Multi-robot grouping and tracking control method and system

Abstract

The invention belongs to the technical field of robot formation, and provides a multi-robot team formation and tracking control method and system, and the method comprises the steps: analyzing a voice signal, taking a subject in the voice signal as the number of a navigator robot, and taking an object in the voice signal as the number of a follower robot, thereby completing the team formation; taking image acquisition of the follower robot as an original point, establishing a coordinate system, and converting the established coordinate system into a pixel coordinate system; determining a pixel value of a navigator robot on a pixel plane in the pixel coordinate system; the direction between the follower robot and the navigator robot is determined according to the pixel value, and the distance between the follower robot and the navigator robot is determined according to the voice signal transmission time; performing tracking control according to the determined direction and distance; the team forming information is transmitted in a voice processing sequence analysis mode, and the team forming efficiency is greatly improved compared with the mode that an operator performs robot identity assignment or team member team forming through a man-machine interaction screen in the modes of clicking, dragging and the like.

Description

Technical Field

[0001] The present invention belongs to the technical field of robot formation, and in particular relates to a multi-robot team formation and tracking control method and system. Background Art

[0002] Robot formation refers to a mode in which multiple robots form a certain formation or structure through collaboration and work together to complete a task. The core of robot formation lies in the collaboration and cooperation between multiple robots. These robots can adjust their position, speed and posture according to preset algorithms or real-time environmental information to maintain or change a specific formation. Common formation control methods include behavior-based methods, leader-follower methods, model predictive control-based methods, and artificial potential field-based methods. Robot formations have a wide range of applications and can be applied to military reconnaissance, collaborative operations, material transportation, and post-disaster rescue. Robot formations can effectively improve production efficiency and shorten production cycles through more efficient and collaborative working modes; they can undertake high-risk or low-security risk work and fundamentally eliminate the safety risks brought by some manual operations; in complex terrain and severe weather conditions, robot formations can overcome environmental obstacles through mutual collaboration, maintain stable formations, and ensure the smooth completion of tasks; multiple robots can also share information about the surrounding environment to achieve real-time situational awareness and collaborative decision-making, and improve flexibility and response speed. Therefore, as an efficient and collaborative working mode, robot formations have shown broad application prospects and far-reaching significance in many fields.

[0003] Multi-robot teaming is the first step in multi-robot team formation. At present, when robots are teamed, operators generally need to use the human-machine interaction screen to click, drag, etc. to specify the robot identity or team members, and then further realize the formation of the formation; among them, robot identity specification and team members are the key links that affect the efficiency of the formation, which makes the traditional robot formation operation inefficient. Summary of the invention

[0004] In order to solve the above problems, the present invention proposes a multi-robot teaming and tracking control method and system. The present invention uses the subject in the voice signal as the number of the navigator robot and the object as the number of the follower robot to complete the teaming; establishes a coordinate system with the image acquisition of the follower robot as the origin, and converts the established coordinate system into a pixel coordinate system; determines the pixel value of the navigator robot on the pixel plane in the pixel coordinate system; determines the direction between the follower robot and the navigator robot according to the pixel value, and determines the distance between the follower robot and the navigator robot according to the voice signal transmission time; performs tracking control according to the determined direction and distance; and transmits teaming information through voice processing sequence analysis, which greatly improves the teaming efficiency compared to the operator specifying the robot identity or teaming the team members through the human-computer interaction screen by clicking, dragging, etc.

[0005] In order to achieve the above object, the present invention is implemented through the following technical solutions:

[0006] In a first aspect, the present invention provides a multi-robot team formation and tracking control method, comprising:

[0007] Acquire voice signals of multiple robot numbers and image data of tracking robots;

[0008] Analyze the voice signal, use the subject in the voice signal as the number of the navigator robot, and the object as the number of the follower robot, to complete the team formation; wherein, for the follower robot for which the navigator robot does not exist in the image data, control the follower robot to rotate in a preset direction until the navigator robot appears in the image data;

[0009] Taking the image acquisition device of the follower robot as the origin, a coordinate system is established, and the established coordinate system is converted into a pixel coordinate system; the pixel value of the leader robot on the pixel plane is determined in the pixel coordinate system;

[0010] Determine the direction between the follower robot and the navigator robot based on the pixel value, and determine the distance between the follower robot and the navigator robot based on the voice signal transmission time;

[0011] Tracking control is performed according to the determined direction and distance.

