Cluster control method and device, equipment, medium and product
By analyzing the vigilance behavior of biological groups through biomimetic analysis and combining it with distributed auction rules to determine the execution objects in unmanned clusters, the problem of insufficient multi-person collaboration ability of unmanned clusters under weak communication interaction is solved, thereby improving the vigilance capability and perception efficiency of unmanned clusters.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-12-17
- Publication Date
- 2026-03-10
AI Technical Summary
Unmanned swarms lack multi-person collaboration capabilities under weak communication interaction, resulting in insufficient vigilance and an inability to effectively respond to threats in complex environments.
By analyzing the vigilance behavior of biological groups through biomimetic analysis, constraints are set to select agents to perform vigilance tasks. A distributed auction rule is used to determine the agent with the highest global efficiency as the execution target, and the agent is controlled to execute the corresponding sub-task, ensuring that each agent undertakes the most suitable vigilance task according to its capabilities, location, and environmental conditions.
It improves the alertness capability of unmanned swarms, enhances their ability to perceive the environment and respond quickly, and achieves efficient group self-organized alertness.
Smart Images
Figure CN121635477A_ABST
Abstract
Description
Technical Field
[0001] This disclosure belongs to the field of cluster control technology, specifically relating to a cluster control method, device, equipment, medium, and product. Background Technology
[0002] An unmanned swarm is a group system consisting of multiple autonomous or semi-autonomous unmanned systems (such as drones, unmanned vehicles, unmanned boats, and unmanned underwater vehicles) interconnected through a communication network to form a distributed intelligent collaborative system and jointly complete complex tasks. Unmanned swarms play an important role in many fields due to their advantages such as wide coverage, high mobility, and low unit cost.
[0003] In related technologies, poor multi-person collaboration capabilities in weak communication interaction clusters limit the cluster's collaborative perception efficiency. This makes it impossible to meet the alert and response requirements in complex environments, thus reducing the alert capability of unmanned clusters. Summary of the Invention
[0004] This disclosure addresses some deficiencies mentioned in the background art by providing a cluster control method, apparatus, equipment, medium, and product that can improve the alerting capabilities of unmanned clusters.
[0005] In a first aspect, embodiments of this disclosure provide a cluster control method, comprising: Determine the number and location of subtasks required to execute the target task; For any one of the subtasks, obtain the performance information of each agent participating in the subtask; one agent corresponds to a device in the cluster; Determine the execution object corresponding to each subtask, wherein the execution object is the intelligent agent with the highest global performance; Control each of the aforementioned execution objects to execute its corresponding subtask.
[0006] Optionally, if the target task is a surveillance task, determining the number and location of subtasks required to execute the target task includes: Based on the preset first constraint, determine the minimum number of subtasks that satisfy the first constraint and the corresponding task positions; The first constraint includes one or more of the following: The boundary coverage rate of the area where the cluster is located is greater than or equal to the boundary coverage rate threshold. The area coverage rate of the region where the cluster is located is greater than or equal to the area coverage rate threshold. The number of rounds in which each of the aforementioned intelligent agents continuously executes the sub-task is greater than or equal to a first threshold. Each of the aforementioned intelligent agents shall perform the task at least once.
[0007] Optionally, for any one of the sub-tasks, obtaining the performance information of each agent participating in the sub-task includes: The performance information is obtained by the distributed transmission of each of the intelligent agents; the performance information is determined by the intelligent agents based on the cost and benefit of each intelligent agent performing the sub-task.
[0008] Optionally, determining the execution object corresponding to each subtask includes: Based on the preset second constraint, a target intelligent agent that satisfies the second constraint is determined; Based on the distributed auction rules, the agent with the highest global performance among the target agents is determined as the execution object; The second constraint includes one or more of the following: The distance between the target agent and each of the subtasks is less than a second threshold, and the second threshold is positively correlated with the side length of the region where the cluster is located. The total energy consumed by the target agent in executing each of the sub-tasks is greater than a third threshold, and the third threshold is positively correlated with the energy consumed by the target agent in executing each of the sub-tasks.
[0009] Optionally, obtaining the performance information of each agent participating in the sub-task includes: Based on the location information of each target intelligent agent and the task position of each subtask, the distance between each target intelligent agent and each subtask is determined. Based on the energy consumed by each target agent in executing each sub-task and the distance, determine the energy required for each target agent to move to each sub-task; Based on the energy consumed by each target agent in executing each subtask and the energy required to move to each subtask, the total energy consumed by each target agent in executing each subtask is determined. Based on the total energy and the distance, the cost for each target agent to perform each subtask is determined.
