Distributed robot cluster configuration method and system

Abstract

The invention discloses a distributed robot cluster configuration method and system, and belongs to the technical field of artificial intelligence, and the main points of the technical scheme are that the method comprises the steps: obtaining the total feeding amount and feeding time period of each first culture pond according to the fingerling type, fingerling growth stage and environmental parameters in each first culture pond in a preset region; according to the current moment and the feeding time period, multiple second culture ponds and the remaining feeding time of each second culture pond are determined; whether the intelligent bait casting robot can complete bait casting work within the remaining bait casting time or not is judged; if not, calling the idle robot from an adjacent area of the preset area to the preset area; according to the remaining bait casting time of each second culture pond, bait casting paths are configured for the intelligent bait casting robot and the idle robots, the optimal bait casting paths are configured for the intelligent bait casting robot and the idle robots on the basis of the remaining bait casting time and the path length, and bait casting work can be completed within the shortest time.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and more specifically to a distributed robot cluster configuration method and system. Background Art

[0002] With the development of aquaculture, the workload of feeders has gradually increased. In order to reduce the workload of feeders and improve the intelligence of feeding, feeders are usually used to feed the aquaculture objects in the prior art.

[0003] However, the feeding method in the prior art is usually based on a fixed feeding machine, and each fixed feeding machine can only solve the feeding problem of a single feeding water area. Therefore, when the farm is large and the number of feeding water areas is large, multiple feeding machines need to be configured, which requires high costs, so the prior art has shortcomings. Summary of the invention

[0004] In view of the shortcomings of the prior art, the purpose of the present invention is to provide a distributed robot cluster configuration method and system, which plans a feeding path for a feeding robot according to the remaining feeding time of each second breeding pond and the path length between the second breeding ponds, and completes the feeding work by a mobile feeding robot, thereby reducing the feeding cost compared to the prior art.

[0005] To achieve the above object, the present invention provides the following technical solutions:

[0006] This application provides a distributed robot cluster configuration method, including:

[0007] According to the fish species type, fish species growth stage and environmental parameters in each first breeding pond in the preset area, the total feeding amount and feeding time period of each first breeding pond are obtained, and each preset area corresponds to an intelligent feeding robot;

[0008] Determine, according to the current time and the feeding period, a plurality of second breeding ponds and the remaining feeding time of each of the second breeding ponds, wherein the second breeding pond is the first breeding pond that needs to be fed at the current time;

[0009] Determine whether the intelligent bait-feeding robot can complete the bait-feeding task within the remaining bait-feeding time;

[0010] If not, calling an idle robot from an adjacent area of ​​the preset area to the preset area;

[0011] According to the remaining feeding time of each of the second breeding ponds, a feeding path is configured for the intelligent feeding robot and the idle robot.

[0012] As a further improvement of the present invention, configuring a feeding path for the intelligent feeding robot and the idle robot according to the remaining feeding time of each of the second breeding ponds includes:

[0013] Dividing the plurality of second breeding ponds into a plurality of feeding areas according to the number of the intelligent feeding robots and the idle robots, each of the feeding areas corresponding to one of the intelligent feeding robots or one of the idle robots;

[0014] In each feeding area, determining the objective function and constraint conditions of the feeding path according to the remaining feeding time of each second breeding pond and the distance between each second breeding pond;

[0015] According to the objective function and the constraint conditions, the bait-feeding paths of the intelligent bait-feeding robot and the idle robot are obtained.

[0016] As a further improvement of the present invention, according to the objective function and the constraint conditions, the bait-feeding paths of the intelligent bait-feeding robot and the idle robot are obtained, including:

[0017] Taking the position of the intelligent feeding robot or the idle robot as the root node, selecting the first child node to the Nth child node for the root node according to the constraint condition, to obtain a plurality of first feeding paths, where N is the number of the second breeding ponds in each feeding area;

[0018] The bait feeding path is obtained according to the objective function and the plurality of first bait feeding paths.

