Cluster hunting control method, electronic equipment and storage medium
The gene regulation network model generates adaptive roundup modes and morphology, which solves the problem of obstacle avoidance in group robot roundup and improves the roundup efficiency and success rate.
Patent Information
- Application Number
- CN202410919568.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-10
- Publication Date
- 2024-11-12
- Estimated Expiration
- 2044-07-10
AI Technical Summary
In the prior art, group robots cannot achieve obstacle avoidance that meets environmental characteristics when surrounding targets, which affects the roundup effect and may even lead to task failure.
By obtaining the position information of rounding up targets and obstacles, using the gene regulation network model to generate extruded and fusion rounding up modes, a comprehensive concentration field is generated to determine the rounding up morphology, and a cluster movement of the agent is controlled through the gene regulation network model to achieve roundup. .
The roundup efficiency and task success rate are improved, obstacle avoidance that conforms to environmental characteristics is achieved, and the stability of roundup is enhanced.
Smart Images

Figure CN118938657A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technical field of cluster control, and in particular to a cluster roundup control method, electronic equipment and storage medium. Background Art
[0002] Multi-robot systems (MRSs) are composed of a large number of small autonomous robots and are widely used to perform a variety of tasks. Applications of such robot swarms include clustering, forming shapes, transporting large objects to targets, exploring unknown environments, and autonomously sequencing several specific tasks. The interaction of robots with each other and with the environment results in many desirable properties: scalability to different tasks, adaptability to harsh environments, and robustness to local damage. Overall, swarm robots exhibit capabilities that individual robots lack.
[0003] Using swarm robots to capture targets is an emerging research hotspot. MRSs can be deployed in dangerous environments more appropriately than humans to capture targets. However, in related technologies, when using swarm robots to capture targets, obstacle avoidance that meets the characteristics of the environment cannot be achieved, which affects the capture effect (i.e., it is difficult to achieve stable capture performance) and may even lead to the failure of the capture mission. Summary of the invention
[0004] The main purpose of the embodiments of the present application is to provide a cluster capture control method, electronic device and storage medium, aiming to improve the capture efficiency.
[0005] To achieve the above-mentioned purpose, one aspect of an embodiment of the present application proposes a cluster capture control method, including: obtaining position information of a capture target and an obstacle; generating a corresponding capture mode through a gene regulatory network model according to the position information of the obstacle, the capture mode including an extrusion type and a fusion type; inputting the position information of the capture target and the obstacle into the gene regulatory network model corresponding to the capture mode to generate a comprehensive concentration field based on the position information of the capture target and the obstacle, wherein the position information is determined by a local coordinate system; determining the capture form through the comprehensive concentration field; controlling the movement of the intelligent body cluster through the gene regulatory network model according to the capture form to achieve the capture of the capture target; wherein the extrusion type capture mode is applied to the situation where the position relationship between obstacles is within a first set range, and the fusion type capture mode is applied to the situation where the position relationship between obstacles is within a second set range.
[0006] In some embodiments, the method for establishing the local coordinate system includes: determining a first intelligent agent, which is the intelligent agent closest to the encirclement target; setting the position of the first intelligent agent as the center of the local coordinate system; determining the intelligent agent closest to the first intelligent agent as the second intelligent agent; determining the axis of the local coordinate system based on the positional relationship between the second intelligent agent and the first intelligent agent; determining a third intelligent agent, wherein the distance between the third intelligent agent, the first intelligent agent and the second intelligent agent is less than a preset value; and determining the local coordinate system through the first intelligent agent, the second intelligent agent and the third intelligent agent.
[0007] In some embodiments, the corresponding roundup pattern is generated through a gene regulatory network model according to the position information of the obstacle, including: determining the obstacle avoidance component speed of the agent through the gene regulatory network model through the upper limit position information of the obstacle, the lower limit position information of the obstacle, the linear coefficient of the agent speed change and the linear coefficient of the agent turning; determining the expected speed of the agent through the sum of the obstacle avoidance component speed of the agent and the roundup task speed in an obstacle-free environment; determining the roundup pattern through the gene regulatory network model through the angle between the expected speed and the roundup task speed in the obstacle-free environment.
[0008] In some embodiments, the upper limit position information of the obstacle, the lower limit position information of the obstacle, the linear coefficient of the agent speed change and the linear coefficient of the agent turning are used to determine the obstacle avoidance component speed of the agent through the gene regulatory network model, including: determining the obstacle avoidance component speed of the agent through a first formula, wherein the first formula is expressed as:
[0009]
[0010] in, is the upper limit position information of the obstacle, is the lower limit position information of the obstacle, p f and p a Respectively characterize the linear coefficient of the speed change of the intelligent agent and the linear coefficient of the turning of the intelligent agent.
[0011] In some embodiments, generating a comprehensive concentration field based on the position information of the capture target and the obstacle includes: when the capture mode is the extrusion mode, determining the comprehensive concentration field according to a second formula; the second formula is expressed as:
[0012]
[0013] Among them, p1 represents the position information of the encirclement target, p2 represents the position information of the obstacle; g1 represents the concentration field formed according to the position information of the encirclement target and the obstacle; g2 represents the concentration field formed according to the position information of the obstacle; g3 represents the comprehensive concentration field that combines g1 and g2, sig() represents the sigmod function, θ1, θ2 and θ3 are the thresholds of the s-type function, and k is the concentration field influencing factor.
[0014] In some embodiments, the generating of the comprehensive concentration field based on the position information of the capture target and the obstacle further includes: when the capture mode is the fusion mode, determining the comprehensive concentration field according to a third formula; the third formula is expressed as:
[0015]
[0016] Among them, p1 represents the position information of the target, p2 represents the position information of the obstacle; g1 represents the comprehensive concentration field formed according to g2 and the position information of the target and the obstacle; g2 represents the concentration field formed according to the position information of the obstacle; sig() represents the sigmod function, θ1, θ2 and θ3 are the thresholds of the s-type function, and k is the concentration field influencing factor.
[0017] In some embodiments, determining the capture morphology through the comprehensive concentration field includes: projecting the comprehensive concentration field onto a two-dimensional plane to obtain closed contour lines of concentration values; and determining the capture morphology according to the closed contour lines.