[0012] Furthermore, the navigator robot continuously emits a sound signal at a preset frequency, the content of the sound signal is the number of the navigator robot, and the follower robot obtains the distance between the two preset microphones on the follower robot and the preset speaker on the navigator robot through sound ranging.

[0013] Furthermore, taking the image acquisition of the follower robot as the origin, a coordinate system is established, Z CThe axis is perpendicular to the imaging plane and points to the front of the image acquisition device. C The axis passes through the centers of the two microphones and points to the microphone on the right side of the robot's forward direction; the established coordinate system to pixel coordinate system transformation relationship is:

[0014]

[0015] Wherein, (X, Y, Z) is the position coordinate of the navigator robot in the image acquisition device coordinate system; (u, v) is the coordinate of the navigator robot in the pixel coordinate system; is the internal parameter of the image acquisition device, where f is the focal length of the camera, (c x , c y ) is the coordinate of the optical center of the image acquisition device in the pixel coordinate system.

[0016] Furthermore, the speaker on the navigator robot, the image acquisition device and the microphone on the follower robot are connected to establish a geometric relationship; the microphone on the right side of the follower robot is set as point A, the microphone on the left side is set as point B, and the speaker of the navigator robot is set as point C. According to the triangle cosine theorem, we can obtain:

[0017]

[0018] Assume that the optical center of the image acquisition device is point O. According to the law of cosines, the distance between the optical center of the image acquisition device and the navigator robot is expressed as:

[0019] OC 2 =AC 2 +OA 2 -2·AC·OA·cosA

[0020] Obtain the pixel value u of the leader robot on the pixel plane:

[0021]

[0022]

[0023]

[0024] Furthermore, if the imaging point of the navigator robot is smaller than the coordinate value of the optical center of the image acquisition device in the pixel coordinate system, it means that the navigator robot is in front of the left of the follower robot, and the follower robot is controlled to turn left; if the imaging point of the navigator robot is larger than the coordinate value of the optical center of the image acquisition device in the pixel coordinate system, it means that the navigator robot is in front of the right of the follower robot, and the follower robot is controlled to turn right.

[0025] Furthermore, when the follower robot turns toward the navigator robot, the distance between the navigator robot and the follower robot is obtained by sound ranging through the navigator robot speaker and the follower robot microphone; the distance between the navigator robot and the follower robot is controlled to always remain at a preset value.

[0026] In a second aspect, the present invention further provides a multi-robot team formation and tracking control system, comprising:

[0027] The data acquisition module is configured to: obtain voice signals of multiple robot numbers and image data of tracking robots;

[0028] The team formation module is configured to: analyze the voice signal, use the subject in the voice signal as the number of the navigator robot, and the object as the number of the follower robot, to complete the team formation; wherein, for the follower robot for which the navigator robot does not exist in the image data, control the follower robot to rotate in a preset direction until the navigator robot appears in the image data;

[0029] The pixel determination module is configured to: establish a coordinate system with the image acquisition device of the follower robot as the origin, and convert the established coordinate system into a pixel coordinate system; determine the pixel value of the leader robot on the pixel plane in the pixel coordinate system;

[0030] The distance determination module is configured to: determine the direction between the follower robot and the navigator robot according to the pixel value, and determine the distance between the follower robot and the navigator robot according to the voice signal transmission time;

[0031] The tracking control module is configured to perform tracking control according to the determined direction and distance.

[0032] In a third aspect, the present invention further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the multi-robot team formation and tracking control method described in the first aspect.

[0033] In a fourth aspect, the present invention further provides an electronic device comprising a memory, a processor, and a computer program stored in the memory and capable of running on the processor, wherein when the processor executes the program, the steps of the multi-robot teaming and tracking control method described in the first aspect are implemented.

