Multi-robot cooperative manure cleaning method and system and electronic equipment

Abstract

The invention provides a multi-robot cooperative manure cleaning method and system and electronic equipment. The system comprises a communication server subsystem, a driving robot subsystem, an inspection robot subsystem, a manure cleaning robot subsystem, a main controller system, an environment monitoring robot subsystem, a two-dimensional code positioning subsystem and a disinfection robot subsystem. The method comprises the following steps: acquiring environment information in a live pig breeding area and position information of at least one excrement through an inspection robot; acquiring a cleaning path of the excrement cleaning robot according to the environment information and the position information of the at least one excrement, wherein the cleaning path passes through the position of the excrement; and finally, the manure cleaning robot is controlled to clean manure in the pig breeding area based on the cleaning path. The excrement in the breeding area is automatically cleaned, so that the breeding convenience is improved, the working efficiency is improved, and the labor cost of breeding is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent breeding, and specifically relates to a multi-robot collaborative manure cleaning method and an electronic device. Background Art

[0002] In the current social breeding field, small-scale breeding industries are gradually decreasing, while large-scale breeding industries are on the rise. Intelligent breeding can provide services for livestock breeding through the new generation of Internet, mobile Internet, cloud storage, Internet of Things, intelligent acquisition terminals, etc., helping to transform and upgrade the modern livestock industry. Among them, in the field of pig breeding, intelligent breeding will greatly improve the convenience of raising pigs. However, cleaning the breeding area of pigs during the breeding process remains a difficult problem.

[0003] With the development of robot technology, the concepts of unmanned and intelligent operations are gradually maturing. However, the breeding area of pigs is an indoor environment, and it is impossible to achieve real-time positioning of the robots in the pen through satellite positioning. Moreover, most of the existing manure cleaning methods are single-robot operations in an exploration and mapping manner, with poor work efficiency. Summary of the Invention

[0004] Aiming at the deficiencies of the existing technology, the present invention proposes a multi-robot collaborative manure cleaning method and an electronic device to improve work efficiency.

[0005] In a first aspect, the present invention provides a multi-robot collaborative manure cleaning method. The multi-robot collaborative manure cleaning method is applied to a multi-robot collaborative manure cleaning device, and the multi-robot collaborative manure cleaning device includes manure cleaning robots, and includes: obtaining environmental information and the position information of at least one piece of manure in the pig breeding area; obtaining the cleaning path of the manure cleaning robots according to the environmental information and the position information of at least one piece of manure, and the cleaning range formed by the cleaning path includes the position where the manure is located; controlling the manure cleaning robots to clean the manure in the pig breeding area based on the cleaning path.

[0006] In an embodiment, the method further includes: judging whether there are dynamic obstacles in the pig breeding area according to the environmental information; if so, driving the dynamic obstacles in the pig breeding area;

[0007] Re-obtaining the environmental information of the pig breeding area after the driving treatment.

[0008] In an embodiment, the step of obtaining the cleaning path of the manure cleaning robots according to the environmental information and the position information of at least one piece of manure includes: constructing an environmental map of the pig breeding area according to the environmental information; performing area division on the environmental map of the pig breeding area to obtain a cleaning area; performing path planning processing in the cleaning area based on the position information of the manure to obtain the cleaning path of the manure cleaning robots.

[0009] In one embodiment, the environmental information includes two-dimensional code positioning information and image information. The steps of constructing an environmental map of the pig breeding area according to the environmental information include: determining the diagonal spatial position information of the boundary area of the pig breeding area according to the two-dimensional code positioning information; analyzing and processing the image information to obtain the position information of static obstacles; and performing map construction processing based on the diagonal spatial position information and the position information of static obstacles to obtain the environmental map of the pig breeding area.

[0010] In one embodiment, the steps of controlling the manure cleaning robot to clean the manure in the pig breeding area based on the cleaning path include: clustering the manure in the pig breeding area by using a manure clustering method to obtain manure clustering areas; controlling the manure cleaning robot to move along the cleaning path; picking up the manure in the manure clustering areas during the movement; obtaining the gas information after the manure cleaning robot finishes moving; obtaining the cleaning result of the pig breeding area according to the gas information after the manure cleaning robot finishes moving; and determining that the cleaning is completed in response to the cleaning result indicating that there is no manure in the pig breeding area.

[0011] In one embodiment, the gas information includes the gas type and the gas concentration corresponding to the gas type. The steps of obtaining the cleaning result of the pig breeding area according to the gas information after the manure cleaning robot finishes moving include: determining that the cleaning result is cleaning completed in response to the gas concentration corresponding to the gas type being less than or equal to the gas concentration threshold corresponding to the gas type; and determining that the cleaning result is cleaning not completed in response to the gas concentration corresponding to the gas type being greater than the gas concentration threshold corresponding to the gas type.

[0012] In one embodiment, after the steps of controlling the manure cleaning robot to clean the manure in the pig breeding area based on the cleaning path, the method further includes: disinfecting the disinfected area of the pig breeding area.

[0013] In a second aspect, the present invention provides a multi-robot collaborative manure cleaning system. The multi-robot collaborative manure cleaning system at least includes an inspection module, a control module, and a cleaning module. The multi-robot collaborative manure cleaning system includes: an inspection module, configured to obtain the environmental information and the position information of at least one piece of manure in the pig breeding area, and send the environmental information and the position information of at least one piece of manure to the control module; a control module, configured to obtain the cleaning path of the manure cleaning robot according to the environmental information and the position information of at least one piece of manure, the cleaning path passing through the position where the manure is located, and send a cleaning instruction including the cleaning path to the cleaning module; and a cleaning module, configured to, after receiving the cleaning instruction, control the manure cleaning robot to clean the manure in the pig breeding area based on the cleaning path.