[0018] In some embodiments, the controlling the movement of the intelligent body cluster through the gene regulatory network model according to the capture form to achieve the capture of the capture target includes: determining the movement speed of the leader in the cluster through a fourth formula, and the fourth formula is expressed as:
[0019] v il (t) = v is (t)+v it (t)+v io (t);
[0020] The leader is the agent that first senses the abnormal environment information and adjusts its own movement mode; the movement speed of the followers in the cluster is determined by the fifth formula, which is expressed as:
[0021] v if (t) = v is (t)+v it (t)+v io (t)+v iw (t);
[0022] Among them, v is (t) and v it (t) represents the speed required to complete the basic round-up task in an obstacle-free environment, v io (t) represents the obstacle avoidance component speed determined by the hunting pattern generated by the gene regulatory network model in an environment with obstacles, v il (t) represents the movement speed of the leader in the cluster, v if (t) represents the movement speed of the follower in the cluster, v iw (t) represents the speed used to accelerate the transformation of the group into the trapping form, and t represents time;
[0023]
[0024] Among them, v j (t) is the speed of neighbor agent j, w j is the influence of neighbor agent j on agent i in accelerating the transformation of the group into a hunting form, and N is the number of neighbor agents within the detection range of agent i.
[0025] To achieve the above-mentioned purpose, another aspect of an embodiment of the present application proposes an electronic device, which includes a memory and a processor, wherein the memory stores a computer program, and the processor implements the above-mentioned cluster roundup control method when executing the computer program.
[0026] To achieve the above-mentioned purpose, another aspect of an embodiment of the present application proposes a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and is characterized in that the computer program implements the above-mentioned cluster roundup control method when executed by a processor.
[0027] The embodiments of the present application include at least the following beneficial effects:
[0028] The present application provides a cluster capture control method, electronic device and storage medium. In the embodiment of the present application, first, the position information of the capture target and the obstacle is obtained; then, the corresponding capture mode is generated through the gene regulatory network model according to the position information of the obstacle, and the capture mode includes extrusion type and fusion type; and the position information of the capture target and the obstacle is input into the gene regulatory network model corresponding to the capture mode to generate a comprehensive concentration field based on the position information of the capture target and the obstacle, wherein the position information is determined by the local coordinate system; then, the capture form is determined by the comprehensive concentration field; further, according to the capture form, the intelligent body cluster movement is controlled through the gene regulatory network model to realize the capture of the capture target; wherein, the extrusion capture mode is applied to the situation where the position relationship between the obstacles is within the first set range, and the fusion capture mode is applied to the situation where the position relationship between the obstacles is within the second set range. In this way, obstacle avoidance that meets the characteristics of the environment can be achieved, thereby improving the capture efficiency and further improving the success rate of the capture task.
[0029] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through the practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS
[0030] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the description of the embodiments in conjunction with the following drawings, in which:
[0031] Figure 1 is a flow chart of a cluster roundup control method provided by some embodiments of the present application;
[0032] Figure 2 is a schematic diagram of a local coordinate system provided by some embodiments of the present application;
[0033] Figure 3 It is a schematic diagram of the squeezing type roundup process in the cluster roundup control method provided in some embodiments of the present application;
[0034] Figure 4 is a schematic diagram of a fusion capture process in a cluster capture control method provided in some embodiments of the present application;
[0035] Figure 5 is a schematic diagram of obstacle avoidance component speed provided by some embodiments of the present application;
[0036] Figure 6 It is a schematic block diagram of modules of a cluster roundup control device provided in some embodiments of the present application;
[0037] Figure 7 It is a schematic diagram of the hardware structure of an electronic device provided in some embodiments of the present application. DETAILED DESCRIPTION
[0038] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the reference to "embodiment" in this article means that the specific features, structures or characteristics described in conjunction with the embodiment may be included in at least one embodiment of the present application. The appearance of this phrase in various positions in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the embodiments of the present application. They are only examples of devices and methods consistent with some aspects of the embodiments of the present application as detailed in the attached claims.
[0039] It is understood that the terms "first", "second", etc. used in this application can be used to describe various concepts in this article, but unless otherwise specified, these concepts are not limited by these terms. These terms are only used to distinguish one concept from another concept. For example, without departing from the scope of the embodiment of the present application, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Depending on the context, the words "if" and "if" as used herein can be interpreted as "at the time of" or "when" or "in response to determination".
[0040] The terms "at least one", "multiple", "each", "any", etc. used in this application, at least one includes one, two or more, multiple includes two or more, each refers to each of the corresponding multiple, and any refers to any one of the multiple.
[0041] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application and are not intended to limit this application.
[0042] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application may also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present application.
[0043] In order to make the inventive concept of the present application easy to understand, before describing the embodiments of the present application in detail, the English abbreviations (terms) / related concepts involved in the embodiments of the present application are first described. The English abbreviations (terms) / related concepts involved in the embodiments of the present application are subject to the following explanations.
[0044] GRN: The full name of GRN is Gene Regulatory Network, which is explained in Chinese as gene regulatory network. Gene regulatory network refers to the network formed by the interaction between genes in a cell or a genome, especially gene regulation. This network is an indirect relationship network established by regulating RNA or protein. The research on gene regulatory network mainly focuses on how to describe and analyze these complex networks to reveal the regulatory mechanism of gene expression in organisms. In previous studies, there has been a concept of using GRN and morphological gradient to realize the morphogenesis of swarm robot system. The basic idea of applying the gene expression mechanism in biological morphogenesis to swarm robot control is to establish a metaphor between cells and robots. That is, each cell can be regarded as a robot. The genes in the cell generate proteins to build protein concentration fields, which in turn affect the movement of the cell, map to the robot to establish the target and obstacle information concentration field, and in turn regulate its own gene expression through the concentration field generated by itself, and then regulate the cell life activities (i.e. robot movement).
[0045] CH-GRN: CH-GRN is a cooperative hierarchical gene regulatory network (CH-GRN) is a gene regulatory network applied in swarm robot systems, which aims to enhance mutual cooperation between robots and use obstacles to achieve more effective and efficient target trapping. The upper layer of this network design proposes a gene regulation strategy based on cooperation to improve the overall performance of the system. CH-GRN achieves its function through a multi-level gene regulatory network. In this network, the regulation of gene expression involves not only the regulation of a single gene, but also the interaction and synergy between multiple genes.