[0034] In a fifth aspect, the present invention further provides a computer program product, which includes a computer program. When the computer program is executed by a processor, the steps of the multi-robot team formation and tracking control method described in the first aspect are implemented.

[0035] Compared with the prior art, the present invention has the following beneficial effects:

[0036] 1. In the present invention, the subject in the voice signal is analyzed as the number of the navigator robot, and the object is used as the number of the follower robot to complete the team formation; a coordinate system is established with the image acquisition of the follower robot as the origin, and the established coordinate system is converted into a pixel coordinate system; the pixel value of the navigator robot on the pixel plane is determined in the pixel coordinate system; the direction between the follower robot and the navigator robot is determined according to the pixel value, and the distance between the follower robot and the navigator robot is determined according to the voice signal transmission time; tracking control is performed according to the determined direction and distance; team formation information is transmitted by voice processing sequence analysis, which greatly improves the team formation efficiency compared to the operator specifying the robot identity or teaming the team members through the human-computer interaction screen by clicking, dragging, etc.; at the same time, for the follower robot whose image data does not contain the navigator robot, the follower robot is controlled to rotate in a preset direction until the navigator robot appears in the image data, thereby realizing the following of the navigator robot during team formation in a simple manner, further improving the team formation efficiency.

[0037] 2. The target imaging point (u, v) obtained by the imaging system composed of a loudspeaker, a microphone and a camera in the present invention is not affected by light, that is, the team system can also realize the visualization of the followed target in a night environment. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] The drawings in the specification that constitute a part of this embodiment are used to provide a further understanding of this embodiment. The schematic embodiments of this embodiment and their descriptions are used to explain this embodiment and do not constitute improper limitations on this embodiment.

[0039] Figure 1 This is a schematic diagram of the overall structure of a single robot according to an embodiment of the present invention;

[0040] Figure 2 A schematic diagram of the geometric relationship between the speaker of the leader robot and the microphone and camera of the follower robot according to an embodiment of the present invention;

[0041] Figure 3 This is a schematic diagram of target imaging of a navigator robot according to an embodiment of the present invention;

[0042] Figure 4 is a flow chart of a method according to an embodiment of the present invention;

[0043] Among them, 1. robot; 101. speaker; 102. left microphone in the robot's forward direction; 103. right microphone in the robot's forward direction; 104. camera; 201. speaker of the navigator robot; 202. left microphone in the follower robot's forward direction; 203. right microphone in the follower robot's forward direction; 204. camera of the follower robot; 205. camera imaging plane; 206. camera field of view; 301. camera imaging plane of the follower robot; 302. navigator robot; 303. follower robot; 304. calculated target imaging point. DETAILED DESCRIPTION

[0044] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0045] It should be noted that the following detailed descriptions are exemplary and are intended to provide further explanation of the present application. Unless otherwise specified, all technical and scientific terms used herein have the same meanings as those commonly understood by those skilled in the art to which the present application belongs.

[0046] Embodiment 1:

[0047] The present embodiment provides a multi-robot teaming and tracking control method, and a system corresponding to the method, the system including a teaming system, an imaging system and a tracking system. The teaming system realizes multi-robot rapid teaming by means of speech processing sequence analysis. Optionally, each robot is equipped with a speaker and two microphones as a voice sending and receiving device, wherein the speaker is located at the tail end of the robot, the two microphones are located at the front end of the robot and are placed horizontally and at a fixed distance, and the plane formed by the speaker and the two microphones is parallel to the ground. In addition, each robot is also equipped with a camera to form the robot's imaging system, and the camera is located between the two microphones so that the optical center of the camera and the center of the microphone are on the same horizontal line. The tracking system is composed of a microphone, a speaker and a camera, wherein the camera provides position information, and the microphone and the speaker provide distance information.

[0048] S1. Rapid multi-robot teaming: using speech processing sequence analysis to transmit teaming information;

[0049] S1.1. First, all robots are numbered in Arabic numerals to distinguish each robot.

[0050] S1.2. Determine the navigator (tracked robot) and the follower (tracking robot), and shout in the form of a voice sequence of "navigator robot number plus follower robot number". The sound is received by all robots in the form of broadcast. All robots determine the subject and object of the sentence through syntactic structure analysis in natural language processing (NLP). The subject is the number of the navigator robot, and the object is the number of the follower robot. There can be multiple follower robot numbers.