[0014] In a third aspect, the present invention provides a multi-robot collaborative manure cleaning system, which is characterized in that the multi-robot collaborative manure cleaning system includes a communication server subsystem, a driving robot subsystem, an inspection robot subsystem, a manure cleaning robot subsystem, a main controller system, an environmental monitoring robot subsystem, a QR code positioning subsystem, and a disinfection robot subsystem; the communication server subsystem is used to provide communication services for each robot system; the driving robot subsystem is used to drive live pigs by driving robots; the inspection robot subsystem is used to collect environmental information of the live pig breeding area by inspection robots; the manure cleaning robot subsystem is used to clean the manure in the live pig breeding area by manure cleaning robots; the main controller system is used to detect the distribution of manure and other obstacles in the live pig breeding area, calculate the cleaning path of the manure cleaning robot, and send operation instructions; the environmental monitoring robot subsystem is used to obtain the environmental information of the live pig breeding area after cleaning by environmental detection robots; the QR code positioning subsystem is used to feedback the boundary information of the live pig breeding area and the positions of the robots in each operation, and feedback positioning information; the disinfection robot subsystem is used to disinfect the live pig breeding area after cleaning by disinfection robots, and feedback disinfection information.

[0015] In a fourth aspect, the present invention provides an electronic device, including a processor and a memory storing program instructions, and the processor is configured to execute the method as described above when running the program instructions.

[0016] As can be seen from the above technical solutions, the beneficial technical effects of the present invention are as follows:

[0017] 1. By obtaining the environmental information in the live pig breeding area and the position information of at least one piece of manure; then obtaining the cleaning path of the manure cleaning robot according to the environmental information and the position information of at least one piece of manure, and the cleaning path passes through the position where the manure is located; finally, controlling the manure cleaning robot to clean the manure in the live pig breeding area based on the cleaning path. Thus, by constructing a cleaning path passing through the position where the manure is located, and then controlling the manure cleaning robot to clean the manure according to the cleaning path, the manure in the breeding area can be automatically cleaned without human intervention, thereby improving the convenience of breeding, improving work efficiency, and reducing the labor cost of breeding.

[0018] 2. For an indoor environment such as a live pig breeding area, satellite positioning cannot be used to real-time feedback navigation information. The present application adopts a multi-robot collaborative method, which can help the manure cleaning robot improve the global information perception ability, and thus is beneficial to specifying the cleaning path and improving the cleaning efficiency.

[0019] 3. By constructing a collision buffer area in the environmental map of the live pig breeding area, dividing the cleaning area and planning the cleaning path within the cleaning area, the interference operation between multi-robot manure cleaning can be avoided, the independent functions of each robot can be realized, and the operation accuracy of the robot can be improved.

[0020] 4. Clustering the feces is beneficial to improving the working efficiency of the robot. Description of the Drawings

[0021] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following will briefly introduce the drawings required for the description of the specific embodiments or the prior art. In all the drawings, similar elements or parts are generally identified by similar reference numerals. In the drawings, the elements or parts are not necessarily drawn to scale.

[0022] Figure 1 is a schematic flowchart of an exemplary embodiment of the multi-robot collaborative feces cleaning method shown in the present application;

[0023] Figure 2 is a schematic plan view of an exemplary embodiment of the pig breeding area shown in the present application;

[0024] Figure 3 is a schematic plan view of an exemplary embodiment of the cleaning area shown in the present application;

[0025] Figure 4-A is a schematic plan view of an exemplary embodiment of the cleaning path shown in the present application;

[0026] Figure 4-B is a schematic diagram of feces of an exemplary embodiment shown in the present application;

[0027] Figure 5 is a flowchart of an exemplary embodiment of the multi-robot collaborative feces cleaning method shown in the present application;

[0028] Figure 6 is a flowchart of another exemplary embodiment of the multi-robot collaborative feces cleaning method shown in the present application;

[0029] Figure 7 is a block diagram of an exemplary embodiment of the multi-robot collaborative feces cleaning system shown in the present application;

[0030] Figure 8 is a block diagram of another exemplary embodiment of the multi-robot collaborative feces cleaning system shown in the present application;

[0031] Figure 9 is a schematic structural diagram of an embodiment of an electronic device shown in the present application;

[0032] Figure 10 is a schematic structural diagram of an embodiment of a computer-readable storage medium shown in the present application. Detailed Embodiments

[0033] The embodiments of the technical solution of the present invention will be described in detail below with reference to the accompanying drawings. The following embodiments are only used to illustrate the technical solution of the present invention more clearly, so they are only examples and cannot be used to limit the protection scope of the present invention.

[0034] It should be noted that, unless otherwise specified, the technical terms or scientific terms used in this application should have the ordinary meanings understood by those skilled in the art to which the present invention belongs. The terms "first", "second", etc. in the description and claims of the embodiments of the present disclosure and the above drawings are used to distinguish similar objects, and do not have to be used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged under appropriate circumstances so as to implement the embodiments of the present disclosure described herein. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusions. Unless otherwise specified, the term "plurality" means two or more. In the embodiments of the present disclosure, the character " / " means that the objects before and after are in an "or" relationship. For example, A / B means: A or B. The term "and / or" is a description of the association relationship of an object, indicating that three relationships can exist. For example, A and / or B means: A or B, or, the three relationships of A and B. The term "corresponding" may refer to an association relationship or a binding relationship. A corresponding to B means that there is an association relationship or a binding relationship between A and B.

[0035] First of all, it should be noted that in the current social breeding field, small-scale breeding industries are gradually decreasing, and large-scale breeding industries are emerging. Smart breeding can provide services for livestock breeding through the new generation of Internet, mobile Internet, cloud storage, Internet of Things, intelligent acquisition terminals, etc., helping to transform and upgrade the modern livestock industry. Among them, in the field of pig breeding, smart breeding will greatly improve the convenience of breeding pigs.

[0036] Currently, in the process of pig breeding, cleaning the breeding area of pigs is still a difficult problem and usually requires manual cleaning. Therefore, there is an urgent need for a method that can automatically clean the pig manure in the breeding area.