[0019] As a further improvement of the present invention, the first child node to the second child node are selected for the root node according to the constraint condition. Subnodes, including:

[0020] Establish the first sub-node to the Preset conditions corresponding to the child nodes;

[0021] According to the first sub-node to the The preset conditions corresponding to the child nodes are to select the first child node to the Child nodes.

[0022] As a further improvement of the present invention, the objective function is determined according to the distance between each child node.

[0023] As a further improvement of the present invention, the step of judging whether the intelligent bait-feeding robot can complete the bait-feeding task within the remaining bait-feeding time includes:

[0024] According to the positions of the second breeding ponds and the intelligent feeding robot, calculating the distance between each of the second breeding ponds and the intelligent feeding robot and the distance between each of the second breeding ponds;

[0025] According to the remaining feeding time of each of the second breeding ponds, each of the second breeding ponds is sorted to obtain a feeding order;

[0026] Calculate the travel time required for the intelligent bait-feeding robot to reach each of the second breeding ponds according to the distance between each of the second breeding ponds and the intelligent bait-feeding robot, and the distance between each of the second breeding ponds;

[0027] According to the bait throwing sequence and the driving time, it is determined whether the intelligent bait throwing robot can complete the bait throwing task within the remaining bait throwing time.

[0028] As a further improvement of the present invention, the total feeding amount and feeding time period of each first breeding pond are obtained according to the fish species type, fish species growth stage and environmental parameters in each first breeding pond in the preset area, including:

[0029] Calculating the total weight of the fish in each first breeding pond according to the growth stage of the fish, the breeding density and the breeding area of ​​each first breeding pond;

[0030] Obtaining a total feeding amount for each first breeding pond according to the total weight of the fish species and the environmental parameters, wherein the environmental parameters include water temperature, pH value and dissolved oxygen content;

[0031] According to the total feeding amount, the fish type and the fish growth stage, the feeding time period of each first breeding pond and the feeding amount corresponding to the feeding time period of each first breeding pond are obtained.

[0032] As a further improvement of the present invention, the total amount of feed fed to each first breeding pond on that day is determined according to environmental parameters, feeding rate and the total weight of fish species in each first breeding pond, wherein the environmental parameters are determined by water temperature, pH value and dissolved oxygen content, and the total weight of fish species in each first breeding pond is determined according to the growth stage of the fish species in each first breeding pond, the breeding density of each first breeding pond and the breeding area of ​​each first breeding pond.

[0033] As a further improvement of the present invention, the intelligent feeding robot collects images of each second breeding pond through a camera while completing the feeding work to complete the inspection work.

[0034] The present invention provides a distributed robot cluster configuration system, comprising:

[0035] A calculation module, for obtaining the total feeding amount and feeding time period of each first breeding pond in a preset area according to the fish species type, fish species growth stage and environmental parameters in each first breeding pond, each preset area corresponds to an intelligent feeding robot, and according to the current time and the feeding time period, determining the remaining feeding time of multiple second breeding ponds and each of the second breeding ponds, the second breeding pond being the first breeding pond that needs to be fed at the current time;

[0036] A judgment module, used to judge whether the intelligent bait-feeding robot can complete the bait-feeding task within the remaining bait-feeding time, and if not, call an idle robot from an adjacent area of ​​the preset area to the preset area;

[0037] A configuration module is used to configure a feeding path for the intelligent feeding robot and the idle robot according to the remaining feeding time of each of the second breeding ponds.

[0038] The present invention can quickly determine whether the intelligent bait-feeding robot can complete the bait-feeding task through the bait-feeding algorithm and judgment logic, and timely call the idle robot to assist the intelligent bait-feeding robot when the intelligent bait-feeding robot cannot complete the bait-feeding task. Finally, the optimal bait-feeding path is configured for the intelligent bait-feeding robot and the idle robot through the objective function and constraint conditions to quickly complete the bait-feeding task. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 A flow chart of the method steps provided by the present invention;

[0040] Figure 2 This is the preliminary bait throwing sequence of the intelligent bait throwing robot;

[0041] Figure 3 The final bait throwing sequence of the intelligent bait throwing robot;

[0042] Figure 4 This is a schematic diagram of the baiting area;

[0043] Figure 5 A schematic diagram of the steps for selecting a bait casting path;

[0044] Figure 6 This is a schematic diagram of the system structure provided by the present invention. DETAILED DESCRIPTION

[0045] The technical solution of the present invention is described in detail below through the accompanying drawings and specific embodiments. It should be understood that the embodiments of the present invention and the specific features in the embodiments are detailed descriptions of the technical solution of the present invention, rather than limitations of the technical solution of the present invention.