[0046] Artificial Intelligence Entity Swarm: An Artificial Intelligence Entity Swarm is a collection of multiple agents that complete complex tasks and goals through collaborative work, mutual communication, and self-organization. The concept of an artificial intelligence swarm comes from group behavior in nature, such as ant colonies, fish schools, and bird flocks, which achieve highly coordinated and efficient collective behavior through simple individual behavior rules.
[0047] Swarm robotic systems are composed of a large number of small autonomous robots and are widely used to perform various tasks. Applications of such robot swarms include swarming, forming shapes, transporting large objects to targets, exploring unknown environments, and autonomous sequencing of several specific tasks. The interaction of robots with each other and with the environment produces many desirable properties: scalability to different tasks, adaptability to harsh environments, and robustness to local damage. Overall, swarm robots exhibit capabilities that individual robots lack. Among their applications, the use of swarm robots to round up targets is an emerging research hotspot. Swarm robotic systems can be deployed in dangerous environments to round up targets better than humans, especially in applications related to counter-terrorism, hazardous material marking in densely populated areas, and isolation of dangerous targets.
[0048] In the related art, there is a swarm agent pattern formation method based on the evolutionary hierarchical gene regulatory network model (EH-GRN), which improves the flexibility of pattern generation and adaptability to various tasks. The upper layer of the gene regulatory network uses obstacle information and the location information of the capture target to generate environmental concentration information, and samples the concentration information to obtain a pattern (i.e., the capture form) as the moving target of the agent. The lower layer of the gene regulatory network avoids obstacles and moves toward the target pattern based on the environmental concentration information, forming an encirclement near the capture target. The automatic generation of the upper layer structure of the gene regulatory network can be achieved using genetic programming methods. The gene network regulation model can be applied to different application scenarios of swarm agents.
[0049] In the related art, there is also a cooperative hierarchical gene regulatory network (CH-GRN) that aims to enhance mutual cooperation between robot neighbors and use obstacles to achieve more effective and efficient capture. In the upper layer design of CH-GRN, a target-neighbor-obstacle (TNO) pattern generation method is proposed; it integrates the information of the target, neighbors, and obstacles to generate more accurate patterns around the target. The concentration vector method is applied in the lower layer of CH-GRN, which enables the robot to quickly adapt to the pattern and complete the capture task.
[0050] However, in the related cluster capture technology, when using obstacles for joint capture, the group robots cannot avoid obstacles in accordance with the characteristics of the environment, and a stable capture effect cannot be achieved, which affects the capture efficiency. In addition, CH-GRN only provides a collaboration framework, but the specific collaboration strategy still needs to be adjusted and optimized according to different tasks and environments.
[0051] In view of this, the present application proposes a cluster capture control method, electronic device and storage medium. The scheme first obtains the position information of the capture target and the obstacle; then, generates the corresponding capture mode through the gene regulatory network model according to the position information of the obstacle, and the capture mode includes extrusion type and fusion type; and inputs the position information of the capture target and the obstacle into the gene regulatory network model corresponding to the capture mode to generate a comprehensive concentration field based on the position information of the capture target and the obstacle, wherein the position information is determined by the local coordinate system; then, the capture form is determined by the comprehensive concentration field; further, according to the capture form, the intelligent body cluster movement is controlled through the gene regulatory network model to realize the capture of the capture target; wherein, the extrusion capture mode is applied to the situation where the position relationship between the obstacles is within the first set range, and the fusion capture mode is applied to the situation where the position relationship between the obstacles is within the second set range. In this way, obstacle avoidance that meets the characteristics of the environment can be achieved, thereby improving the capture efficiency and further improving the success rate of the capture task.
[0052] The method provided in the embodiment of the present application can be applied to the electronic device provided in the embodiment of the present application, wherein the electronic device can be various types of intelligent entities or shore-based equipment (master control equipment).
[0053] The intelligent agent can be an intelligent robot, a drone, an unmanned ship or an unmanned car, etc.
[0054] The shore-based equipment or central control equipment can be a server, which can be an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content distribution networks, as well as big data and artificial intelligence platforms.
[0055] The following will describe in detail the implementation steps of a cluster roundup control method provided by an embodiment of the present application in conjunction with the accompanying drawings.
[0056] Please refer to Figure 1 , Figure 1 A flowchart of a cluster roundup control method provided for some embodiments of the present application; it should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in an order different from that shown here.
[0057] The method of the embodiment of the present application comprises the following steps:
[0058] Step 101: first obtain the location information of the capture target and obstacles;
[0059] Step 102: Afterwards, a corresponding capture pattern is generated through GRN (i.e., gene regulatory network model) based on the location information of the obstacle, wherein the generated capture pattern may include a squeeze capture pattern and a fusion capture pattern;
[0060] Step 103: Then, the position information of the capture target and the position information of the obstacle are input into the GRN corresponding to the capture mode, and a comprehensive concentration field integrating the position information of the capture target and the obstacle can be generated through the GRN. It should be understood that the position information is determined by the local coordinate system;
[0061] Step 104: Then, the applicable trapping form can be determined according to the comprehensive concentration field;
[0062] Step 105: Finally, based on the determined capture pattern, the GRN can be used to control the movement of the intelligent agent cluster to finally capture the capture target;
[0063] The above-mentioned squeeze-type capture mode can be applied to the case where the positional relationship between obstacles is within the first set range, and the above-mentioned fusion-type capture mode can be applied to the case where the positional relationship between obstacles is within the second set range.
[0064] Steps 101 to 105 shown in the embodiment of the present application generate a corresponding capture pattern by using the position information of the obstacle through GRN, and input the position information of the capture target and the obstacle into the GRN corresponding to the capture pattern to generate a comprehensive concentration field based on the position information of the capture target and the obstacle, and determine the capture form through the comprehensive concentration field; further, according to the capture form, the movement of the intelligent agent cluster is controlled through the gene regulatory network model to achieve the capture of the capture target; thereby, obstacle avoidance that conforms to the characteristics of the environment can be achieved, and different types of GRNs can be introduced to generate corresponding capture forms according to the characteristics of the environment. Under different environmental conditions, multiple agents can select the most suitable GRN model through an adaptive selection mechanism, thereby generating a specific capture pattern and achieving target capture.