[0037] Based on this, the present application provides a multi-robot collaborative manure cleaning method, system, and electronic device. The execution subject of a multi-robot collaborative manure cleaning method can be a terminal device, a server, or other processing devices. Among them, the terminal device can be a computer, a mobile device, a terminal, a computing device, a vehicle-mounted device, etc. The execution subject of the multi-robot collaborative manure cleaning method can also be a multi-robot collaborative manure cleaning device. In some possible implementation manners, the multi-robot collaborative manure cleaning method can be implemented by a processor calling computer-readable instructions stored in a memory. The execution subject of the multi-robot collaborative manure cleaning method can also be a big data cluster. A big data cluster is a computer system architecture formed by connecting multiple computers through a network. The big data cluster can be deployed on a private cloud built by K8S (Kubernetes, a container orchestration engine).

[0038] Combined with Figure 1 As shown, this embodiment provides a multi-robot collaborative manure cleaning method. The multi-robot collaborative manure cleaning method is applied to a multi-robot collaborative manure cleaning device. The multi-robot collaborative manure cleaning device includes manure cleaning robots, and includes:

[0039] Step S110: Obtain the environmental information and the position information of at least one manure in the pig breeding area through an inspection robot.

[0040] The pig breeding area is an area for breeding organisms. The pig breeding area can be a pig breeding region.

[0041] Such as Figure 2 As shown, the pig breeding area can include 2 breeding sub-areas. The length and width of the breeding sub-areas are 30000mm and 9080mm respectively. The floor of the breeding sub-areas is formed by splicing a solid cement floor and a wire mesh floor. The width of the wire mesh floor is 4300mm. Each breeding sub-area is divided into multiple small compartments. The left breeding sub-area includes small compartments B1, B2, B3, B4, and B5. The right breeding sub-area includes small compartments A1, A2, A3, A4, and A5. The length of one small compartment is 6000mm, and the length of two small compartments is 12000mm. Each small compartment is provided with a double-sided feeding trough and a drinking bowl inside the wall.

[0042] The environmental information can include the environmental image of the pig breeding area. The environmental image includes breeding equipment information and boundary information. The environmental information can also include the environmental image of the pig breeding area and QR code positioning information. The environmental image includes breeding equipment information. The environmental image can be an RGBD image. The QR code positioning information includes boundary information. Among them, the breeding equipment information is a static obstacle and can include drinking devices, feeding troughs, etc.

[0043] Feces are objects waiting to be cleaned in the pig breeding area. The feces can be the feces of breeding organisms, such as pig manure, or other objects to be cleaned, such as garbage, etc.

[0044] Location information refers to the information about the location where the feces are located.

[0045] The multi-robot collaborative feces cleaning device obtains the environmental information in the pig breeding area and the location information of at least one feces. Specifically, the multi-robot collaborative feces cleaning device uses a shooting device to take pictures of the pig breeding area to obtain an environmental image, performs image analysis on the environmental image to obtain the breeding equipment information in the pig breeding area and the location information of at least one feces, and scans the two-dimensional code at a preset position in the pig breeding area through a scanning device to obtain the two-dimensional code positioning information. Among them, the shooting device can be a depth camera, and the preset position can be on the boundary of the pig breeding area. For example, the two-dimensional codes are set at the four diagonal spatial positions of the pig breeding area.

[0046] Furthermore, before the multi-robot collaborative feces cleaning device obtains the environmental information in the pig breeding area and the location information of at least one feces, it also includes: driving away the dynamic obstacles in the pig breeding area. Among them, the dynamic obstacles can include breeding organisms, staff, robots, etc.

[0047] Furthermore, the multi-robot collaborative feces cleaning device performs image analysis on the environmental image to obtain an analysis result; in response to the analysis result including dynamic obstacles, it drives away the dynamic obstacles again.

[0048] In one embodiment, the multi-robot collaborative feces cleaning device includes a driving robot and an inspection robot. The inspection robot is installed on the moving track at the roof of the pig breeding area, and a depth camera is installed on the surface of the inspection robot facing the pig breeding area. The multi-robot collaborative feces cleaning device controls the driving robot to perform sound driving and physical driving on the dynamic obstacles in the pig breeding area, and returns to the initial position after the driving ends. Among them, the sound driving includes playing a preset attracting audio to attract the breeding organisms to leave the pig breeding area, playing a preset warning audio to notify the staff and robots to leave the pig breeding area, or sending a leaving instruction to the robot. The physical driving includes moving to the position of the dynamic obstacle and pushing it to leave the pig breeding area; the inspection robot moves to the center of the pig breeding area and obtains an image of the pig breeding area from top to bottom through the depth camera to obtain an environmental image.

[0049] Step S120: Obtain the cleaning path of the feces cleaning robot according to the environmental information and the location information of at least one feces, and the cleaning range formed by the cleaning path includes the location where the feces are located.

[0050] The cleaning path refers to the path used by the manure cleaning robot to clean the manure. When the manure cleaning robot moves along the cleaning path, the cleaning range of the manure cleaning robot includes all the manure.

[0051] The multi-robot collaborative manure cleaning device obtains the cleaning path of the manure cleaning robot according to the environmental information and the position information of at least one piece of manure. Specifically, the multi-robot collaborative manure cleaning device performs image analysis and processing on the environmental image to obtain the breeding equipment information and the QR code positioning information; identifies the QR code positioning information to obtain the boundary information of the live pig breeding area; draws the environmental map of the live pig breeding area according to the breeding equipment information and the boundary information; plans the cleaning path passing through the position where the manure is located on the environmental map. The environmental map can be a two-dimensional plane map, and the two-dimensional plane map includes the boundary of the live pig breeding area, breeding equipment, and manure.

[0052] Step S130, control the manure cleaning robot to clean the manure in the live pig breeding area based on the cleaning path.