[0051] S1.3. Activate the tracking status of the corresponding numbered leader robot and follower robot, and other non-leader or follower robots are in an inactive state.

[0052] S1.4. In general, the multiple robots that want to form a team are usually in a disordered state, that is, the leader robot is sometimes not in the field of view of the follower robot's camera. At this time, the follower robot rotates clockwise on the spot until the leader robot appears in the field of view of the follower robot's camera. The imaging method of the leader robot is described in the second part.

[0053] S2, tracking robot imaging: the tracking robot target imaging is achieved through the geometric relationship between the camera, microphone and speaker;

[0054] S2.1. Turn on the speaker of the navigator robot and the microphone of the follower robot. The navigator robot continuously emits sound at a certain frequency. The sound content is the number of the navigator robot. The follower robot obtains the distance between the two microphones on the follower robot and the speaker of the navigator robot through sound ranging.

[0055] S2.2. Establish the camera coordinate system with the camera optical center as the origin of the coordinate system, where Z C The axis is perpendicular to the imaging plane and points to the front of the camera. C The axis passes through the centers of the two microphones and points to the microphone on the right side of the robot's forward direction. The transformation relationship from the camera coordinate system to the pixel coordinate system is:

[0056]

[0057] Among them, (X, Y, Z) is the position coordinate of the navigator robot in the camera coordinate system; (u, v) is the coordinate of the navigator robot in the pixel coordinate system; is the camera internal parameter, which can be obtained by Zhang Zhengyou calibration method, where f is the camera focal length, (c x , c y ) is the offset from the optical center to the CMOS zero point, that is, the coordinate of the camera optical center in the pixel coordinate system.

[0058] S2.3. Since the plane formed by the loudspeaker and the two microphones is parallel to the ground, the Y of the navigator robot in the camera coordinate system is 0. Substitute it into the following formula:

[0059]

[0060] We can obtain v = c y .

[0061] S2.4. Connect the speaker of the leader robot, the camera and microphone of the follower robot to establish geometric relationships. Suppose the microphone on the right side of the follower robot is point A, the microphone on the left side is point B, and the speaker of the leader robot is point C. According to the triangular cosine theorem, we know that:

[0062]

[0063] Assume that the optical center of the follower robot camera is point O. According to the cosine theorem, the distance between the optical center of the camera and the leader robot can be expressed as:

[0064] OC 2 =AC 2 +OA 2 -2·AC·OA·cosA;

[0065] Then OC and camera coordinate system X C The positive semi-axis angle β can be expressed by the cosine theorem as:

[0066]

[0067] Known By combining the equations in step S2.4, we can find the relationship between cosβ and the three known sides AB, AC, and BC:

[0068]

[0069] S2.5. Consider the u value of the navigator robot in the pixel coordinate system, that is, the horizontal coordinate of the imaging plane:

[0070]

[0071] For the above formula, the X and Z values ​​of the navigator robot in the camera coordinate system can be expressed as:

[0072]

[0073]

[0074] By combining the equations in step S2.5, we can obtain the pixel value u of the navigator robot on the pixel plane:

[0075]

[0076] Here, cosβ has been calculated in step S2.4.

[0077] S2.6. Mark a dot on the pixel plane using the calculated pixel value (u, v) through graphic processing, and this dot coincides with the target of the navigator robot on the imaging plane. This dot can be regarded as the imaging point of the navigator robot, and will be used as the tracking target later.

[0078] S3. Multi-robot tracking: Multi-robot tracking is achieved through target position information and distance information.

[0079] S3.1. Before tracking, the leader robot must always be in the center of the follower robot's camera field of view. Therefore, the follower robot determines the direction based on the leader robot's imaging point u, and finally makes the imaging point u always tend to c. x .

[0080] If u <c x , indicating that the leader robot is in front of the left of the follower robot. Since the camera field of view moves with the follower robot, the follower robot turns left.

[0081] If u>c x , indicating that the leader robot is in front of the right of the follower robot and the follower robot turns right.