[0065] The specific implementation methods of the above steps are introduced below.
[0066] In step 101, firstly, the position information of the capture target and obstacles is obtained.
[0067] It should be understood that the acquired position information of the encircled target and the position information of the obstacle are both acquired based on the local coordinate system, and the establishment of the local coordinate system will be introduced in the subsequent section.
[0068] The position information of the target may be the coordinate position of the target in the local coordinate system, and may also include the morphological information of the target, including the shape of the target, the size of the coverage area, etc., which is not limited in this application.
[0069] The position information of the obstacle may be the coordinate position of the obstacle in the local coordinate system, and may also include the shape information of the obstacle and the coverage of the obstacle, or the shape formed by multiple obstacles and specific range data, etc. Among them, the obstacle may include static obstacles or dynamic obstacles, actual obstacles and potential obstacles, and this application does not limit this.
[0070] The location information can be obtained by using sensors carried by the agent itself, such as a laser radar. The location information of obstacles and encirclement targets can be obtained by one or more agents, and the present application does not limit the method of obtaining the location information.
[0071] The embodiment provided in the present application provides data support for the subsequent generation of the capture pattern through GRN by obtaining the position information of the capture target and obstacles.
[0072] In some embodiments, the establishment of a local coordinate system can be achieved by first determining a first agent, wherein the first agent can be one of the agents closest to the target; then, setting the position of the first agent as the center of the local coordinate system (i.e., the origin, the coordinate position can be set to (0,0)); then, setting one of the agents closest to the first agent as the second agent; and setting one of the axes of the local coordinate system based on the positional relationship between the second agent and the first agent; then, determining a third agent, and for the third agent, the distance between the third agent and the first agent and the second agent must be less than a preset value; finally, the local coordinate system (also called the local coordinate system) can be determined by the first agent, the second agent, and the third agent.
[0073] It should be understood that the above-mentioned setting of the axis of the local coordinate system according to the positional relationship between the second intelligent agent and the first intelligent agent can be to set the direction of the line between the second intelligent agent and the first intelligent agent as the horizontal axis of the local coordinate system, or to set the direction of the line between the two as the vertical axis of the local coordinate system, and the present application does not impose any limitation on this.
[0074] The local coordinate system determined according to the above method can be a two-dimensional coordinate system or a three-dimensional coordinate system, and this application does not impose any limitation on this.
[0075] Among them, the intelligent agent can be an unmanned device or an intelligent robot, and the unmanned device can be an unmanned vehicle, a drone or an unmanned ship, and this application does not impose any restrictions on this.
[0076] For example, refer to Figure 2 , Figure 2 is a schematic diagram of a local coordinate system provided in some embodiments of the present application, Figure 2 A schematic diagram of a 2D plane local coordinate system is provided, the coordinate system includes an X-axis and a Y-axis, and the origin of the coordinate system is not at the intersection of the X-axis and the Y-axis, but is located at the position of the Center-bot. Among them, Center-bot represents the first agent, and the coordinate position of Center-bot in the local coordinate system is (0,0). X-bot represents the second agent, and H-bot represents the third agent. In the figure, the red line segment represents the distance between the first agent and the second agent, the green line segment represents the distance between the second agent and the third agent, and the blue line segment represents the distance between the first agent and the third agent. For the third agent, it is necessary to meet the requirement that the distance between the third agent and the first agent and the second agent is less than the preset value, that is, the length difference between the red line segment and the green line segment and the blue line segment is required to be less than the preset value, wherein the preset value can be flexibly set according to the specific environment, and the present application does not limit this. For example, the length difference between the red line segment and the green line segment and the blue line segment is 0, that is, the distance between the above-mentioned agents is equal.
[0077] The horizontal axis of the local coordinate system is determined by the direction of the above red line segment, that is, the horizontal axis of the local coordinate system is parallel to the red line segment.
[0078] For example, the agent closest to the target can be determined as the center of the coordinate system, i.e., the central robot. First, the central robot broadcasts the identification identifier (ID) of its nearest neighbor. The x-axis of the coordinate system is determined by the nearest neighbor, called X-bot. Once the X-bot receives the message from the central robot and identifies itself as the X-bot, it sets its position to (d cx ,0), where d cx is the distance between the X-bot and the central robot. The X-bot then determines its position in the new coordinate system and broadcasts this position to the other robots. Once the task is completed, the central robot can select a robot as the H-bot from those robots that can receive the information sent by the X-bot. Figure 2 The H-bot should satisfy the following condition, that is, the H-bot, the center robot and the X-bot should keep the same distance as much as possible. Therefore, the relative position coordinates can be calculated as:
[0079]
[0080] Among them, d hx is the distance between H-bot and X-bot, d hcis the distance between H-bot and the center robot, which are all measured and calculated by H-bot, d cx is the distance between X-bot and the center robot. α is the angle between H-bot and the x-axis. Other robots that can communicate with these three robots can calculate their relative positions after the three robots (center robot, X-bot and H-bot) build their local coordinate system.
[0081] In step 102, a corresponding capture pattern may be generated through a GRN (i.e., a gene regulatory network model) based on the location information of the obstacle, wherein the generated capture pattern may include a squeeze capture pattern and a fusion capture pattern.
[0082] Among them, the location information of obstacles can be detected by the group robot. For example, each individual in the group robot can be equipped with a laser beam that can irradiate 360° counterclockwise from the current movement direction, and the distribution of obstacles in the environment can be detected by the situation where the laser beam is blocked.
[0083] In some embodiments, the position information of the obstacle may include the upper limit position information of the obstacle and the lower limit position information of the obstacle. Then, the obstacle avoidance component speed of the agent is determined by GRN through the above-determined position information and the linear coefficient of the agent speed change and the linear coefficient of the agent turning.
[0084] Specifically, the obstacle avoidance component speed of the agent can be determined by the first formula, where the first formula can be expressed as:
[0085]
[0086] in, is the upper bound position information of the obstacle, is the lower bound position information of the obstacle, p f and p a They are used to characterize the linear coefficients of the agent's speed change and the linear coefficients of the agent's turning, respectively.