[0053] The manure cleaning robot can be a mobile robot with a wheeled motion structure and a cleaning mechanism. Among them, the manure cleaning robot can be a manure cleaning robot used for cleaning manure.

[0054] The multi-robot collaborative manure cleaning device controls the manure cleaning robot to clean the manure in the live pig breeding area based on the cleaning path. Specifically, the multi-robot collaborative manure cleaning device controls the manure cleaning robot to move along the cleaning path, and when it reaches the nearest manure, controls the cleaning end of the manure cleaning robot to clean the manure until it moves to the end of the cleaning path and the cleaning ends.

[0055] As an example, the multi-robot collaborative manure cleaning device determines the operation instruction information of the current position according to the cleaning path, sends the operation instruction information of the current position to the manure cleaning robot. After receiving the operation instruction information of the current position, the manure cleaning robot moves from the current position to the next moving position in the moving direction according to the next moving position and the moving direction in the operation instruction information. In an embodiment, the multi-robot collaborative manure cleaning device converts each moving position and moving direction in the cleaning path on the two-dimensional plane map into the actual map to obtain the next moving position and moving direction corresponding to each current moving position in the actual map, and determines the position value corresponding to each next moving position and the moving value corresponding to the moving direction in the preset array mapping table according to the next moving position and the moving direction corresponding to each current moving position; combines the position values and moving values corresponding to each current position into an array sequence and sends it to the manure cleaning robot as the operation instruction information.

[0056] It can be seen that by obtaining the environmental information in the pig breeding area and the position information of at least one feces; then obtaining the cleaning path of the manure cleaning robot according to the environmental information and the position information of at least one feces, and the cleaning path passes through the position where the feces are located; finally, controlling the manure cleaning robot to clean the feces in the pig breeding area based on the cleaning path. Thus, by constructing a cleaning path passing through the position where the feces are located, and then controlling the manure cleaning robot to clean the feces according to the cleaning path, the automatic cleaning of the feces in the breeding area is realized, thereby improving the convenience of breeding and reducing the labor cost of breeding.

[0057] Optionally, before the step of obtaining the cleaning path of the manure cleaning robot according to the environmental information and the position information of at least one feces, the method further includes: in response to the environmental information indicating the presence of dynamic obstacles in the pig breeding area, driving the dynamic obstacles in the pig breeding area; and re-obtaining the environmental information of the pig breeding area after the driving process. Thus, by driving the dynamic obstacles, the interference items for cleaning are reduced and the cleaning success rate is improved.

[0058] In one embodiment, the multi-robot collaborative manure cleaning device performs image analysis processing on a continuous multi-frame environmental image to obtain dynamic obstacles; drives the dynamic obstacles according to the driving method corresponding to the type of the dynamic obstacles, and re-collects the environmental information. For example, if the type of the dynamic obstacle is a breeding organism, the method of sound attraction is adopted; if the type of the dynamic obstacle is a person, the method of voice warning is adopted; if the type of the dynamic obstacle is a robot, the method of sending an instruction is adopted.

[0059] Furthermore, the multi-robot collaborative manure cleaning device obtains the cleaning path of the manure cleaning robot by using the re-obtained environmental information of the pig breeding area after the driving process and the position information of at least one feces; and controls the manure cleaning robot to clean the feces in the pig breeding area based on the cleaning path.

[0060] Optionally, the step of obtaining the cleaning path of the manure cleaning robot according to the environmental information and the position information of at least one feces includes: constructing an environmental map of the pig breeding area according to the environmental information; performing area division on the environmental map of the pig breeding area to obtain a cleaning area; and performing path planning processing in the cleaning area based on the position information of the feces to obtain the cleaning path of the manure cleaning robot.

[0061] Optionally, the step of obtaining the cleaning path of the manure cleaning robot according to the environmental information and the position information of at least one feces includes: constructing an environmental map of the pig breeding area according to the environmental information; performing path planning processing in the cleaning area of the environmental map based on the position information of the feces to obtain the cleaning path of the manure cleaning robot.

[0062] The cleaning area refers to the area waiting to be cleaned. Specifically, the multi-robot collaborative manure cleaning device obtains the collision buffer area when the manure cleaning robot moves in the environmental map according to the size information of the manure cleaning robot; and determines the cleaning area based on the collision buffer area.

[0063] The collision buffer area refers to the area to avoid the collision of the manure cleaning robot. The collision buffer area is the area expanded outside the occupied area of the manure cleaning robot with the center point of the pig breeding area as the reference position. Specifically, the multi-robot collaborative manure cleaning device draws a moving window according to the length and width in the size information, and at the center point of the center point of the pig breeding area, the rectangular area formed by moving the moving window is used as the collision buffer area when at least two manure cleaning robots move in the environmental map.

[0064] In one embodiment, as Figure 3 shown, two-dimensional codes 1, 2, 3, 4, 5, and 6 are respectively set at six diagonals of the pig breeding area. At the center position of the left area of the pig breeding area, a collision buffer area is set according to the length of the manure cleaning robot and the length of the pig breeding area. The left space of the pig breeding area is divided into two cleaning areas through the collision buffer area. Then each cleaning area is divided into 4 sub-areas, and each sub-area is cleaned in the order of R1 - R2 - R3 - R4, and each sub-area is also cleaned in the order of r1 - r2 - r3 - r4. Similarly, the right area of the pig breeding area is used as the next cleaning area to obtain the cleaning order in the same way as the acquisition method of the cleaning order of the left area.

[0065] Optionally, the steps of constructing the environmental map of the pig breeding area according to the environmental information include: determining the diagonal spatial position information of the boundary area of the pig breeding area according to the two-dimensional code positioning information; analyzing and processing the image information to obtain the position information of the static obstacles; and performing map construction processing based on the diagonal spatial position information of the boundary area of the pig breeding area and the position information of the static obstacles to obtain the environmental map of the pig breeding area.