[0082] S3.2. When the follower robot turns toward the navigator robot, the distance between the navigator robot and the follower robot is obtained by sound ranging through the navigator robot speaker and the follower robot microphone.

[0083] S3.3. Keep the distance OC between the leader robot and the follower robot at a certain value at all times, and use the relevant control algorithm to act on the follower robot, so that the follower robot can track the leader robot.

[0084] S3.4, finally realize multi-robot rapid teaming and tracking.

[0085] Embodiment 2:

[0086] This embodiment provides a multi-robot team formation and tracking control method, which illustrates the method in Embodiment 1:

[0087] S1. First, all robots are numbered in Arabic numerals to distinguish each robot.

[0088] S2. Determine the navigator (tracked robot) and the follower (tracking robot). The operator shouts in the form of a voice sequence of "(navigator robot number) brings (follower robot number)". The voice is received by all robots in the form of broadcast. All robots determine the subject and object of the sentence through syntactic structure analysis in natural language processing (NLP). The subject is the number of the navigator robot, and the object is the number of the follower robot. There can be multiple numbers of follower robots. For example, "No. 1 brings No. 2 and No. 3", where No. 1 is the navigator robot, and No. 2 and No. 3 are follower robots.

[0089] S3. Activate the tracking status of the corresponding numbered leader robot and follower robot, and other non-leader or follower robots are in an inactive state.

[0090] S4. In general, the multiple robots that want to form a team are usually in a disordered state, that is, the leader robot is sometimes not in the field of view of the follower robot's camera. At this time, the follower robot rotates clockwise on the spot until the leader robot appears in the field of view of the follower robot's camera. The imaging method of the leader robot is described in the second part.

[0091] S5. Turn on the speaker 201 of the navigator robot, the left microphone 202 of the follower robot in the forward direction, and the right microphone 203 of the follower robot in the forward direction; the navigator robot continuously emits sound at a certain frequency, and the sound content is (the number of the navigator robot). The follower robot obtains the distance between the two microphones on the follower robot and the speaker of the navigator robot through sound ranging.

[0092] S6. Establish the camera coordinate system with the camera optical center as the origin of the coordinate system, where Z C The axis is perpendicular to the imaging plane and points to the front of the camera. C The axis passes through the centers of the two microphones and points to the microphone on the right side of the robot's forward direction. The transformation relationship from the camera coordinate system to the pixel coordinate system is:

[0093]

[0094] Where (X, Y, Z) is the position coordinate of the navigator robot in the camera coordinate system, (u, v) is the coordinate of the navigator robot in the pixel coordinate system, is the camera internal parameter, which can be obtained by Zhang Zhengyou calibration method, where f is the camera focal length, (c x , c y ) is the offset from the optical center to the CMOS zero point, that is, the coordinate of the camera optical center in the pixel coordinate system.

[0095] S7. Since the plane formed by the speaker and the two microphones is parallel to the ground, the Y of the navigator robot in the camera coordinate system is 0. Substitute it into the following formula:

[0096]

[0097] We can obtain v = c y .

[0098] S8. Connect the speaker of the navigator robot, the camera and microphone of the follower robot to establish geometric relationships. Suppose the microphone on the right side of the follower robot is point A, the microphone on the left side is point B, and the speaker of the navigator robot is point C. According to the triangular cosine theorem, we know that:

[0099]

[0100] Assume that the optical center of the follower robot camera is point O. According to the cosine theorem, the distance between the optical center of the camera and the leader robot can be expressed as:

[0101] OC 2 =AC 2 +OA 2 -2·AC·OA·cosA;

[0102] Then OC and camera coordinate system X C The positive semi-axis angle β can be expressed by the cosine theorem as:

[0103]

[0104] Known By combining the equations in step S8, we can find the relationship between cosβ and the three known sides AB, AC, and BC:

[0105]

[0106] S9. Consider the u value of the navigator robot in the pixel coordinate system, that is, the horizontal coordinate of the imaging plane:

[0107]

[0108] For the above formula, the X and Z values ​​of the navigator robot in the camera coordinate system can be expressed as:

[0109]

[0110]

[0111] By combining the equations in step S9, the pixel value u of the navigator robot on the pixel plane can be obtained:

[0112]

[0113] Here, cosβ has been obtained in step S8.