[0010] Optionally, the method further includes: When the performance information of multiple agents is the same, the agent closest to the subtask is determined as the execution object.
[0011] In a second aspect, embodiments of this disclosure provide a cluster control device, comprising: The first determining module is used to determine the number and location of subtasks required to execute the target task. The acquisition module is used to acquire, for any one of the subtasks, the performance information of each agent participating in the subtask; one agent corresponds to a device in the cluster; The second determining module is used to determine the execution object corresponding to each subtask, wherein the execution object is the intelligent agent with the highest global efficiency. The control module is used to control each of the execution objects to execute its corresponding subtask.
[0012] In a third aspect, embodiments of this disclosure provide an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the above-described cluster control method.
[0013] In a fourth aspect, embodiments of this disclosure provide a computer-readable storage medium having a computer program stored thereon, the program being executed by a processor to implement the above-described cluster control method.
[0014] In a fifth aspect, embodiments of this disclosure provide a computer program product including computer-readable code, or a non-volatile computer-readable storage medium carrying computer-readable code, wherein when the computer-readable code is run in a processor of an electronic device, the processor in the electronic device executes the above-described cluster control method.
[0015] This disclosure determines the number and location of subtasks required to execute the target task; for any subtask, it obtains the performance information of each agent participating in the subtask; one agent corresponds to one device in the cluster; it determines the execution object corresponding to each subtask, with the execution object being the agent with the highest global performance; and it controls each execution object to execute its corresponding subtask. By selecting agents capable of undertaking alert tasks in the current alert round as execution objects, the alert role allocation of each agent in the unmanned cluster is determined. Combining the global performance of multiple agents, suitable subtasks are assigned to each execution object, ensuring that each agent can undertake the most suitable alert task based on its capabilities, location, and current environmental conditions. This solves the problem of multi-agent collaboration capability restricting the collaborative perception efficiency of the cluster. Therefore, it can improve the alert capability of the unmanned cluster.
[0016] It should be understood that both the foregoing general description and the following detailed description are exemplary and intended to provide further illustration of the claimed technology. Attached Figure Description
[0017] Figure 1 A flowchart of a cluster control method provided in this disclosure.
[0018] Figure 2This is a schematic diagram illustrating the coverage area of the warning boundary provided in this disclosure.
[0019] Figure 3 A schematic diagram illustrating the warning and sensing range provided in this disclosure.
[0020] Figure 4 This is a schematic diagram illustrating the location information of the subtasks provided in this disclosure.
[0021] Figure 5 This is a schematic diagram of the structure of a cluster control device provided in this disclosure.
[0022] Figure 6 This is a hardware block diagram of an electronic device provided in this disclosure.
[0023] Figure 7 This is a schematic diagram of a computer program product provided in this disclosure. Detailed Implementation
[0024] To enable those skilled in the art to better understand the technical solution of this application, the application scenario of this application will be described first below.
[0025] An unmanned swarm is a group system consisting of multiple autonomous or semi-autonomous unmanned systems (such as drones, unmanned vehicles, unmanned boats, and unmanned underwater vehicles) interconnected through a communication network to form a distributed intelligent collaborative system and jointly complete complex tasks. Unmanned swarms play an important role in many fields due to their advantages such as wide coverage, high mobility, and low unit cost.
[0026] In the face of a rapidly changing external environment, improving the system's efficiency in perceiving external threats is crucial for maintaining the safe operation of unmanned swarm systems. In unmanned swarms, the perception and threat avoidance capabilities of individual machines are insufficient, while mutual coordination and cooperation among individuals can greatly enhance the system's threat perception capabilities. Therefore, designing the early warning mechanism for unmanned swarm systems is a critical and challenging issue that urgently needs to be addressed.
[0027] In related technologies, unmanned swarm systems mainly focus on global perception, multi-source information fusion, and swarm collaborative control to address collaborative perception issues. However, research on swarm vigilance, which comprehensively considers constraints such as local perception, self-organized situational awareness, and task scheduling, is currently lacking. Furthermore, in swarms with weak communication interaction, poor multi-person collaboration capabilities limit the effectiveness of swarm collaborative perception. This makes it impossible to meet vigilance response requirements in complex environments, thus reducing the vigilance capability of unmanned swarms.