[0066] In one embodiment, a preset image analysis algorithm is used to analyze and process the environmental image to obtain the position information of each static obstacle in the pig breeding area. Each static obstacle is other obstacles except manure, and the static obstacle can be breeding equipment.

[0067] In one embodiment, the multi-robot collaborative manure cleaning device performs image analysis and processing on environmental images to obtain aquaculture equipment information, where the aquaculture equipment information includes the positions and sizes of each aquaculture equipment; taking the depth camera image coordinates as a reference, the boundary positions, the positions of the aquaculture equipment, and the positions of the manure are obtained; in the camera coordinate system, the boundary of the pig breeding area is drawn according to the boundary positions, each aquaculture equipment is drawn according to the size of each aquaculture equipment, and each aquaculture equipment and manure are placed at the positions of the aquaculture equipment within the boundary to obtain the environmental map of the pig breeding area.

[0068] Optionally, the step of controlling the manure cleaning robot to clean the manure in the pig breeding area based on the cleaning path includes: clustering the manure in the pig breeding area by using the manure clustering method to obtain the manure clustering area; controlling the manure cleaning robot to move according to the cleaning path; picking up the manure in the manure clustering area during the movement; obtaining the gas information after the manure cleaning robot finishes moving; obtaining the cleaning result of the pig breeding area according to the gas information after the manure cleaning robot finishes moving; and determining that the cleaning is completed in response to the cleaning result indicating that there is no manure in the pig breeding area.

[0069] In one embodiment, as Figure 4-B shown, the multi-robot collaborative manure cleaning device identifies the manure through the deep learning method, and obtains the spatial coordinates of the four vertices of the annotation box, which are (X max , Y min ), (X mix , Y min ), (X mix , Y man ), (X max , Y man ). An inscribed circle is constructed within the annotation box, and the center of the inscribed circle is used as the target point coordinates. As Figure 4-A shown, each manure is respectively P1(X1, Y1), P2(X2, Y2), P3(X3, Y3), P4(X4, Y4). Taking the target point coordinates as the input, the optimal order of cleaning these four points is calculated, and the existing algorithm is used to solve the cleaning path with the minimum cost function, where the cost function can be the following formula:

[0070] f(n) = w ij ∑T c (P i , P j )

[0071]

[0072] In the above formula, f(n) is the cost function, T C is the Euclidean distance between two points, and W ij is P i , Pj The weight, which is formulated according to the regional relationship between the cleaning points and is assigned according to the cleaning sequence of R1 - R2 - R3 - R4.

[0073] Optionally, the steps of controlling the manure cleaning robot to clean the manure in the pig breeding area based on the cleaning path include: controlling the manure cleaning robot to move along the cleaning path and pick up the manure during the movement; obtaining the gas information after the manure cleaning robot finishes moving; obtaining the cleaning result of the pig breeding area according to the gas information after the manure cleaning robot finishes moving; and determining that the cleaning is completed in response to the cleaning result indicating that there is no manure in the pig breeding area.

[0074] In one embodiment, as shown in Figure 4-A The multi - robot collaborative manure cleaning device divides the pig breeding area into two cleaning areas with the collision buffer zone as the boundary; the multi - robot collaborative manure cleaning device may include two manure cleaning robots, and the two manure cleaning robots start cleaning from the starting points X c1 、Y c1 and the starting points X c2 、Y c2 respectively. The multi - robot collaborative manure cleaning device may also include only one manure cleaning robot, and this manure cleaning robot starts cleaning from the starting points Xc1, Yc1 and the starting points Xc2, Yc2 in sequence. The manure can be marked manure, and the multi - robot collaborative manure cleaning device formulates the operation routes of the manure cleaning robots respectively according to the principle of the minimum operation path; the principle of the minimum operation path refers to the strategy of the shortest operation path without collision for the manure cleaning robot in the cleaning area, specifically including clustering and dividing the areas with manure and the areas with other obstacles except manure, taking the spatial coordinates of the clustering center as the input quantity, combining with the spatial coordinates of the starting point position, and formulating an operation route that bypasses the obstacles and traverses all the manure based on the shortest path to obtain the cleaning path, such as the cleaning path passing through the manure P1, P2, P3 and P4 in the left cleaning area.

[0075] In one embodiment, as shown in Figure 3 The multi - robot collaborative manure cleaning device obtains the spatial coordinates (x1, y1), (x2, y2), (x3, y3), (x4, y4) of four two - dimensional codes, and these four coordinates are in the camera coordinate system with the base coordinates, and the camera coordinate system is as shown in Figure 4-B Taking the center coordinate of the two - dimensional code 2 in Figure 3 as the origin, the line connecting the origin of the two - dimensional code 2 to the origin of the two - dimensional code 1 as the y - axis, and the line connecting the origin of the two - dimensional code 2 to the origin of the two - dimensional code 3 as the x - axis, a coordinate system is constructed as shown in Figure 4-AAs shown in the figure, calculate the center coordinates [x3 - x2, y1 - y2] inside the pig breeding area. With the center coordinates inside the circle as a reference, construct a collision area, which is a rectangle with coordinates [(x3 - x2 - l / 2), (y1 - y2)], [(x3 - x2 + l / 2), (y1 - y2)], [(x3 - x2 - l / 2), 0] and [(x3 - x2 + l / 2), 0]; where l is the width of the manure cleaning robot. The collision area is a rectangle, which divides the cleaning area into two areas. Similarly, construct a collision buffer zone in the same way to form the cleaning areas of multiple manure cleaning robots. As Figure 3 shown in the figure, taking two cleaning areas as an example, each cleaning area is divided into four small parts R1, R2, R3, and R4.

[0076] Optionally, the gas information includes the gas type and the gas concentration corresponding to the gas type. The steps of obtaining the cleaning result of the pig breeding area according to the gas information after the manure cleaning robot finishes moving include: in response to the gas concentration corresponding to the gas type being less than or equal to the gas concentration threshold corresponding to the gas type, determining that the cleaning result is cleaning completed; in response to the gas concentration corresponding to the gas type being greater than the gas concentration threshold corresponding to the gas type, determining that the cleaning result is cleaning not completed.