[0046] The term "and / or" in the following text is only a description of the association relationship between the associated objects, indicating that there can be three relationships. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " generally indicates that the associated objects before and after are in an "or" relationship.

[0047] like Figure 1 As shown, the embodiment of the present application provides a distributed robot cluster configuration method, including:

[0048] According to the fish species type, fish species growth stage and environmental parameters in each first breeding pond in the preset area, the total feeding amount and feeding time period of each first breeding pond are obtained, and each preset area corresponds to an intelligent feeding robot;

[0049] According to the current time and the feeding period, determining the remaining feeding time of the plurality of second breeding ponds and each second breeding pond, the second breeding pond being the first breeding pond that needs to be fed at the current time;

[0050] Determine whether the intelligent bait-feeding robot can complete the bait-feeding task within the remaining bait-feeding time;

[0051] If not, call an idle robot from an adjacent area of ​​the preset area to the preset area;

[0052] According to the remaining feeding time of each second breeding pond, a feeding path is configured for the intelligent feeding robot and the idle robot.

[0053] The method provided in this embodiment can call on idle robots to jointly complete the feeding task under the premise that a single robot cannot complete the feeding task, and configure the feeding path for the intelligent feeding robot and the idle robot according to the remaining feeding time of each second breeding pond, so that each robot can complete the feeding task under the optimal path.

[0054] Furthermore, this embodiment provides a step of determining whether the intelligent bait-feeding robot can complete the bait-feeding task within the remaining bait-feeding time, including:

[0055] According to the positions of the second breeding ponds and the intelligent feeding robot, the distance between each second breeding pond and the intelligent feeding robot and the distance between each second breeding pond are calculated;

[0056] According to the remaining feeding time of each second breeding pond, each second breeding pond is sorted to obtain a feeding order;

[0057] Calculate the travel time of the intelligent feeding robot to each second breeding pond according to the distance between each second breeding pond and the intelligent feeding robot, and the distance between each second breeding pond;

[0058] According to the bait feeding sequence and driving time, it is determined whether the intelligent bait feeding robot can complete the bait feeding task within the remaining bait feeding time.

[0059] Specifically, first according to the current time and bait casting period, in the above The first breeding pond is determined The remaining feeding time of each second breeding pond is then calculated, and each second breeding pond is sorted in ascending order according to the remaining feeding time to obtain a preliminary feeding order.

[0060] Then the initial feeding sequence was tested for collinearity, and the feeding sequence of the second culture pond located on the same straight line was adjusted.

[0061] For example, it is assumed that the second breeding ponds are six, such as Figure 2-Figure 3 As shown, Figure 2 For the initial baiting sequence, Figure 3 This is the final adjusted feeding order. In the preliminary feeding order, breeding pond No. 1, which is in the third place, and breeding pond No. 2, which is in the first place, are located in the same straight line. Since the robot must pass through breeding pond No. 1 when going to breeding pond No. 2, in order to save driving time, the ranking of breeding pond No. 1 is updated to the first place, and the adjusted feeding order is obtained.

[0062] Assuming that after the above adjustments, the final baiting order is , Indicates the location of the second breeding pond in the first place, Indicates that it is located at The location of the second breeding pond in sequence.

[0063] Then, according to the distance between each second breeding pond and the intelligent feeding robot, and the distance between each second breeding pond, the time required for the intelligent feeding robot to reach the first breeding pond is calculated. Travel time required for the second breeding pond for:

[0064]

[0065] in Indicates that from -1st in the order of the second breeding pond to the first The time spent in the second breeding pond is , It is the time taken for the intelligent feeding robot to travel from its initial position to the second breeding pond in the first priority. Indicates The total amount of feed added to the second breeding pond on that day, , Indicates The number of times the second breeding pond is fed on the same day, , Indicates the amount of bait delivered by the intelligent bait-feeding robot per unit time.

