Cluster robot material proportion collection method based on consensus initiative and related device

Abstract

The invention discloses a consensus initiative-based cluster robot material proportion collection method and a related device. The method comprises the following steps of S1, controlling a robot to randomly move to any target node; s2, judging whether the target node has a required object type or not; if not, a non-existence signal is stored in a short-term memory of the corresponding robot, and S1 is executed; if yes, whether the type of object needs to be picked up or not is judged; if not, executing S1; if so, executing S3; s3, a corresponding robot is controlled to pick up the type of object and store the type of the object, and S4 is executed; s4, the robot is controlled to continue to move randomly, and if the robot moves to any idle point, whether the robot needs to release the type of object at the idle point or not is judged; if the release is not needed, executing S4; if so, executing S5; s5, controlling a corresponding robot to release the type of object, executing S1, and executing S6 until a material collection area with a set scale is formed; s6, the proportions of all types of objects in the material collection area are evaluated, the collection priorities of all types of objects are determined according to the proportions of all types of objects, the collection priorities of all types of objects are the highest priorities of objects with the lowest proportions, all types of objects are collected according to the priorities, S1 is executed, and S2 is executed; and the proportion of each type of objects in the material collection area reaches the expected proportion. The material collecting device can flexibly adapt to the actual distribution condition of materials, and the material collecting efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of swarm robot material collection, and specifically to a swarm robot material proportion collection method based on consensus initiative and related devices. Background Art

[0002] "In-situ construction" refers to the use of on-site materials for construction. Its core is to make full use of the materials available on site for construction operations. This method can not only effectively reduce dependence on external resources, but also reduce transportation costs and environmental impacts. Therefore, it has advantages in remote areas, harsh climatic conditions or extreme environments with limited resources. In the implementation of "in-situ construction", material collection is the first link. Usually, concrete, as the main building material, requires a mixture of multiple raw materials such as water, sand, stone, etc. in a specific ratio. These materials are often randomly distributed in the natural environment, rather than arranged in an orderly manner, making the collection of materials more complicated.

[0003] When performing material collection tasks, existing single robots show high efficiency when faced with scenarios where materials are evenly distributed, but their efficiency is greatly reduced when dealing with randomly distributed materials. The reason is that existing material collection technologies often rely on preset paths or fixed collection patterns, which make it difficult to flexibly adapt to the actual distribution of materials. Summary of the invention

[0004] In response to the problems existing in the prior art, the present invention provides a material proportion collection method and related devices of a cluster robot based on consensus initiative, which can flexibly adapt to the actual distribution of materials and improve the material collection efficiency.

[0005] In order to solve the above technical problems, the present invention is implemented by the following technical solutions:

[0006] According to a first aspect of the present invention, a method for collecting material proportions of a cluster robot based on consensus initiative is provided, comprising:

[0007] S1, control the robot to move randomly to any target node;

[0008] S2, determine whether the target node has the required object type; if not, store the non-existence signal in the short-term memory of the corresponding robot and execute S1; if it exists, determine whether it is necessary to pick up this type of object; if not, execute S1; if it is necessary to pick up, execute S3;

[0009] S3, control the corresponding robot to pick up the object of this type and store the object type, and execute S4;

[0010] S4, control the robot to continue to move randomly. If the robot moves to any idle point, determine whether the robot needs to release this type of object at the idle point; if not, execute S4; if necessary, execute S5;

[0011] S5, control the corresponding robot to release the object of this type, execute S1, until a material collection area of ​​a set size is formed, and then execute S6;

[0012] S6. Evaluate the proportion of each type of object in the material collection area, and determine the priority of collecting each type of object according to the proportion of each type of object, wherein the priority of collecting each type of object is that the object with the lowest proportion has the highest priority, and collect each type of object according to the priority, and execute S1 until the proportion of each type of object in the material collection area reaches the expected proportion.

[0013] In a possible implementation manner of the first aspect, the determining whether it is necessary to pick up the object of this type is specifically:

[0014] Determine the probability of picking up this type of object at the current moment;

[0015] If the probability of picking up this type of object at the current moment reaches or exceeds the expected probability of picking up, then this type of object needs to be picked up; otherwise, it does not need to be picked up.