[0077] The gas types at least include ammonia, hydrogen sulfide, carbon dioxide, and methane generated by feces, etc.

[0078] In one embodiment, the multi-robot collaborative manure cleaning device detects the gas in the pig breeding area after cleaning through an environmental detection robot, and obtains the current ammonia concentration, hydrogen sulfide concentration, carbon dioxide concentration, and methane concentration in the pig breeding area. Compare the ammonia concentration with the preset ammonia concentration threshold, compare the hydrogen sulfide concentration with the preset hydrogen sulfide concentration threshold, compare the carbon dioxide concentration with the preset carbon dioxide concentration threshold, and compare the methane concentration with the preset methane concentration threshold; when the ammonia concentration is less than or equal to the preset ammonia concentration threshold, the hydrogen sulfide concentration is less than or equal to the preset hydrogen sulfide concentration threshold, the carbon dioxide concentration is less than or equal to the preset carbon dioxide concentration threshold, and the methane concentration is less than or equal to the preset methane concentration threshold, it is determined that all the feces in the pig breeding area have been cleaned, otherwise there is feces.

[0079] Optionally, after the step of controlling the manure cleaning robot to clean the feces in the pig breeding area based on the cleaning path, the method further includes: disinfecting the disinfection area of the pig breeding area.

[0080] The disinfection area can be walls, floors, railings, feeding troughs, water troughs, etc.

[0081] In one embodiment, the multi-robot collaborative manure cleaning device uniformly sprays disinfectant liquid onto disinfection areas such as walls, floors, railings, feeding troughs, and water troughs through a spraying device to achieve disinfection treatment of the pig breeding area. Thereby, the bacteria in the pig breeding area can be reduced, which is beneficial to improving the breeding success rate.

[0082] Furthermore, the disinfection starting point and the gas detection starting point in the pig breeding area are located outside the cleaning area of the pig breeding area.

[0083] In one embodiment, as shown in Figure 5 the multi-robot collaborative manure cleaning device drives dynamic obstacles including breeding organisms out of the pig breeding area through a driving robot; obtains environmental images and two-dimensional code positioning information of the pig breeding area through an inspection robot; analyzes and processes the environmental images and two-dimensional code positioning information through a main controller to construct an environmental map and obtain the manure distribution, and plans the cleaning path of the manure cleaning robot based on the cleaning area of the environmental map; cleans the pig breeding area through the manure cleaning robot; collects information of the cleaned pig breeding area through an environmental monitoring robot to obtain gas information; evaluates the cleaning qualification degree of the pig breeding area according to the gas information, and re-cleans when the evaluation result is unqualified, and when the evaluation result is qualified, performs spray disinfection treatment on the disinfection area of the pig breeding area through a disinfection robot. Thereby, the multi-robot collaborative manure cleaning device realizes multi-robot collaborative cleaning of the pig breeding area, achieves automation, and greatly improves the convenience of breeding.

[0084] In one embodiment, Figure 6 is a flowchart of pig manure cleaning. As shown in Figure 6As shown in the figure, the multi-robot collaborative manure cleaning device includes a pig driving robot, an inspection robot, a main controller, a manure cleaning robot, an environment detection robot, and a disinfection robot. The multi-robot collaborative manure cleaning device triggers the pig driving robot to obtain a remote control movement instruction to drive the pigs in the pig breeding area. After the driving work is completed, it controls the pig driving robot to return to the initial position; it controls the inspection robot to move to a preset position, obtains the environmental information of the pig breeding area, and obtains dynamic obstacle, static obstacle, and QR code positioning information based on the environmental information; it determines whether there is a dynamic obstacle. If so, it returns to control the pig driving robot to perform a driving operation. If not, it controls the main controller to obtain the boundary information of the pig breeding area, constructs a two-dimensional map coordinate system, calculates the collision buffer area, and divides the cleaning area; it obtains the distribution spatial position information of the pig manure in the pig breeding area, constructs a circumcircle including the manure; it constructs a two-dimensional environmental map in the two-dimensional map coordinate system and plans the cleaning path. The multi-robot collaborative manure cleaning device controls the manure cleaning robot to traverse the movement trajectory where the cleaning path is located, obtains the array sequence corresponding to the movement route, and the array sequence includes the next moving position and the moving direction; after the manure cleaning robot moves, it determines whether the manure cleaning robot has moved to the target position. If not, it returns to obtain the array sequence corresponding to the movement route. If so, it starts the cleaning operation. The multi-robot collaborative manure cleaning device controls the inspection robot to feedback the current position of the manure cleaning robot and perform motion compensation. The multi-robot collaborative manure cleaning device determines whether the manure cleaning robot has completed the trajectory traversal. If not, it returns to the step of obtaining the array sequence corresponding to the movement route. If so, it controls the manure cleaning robot to move to the initial position. The multi-robot collaborative manure cleaning device controls the environment detection robot to obtain the environmental information of the cleaning area, controls the inspection robot to obtain the distribution of pig manure in the cleaning area, determines whether the cleaning area meets the cleaning standard. If not, it returns to the step of obtaining the array sequence corresponding to the movement route. If so, it controls the disinfection robot to disinfect the pig breeding area.

[0085] Combined with Figure 7 As shown in the figure, the present invention provides a multi-robot collaborative manure cleaning system. The multi-robot collaborative manure cleaning system at least includes an inspection module 710, a control module 720, and a cleaning module 730. The multi-robot collaborative manure cleaning system includes: an inspection module 710, which is used to obtain the environmental information and the position information of at least one manure in the pig breeding area, and send the environmental information and the position information of at least one manure to the control module 720; a control module 720, which is used to obtain the cleaning path of the manure cleaning robot according to the environmental information and the position information of at least one manure, the cleaning path passes through the position where the manure is located, and send the cleaning instruction including the cleaning path to the cleaning module 730; a cleaning module 730, which is used to control the manure cleaning robot to clean the manure in the pig breeding area based on the cleaning path after receiving the cleaning instruction.