[0087] You can refer to Figure 5 , Figure 5 is a schematic diagram of obstacle avoidance component speed provided by some embodiments of the present application; Figure 5 In the local coordinate system, the black dot represents one of the agents, and the filled gray box represents the detected obstacle. The agent can detect the upper bound position information of the obstacle. and the Nether location information The obstacle avoidance component speed v of the agent can be calculated by combining the detected upper and lower bound position information with the linear coefficient of the agent's speed change and the linear coefficient of the agent's steering. i0It can be seen that the obstacle avoidance component velocity is in the opposite direction to the obstacle.
[0088] Afterwards, the expected speed of the robot (agent) is determined by the sum of the calculated obstacle avoidance component speed of the agent and the capture task speed in an obstacle-free environment.
[0089] For example, the expected speed of the robot can be the final speed of the agent at the next moment, expressed as:
[0090] v id (t) = v i (t)+v io (t);
[0091] Among them, v i (t) = v is (t)+v it (t),v is (t) and v it (t) is the speed component that can ensure the completion of the basic roundup task, that is, the speed required in an obstacle-free environment, t represents time, v i0 is the obstacle avoidance component velocity, v id (t) is the final velocity of robot i at the next moment.
[0092] v it (t) = τ*(p i -p j );
[0093] p j is the coordinates (target coordinates) of robot j on the capture circle (i.e., capture form or Pattern) generated by the current GRN, p i is the coordinate of the current robot i, and τ is the influence degree between robot i and the target depending on the distance.
[0094]
[0095] r esp is the obstacle avoidance safety distance, d ij is the distance between robot i and its neighbor robot j, a ij is the influence degree between robot i and neighbor robot j depending on the distance, N is the number of neighbor robots within the detection range of robot i, and p i is the coordinate of robot i, p j is the coordinate of robot j.
[0096] Then, through the expected speed (the final speed of the agent at the next moment) v id (t) and the capture task speed v in an obstacle-free environment iThe angle between (t) determines the capture pattern through the upper network structure of GRN.
[0097] For example, when the speed v id (t) and the capture task speed v in an obstacle-free environment i (t) is greater than 90°, indicating that the current capture form conflicts with the obstacle avoidance requirement and needs to be changed to adapt to the specific environment. That is, a capture mode that can adapt to the characteristics of the target's surrounding environment can be generated through the GRN upper network structure, where the capture mode can include an extrusion capture mode and a fusion capture mode. It should be understood that the realization of the final capture mode is achieved by generating a comprehensive concentration field based on the position information of the capture target and obstacles through the GRN upper network structure, and then determining the capture form.
[0098] The embodiments provided in the present application generate corresponding capture patterns through the GRN upper-layer network structure according to the location information of the obstacle, wherein the generated capture patterns may include an extrusion capture pattern and a fusion capture pattern. Since the morphological information of the obstacle is fully considered, the capture pattern generated in this way can achieve the rapid completion of the capture task.
[0099] In step 103, the position information of the capture target and the position information of the obstacle are input into the GRN corresponding to the capture mode. The GRN can generate a comprehensive concentration field that integrates the position information of the capture target and the obstacle. It should be understood that the position information is determined by the local coordinate system.
[0100] The location information of the capture target and the location information of the obstacle are used as the input of the gene regulatory network model to generate a comprehensive concentration field based on the capture target and obstacle location information. It should be noted that in this concentration field, the concentration value is the highest at the location of the target, and the concentration values at other locations decrease with the increase of spatial distance. When this comprehensive concentration field is mapped to a two-dimensional space, multiple closed contour lines will be formed around the target. According to the safe distance from the intelligent agent to the target and obstacles, the appropriate contour line is selected as the capture form.
[0101] The basic method of constructing the concentration field can be:
[0102] First, the agent detects several targets and obstacles within the range, and the calculation expression is as follows:
[0103]
[0104] Where p is the total matrix of all detected target and obstacle position information; (T i,x ,T i,y )(i=1,2,…,n) represents the location of the target, (O j,x ,O j,y)(j=1,2,…,m) represents the position of the obstacle.
[0105] Secondly, all obstacle and target position information is regulated by the upper network model of GRN to form the final comprehensive concentration field. The calculation expression is as follows:
[0106]
[0107] g1 is responsible for regulating according to the position information to form the concentration field of the final required capture shape; θ and k are adjustment parameters, which are the threshold of the sigmoid function and the concentration field influencing factor, respectively, and p is the total matrix of all detected target and obstacle position information.
[0108] In some embodiments, a comprehensive concentration field based on the position information of the capture target and the obstacle is generated, wherein, when the capture mode is the extrusion mode, the corresponding comprehensive concentration field can be determined according to the second formula;
[0109] The second formula is expressed as:
[0110]
[0111]
[0112] Among them, p1 represents the location information of the target, p2 represents the location information of the obstacle; g1 represents the concentration field formed according to the location information of the target and the obstacle; g2 represents the concentration field formed according to the location information of the obstacle; g3 represents the comprehensive concentration field that combines g1 and g2, sig() represents the sigmod function, θ1, θ2 and θ3 are the thresholds of the s-type function, and k is the concentration field influencing factor.
[0113] It should be understood that the upper network structure of GRN is responsible for generating a capture mode that can adapt to the characteristics of the target's surrounding environment. In this layer, two capture modes that can be adaptively adjusted can be included, namely, a squeeze capture mode and a fusion capture mode.
[0114] The extrusion type is when the GRN capture circle is deformed by obstacles. This type is suitable for scenes with moderate obstacle spacing. For example, please refer to Figure 3 , Figure 3 is a schematic diagram of the squeezing type roundup process in the cluster roundup control method provided in some embodiments of the present application, Figure 3 In the figure, the blue solid dot represents the robot, the five-pointed star represents the target, the closed curve surrounded by the orange dotted line represents the capture pattern, t represents time, and the gray rectangle represents the obstacle. Figure 3In the wider road capture scenario, it can be seen that the capture circle has deformed at time t2, and at time t3, the multi-agent can successfully complete the capture of the target in the wide road by relying on this mode.