[0066] Finally, the Remaining feeding time for the second culture pond With arrival Travel time required for the second breeding pond For comparison, , if exists If the situation is that the intelligent feeding robot cannot complete the feeding task within the remaining feeding time.

[0067] Since the feeding time needs to be strictly followed in aquaculture, this embodiment quickly determines whether a single intelligent feeding robot can complete the feeding work within the remaining feeding time through the remaining feeding time and the driving time. If not, it is necessary to call an idle robot from an adjacent area of ​​the preset area to the preset area to assist the intelligent feeding robot in completing the feeding work. Since the idle robot is called from an adjacent area, it is necessary to complete the assisting work in the shortest time and return to the adjacent area.

[0068] Furthermore, this embodiment provides a step of configuring a feeding path for the intelligent feeding robot and the idle robot according to the remaining feeding time of each second breeding pond, including:

[0069] Dividing the plurality of second breeding ponds into a plurality of feeding areas according to the number of intelligent feeding robots and idle robots, each feeding area corresponds to an intelligent feeding robot or an idle robot;

[0070] In each feeding area, according to the remaining feeding time of each second breeding pond and the distance between each second breeding pond, the objective function and constraint conditions of the feeding path are determined;

[0071] According to the objective function and constraints, the bait-feeding paths of the intelligent bait-feeding robot and the idle robot are obtained.

[0072] Specifically, the method for dividing the bait throwing area can be selected from the cluster analysis method, that is, assuming that the intelligent bait throwing robot and the idle robot have Then, it is necessary to divide the multiple second breeding ponds into For example, assuming that the number of intelligent bait-feeding robots and idle robots is one, then The number of the second breeding pond is 12, and the feeding area after division is as follows Figure 4 shown.

[0073] Furthermore, this embodiment provides a step of obtaining bait-feeding paths of the intelligent bait-feeding robot and the idle robot according to the objective function and the constraint conditions, including:

[0074] Take the position of the intelligent bait-feeding robot or the idle robot as the root node, and select the first child node to the second child node for the root node according to the constraint conditions. Child nodes, get multiple first bait paths, is the number of second culture ponds in each feeding area;

[0075] A bait delivery path is obtained according to the objective function and multiple first bait delivery paths.

[0076] Further, according to the constraint condition, the first child node to the The steps of the child node include:

[0077] According to the constraints, establish the first child node to the Preset conditions corresponding to the child nodes;

[0078] According to the first child node to the The preset conditions corresponding to the child nodes are to select the first child node to the Child nodes.

[0079] Specifically, the objective function for:

[0080]

[0081] in, Indicates the number of second breeding ponds in each feeding area, Indicates the first Subnode and The distance between child nodes, ,when hour, Represents the distance between the root node and the first child node. The purpose of establishing this objective function is to minimize the total length of the bait casting path.

[0082] The constraints include:

[0083]

[0084] in:

[0085]

[0086] Indicates arrival The time required for the child node, Indicates The remaining baiting time of the child node, Indicates the speed of the intelligent bait-feeding robot or idle robot. Indicates The total amount of bait fed to the child node on that day, , Indicates The number of times the child node is baited on the day, The purpose of this constraint is to enable each child node to complete feeding within the remaining feeding time, which is equivalent to enabling each second breeding pond to complete feeding within the remaining feeding time.

[0087] In addition to the above constraints, the intelligent bait-feeding robot and the idle robot must also meet the basic conditions for bait-feeding, that is, the remaining power and stored bait of the intelligent bait-feeding robot and the idle robot are sufficient to complete the bait-feeding task.

[0088] Based on the above conditions, we can get The preset conditions corresponding to the child nodes are: , that is, select The basis of the child node is that after completing the After the child nodes have finished feeding, there is still enough time to complete the The baiting work of the child nodes is to select the first child node to the The first baiting path can be obtained by selecting a child node, and there may be multiple first baiting paths.