[0028] The vigilance behavior of biological groups is highly efficient when facing predators, providing a good reference for unmanned swarm systems to achieve efficient and intelligent threat vigilance. Biomimetic swarm vigilance refers to applying the highly coordinated and consistent behavioral patterns exhibited by biological groups (such as birds and fish) in nature when facing external threats to the design of unmanned systems, thereby enhancing the system's perception of the surrounding environment and its rapid response capabilities.
[0029] To address the aforementioned technical problems, this disclosure provides an inventive concept: based on biomimetic analysis of the vigilance behavior of spotted thrushes and babblers, corresponding constraints are set to select agents to perform vigilance tasks and determine the vigilance role allocation of each agent in the unmanned swarm, i.e., determining the execution target; based on biomimetic analysis of the vigilance movement behavior of ibex swarms, corresponding rules are abstracted to plan where to perform vigilance, adopting a coordination mode, i.e., agents taking turns performing vigilance tasks, and assigning appropriate sub-tasks to each execution target. Based on the swarm vigilance role allocation and swarm vigilance task planning, the key issues of who should act as sentinels (i.e., the execution target) and where to perform vigilance are solved, ensuring that each agent can undertake the most suitable vigilance task according to its capabilities, location, and current environmental conditions, thereby achieving the task objective of swarm self-organized vigilance.
[0030] The present disclosure will now be described in further detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present disclosure and not intended to limit it. Furthermore, it should be noted that, for ease of description, only the parts relevant to the present disclosure are shown in the drawings, not the entire structure.
[0031] Figure 1 A flowchart illustrating a cluster control method provided in this disclosure. Figure 1 As shown, the method includes: S101: Determine the number and location of subtasks required to execute the target task.
[0032] Specifically, for an unmanned swarm, the side length of the swarm's region is d (determined as needed). That is, the unmanned swarm region is a square area with side length d, and the number of agents in the swarm is K, of which k are reconnaissance agents, representing a proportion of the total number of agents. ,Right now The reconnaissance agent is equipped with multiple visual sensors, enabling it to keenly perceive targets and execute target tasks. In other words, an unmanned swarm comprises multiple agents. Agents other than the reconnaissance agent cannot perform surveillance tasks. A target task includes multiple sub-tasks, and each agent must execute its respective sub-task to achieve the surveillance objective.
[0033] For multiple agents, each agent has different task execution parameters in the current alert round. Some agents may not meet the alert constraints in this round. Therefore, it is necessary to select at least one agent that can execute the sub-task. In other words, in this round of alerting, there must be an agent that can execute the alert target task to meet the alert requirements. This can improve alert efficiency. The alert ratio should be minimized as much as possible, using the fewest possible agents for alerting.
[0034] In other words, it is necessary to assign roles to agents in the unmanned swarm through constraints, and to efficiently and reasonably allocate vigilance roles within the unmanned swarm, so as to ensure that each member can undertake the most suitable vigilance target task according to its capabilities, location and current environmental conditions, thereby maximizing the overall vigilance efficiency and response speed of the swarm.
[0035] The agent's boundary perception parameter is the radius of the area the agent can monitor; this parameter determines the agent's perception range. By combining the area's side length and the agent's boundary perception parameter, the number of sub-tasks within the monitoring area can be determined. To minimize the monitoring ratio in the unmanned swarm while maximizing monitoring coverage, the goal is to maximize the probability of detecting the target when it appears. A monitoring task is located at each corner of the square swarm area, with monitoring task points evenly distributed along the swarm's edge; each monitoring task point represents a sub-task.
[0036] In this embodiment, the agent boundary perception parameters of two adjacent target agents overlap at least partially. In this embodiment, the overlapping portion can be half the radius.
[0037] S102: For any subtask, obtain the performance information of each agent participating in the subtask.
[0038] Specifically, one agent corresponds to one device in the cluster. The agent's performance information characterizes the relationship between the agent's gains and costs when performing sub-tasks. By comprehensively evaluating the performance information of agents, the allocation and utilization of the overall cluster resources can be optimized.
[0039] S103: Determine the execution object corresponding to each subtask.