[0115] It should be understood that the above-mentioned extrusion-type capture mode can be applied to the situation where the positional relationship between obstacles is within the first set range, and the above-mentioned fusion-type capture mode can be applied to the situation where the positional relationship between obstacles is within the second set range. Among them, the first set range is usually larger than the second set range. Since the distance between the obstacles meets the first set range, that is, the distance is still relatively large, the intelligent body cluster can complete the pursuit of the capture target through extrusion-type deformation. When the distance between the obstacles meets the second set range, it means that the minimum distance between the obstacles may be relatively small. At this time, the intelligent body cluster cannot pass through the obstacles smoothly through the extrusion-type deformation and achieve the pursuit of the capture target at the same time. Therefore, it is necessary to complete the pursuit of the obstacles through fusion-type deformation.
[0116] The fusion type can adaptively change the capture form according to environmental conditions and use obstacles to assist in the capture, which is suitable for scenes where obstacles are close or special. Figure 4 As shown, Figure 4 is a schematic diagram of a fusion capture process in a cluster capture control method provided in some embodiments of the present application, Figure 4 In the figure, the blue solid dot represents the intelligent agent Robot, the five-pointed star shape represents the target Target, the closed curve surrounded by the orange dotted line represents the capture pattern, t represents time, and the gray rectangle represents an obstacle. Figure 4 Figure 1 shows a narrow road capture scenario. If the agent cluster still uses the squeeze capture mode, it will face collision problems, so it will change to the fusion capture mode in the narrow road. Figure 4 It can be seen that the capture circle is deformed at time t2, and at time t3, the multi-agent cluster can capture the target with the help of obstacles.
[0117] In some embodiments, when the round-up mode is a fusion mode, the comprehensive concentration field may be determined according to a third formula;
[0118] The third formula is expressed as:
[0119]
[0120] Among them, p1 represents the location information of the target, p2 represents the location information of the obstacle; g1 represents the comprehensive concentration field formed according to g2 and the location information of the target and the obstacle; g2 represents the concentration field formed according to the location information of the obstacle; sig() represents the sigmod function, θ1, θ2 and θ3 are the thresholds of the sigmoid function, and k is the concentration field influencing factor.
[0121] In step 104, the applicable trapping form may be determined based on the comprehensive concentration field.
[0122] In some embodiments, the integrated concentration field may be projected onto a two-dimensional plane to obtain closed contour lines of concentration values; thereafter, the trapping morphology may be determined based on the closed contour lines.
[0123] When the comprehensive concentration field can be mapped to a two-dimensional space, multiple closed contour lines will be formed around the capture target. Then, according to the safe distance from the intelligent agent to the target and obstacles, the appropriate contour line is selected as the capture pattern.
[0124] In step 105, based on the determined capture pattern, the movement of the intelligent agent cluster can be controlled by GRN to finally capture the capture target.
[0125] It should be understood that the lower layer of GRN provides a complete swarm robot control model, which includes the basic conditions that drive the swarm robots to achieve capture and the adaptive mode conversion mechanism that assists in achieving better obstacle avoidance. In this layer, the swarm robots are also divided into emergent leaders and followers. The leader is the first object to perceive the abnormal environment, and the follower is the individual in the swarm robot that perceives the leader's morphological change information. This method can achieve accelerated changes in the capture morphology.
[0126] The lower-level control mechanism can be divided into control in an obstacle-free environment and control in an obstacle-filled environment. The control in an obstacle-free environment has been introduced in the above-mentioned section on obtaining the obstacle avoidance component and will not be repeated here.
[0127] In an environment with obstacles, the corresponding motion model of the swarm robot can be determined by the fourth formula, where the motion speed of the leader in the swarm (i.e., the first individual in the swarm to perceive the abnormal environment and adjust its own mode through the above-mentioned adaptive GRN mode conversion mechanism in the current environment) can be expressed as follows:
[0128] v il (t) = v is (t)+v it (t)+v io (t);
[0129] The movement speed of the followers in the cluster can be calculated by the fifth formula, which can be expressed as:
[0130] v if (t) = v is (t)+v it (t)+v io (t)+v iw (t);
[0131] Among them, v is (t) and v it (t) represents the speed required to complete the basic round-up task in an obstacle-free environment, v io (t) represents the obstacle avoidance component velocity determined by the capture pattern generated by GRN in an environment with obstacles, v il (t) represents the movement speed of the leader in the cluster, v if (t) represents the movement speed of the follower in the cluster, v iw (t) represents the speed used to accelerate the transformation of the group into the trapping form, and t represents time;
[0132]
[0133] Among them, v j (t) is the speed of neighbor agent j, w j is the influence of neighbor agent j on agent i in accelerating the transformation of the group into a hunting form, and N is the number of neighbor agents within the detection range of agent i.
[0134] By controlling the movement speed as described above, the swarm robots can be made to move to the corresponding Pattern to capture the target.
[0135] The present application also provides a method for evaluating the performance of rounding up, which can be achieved by using the convergence error (C e ) is used to measure the performance of the proposed method in the roundup task: that is, the convergence error (C e ) indicates the capture accuracy:
[0136]
[0137] Where g=(g1,g2,…,g n ) T represents a group robot. f(g i ) is an implicit function that generates the bracketing pattern, such as f(g i ): is a unit circle. min (f(g i ),i,t) is the shortest distance between the ith robot and the expected capture pattern in the tth time step. eA value of zero indicates that all swarm robots are exactly distributed in the roundup pattern. n is the number of swarm robots. T is the total time step.
[0138] By setting a convergence error threshold, it can be determined whether the capture effect meets expectations.
[0139] The above is an introduction to the cluster roundup control method in the embodiment of the present application.
[0140] The implementation of the cluster roundup control device provided in the embodiment of the present application will be described in detail below with reference to the accompanying drawings.
