processing on the image information of the enemy robot to obtain a second image; Perform binary bit processing on the first image and the second image to obtain a grayscale image; Perform rotated rectangle fitting processing on the grayscale image to obtain a preliminary light bar; Obtain the geometric information of the preliminary light bar, and determine the preliminary armor plate and the geometric information of the preliminary armor plate according to the geometric information of the preliminary light bar; Determine candidate armor plates from the preliminary armor plates according to the geometric information of the preliminary armor plates and the central position relationship between each preliminary armor plate.

3. The robot automatic aiming method according to claim 1, characterized in that The step of calculating the spatial position information and rotation angle information of each candidate armor plate relative to itself includes: Obtain the corner point position information of each candidate armor plate; Calculate the spatial position information and rotation angle information of each candidate armor plate relative to itself according to the corner point position information of each candidate armor plate.

4. The robot automatic aiming method according to claim 1, characterized in that The step of determining the candidate armor plate closest to itself according to the spatial position information of each candidate armor plate relative to itself includes: Determine the target weight value of each candidate armor plate according to the spatial position information of each candidate armor plate relative to itself; Determine the candidate armor plate with the largest target weight value from the candidate armor plates; The step of switching the target armor plate to the candidate armor plate closest to itself when the distance difference between the candidate armor plate closest to itself and the target armor plate relative to itself is less than the preset distance switching threshold includes: When the weight difference between the candidate armor plate with the largest target weight value and the target armor plate is greater than the preset weight switching threshold, switch the target armor plate to the candidate armor plate with the largest target weight value.

5. The robot automatic aiming method according to claim 1, wherein, The step of performing Kalman filter fusion processing on the rotation angle information of the target armor plate relative to itself to obtain the target rotation angle information includes: Initialize the state transition matrix parameters of the Kalman filter; Determine the prior estimate value according to the previous posterior estimate value and the state transition matrix parameters; Determine the Kalman gain parameter according to the previous covariance matrix parameter, process noise, and measurement noise; Determine the target rotation angle information according to the rotation angle information of the target armor plate relative to itself, the prior estimate value, and the Kalman gain parameter.

6. The robot automatic aiming method according to claim 5, characterized in that, The step of determining the Kalman gain parameter according to the previous covariance matrix parameter, process noise, and measurement noise includes: Determine the prior covariance matrix parameter according to the previous covariance matrix parameter and process noise; Determine the posterior covariance matrix parameter according to the prior covariance matrix parameter and measurement noise; Determine the Kalman gain parameter according to the posterior covariance matrix parameter and measurement noise.

7. The robot automatic aiming method according to claim 1, characterized in that The rotation angle information includes yaw angle information and pitch angle information.

8. A robot automatic aiming system, characterized in that, including: An image information acquisition module for acquiring image information of the enemy robot; A first candidate armor plate determination module for determining candidate armor plates according to the image information of the enemy robot; A pose calculation module for calculating the spatial position information and rotation angle information of each of the candidate armor plates relative to itself; A second candidate armor plate determination module for determining the candidate armor plate closest to itself according to the spatial position information of each of the candidate armor plates relative to itself; A target armor plate determination module for switching the target armor plate to the candidate armor plate closest to itself when the distance difference between the candidate armor plate closest to itself and the target armor plate relative to itself is less than a preset distance switching threshold; and A target armor plate aiming module for performing Kalman filter fusion processing on the rotation angle information of the target armor plate relative to itself to obtain the target rotation angle information, so as to aim at the target armor plate according to the target rotation angle information.

9. A robot, characterized in that, The robot includes the robot automatic aiming system according to claim 8.

10. A computer device, characterized in that, The computer device includes a memory and a processor. A computer program is stored on the memory and can run on the processor. When the processor executes the computer program, the steps of the robot automatic aiming method according to any one of claims 1 to 7 are implemented.

Images