[0040] Specifically, the execution target is the agent with the highest global efficiency. In this embodiment, a distributed auction algorithm can be used to determine the execution target of each subtask. In the auction, the agent's efficiency information is the price that the agent can bid for when executing the subtask. By using the auction method, a better execution target can be selected for each subtask, avoiding resource waste and unreasonable task planning. By simulating the behavior mechanism of biological swarm vigilance, the vigilance roles are efficiently and rationally allocated within the unmanned swarm, ensuring that each agent can undertake the most suitable vigilance subtask based on its capabilities, location, and current environmental conditions, thereby maximizing the overall vigilance efficiency and response speed of the swarm. Furthermore, it improves adaptability and versatility to different environments, effectively plans the vigilance target tasks of the unmanned swarm in a specific area, and improves the swarm's ability to flexibly respond to various potential threats in emergency situations.
[0041] In other words, task planning is required for the sub-tasks within the unmanned swarm, outlining the swarm's surveillance mission paths and strategies within a specific area. This may include patrol routes, the establishment of alert points, and emergency response plans for different scenarios, ensuring the swarm can flexibly respond to various potential threats and challenges.
[0042] S104: Controls each execution object to execute its corresponding subtask.
[0043] Specifically, the central control unit controls each execution object to perform its corresponding sub-tasks in order to achieve the final target task in the unmanned cluster.
[0044] This disclosure determines the number and location of subtasks required to execute the target task; for any subtask, it obtains the performance information of each agent participating in the subtask; one agent corresponds to one device in the cluster; it determines the execution object corresponding to each subtask, with the execution object being the agent with the highest global performance; and it controls each execution object to execute its corresponding subtask. By selecting agents capable of undertaking alert tasks in the current alert round as execution objects, the alert role allocation of each agent in the unmanned cluster is determined. Combining the global performance of multiple agents, suitable subtasks are assigned to each execution object, ensuring that each agent can undertake the most suitable alert task based on its capabilities, location, and current environmental conditions. This solves the problem of multi-agent collaboration capability restricting the collaborative perception efficiency of the cluster. Therefore, it can improve the alert capability of the unmanned cluster.
[0045] In one possible implementation, if the target task is a surveillance task, an exemplary method for determining the number and location of subtasks required to execute the target task includes: Based on the preset first constraint, determine the minimum number of subtasks that satisfy the first constraint and the corresponding task positions.
[0046] Specifically, by using the preset first constraint, the agents executing subtasks can be optimized to determine the minimum number of subtasks that satisfy the target task. In other words, the minimum number of agents that can complete the target task and the corresponding task positions can be determined.
[0047] The following is an example optimization objective function for determining the minimum number of subtasks:
[0048] When agent j executes a subtask =1, otherwise =0, and the objective function needs to be minimized while satisfying the following first constraint condition.
[0049] The first constraint includes one or more of the following: (1) The boundary coverage of the area where the cluster is located is greater than or equal to the boundary coverage threshold.
[0050] Specifically, confirming the alert range ensures that targets can be detected when they are close to the cluster or at a certain distance from it, while also guaranteeing coverage of as large an area as possible. The boundary coverage rate is the probability that edge sampling points are covered by the agent, and the side length of the alert range is greater than the side length of the unmanned cluster.
[0051] When the warning target, i.e., the subtask, reaches the distance from the cluster When locating a position, the preset probability of being detected is greater than... This is how the intelligent agent can complete the surveillance task. The geometric center coordinates of the cluster are... With that point as the center, the side length is The sides of a square are defined as the side lengths of the warning zone.
[0052] Figure 2 This is a schematic diagram of the coverage area of the warning boundary provided in this disclosure, such as... Figure 2 As shown, the locational relationships between the unmanned swarm range, the alert boundary, and the alert area are clearly defined. Since the alerting agent is mobile, it is necessary to consider edge coverage over a period of time, not just instantaneous coverage.
[0053] First, the warning boundary is discretized, and each edge is divided into N segments. Then, the sampling points of each segment are... indivual.
[0054] The following are exemplary formulas for determining the upper and lower boundaries:
[0055]
[0056] An example formula for determining the left and right boundaries is as follows:
[0057]
[0058] in, For the edge Upper The coordinates of each edge sampling point (relative to the expanded region). The index of the edge sampling points, from 0 to .
[0059] Define a coverage judgment function to determine whether each edge sampling point is covered by at least one agent; if covered, the value is 1, and if not covered, the value is 0.
[0060] in, For the edge Upper Each edge sampling point in time An indicator function for whether something is overridden. For time indexing, For intelligent agents coordinates For intelligent agents In time Whether the binary variable is selected These are the boundary perception parameters for the intelligent agent.
[0061] For each edge and each time point, calculate the number of edge sampling points that are covered, which is used as the warning boundary coverage rate:
[0062] in, For the edge In time The number of edge sampling points that are covered.