[0016] In a possible implementation manner of the first aspect, determining the probability of picking up objects of this type at the current moment is specifically:

[0017]

[0018] in, is the probability of picking up this type of object at the current time t; k1 is a constant; α is the picking preference parameter, which is used to increase the probability of picking up the highest priority object when collecting the highest priority object; f i o (M) is the estimate of the proportion of objects of type o in robot i’s short-term memory M, defined as follows:

[0019]

[0020] Among them, s is the time step number of robot movement; is the number of objects of type o encountered by robot i.

[0021] In a possible implementation manner of the first aspect, determining whether the robot needs to release the object of this type at an idle point is specifically:

[0022] Determine the probability of release of this type of object at the current moment;

[0023] If the release probability of this type of object reaches or exceeds the expected release probability at the current moment, this type of object needs to be released; otherwise, it does not need to be released.

[0024] In a possible implementation manner of the first aspect, determining the release probability of the object of this type at the current moment is specifically:

[0025]

[0026] in, is the probability of releasing this type of object at the current time t; k2 is a constant; β is the release preference parameter. If the current position is an idle point and the number of heterogeneous objects in the neighboring nodes is greater than 2, the probability of releasing the object at this position is increased; f i o (M) is the estimate of the proportion of objects of type o in robot i’s short-term memory M, defined as follows:

[0027]

[0028] Among them, s is the time step number of robot movement; is the number of objects of type o encountered by robot i.

[0029] In a possible implementation manner of the first aspect, determining the collection priority of each type of object according to the proportion of each type of object is specifically:

[0030] Compare the ratio set of each type of object with the expected ratio set, and find the object type whose number is far less than the ratio. The robot will give priority to collecting objects of this type. The priority function of object collection is:

[0031]

[0032] in, is a set of proportions of various types of objects, is the expected ratio set, h k is the difference between the current ratio and the ideal ratio of each type of object, argmin(h k ) is to find the largest h k , k is the type of object to be collected first.

[0033] In a possible implementation manner of the first aspect, determining whether the target node has a required object type includes:

[0034] The robot obtains the image information of the target node;

[0035] Determine whether the target node has the required object type based on the image information of the target node.

[0036] According to a second aspect of the present invention, there is provided a device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the method for collecting material proportions of cluster robots based on consensus initiative is implemented.

[0037] According to a third aspect of the present invention, there is provided a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the consensus-based initiative-based cluster robot material ratio collection method.

[0038] According to a fourth aspect of the present invention, a computer program product is provided, which, when executed by a processor, implements the consensus-based initiative-based cluster robot material ratio collection method.

[0039] Compared with the prior art, the present invention has at least the following beneficial effects:

[0040] The present invention provides a method for collecting material proportions of cluster robots based on consensus initiative. By controlling the robot to randomly move to any target node and judging whether the target node has the required object type, this mechanism enables the robot to flexibly respond to the random distribution state of the material. Compared with the traditional method that relies on a preset path or a fixed collection mode, the present invention improves the adaptability of material collection. After confirming that the target node has the required object type, the robot will judge whether it is necessary to pick up this type of object according to the current situation, and perform the picking operation when necessary. In addition, the robot will also judge whether to release the object according to the release probability at the idle point, thereby further optimizing the material collection and release process. The method based on real-time judgment and dynamic decision-making of the present invention enables the robot to efficiently complete the material collection task in a complex environment. At the same time, the present invention evaluates the proportion of each type of object in the material collection area and determines the priority of collecting each type of object according to the proportion. The priority adjustment mechanism ensures that the robot can collect the object with the lowest proportion first, thereby gradually making the proportion of each type of object in the material collection area reach the desired proportion, which is very critical for the in-situ construction process that needs to mix multiple raw materials according to a specific ratio. In summary, the consensus-based initiative-based cluster robot material proportion collection method proposed in the present invention can flexibly adapt to the actual distribution of materials. In the in-situ material collection link, the cluster robot significantly improves the collection speed and task completion efficiency through multi-robot collaborative operation, and also reduces dependence on external resources and transportation costs. It has good adaptability and robustness, can flexibly respond to task requirements and environmental changes, and has good scalability to ensure task continuity and efficiency.