[0089] Then calculate the objective function of each first feeding path. The first feeding path corresponding to the minimum function value is the feeding path. Repeat the above steps in each feeding area to obtain the feeding path of each intelligent feeding robot and idle robot.

[0090] For example, Figure 5 As shown in the figure, "0" represents the position of the intelligent feeding robot, and "1-6" represents the six second breeding pools in the feeding area corresponding to the intelligent feeding robot. Taking the position of the intelligent feeding robot as the root node, the first to sixth child nodes are selected layer by layer according to the preset conditions to obtain three first feeding paths, namely, 2→3→1→6→4→5, 4→2→1→3→6→5 and 4→2→1→3→5→6. Then the objective functions of the three paths are calculated, and the first feeding path corresponding to the minimum function value is the feeding path.

[0091] The method provided in this embodiment divides the multiple second breeding ponds into multiple feeding areas through cluster analysis, dispatches a robot to each feeding area, and configures the feeding path of each robot according to the objective function and preset conditions. The feeding task can be completed in the shortest time within the remaining feeding time, thereby improving work efficiency.

[0092] Furthermore, this embodiment provides a step of obtaining the total feeding amount and feeding time period of each first breeding pond according to the fish species type, fish species growth stage and environmental parameters in each first breeding pond in a preset area, including:

[0093] Calculate the total weight of the fingerlings in each first breeding pond according to the growth stage of the fingerlings, the breeding density and the breeding area of ​​each first breeding pond;

[0094] Obtaining a total feeding amount for each first breeding pond according to the total weight of the fish species and environmental parameters, wherein the environmental parameters include water temperature, pH value and dissolved oxygen content;

[0095] According to the total feeding amount, the fish species type and the fish species growth stage, the feeding time period of each first breeding pond and the feeding amount corresponding to the feeding time period of each first breeding pond are obtained.

[0096] Specifically, Total weight of fingerlings in the first breeding pond for:

[0097]

[0098] in, , is the number of the first breeding pond in the preset area, Indicates The fish species in the first breeding pond are in the growth stage, Indicates The fish species in the first breeding pond are The average weight of each growth stage, , corresponding to the four growth stages of larvae, juveniles, young fish and adults. and Respectively represent The stocking density and stocking area of ​​the first stocking pond.

[0099] No. The total amount of feed added to the first breeding pond on that day for:

[0100]

[0101] in Represents environmental parameters, through The water temperature, pH value and dissolved oxygen content of the first breeding pond are determined. Specifically, different weights can be determined for different factors according to the type and growth stage of the fish species in the breeding pond, and finally the environmental parameters are obtained according to the weighted method. In addition, since the dimensions of water temperature, pH value and dissolved oxygen content are different, normalization processing is required when calculating the weighted results; is the feeding rate, which means that without considering environmental factors, The total amount of feed added to the first breeding pond on that day accounted for The proportion of the total weight of fingerlings in the first breeding pond.

[0102] Then, according to the fish type and growth stage of each first breeding pond, the number of feeding times of each first breeding pond on the day is determined, and according to the number of feeding times and the total feeding amount, the feeding time period and the feeding amount corresponding to each feeding time period are allocated to each first breeding pond.

[0103] For example, assuming The first breeding pond is used to raise juvenile crucian carp. According to the feeding standard of crucian carp, the number of times of feeding in the first breeding pond is three times. The three feedings are evenly distributed, and the feeding time periods of the first breeding pond are 8:00-9:00, 13:00-14:00, and 17:00-18:00. The amount of feeding each time is .

[0104] Furthermore, the intelligent feeding robot and the idle robot collect images of each second breeding pond through the camera while completing the feeding work to complete the inspection work. Moreover, through the images collected by the camera, the feeding remaining rate of each breeding pond at the last feeding can be obtained. Specifically, according to the image recognition technology, the remaining bait can be accurately identified from the collected image, and the remaining amount of bait can be calculated according to the area of ​​the remaining bait in the image. Then, combined with the last feeding amount, the feeding remaining rate can be obtained. According to the feeding remaining rate, the total feeding amount of the next time can be further adjusted.