[0063] The warning boundary coverage constraint requires that the coverage of each edge is not lower than a certain boundary coverage threshold. :
[0064] in, This is the boundary coverage threshold (e.g., 0.9, meaning that at least 90% of each edge is covered). To plan the length of the time period.
[0065] The complete expression for the boundary coverage constraint is as follows:
[0066] in, The boundary coverage threshold, To plan the length of the time period, For intelligent agents coordinates For intelligent agents In time Whether the binary variable is selected These are the boundary perception parameters for the intelligent agent.
[0067] (2) The area coverage of the cluster is greater than or equal to the area coverage threshold.
[0068] Specifically, the area of the alert coverage zone is greater than γ times the total area of the region, and the sampling area needs to include all possible alert coverage areas. In addition, since the alert agent is mobile, the edge coverage situation over a period of time needs to be considered, not just the instantaneous situation.
[0069] Assume the sampling region has a side length of A square shape is formed, with its center coinciding with the center of the cluster region. Monte Carlo sampling points are generated, that is, randomly generated within the expanded square region. Sampling points in each area:
[0070] in, For the first The coordinates of each sampling point in the region The index of the sampling point, from 1 to , These are the boundary perception parameters for the intelligent agent.
[0071] Define a coverage judgment function to determine whether any region's sampling points are covered by at least one selected agent; if covered, the function is set to 1, and if not covered, it is set to 0.
[0072] in, To determine whether agent j is selected at time t. For boundary perception parameters of the intelligent agent For intelligent agents The coordinates.
[0073] For each time point, the number of sampling points in the covered area is calculated as the area coverage rate:
[0074] in, Sampling points In time An indicator function for whether something is overridden. For time The number of sampling points in the covered area.
[0075] The area coverage constraint requires that the actual warning coverage area be no less than γ times the area of the cluster region, which can be expressed as the following expression:
[0076] in, The area of the sampling region ( ), To plan the length of the time period, This represents the number of sampling points in the area.
[0077] An exemplary expression for the area coverage constraint is:
[0078] in, For the first The coordinates of each sampling point in the region The index of the sampling point, from 1 to , For boundary perception parameters of the intelligent agent The area of the sampling region. To plan the length of the time period, The number of sampling points in the area. This represents the area coverage threshold.
[0079] (3) The number of rounds in which each agent continuously executes the sub-task is greater than or equal to the first threshold.
[0080] Specifically, to avoid excessive energy consumption due to agents continuously performing tasks, each agent must rest at least once between being selected as an agent. The term "round" refers to the number of consecutive alerts used to determine the number of rest rounds.
[0081] An exemplary expression for the rest round constraint is:
[0082] in, In the first In the wheel, intelligent agents Whether it is selected as the execution target (0 indicates not selected, 1 indicates selected). This is the round offset, used to calculate the number of rounds an agent needs to rest after being selected as the vigilant agent. For the index of the intelligent agent, This is the index for the current round.
[0083] (4) Each agent executes a subtask at least once.
[0084] Specifically, within a certain period of time, each agent should have at least one opportunity to execute the alert subtask in order to achieve even rotation. In other words, the rotation cycle is determined by the total number of execution rounds and the total number of agents.
[0085] An example expression for the rotation cycle constraint is:
[0086] in, For the index of the agent, ranging from 1 to , The index for the current round, ranging from 1 to... , In the first Should the first round be selected? Each intelligent agent is used as the execution object. The total number of intelligent agents. The total number of rounds refers to the total time during the mission.
[0087] In one possible implementation, an exemplary method for obtaining performance information of each agent participating in the subtask for any given subtask includes: Obtain the performance information of distributed transmission from each intelligent agent.
[0088] Specifically, performance information is determined by the agents based on the cost and benefit of each agent executing a sub-task. The cost of each agent executing each sub-task is determined; for each sub-task, based on the benefit and cost of each agent's execution, the performance information of each agent is determined. In other words, each agent, distributed among themselves, calculates its performance information and then sends it to the central control unit, so that the central control unit can allocate appropriate agents as execution targets for each sub-task based on the performance information. Execute subtasks The reward is determined by the value of the task, which is preset. In this embodiment, it is assumed that the value of each agent performing the task is equal and unchanged, and the cost of performing sub-tasks is determined by the agent's own condition.
[0089] implement An exemplary formula for subtask performance is:
[0090] in, For performance information, To the benefit of performing sub-tasks, The cost of performing a subtask.