[0041] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the technical solutions in the specific implementation modes of the present invention, the drawings required for use in the description of the specific implementation modes will be briefly introduced below. Obviously, the drawings described below are some implementation modes of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0043] Figure 1 This is a flow chart of a method for collecting material proportions of cluster robots based on consensus initiative in an embodiment of the present invention. DETAILED DESCRIPTION

[0044] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0045] The present invention uses a homogeneous cluster robot, which can sense the type and position of the material, and the robot head is equipped with a device for picking up the material, so that the material can be picked up and released.

[0046] like Figure 1 As shown, the embodiment of the present invention provides a method for collecting material proportions of cluster robots based on consensus initiative, which is mainly to solve the problem of low material collection efficiency in a randomly distributed material environment in the prior art. The collection method specifically includes the following steps:

[0047] S1. Control the robot to move randomly to any target node.

[0048] Specifically, at the beginning of the material collection task, all cluster robots are initialized and randomly distributed in the working area. Through a preset random motion algorithm, such as the random walk algorithm or the Levy flight algorithm, each robot independently selects the next target node to move to, ensuring that the robot can cover the entire working area and increase the probability of encountering randomly distributed materials.

[0049] S2. Determine whether the target node has the required object type; if not, store the non-existence signal in the short-term memory of the corresponding robot and execute S1; if it exists, determine whether this type of object needs to be picked up; if not, execute S1; if it needs to be picked up, execute S3.

[0050] Specifically, when the robot reaches the target node, it scans the surrounding environment through integrated sensors (such as cameras, infrared sensors or lidar) to identify whether there are objects of the required type (such as sand, stones or water). The sensor data is processed in real time to determine whether the target node contains a specific type of material.

[0051] If the required object type does not exist, the robot stores the "non-existence signal" in its short-term memory and returns to execute S1, i.e., reselects and moves to another random target node. Exemplarily, the "non-existence signal" can be assigned to 0.

[0052] If the required object type exists, the robot will further determine whether it needs to pick up such objects.

[0053] S3, control the corresponding robot to pick up this type of object and store the object type, and execute S4.

[0054] Specifically, when it is determined that a certain type of object needs to be picked up, the robot will use its operating mechanism (such as a robotic arm or a suction cup) to pick up the object and store it in a built-in container. At the same time, the robot stores the type information of the object in its memory.

[0055] S4, control the robot to continue to move randomly. If the robot moves to any idle point, determine whether the robot needs to release this type of object at the idle point; if not, execute S4; if necessary, execute S5.

[0056] Specifically, after picking up the object, the robot continues to move to a new target node according to the random motion algorithm to find more materials or free spots for material release.

[0057] S5, control the corresponding robot to release this type of object, execute S1, until a material collection area of ​​a set size is formed, and then execute S6.

[0058] Specifically, when the robot moves to a preset idle point and decides to release the material, the robot will release the object it carries. It should be understood that the release operation is also completed by the robot's operating mechanism.

[0059] It should be noted that the material collection area of ​​a set scale refers to a material collection area of ​​a set scale formed when objects are released, piled up or accumulated to a certain extent.

[0060] S6. Evaluate the proportion of each type of object in the material collection area, and determine the priority of collecting each type of object according to the proportion of each type of object, wherein the priority of collecting each type of object is that the object with the lowest proportion has the highest priority, and collect each type of object according to the priority, and execute S1 until the proportion of each type of object in the material collection area reaches the expected proportion.

[0061] Specifically, as the material collection process proceeds, the cluster robot will periodically evaluate the proportion of each type of object in the current material collection area. It should be understood that the evaluation is achieved through communication between robots, and each robot shares the type and quantity information of the materials it has collected to form a global material distribution map. According to the evaluation results, the priority of collecting each type of object is determined, that is, the object with the lowest proportion has the highest priority. This strategy ensures that the material collection process can gradually tend towards the desired material proportion. Finally, the robot continues to execute steps S1 to S5 according to the new priority rules until the proportion of each type of object in the material collection area reaches or approaches the desired proportion.