[0086] Among them, the functions of each module can be referred to in the embodiments of the multi-robot collaborative manure cleaning method, which will not be elaborated here.

[0087] The multi-robot collaborative manure cleaning system obtains the environmental information in the pig breeding area and the position information of at least one piece of manure; then obtains the cleaning path of the manure cleaning robot according to the environmental information and the position information of at least one piece of manure, and the cleaning path passes through the position where the manure is located; finally, controls the manure cleaning robot to clean the manure in the pig breeding area based on the cleaning path. Thus, by constructing a cleaning path passing through the position where the manure is located and then controlling the manure cleaning robot to clean the manure according to the cleaning path, the manure in the breeding area can be automatically cleaned, thereby improving the convenience of breeding and reducing the labor cost of breeding.

[0088] Combined with Figure 8 As shown, the multi-robot collaborative manure cleaning system includes a communication server subsystem, which is respectively connected to a driving robot subsystem, an inspection robot subsystem, a manure cleaning robot subsystem, a main controller system, an environmental monitoring robot subsystem, a QR code positioning subsystem, and a disinfection robot subsystem. The main controller system is connected to the driving robot subsystem, the inspection robot subsystem, the environmental monitoring robot subsystem, and the disinfection robot subsystem through the communication server subsystem.

[0089] Optionally, the communication server subsystem is used to provide communication services for each robot system. Specifically, the communication server subsystem communicates with the industrial control computer modules of each robot subsystem through WIFI and communicates with the communication modules of the main controller system and the QR code positioning subsystem.

[0090] Optionally, the driving robot subsystem is used to drive the breeding organisms. Specifically, the driving robot subsystem includes a driving robot, an industrial control computer module, a driving end effector module, and a binocular camera module. The driving robot subsystem is also used to receive the operation instructions sent by the communication server subsystem and send driving information.

[0091] Optionally, the inspection robot subsystem is used to collect the environmental information in the pig breeding area and feedback inspection information. Specifically, the inspection robot subsystem includes an inspection robot, an industrial control computer module, and a depth camera module.

[0092] Optionally, the manure cleaning robot subsystem is used to clean the manure in the pig breeding area and feedback cleaning information. Specifically, the manure cleaning robot subsystem includes a manure cleaning robot, an industrial control computer module, a cleaning end effector module, a ranging module, and a collision detection module.

[0093] Optionally, the main controller system is used to detect the distribution of feces and other obstacles in the pig breeding area, calculate the cleaning path of the manure cleaning robot, and send operation instructions. The main controller system issues motion instructions and obtains perception information for the driving robot subsystem, the inspection robot subsystem, the manure cleaning robot subsystem, the environmental monitoring robot subsystem, the two-dimensional code positioning subsystem, and the disinfection robot subsystem respectively through the communication server subsystem. Specifically, the main controller system includes an information collection module, a target detection module, a to-be-cleaned area planning module, a motion control module, a path planning module, and a communication module.

[0094] Among them, the target detection module is used to process the environmental images sent by the inspection robot subsystem, specifically including the recognition of dynamic obstacles, static obstacles, and feces distribution areas in the images; the to-be-cleaned area planning module is used to construct a two-dimensional environmental map and a collision buffer area according to the boundary information obtained by the information collection module and the target recognition information of the target detection module, and divide the to-be-cleaned area; the path planning module is used to plan the cleaning paths of each manure cleaning robot in the cleaning area, as well as the fixed operation paths of the inspection robot, the disinfection robot, and the environmental detection robot; the motion control module is used to send operation path instructions to the industrial control computer modules of each robot subsystem to control the operation of each robot.

[0095] Optionally, the environmental monitoring robot subsystem is used to obtain the environmental information of the pig breeding area after cleaning. The environmental monitoring robot subsystem includes an environmental detection robot, an industrial control computer module, and an environmental detection sensor module.

[0096] Optionally, the two-dimensional code positioning subsystem is used to feedback the boundary information of the pig breeding area and the positions of the robots in each operation, and feedback the positioning information. The two-dimensional code positioning subsystem real-time feeds back the position information of the pig breeding area and the motion pose information of the robots to the main controller through the communication server subsystem. The two-dimensional code positioning subsystem includes a two-dimensional code module and a communication module.

[0097] Optionally, the disinfection robot subsystem is used to disinfect the pig breeding area after cleaning and feedback the disinfection information. The disinfection robot subsystem includes a disinfection robot, an industrial control computer module, and a disinfection spray execution module.

[0098] To implement the multi-robot collaborative manure cleaning method of the above embodiments, the present application proposes another electronic device. For details, please refer to Figure 9 , Figure 9 is a schematic structural diagram of an embodiment of the electronic device provided by the present application.

[0099] The electronic device 900 includes a memory 901 and a processor 902. Among them, the memory 901 and the processor 902 are coupled.

[0100] The memory 901 is used to store program data, and the processor 902 is used to execute the program data to implement the multi-modal based object category detection method of the above embodiments.

[0101] In this embodiment, the processor 902 can also be referred to as a CPU (Central Processing Unit). The processor 902 may be an integrated circuit chip with signal processing capabilities. The processor 902 can also be a general-purpose processor, a digital signal processor, an application-specific integrated circuit, a field-programmable gate array, or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. The general-purpose processor can be a microprocessor or the processor 902 can also be any conventional processor, etc.

[0102] This application also provides a computer-readable storage medium, such as Figure 10 shown, the computer-readable storage medium 1000 is used to store program data 1001, and when the program data 1001 is executed by the processor, it is used to implement the multi-modal based object category detection method in the method embodiments of this application.