[0105] Specific:

[0106]

[0107] in, is the total amount of bait after adjustment, is the bait surplus rate, is the bait remaining rate threshold.

[0108] This embodiment can obtain the feeding rate of each breeding pond more accurately through the type of fish species, the growth stage of fish species, the breeding density of each breeding pond, the breeding area and the environmental parameters. At the same time, the feeding amount can be adjusted through the breeding pond images collected during the inspection process to obtain the accurate feeding amount as the basis for subsequent feeding work.

[0109] The distributed robot cluster configuration method provided in the embodiment of the present application can accurately determine the amount of feed for each breeding pond through the feeding algorithm, which serves as the basis for subsequent feeding work. At the same time, through the judgment logic, it can quickly determine whether the intelligent feeding robot can complete the feeding task, and when the intelligent feeding robot cannot complete the feeding task, the idle robot is promptly called to assist the intelligent feeding robot. Finally, the optimal feeding path is configured for the intelligent feeding robot and the idle robot through the objective function and constraint conditions to quickly complete the feeding task.

[0110] Furthermore, if Figure 6 As shown, the embodiment of the present application provides a distributed robot cluster configuration system, including:

[0111] A calculation module is used to obtain the total feeding amount and feeding time period of each first breeding pond according to the fish species type, fish species growth stage and environmental parameters in each first breeding pond in the preset area, each preset area corresponds to an intelligent feeding robot, and according to the current time and the feeding time period, multiple second breeding ponds and the remaining feeding time of each second breeding pond are determined, and the second breeding pond is the first breeding pond that needs to be fed at the current time;

[0112] A judgment module is used to judge whether the intelligent bait-feeding robot can complete the bait-feeding task within the remaining bait-feeding time. If not, an idle robot is called from an adjacent area of ​​the preset area to the preset area;

[0113] The configuration module is used to configure a feeding path for the intelligent feeding robot and the idle robot according to the remaining feeding time of each second breeding pond.

[0114] The distributed robot cluster configuration method and system provided in the embodiments of the present application configure the feeding amount for the robot through an accurate feeding algorithm, and configure the optimal feeding route for the robot through an objective function and constraints, which can ensure that the robot completes the feeding machine inspection work in the shortest time, thereby saving costs and improving work efficiency.

[0115] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0116] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0117] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0118] The above is only a preferred embodiment of the present invention, and the protection scope of the present invention is not limited to the above embodiments. All technical solutions under the concept of the present invention belong to the protection scope of the present invention. It should be pointed out that for ordinary technicians in this technical field, some improvements and modifications without departing from the principle of the present invention should also be regarded as the protection scope of the present invention.

Claims

1. A distributed robot cluster configuration method, characterized in that: include: According to the fish species type, fish species growth stage and environmental parameters in each first breeding pond in the preset area, the total feeding amount and feeding time period of each first breeding pond are obtained, and each preset area corresponds to an intelligent feeding robot; Determine, according to the current time and the feeding period, a plurality of second breeding ponds and the remaining feeding time of each of the second breeding ponds, wherein the second breeding pond is the first breeding pond that needs to be fed at the current time; Determine whether the intelligent bait-feeding robot can complete the bait-feeding task within the remaining bait-feeding time; If not, calling an idle robot from an adjacent area of ​​the preset area to the preset area; According to the remaining feeding time of each of the second breeding ponds, a feeding path is configured for the intelligent feeding robot and the idle robot.

2. A distributed robot cluster configuration method according to claim 1, characterized in that: The configuring of feeding paths for the intelligent feeding robot and the idle robot according to the remaining feeding time of each of the second breeding ponds comprises: Dividing the plurality of second breeding ponds into a plurality of feeding areas according to the number of the intelligent feeding robots and the idle robots, each of the feeding areas corresponding to one of the intelligent feeding robots or one of the idle robots; In each feeding area, determining the objective function and constraint conditions of the feeding path according to the remaining feeding time of each second breeding pond and the distance between each second breeding pond; According to the objective function and the constraint conditions, the bait-feeding paths of the intelligent bait-feeding robot and the idle robot are obtained.