[0062] The consensus-based initiative-based cluster robot material proportion collection method provided in this embodiment can flexibly adapt to the random distribution of materials, improve the material collection efficiency, and ensure that the final collected materials meet the predetermined proportion requirements. This method has significant advantages in remote areas, harsh climatic conditions or extreme environments with limited resources.

[0063] In an implementable manner, the determining whether it is necessary to pick up the object of this type may specifically include:

[0064] First, determine the probability of picking up this type of object at the current moment;

[0065] Finally, if the picking probability of this type of object at the current moment reaches or exceeds the expected picking probability, then this type of object needs to be picked up; otherwise, it does not need to be picked up.

[0066] That is to say, when judging whether a certain type of object needs to be picked up, a probability-based decision-making mechanism is adopted. The picking probability reflects the rationality and necessity of picking up this type of object in the current situation. If the picking probability of this type of object at the current moment reaches or exceeds the expected picking probability, the robot needs to pick up this type of object. If the picking probability of this type of object at the current moment is lower than the expected picking probability, the robot does not need to pick up this type of object and directly returns to execute S1, that is, reselect and move to another random target node.

[0067] It should be noted that the expected picking probability can be preset according to actual conditions, such as being set to a certain threshold.

[0068] Preferably, the picking probability of the object of this type at the current moment is determined as follows:

[0069]

[0070] in, is the probability of picking up this type of object at the current time t; k1 is a constant; α is the picking preference parameter, which is used to increase the probability of picking up the highest priority object when collecting the highest priority object; f i o (M) is the estimate of the proportion of objects of type o in robot i’s short-term memory M, defined as follows:

[0071]

[0072] Among them, s is the time step number of robot movement; is the number of objects of type o encountered by robot i.

[0073] In one achievable manner, the determination of whether the robot needs to release this type of object at an idle point may be specifically as follows:

[0074] First, determine the release probability of this type of object at the current moment;

[0075] Finally, if the release probability of this type of object reaches or exceeds the expected release probability at the current moment, this type of object needs to be released; otherwise, it does not need to be released.

[0076] That is to say, after the robot moves to the idle point, it also uses a decision-making mechanism based on release probability to determine whether it needs to release a certain type of object it carries. This release probability reflects whether it is appropriate and necessary to release the object. If the release probability at the current moment reaches or exceeds the expected release probability, the robot will release this type of object at the current idle point; if the release probability at the current moment is lower than the expected release probability, the robot will continue to carry this type of object and look for a more appropriate time or place to release it.

[0077] Likewise, the expected release probability can be preset according to actual conditions.

[0078] Preferably, the release probability of this type of object at the current moment is determined as follows:

[0079]

[0080] in, is the probability of releasing this type of object at the current time t; k2 is a constant; β is the release preference parameter. If the current position is an idle point and the number of heterogeneous objects in the neighboring nodes is greater than 2, the probability of releasing the object at this position is increased; f i o(M) is the estimate of the proportion of objects of type o in robot i’s short-term memory M, defined as follows:

[0081]

[0082] Among them, s is the time step number of robot movement; is the number of objects of type o encountered by robot i.

[0083] In an implementable manner, determining the collection priority of each type of object according to the proportion of each type of object may specifically include:

[0084] Compare the ratio set of each type of object with the expected ratio set, and find the object type whose number is far less than the ratio. The robot will give priority to collecting objects of this type. The priority function of object collection is:

[0085]

[0086] in, is a set of proportions of various types of objects, is the expected ratio set, h k is the difference between the current ratio and the ideal ratio of each type of object, argmin(h k ) is to find the largest h k , k is the type of object to be collected first.

[0087] In one possible implementation, the step of determining whether the target node has the required object type may specifically be:

[0088] The robot obtains the image information of the target node; and determines whether the target node has the required object type based on the image information of the target node.