[0141] For the cluster roundup control method provided in the above embodiment, the present application embodiment also provides a cluster roundup control device for implementing the above method, such as Figure 6 As shown, Figure 6 This is a schematic block diagram of a module of a cluster roundup control device according to an embodiment of the present application. The cluster roundup control device includes:
[0142] An acquisition module is used to first obtain the location information of the capture target and obstacles;
[0143] A first generating module is used to generate a corresponding capture mode through a GRN (i.e., a gene regulatory network model) based on the position information of the obstacle, wherein the generated capture mode may include a squeeze capture mode and a fusion capture mode;
[0144] The second generation module is used to input the position information of the capture target and the position information of the obstacle into the GRN corresponding to the capture mode, and the GRN can generate a comprehensive concentration field that integrates the position information of the capture target and the obstacle. It should be understood that the position information is determined by the local coordinate system;
[0145] A determination module is used to determine the applicable capture form according to the comprehensive concentration field;
[0146] The control module is used to control the movement of the intelligent agent cluster through GRN based on the determined capture pattern and finally capture the capture target;
[0147] The above-mentioned squeeze-type capture mode can be applied to the case where the positional relationship between obstacles is within the first set range, and the above-mentioned fusion-type capture mode can be applied to the case where the positional relationship between obstacles is within the second set range.
[0148] It can be understood that the contents of the above method embodiments are all applicable to the present device embodiments, the functions specifically implemented by the present device embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.
[0149] The present application also provides an electronic device, such as Figure 7 As shown, the electronic device includes a memory, one or more processors ( Figure 7 Only one is shown) and a computer program stored in the memory and executable on the processor. Wherein: the memory is used to store software programs and units, and the processor executes various functional applications and data processing by running the software programs and units stored in the memory to obtain the resources corresponding to the above-mentioned preset events. Optionally, the processor implements the above-mentioned cluster roundup control method by running the above-mentioned computer program stored in the memory.
[0150] The memory, as a non-transitory computer-readable medium, can be used to store non-transitory software programs and non-transitory computer executable programs. In addition, the memory may include a high-speed random access memory, and may also include a non-transitory memory, such as at least one disk storage device, a flash memory device, or other non-transitory solid-state storage device. In some embodiments, the memory may optionally include a memory remotely disposed relative to the processor, and these remote memories may be connected to the processor via a network.
[0151] It can be understood that the contents of the above method embodiments are all applicable to the electronic device embodiment, the functions specifically implemented by the electronic device embodiment are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.
[0152] An embodiment of the present application also provides a computer program product, which includes a computer program. When the computer program is executed by one or more processors, it can implement the steps of the above-mentioned cluster roundup control method.
[0153] It can be understood that the contents of the above method embodiments are all applicable to the present computer program product, the functions specifically implemented by the present computer program product embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.
[0154] The cluster round-up control method, device, electronic device and computer program product provided by the embodiment of the present application, wherein the intelligent agent can switch the adaptive round-up mode according to the characteristics of the environment, such as automatically switching the squeeze type or fusion type round-up mode according to the channel width when rounding up the target in the channel. By introducing a variety of gene regulatory network models, a gene regulatory network model library is constructed. Under different environmental conditions, the most suitable model can be selected through the adaptive selection mechanism, thereby generating a corresponding round-up mode suitable for the environment.
[0155] The embodiment of the present application only calculates the concentration information of obstacles within the detection range of the sensor, which has a small amount of calculation and low requirements on computing resources. In addition, multiple agents establish a local coordinate system through local communication without relying on global information.
[0156] The embodiments described in the embodiments of the present application are intended to more clearly illustrate the technical solutions of the embodiments of the present application and do not constitute a limitation on the technical solutions provided in the embodiments of the present application. Those skilled in the art will appreciate that with the evolution of technology and the emergence of new application scenarios, the technical solutions provided in the embodiments of the present application are also applicable to similar technical problems.
[0157] Although specific embodiments are described herein, those of ordinary skill in the art will recognize that many other modifications or alternative embodiments are also within the scope of the present disclosure. For example, any of the functions and / or processing capabilities described in conjunction with a particular device or component may be performed by any other device or component. In addition, although various exemplary implementations and architectures have been described according to embodiments of the present disclosure, those of ordinary skill in the art will recognize that many other modifications to the exemplary implementations and architectures herein are also within the scope of the present disclosure.
[0158] Some aspects of the present disclosure are described above with reference to the block diagram and flow chart of the system, method, system and / or computer program product according to exemplary embodiments.It should be understood that the combination of one or more blocks in the block diagram and flow chart and the blocks in the block diagram and flow chart can be realized by executing computer executable program instructions respectively.Equally, according to some embodiments, some blocks in the block diagram and flow chart may not need to be executed in the order shown, or may not need to be executed in full.In addition, additional components and / or operations beyond those components and / or operations shown in the blocks in the block diagram and flow chart may be present in certain embodiments.
[0159] Therefore, the blocks in the block diagrams and flow charts support the combination of devices for performing the specified functions, the combination of elements or steps for performing the specified functions, and the program instruction devices for performing the specified functions. It should also be understood that each block in the block diagrams and flow charts and the combination of blocks in the block diagrams and flow charts can be implemented by a special-purpose hardware computer system or a combination of special-purpose hardware and computer instructions that performs a specific function, element or step.
[0160] The program modules, applications, etc. described herein may include one or more software components, including, for example, software objects, methods, data structures, etc. Each such software component may include computer-executable instructions that, in response to execution, cause at least a portion of the functionality described herein (e.g., one or more operations of the illustrative methods described herein) to be performed.
[0161] Software components can be encoded with any of various programming languages. An exemplary programming language can be a low-level programming language, such as an assembly language associated with a specific hardware architecture and / or an operating system platform. The software component comprising assembly language instructions may need to be converted to executable machine code by an assembler before being executed by hardware architecture and / or platform. Another exemplary programming language can be a higher-level programming language, which can be transplanted across multiple architectures. The software component comprising a higher-level programming language may need to be converted to an intermediate representation by an interpreter or a compiler before execution. Other examples of programming languages include but are not limited to macro languages, shells or command languages, job control languages, scripting languages, database queries or search languages or report writing languages. In one or more exemplary embodiments, the software component comprising the instruction of one of the above-mentioned programming language examples can be directly executed by an operating system or other software components, without first being converted into another form.
[0162] Software components may be stored as files or other data storage structures. Software components of similar type or related functions may be stored together, such as in a specific directory, folder, or library. Software components may be static (e.g., preset or fixed) or dynamic (e.g., created or modified at execution time).
[0163] The embodiments of the present application are described in detail above in conjunction with the accompanying drawings, but the present application is not limited to the above embodiments, and various changes can be made within the knowledge scope of ordinary technicians in the relevant technical field without departing from the purpose of the present application.