[0114] S10, mark a dot on the pixel plane using the calculated pixel value (u, v) by means of graphic processing, and this dot coincides with the target of the navigator robot on the imaging plane. Figure 3 As shown, 304 is the calculated (u, v) pixel value, which is marked as a dot, and the dot coincides with the image of the navigator robot. This dot can be regarded as the imaging point of the navigator robot, and the dot will be used as the tracking target later.

[0115] S11. Before tracking, the leader robot must always be in the center of the follower robot's camera field of view. Therefore, the follower robot determines the direction based on the leader robot's imaging point u, and finally makes the imaging point u always tend to c. x .

[0116] If u <c x , indicating that the leader robot is in front of the left of the follower robot. Since the camera field of view moves with the follower robot, the follower robot turns left.

[0117] If u>c x , indicating that the leader robot is in front of the right of the follower robot and the follower robot turns right.

[0118] S12. When the follower robot turns toward the navigator robot, the distance between the navigator robot and the follower robot is obtained by sound ranging through the speaker of the navigator robot and the microphone of the follower robot.

[0119] S13, the distance OC between the navigator robot and the follower robot is always kept at a certain value, and the follower robot is acted on by a related control algorithm, so that the follower robot tracks the navigator robot. As a preferred related control algorithm, PID control may be used.

[0120] S14, finally realize the rapid teaming and tracking of multiple robots.

[0121] Embodiment 3:

[0122] This embodiment provides a multi-robot teaming and tracking control system, including:

[0123] The data acquisition module is configured to: obtain voice signals of multiple robot numbers and image data of tracking robots;

[0124] The team formation module is configured to: analyze the voice signal, use the subject in the voice signal as the number of the navigator robot, and the object as the number of the follower robot, to complete the team formation; wherein, for the follower robot for which the navigator robot does not exist in the image data, control the follower robot to rotate in a preset direction until the navigator robot appears in the image data;

[0125] The pixel determination module is configured to: establish a coordinate system with the image acquisition device of the follower robot as the origin, and convert the established coordinate system into a pixel coordinate system; determine the pixel value of the leader robot on the pixel plane in the pixel coordinate system;

[0126] The distance determination module is configured to: determine the direction between the follower robot and the navigator robot according to the pixel value, and determine the distance between the follower robot and the navigator robot according to the voice signal transmission time;

[0127] The tracking control module is configured to perform tracking control according to the determined direction and distance.

[0128] The working method of the system is the same as the multi-robot team formation and tracking control method of Example 1, and will not be repeated here.

[0129] Embodiment 3:

[0130] This embodiment provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the steps of the multi-robot team formation and tracking control method described in Example 1 are implemented.

[0131] Embodiment 4:

[0132] This embodiment provides an electronic device, including a memory, a processor, and a computer program stored in the memory and capable of running on the processor. When the processor executes the program, the steps of the multi-robot team formation and tracking control method described in Example 1 are implemented.

[0133] Embodiment 5:

[0134] This embodiment provides a computer program product, which includes a computer program. When the computer program is executed by a processor, the steps of the multi-robot team formation and tracking control method described in Example 1 are implemented.

[0135] The above description is only a preferred embodiment of the present embodiment and is not intended to limit the present embodiment. For those skilled in the art, the present embodiment may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present embodiment shall be included in the protection scope of the present embodiment.

Claims

1. A multi-robot team formation and tracking control method, characterized in that: include: Acquire voice signals of multiple robot numbers and image data of tracking robots; Analyze the voice signal, use the subject in the voice signal as the number of the navigator robot, and the object as the number of the follower robot, to complete the team formation; wherein, for the follower robot for which the navigator robot does not exist in the image data, control the follower robot to rotate in a preset direction until the navigator robot appears in the image data; Taking the image acquisition device of the follower robot as the origin, a coordinate system is established, and the established coordinate system is converted into a pixel coordinate system; the pixel value of the leader robot on the pixel plane is determined in the pixel coordinate system; Determine the direction between the follower robot and the navigator robot based on the pixel value, and determine the distance between the follower robot and the navigator robot based on the voice signal transmission time; Tracking control is performed according to the determined direction and distance.