[0089] Specifically, the robot uses its integrated camera or other image acquisition device to shoot or scan the target node to obtain the image information of the target node, and the image information can be a static picture, a video frame or a dynamic video stream. After obtaining the image information, the robot will pre-process it to improve the accuracy of subsequent image recognition. Exemplarily, the pre-processing step may include image denoising, image enhancement, image scaling, image cropping, etc. The pre-processing operation can eliminate interference factors in the image, such as illumination changes, shadows, occlusions, etc., thereby improving image quality. The pre-processed image information is input into the image recognition module. It should be noted that the image recognition module uses a pre-trained image recognition network (such as a convolutional neural network, a support vector machine, a decision tree, etc.) to analyze and identify the image to determine whether the target node has the required object type.

[0090] Exemplarily, the robot has a perception function and can identify objects and other robots. The robot obtains the type and location information of the target to be collected through the onboard camera device (binocular camera); based on the type and location information of the target to be collected, it determines whether the target node has the required object type. The robot is equipped with a grasping device that can pick up or release the target. The robot has a communication function and can communicate with each other. When one robot senses another robot, it receives the information sensed by the other robot, and at the same time it also feeds back the information it senses to the other robot. The feedback information content is the types and locations of all target individuals sensed by the individual robot. The host computer evaluates the proportion of each type of object in the material collection area and sends it to the robot according to the priority of object collection.

[0091] In another embodiment of the present invention, a computer device is provided, the computer device comprising a processor and a memory, the memory being used to store a computer program, the computer program comprising program instructions, and the processor being used to execute the program instructions stored in the computer storage medium. The processor may be a central processing unit (CPU), or may be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc., which are the computing core and control core of the terminal, which are suitable for implementing one or more instructions, and are specifically suitable for loading and executing one or more instructions in a computer storage medium to implement a corresponding method flow or corresponding function; the processor described in the embodiment of the present invention can be used for the operation of a method for collecting material proportions of a cluster robot based on consensus initiative.

[0092] In another embodiment of the present invention, the present invention also provides a storage medium, specifically a computer-readable storage medium (Memory), which is a memory device in a computer device for storing programs and data. It is understandable that the computer-readable storage medium here can include both built-in storage media in a computer device and, of course, extended storage media supported by the computer device. The computer-readable storage medium provides a storage space, which stores the operating system of the terminal. In addition, one or more instructions suitable for being loaded and executed by a processor are also stored in the storage space, and these instructions can be one or more computer programs (including program codes). It should be noted that the computer-readable storage medium here can be a high-speed RAM memory or a non-volatile memory, such as at least one disk memory. The processor can load and execute one or more instructions stored in the computer-readable storage medium to implement the corresponding steps of the above-mentioned embodiment of a method for collecting material proportions of a cluster robot based on consensus initiative.

[0093] Those skilled in the art will appreciate 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. Moreover, 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.

[0094] 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.

[0095] 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 1A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0096] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0097] The present invention also provides a computer program product, which is used to execute any of the above-mentioned methods for collecting material ratios of cluster robots based on consensus initiative. Since the computer program product provided by the present invention and the above-mentioned method for collecting material ratios of cluster robots based on consensus initiative belong to the same inventive concept, the computer program product provided by the present invention has all the advantages of the above-mentioned method for collecting material ratios of cluster robots based on consensus initiative, so the beneficial effects of the computer program product provided by the present invention will not be described one by one here.

[0098] In the present invention, the terms "one embodiment", "some embodiments", "examples", "specific examples", or "some examples" etc. mean that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the described specific features, structures, materials or characteristics may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradiction.