Claims
1. A cluster roundup control method, It is characterized in that The following steps are involved: Obtain the location information of the capture target and obstacles; Generate a corresponding capture mode through a gene regulatory network model according to the location information of the obstacle, wherein the capture mode includes a squeeze mode and a fusion mode; Inputting the position information of the capture target and the obstacle into the gene regulatory network model corresponding to the capture mode to generate a comprehensive concentration field based on the position information of the capture target and the obstacle, wherein the position information is determined by a local coordinate system; Determining the trapping morphology through the comprehensive concentration field; According to the capture morphology, the movement of the intelligent body cluster is controlled through the gene regulatory network model to achieve the capture of the capture target; The squeeze-type capture mode is applied when the positional relationship between obstacles is within a first set range, and the fusion-type capture mode is applied when the positional relationship between obstacles is within a second set range.
2. The cluster roundup control method according to claim 1, It is characterized in that The method for establishing the local coordinate system comprises: Determine a first intelligent agent, where the first intelligent agent is the intelligent agent closest to the capture target; Setting the position of the first agent as the center of the local coordinate system; Determine the agent that is closest to the first agent as the second agent; Determining the axis of the local coordinate system according to the positional relationship between the second agent and the first agent; Determining a third agent, wherein the distance between the third agent, the first agent, and the second agent is less than a preset value; The local coordinate system is determined by the first agent, the second agent, and the third agent.
3. The cluster roundup control method according to claim 1, It is characterized in that The generating a corresponding capture pattern through a gene regulatory network model according to the location information of the obstacle includes: The obstacle avoidance component speed of the agent is determined through the gene regulatory network model through the upper limit position information of the obstacle, the lower limit position information of the obstacle, the linear coefficient of the agent speed change and the linear coefficient of the agent turning; Determine the expected speed of the agent by the sum of the obstacle avoidance component speed of the agent and the capture task speed in an obstacle-free environment; The capture mode is determined by the gene regulatory network model according to the angle between the expected speed and the capture task speed in the obstacle-free environment.
4. The cluster roundup control method according to claim 3, It is characterized in that The obstacle avoidance component speed of the agent is determined through the gene regulatory network model by using the upper limit position information of the obstacle, the lower limit position information of the obstacle, the linear coefficient of the agent speed change and the linear coefficient of the agent turning, including: The obstacle avoidance component speed of the agent is determined by the first formula, which is expressed as: in, is the upper limit position information of the obstacle, is the lower limit position information of the obstacle, p f and p a Respectively characterize the linear coefficient of the speed change of the intelligent agent and the linear coefficient of the turning of the intelligent agent.
5. The cluster roundup control method according to claim 1, It is characterized in that The generating of the comprehensive concentration field based on the position information of the capture target and the obstacle comprises: When the trapping mode is the extrusion mode, determining the comprehensive concentration field according to a second formula; The second formula is expressed as: Among them, p 1 represents the location information of the capture target, p 2 Represents the location information of the obstacle; g 1 represents the concentration field formed according to the position information of the capture target and the obstacle; g 2 represents the concentration field formed according to the position information of the obstacle; g 3 Represents the fusion of g 1 and g 2 The comprehensive concentration field, sig() represents the sigmod function, θ 1 ,θ 2 and θ 3 is the threshold of the sigmoid function, and k is the concentration field influence factor.
6. The cluster roundup control method according to claim 1, It is characterized in that The generating of the comprehensive concentration field based on the position information of the encircled target and the obstacle further includes: When the capture mode is the fusion mode, determining the comprehensive concentration field according to a third formula; The third formula is expressed as: Among them, p 1 represents the location information of the capture target, p 2 Represents the location information of the obstacle; g 1 Representative according to g 2 and a comprehensive concentration field formed by the position information of the capture target and the obstacle; g 2 represents the concentration field formed according to the position information of the obstacle; sig() represents the sigmod function, θ 1 ,θ 2 and θ 3 is the threshold of the sigmoid function, and k is the concentration field influence factor.
7. The cluster roundup control method according to claim 1, It is characterized in that Determining the trapping morphology through the comprehensive concentration field includes: Projecting the comprehensive concentration field onto a two-dimensional plane, thereby obtaining closed contour lines of concentration values; The trapping shape is determined according to the closed contour lines.
8. The cluster roundup control method according to claim 1, It is characterized in that The method of controlling the movement of the intelligent body cluster through the gene regulatory network model according to the capture form to achieve the capture of the capture target includes: The movement speed of the leader in the cluster is determined by the fourth formula, which is expressed as: v il (t)=v is (t)+v it (t)+v io (t); The leader is the agent that first senses abnormal environmental information and adjusts its own movement mode; The movement speed of the followers in the cluster is determined by the fifth formula, which is expressed as: v if (t)=v is (t)+v it (t)+v io (t)+v iw (t); Among them, v is (t) and v it (t) represents the speed required to complete the basic round-up task in an obstacle-free environment, v io (t) represents the obstacle avoidance component speed determined by the hunting pattern generated by the gene regulatory network model in an environment with obstacles, v il (t) represents the movement speed of the leader in the cluster, v if (t) represents the movement speed of the follower in the cluster, v iw (t) represents the speed used to accelerate the transformation of the group into the trapping form, and t represents time; Among them, v j (t) is the speed of neighbor agent j, w j is the influence of neighbor agent j on agent i in accelerating the transformation of the group into a hunting form, and N is the number of neighbor agents within the detection range of agent i.
9. An electronic device, It is characterized in that The electronic device includes a memory and a processor, the memory stores a computer program, and the processor implements the cluster roundup control method as described in any one of claims 1 to 8 when executing the computer program.
10. A computer-readable storage medium storing a computer program. It is characterized in that When the computer program is executed by a processor, the cluster roundup control method according to any one of claims 1 to 8 is implemented.
Citation Information
Patent Citations
Multi-target capturing method for cooperative operation of swarm robots in complex convex environment
CN111240332A
Group robot polymerization control method based on three-layer gene regulation and control network
CN114397887A
Target hunting method based on self-organizing grouping and related equipment
CN114610036A
E-GRN-based cluster hunting method, execution device and system
CN114859904A
Robot track obstacle avoidance method and system
CN114879701A