3. A distributed robot cluster configuration method according to claim 2, characterized in that: According to the objective function and the constraint conditions, the bait throwing paths of the intelligent bait throwing robot and the idle robot are obtained, including: The position of the intelligent bait throwing robot or the idle robot is taken as the root node, and the first child node to the second child node are selected for the root node according to the constraint condition. Child nodes, get multiple first bait paths, is the number of the second breeding ponds in each feeding area; The bait feeding path is obtained according to the objective function and the plurality of first bait feeding paths.

4. A distributed robot cluster configuration method according to claim 3, characterized in that: According to the constraint condition, the first child node to the second child node are selected for the root node. Subnodes, including: According to the constraint condition, the first sub-node to the Preset conditions corresponding to the child nodes; According to the first sub-node to the The preset conditions corresponding to the child nodes are to select the first child node to the Child nodes.

5. A distributed robot cluster configuration method according to claim 3, characterized in that: The objective function is determined according to the distance between each child node.

6. A distributed robot cluster configuration method according to claim 1, characterized in that: The determining whether the intelligent bait-feeding robot can complete the bait-feeding task within the remaining bait-feeding time comprises: According to the positions of the second breeding ponds and the intelligent feeding robot, calculating the distance between each of the second breeding ponds and the intelligent feeding robot and the distance between each of the second breeding ponds; According to the remaining feeding time of each of the second breeding ponds, each of the second breeding ponds is sorted to obtain a feeding order; Calculate the travel time required for the intelligent bait-feeding robot to reach each of the second breeding ponds according to the distance between each of the second breeding ponds and the intelligent bait-feeding robot, and the distance between each of the second breeding ponds; According to the bait throwing sequence and the driving time, it is determined whether the intelligent bait throwing robot can complete the bait throwing task within the remaining bait throwing time.

7. A distributed robot cluster configuration method according to claim 1, characterized in that: The method of obtaining the total feeding amount and feeding time period of each first breeding pond according to the fish species type, fish species growth stage and environmental parameters in each first breeding pond in the preset area includes: Calculating the total weight of the fish in each first breeding pond according to the growth stage of the fish, the breeding density and the breeding area of ​​each first breeding pond; Obtaining a total feeding amount for each first breeding pond according to the total weight of the fish species and the environmental parameters, wherein the environmental parameters include water temperature, pH value and dissolved oxygen content; According to the total feeding amount, the fish type and the fish growth stage, the feeding time period of each first breeding pond and the feeding amount corresponding to the feeding time period of each first breeding pond are obtained.

8. A distributed robot cluster configuration method according to claim 7, characterized in that: The total amount of feed fed to each first breeding pond on that day is determined according to environmental parameters, feeding rate and the total weight of the fish species in each first breeding pond, wherein the environmental parameters are determined by water temperature, pH value and dissolved oxygen content, and the total weight of the fish species in each first breeding pond is determined according to the growth stage of the fish species in each first breeding pond, the breeding density of each first breeding pond and the breeding area of ​​each first breeding pond.

9. A distributed robot cluster configuration method according to claim 1, characterized in that: The intelligent feeding robot collects images of each second breeding pond through a camera while completing the feeding work to complete the inspection work.

10. A distributed robot cluster configuration system, characterized in that: include: A calculation module, for obtaining the total feeding amount and feeding time period of each first breeding pond in a preset area according to the fish species type, fish species growth stage and environmental parameters in each first breeding pond, each preset area corresponds to an intelligent feeding robot, and according to the current time and the feeding time period, determining the remaining feeding time of multiple second breeding ponds and each of the second breeding ponds, the second breeding pond being the first breeding pond that needs to be fed at the current time; A judgment module, used to judge whether the intelligent bait-feeding robot can complete the bait-feeding task within the remaining bait-feeding time, and if not, call an idle robot from an adjacent area of ​​the preset area to the preset area; A configuration module is used to configure a feeding path for the intelligent feeding robot and the idle robot according to the remaining feeding time of each of the second breeding ponds.

Images