2. A multi-robot team formation and tracking control method as claimed in claim 1, characterized in that: The navigator robot continuously emits sound signals at a preset frequency. The content of the sound signal is the number of the navigator robot. The follower robot obtains the distance between the two preset microphones on the follower robot and the preset speaker on the navigator robot through sound ranging.

3. A multi-robot team formation and tracking control method as claimed in claim 2, characterized in that: Take the image acquisition of the follower robot as the origin and establish the coordinate system, Z C The axis is perpendicular to the imaging plane and points to the front of the image acquisition device. C The axis passes through the centers of the two microphones and points to the microphone on the right side of the robot's forward direction; the established coordinate system to pixel coordinate system transformation relationship is: Wherein, (X, Y, Z) is the position coordinate of the navigator robot in the image acquisition device coordinate system; (u, v) is the coordinate of the navigator robot in the pixel coordinate system; is the internal parameter of the image acquisition device, where f is the focal length of the camera, (c x , c y ) is the coordinate of the optical center of the image acquisition device in the pixel coordinate system.

4. A multi-robot team formation and tracking control method as claimed in claim 2, characterized in that: Connect the speaker on the navigator robot, the image acquisition device and the microphone on the follower robot to establish geometric relationships. Suppose the microphone on the right side of the follower robot is point A, the microphone on the left side is point B, and the speaker of the navigator robot is point C. According to the triangle cosine theorem, we can get: Assume that the optical center of the image acquisition device is point O. According to the law of cosines, the distance between the optical center of the image acquisition device and the navigator robot is expressed as: OC 2 =AC 2 +OA 2 -2·AC·OA·cosA; Obtain the pixel value u of the leader robot on the pixel plane:

5. A multi-robot team formation and tracking control method as claimed in claim 1, characterized in that: If the imaging point of the navigator robot is smaller than the coordinate value of the optical center of the image acquisition device in the pixel coordinate system, it means that the navigator robot is in front of the left of the follower robot, and the follower robot is controlled to turn left; if the imaging point of the navigator robot is larger than the coordinate value of the optical center of the image acquisition device in the pixel coordinate system, it means that the navigator robot is in front of the right of the follower robot, and the follower robot is controlled to turn right.

6. A multi-robot team formation and tracking control method as claimed in claim 5, characterized in that: When the follower robot turns to the navigator robot, the distance between the navigator robot and the follower robot is obtained by sound ranging through the navigator robot speaker and the follower robot microphone; the distance between the navigator robot and the follower robot is controlled to always remain at a preset value.

7. A multi-robot teaming and tracking control system, characterized in that: include: The data acquisition module is configured to: obtain voice signals of multiple robot numbers and image data of tracking robots; The team formation module is configured to: analyze the voice signal, use the subject in the voice signal as the number of the navigator robot, and the object as the number of the follower robot, to complete the team formation; wherein, for the follower robot for which the navigator robot does not exist in the image data, control the follower robot to rotate in a preset direction until the navigator robot appears in the image data; The pixel determination module is configured to: establish a coordinate system with the image acquisition device of the follower robot as the origin, and convert the established coordinate system into a pixel coordinate system; determine the pixel value of the leader robot on the pixel plane in the pixel coordinate system; The distance determination module is configured to: determine the direction between the follower robot and the navigator robot according to the pixel value, and determine the distance between the follower robot and the navigator robot according to the voice signal transmission time; The tracking control module is configured to perform tracking control according to the determined direction and distance.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps of the multi-robot team formation and tracking control method as described in any one of claims 1-6 are implemented.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and capable of running on the processor, characterized in that: When the processor executes the program, the steps of the multi-robot team formation and tracking control method as described in any one of claims 1-6 are implemented.

10. A computer program product, characterized in that The computer program product includes a computer program, and when the computer program is executed by a processor, the steps of the multi-robot team formation and tracking control method as described in any one of claims 1 to 6 are implemented.

Images