[0103] Regarding the method involved in the multi-modal based object category detection method embodiment of this application, when it is implemented and exists in the form of a software functional unit and is sold or used as an independent product, it can be stored in a device, such as a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor to execute all or part of the steps of the methods in various embodiments of the present invention. The aforementioned storage medium includes: USB flash drives, mobile hard disks, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks, or optical discs, etc., which can store program codes.

[0104] Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit them; although the present invention 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 on some or all of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the various embodiments of the present invention, and they should all be covered by the scope of the claims and the description of the present invention.

Claims

1. A multi-robot collaborative manure cleaning method, characterized in that, Applied to a multi-robot collaborative manure cleaning device, the multi-robot collaborative manure cleaning device includes a manure cleaning robot and an inspection robot, and includes: Obtain the environmental information in the pig breeding area and the position information of at least one piece of manure through the inspection robot; Obtain the cleaning path of the manure cleaning robot according to the environmental information and the position information of the at least one piece of manure, and the cleaning range formed by the cleaning path includes the position where the manure is located; Control the manure cleaning robot to clean the manure in the pig breeding area based on the cleaning path.

2. The multi-robot collaborative manure cleaning method according to claim 1, wherein The method further includes: Judge whether there are dynamic obstacles in the pig breeding area according to the environmental information; If so, drive and process the dynamic obstacles in the pig breeding area; Re-obtain the environmental information of the pig breeding area after the driving and processing.

3. The multi-robot collaborative manure cleaning method according to claim 1, characterized in that The step of obtaining the cleaning path of the manure cleaning robot according to the environmental information and the position information of the at least one piece of manure includes: Construct an environmental map of the pig breeding area according to the environmental information; Perform area division on the environmental map of the pig breeding area to obtain a cleaning area; Perform path planning processing in the cleaning area based on the position information of the manure to obtain the cleaning path of the manure cleaning robot.

4. The multi-robot collaborative manure cleaning method according to claim 3, wherein, The environmental information includes two-dimensional code positioning information and image information. The step of constructing the environmental map of the pig breeding area according to the environmental information includes: Determine the diagonal spatial position information of the boundary area of the pig breeding area according to the two-dimensional code positioning information; Analyze and process the image information to obtain the position information of static obstacles; Perform map construction processing based on the diagonal spatial position information and the position information of static obstacles to obtain the environmental map of the pig breeding area.

5. The multi-robot collaborative manure cleaning method according to claim 1, wherein, The step of controlling the manure cleaning robot to clean the manure in the pig breeding area based on the cleaning path includes: Adopt a manure clustering method to cluster the manure in the pig breeding area to obtain a manure clustering area; Control the manure cleaning robot to move according to the cleaning path; Pick up the manure in the manure clustering area during the movement; Obtain the gas information after the manure cleaning robot finishes moving; Obtain the cleaning result of the pig breeding area according to the gas information after the manure cleaning robot finishes moving; Responding to the cleaning result indicating that there is no manure in the pig breeding area, determine that the cleaning is completed.

6. The multi-robot collaborative manure cleaning method according to claim 5, characterized in that, The gas information includes the gas type and the gas concentration corresponding to the gas type. The step of obtaining the cleaning result of the pig breeding area according to the gas information after the manure cleaning robot finishes moving includes: Responding to the gas concentration corresponding to the gas type being less than or equal to the gas concentration threshold corresponding to the gas type, determine that the cleaning result is cleaning completed; Responding to the gas concentration corresponding to the gas type being greater than the gas concentration threshold corresponding to the gas type, determine that the cleaning result is cleaning not completed.

7. The multi-robot collaborative manure cleaning method according to claim 1, wherein, After the step of controlling the manure cleaning robot to clean the manure in the pig breeding area based on the cleaning path, the method further includes: Disinfect the disinfection area of the pig breeding area.

8. A multi-robot collaborative manure cleaning system, characterized in that, The multi-robot collaborative manure cleaning system at least includes an inspection module, a control module, and a cleaning module. The multi-robot collaborative manure cleaning system includes: The inspection module is used to obtain the environmental information in the pig breeding area and the position information of at least one piece of manure, and send the environmental information and the position information of the at least one piece of manure to the control module; The control module is used to obtain the cleaning path of the manure cleaning robot according to the environmental information and the position information of the at least one piece of manure. The cleaning path passes through the position where the manure is located, and sends a cleaning instruction including the cleaning path to the cleaning module; The cleaning module is used to control the manure cleaning robot to clean the manure in the pig breeding area based on the cleaning path after receiving the cleaning instruction.

9. A multi-robot collaborative manure cleaning system, characterized in that, The multi-robot collaborative manure cleaning system includes a communication server subsystem, a driving robot subsystem, an inspection robot subsystem, a manure cleaning robot subsystem, a main controller system, an environmental monitoring robot subsystem, a two-dimensional code positioning subsystem, and a disinfection robot subsystem; The communication server subsystem is used to provide communication services for each robot system; The driving robot subsystem is used to drive pigs through driving robots; The inspection robot subsystem is used to collect the environmental information of the pig breeding area through inspection robots; The manure cleaning robot subsystem is used to clean the manure in the pig breeding area through manure cleaning robots; The main controller system is used to detect the distribution of manure and other obstacles in the pig breeding area, calculate the cleaning path of the manure cleaning robot, and send operation instructions; The environmental monitoring robot subsystem is used to obtain the environmental information of the pig breeding area after cleaning through environmental detection robots; The two-dimensional code positioning subsystem is used to feedback the boundary information of the pig breeding area and the positions of the robots in each operation, and feedback positioning information; The disinfection robot subsystem is used to disinfect the pig breeding area after cleaning through disinfection robots and feedback disinfection information.

10. An electronic device, comprising a processor and a memory storing program instructions, characterized in that, The processor is configured to execute the method according to any one of claims 1 to 7 when running the program instructions.

Images