[0099] Finally, it should be noted that the above-described embodiments are only specific implementations of the present invention, which are used to illustrate the technical solutions of the present invention, rather than to limit them. The protection scope of the present invention is not limited thereto. Although the present invention is described in detail with reference to the above-described embodiments, ordinary technicians in the field should understand that any technician familiar with the technical field can still modify the technical solutions recorded in the above-described embodiments within the technical scope disclosed by the present invention, or can easily think of changes, or make equivalent replacements for some of the technical features therein; and these modifications, changes or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. A method for collecting material proportions of cluster robots based on consensus initiative, characterized in that: include: S1, control the robot to move randomly to any target node; S2, determine whether the target node has the required object type; If it does not exist, the non-existence signal is stored in the short-term memory of the corresponding robot and S1 is executed; If it exists, determine whether it is necessary to pick up this type of object; if it is not necessary to pick up, execute S1; if it is necessary to pick up, execute S3; S3, control the corresponding robot to pick up the object of this type and store the object type, and execute S4; S4, control the robot to continue to move randomly. If the robot moves to any idle point, determine whether the robot needs to release this type of object at the idle point; if not, execute S4; if necessary, execute S5; S5, control the corresponding robot to release the object of this type, execute S1, until a material collection area of ​​a set size is formed, and then execute S6; S6. Evaluate the proportion of each type of object in the material collection area, and determine the priority of collecting each type of object according to the proportion of each type of object, wherein the priority of collecting each type of object is that the object with the lowest proportion has the highest priority, and collect each type of object according to the priority, and execute S1 until the proportion of each type of object in the material collection area reaches the expected proportion.

2. The method for collecting material proportions of cluster robots based on consensus initiative according to claim 1, characterized in that: The determination of whether to pick up this type of object is specifically as follows: Determine the probability of picking up this type of object at the current moment; If the probability of picking up this type of object at the current moment reaches or exceeds the expected probability of picking up, then this type of object needs to be picked up; otherwise, it does not need to be picked up.

3. The method for collecting material ratios of cluster robots based on consensus initiative according to claim 2 is characterized in that: The picking probability of this type of object at the current moment is determined as follows: in, is the probability of picking up this type of object at the current time t; k1 is a constant; α is the picking preference parameter, which is used to increase the probability of picking up the highest priority object when collecting the highest priority object; f i o (M) is the estimate of the proportion of objects of type o in robot i’s short-term memory M, defined as follows: Among them, s is the time step number of robot movement; is the number of objects of type o encountered by robot i.

4. The method for collecting material ratios of cluster robots based on consensus initiative according to claim 1, characterized in that: The determination of whether the robot needs to release this type of object at an idle point is specifically as follows: Determine the probability of release of this type of object at the current moment; If the release probability of this type of object reaches or exceeds the expected release probability at the current moment, this type of object needs to be released; otherwise, it does not need to be released.

5. The method for collecting material ratios of cluster robots based on consensus initiative according to claim 4 is characterized in that: The determination of the release probability of this type of object at the current moment is specifically as follows: in, is the probability of releasing this type of object at the current time t; k2 is a constant; β is the release preference parameter. If the current position is an idle point and the number of heterogeneous objects in the neighboring nodes is greater than 2, the probability of releasing the object at this position is increased; f i o (M) is the estimate of the proportion of objects of type o in robot i’s short-term memory M, defined as follows: Among them, s is the time step number of robot movement; is the number of objects of type o encountered by robot i.

6. The method for collecting material ratios of cluster robots based on consensus initiative according to claim 1, characterized in that: The priority of collecting each type of object is determined according to the proportion of each type of object, specifically: Compare the ratio set of each type of object with the expected ratio set, and find the object type whose number is far less than the ratio. The robot will give priority to collecting objects of this type. The priority function of object collection is: in, is a set of proportions of various types of objects, is the expected ratio set, h k is the difference between the current ratio and the ideal ratio of each type of object, argmin(h k ) is to find the largest h k , k is the type of object to be collected first.

7. The method for collecting material ratios of cluster robots based on consensus initiative according to claim 1, characterized in that: The step of determining whether the target node has the required object type includes: The robot obtains the image information of the target node; Determine whether the target node has the required object type based on the image information of the target node.

8. A device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, it implements a consensus-based initiative cluster robot material ratio collection method as described in any one of claims 1 to 7.

9. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, it implements a consensus-based initiative cluster robot material ratio collection method as described in any one of claims 1 to 7.

10. A computer program product, characterized in that When the computer program product is executed by a processor, it implements a consensus-based initiative cluster robot material ratio collection method as described in any one of claims 1 to 7.

Images