[0091] For example, obtain the performance information of each agent participating in the sub-task, including: Based on the location information of each agent and the location information of each subtask, the distance from each agent to each subtask is determined; based on the energy consumed by each agent in executing each subtask and the distance, the energy required for each agent to move to each subtask is determined; based on the energy consumed by each agent in executing each subtask and the energy required to move to each subtask, the total energy required for each agent to execute each subtask is determined; based on the total energy and the distance, the cost for each agent to execute each subtask is determined.
[0092] An exemplary formula for the cost of executing a subtask is:
[0093] in, The cost of performing subtasks, The boundary coverage threshold, This relates the area of the warning zone to the area of the region. This represents the distance from each agent to each subtask. The total energy required for each agent to perform its sub-tasks.
[0094] An exemplary formula for the agent to calculate the Euclidean distance to each subtask is as follows:
[0095] in, For the location information of the intelligent agent, For subtask location information, For each agent's distance to each subtask, bid on the one closest to the target; the closer the distance, the lower the cost of executing the task.
[0096] Regarding the energy required for each agent to perform its sub-task, the cluster has a total of [amount missing]. If there are 3 intelligent agents, then their combined energy is:
[0097] The energy consumed by each agent in performing each subtask is The energy required to move to the subtask is The total energy required for each agent to execute each subtask is:
[0098] in, The energy coefficient required for movement, The total energy required for each agent to perform each subtask. The energy consumed by each agent to perform each subtask. This represents the distance from each agent to each subtask.
[0099] In one possible implementation, an exemplary method for determining the execution object corresponding to each subtask includes: Based on the preset second constraint, the target intelligent agent that meets the second constraint is determined; based on the distributed auction rules, the intelligent agent with the highest global efficiency among the target intelligent agents is determined as the execution object.
[0100] Specifically, after determining the performance information of each agent in executing each sub-task, based on the second constraint, target agents that can execute the auction are identified. From these target agents, corresponding execution objects are selected for each sub-task to achieve optimal execution of the target task. Maximizing the overall performance in completing the task is taken as the optimization objective. The following is an example formula for optimization:
[0101] in, For performance information, i represents the agent and j represents the subtask.
[0102] For each subtask Each target intelligent agent that satisfies the second constraint condition Bidding can be conducted, and the bid price can be determined based on performance information. The target agent with the highest bid price will be selected to complete the subtask. Assigned to The second-highest bid will be used as the transaction price. Afterwards, the sets of assigned and unassigned subtasks can be updated, the agent's available resources can be updated, and the above allocation steps can be repeated until all subtasks have been assigned.
[0103] The second constraint includes one or more of the following: (1) The distance between the target agent and each subtask is less than the second threshold.
[0104] Specifically, the second threshold is positively correlated with the edge length of the region where the cluster is located. The following is an example formula for the maximum distance constraint:
[0105] in, This represents the distance from each agent to each subtask. The side length of the region where the cluster is located.
[0106] (2) The total energy of the target agent in executing each sub-task is greater than the third threshold.
[0107] Specifically, the third threshold is positively correlated with the energy consumed by the target agent in executing each sub-task. The following is an example formula for the minimum energy constraint:
[0108] in, The total energy required for each agent to perform sub-tasks. The energy consumed by each agent to perform its sub-tasks.
[0109] In addition, the number of rest shifts and the rotation cycle can be further constrained, and the constraint method is the same as the first constraint condition mentioned above, so it will not be elaborated here.
[0110] In one possible implementation, an exemplary method for determining the number and location of subtasks required to perform a target task includes: Specifically, the number of agents within a square region with side length d in the unmanned swarm is... The set of intelligent agents is:
[0111] Figure 3 This is a schematic diagram of the warning and sensing range provided in this disclosure, such as... Figure 3 As shown. The boundary perception parameters of the agent are a circle centered on itself with a radius of... A circular region is defined, and the boundary perception parameters of the two agents are defined to have at least the following in the cluster region: The warning requirements can only be met when there is overlap, such as Figure 3 .
[0112] The number of subtasks for each edge is:
[0113] The total number of subtasks is:
[0114] Figure 4 This is a schematic diagram of the subtask location information provided in this disclosure, such as... Figure 4 As shown, There are a total of 8 sub-task locations.
[0115] The subtask location information at the upper edge of the cluster region is as follows:
[0116] The subtask location information at the lower edge of the cluster region is as follows:
[0117] The subtask location information on the left edge of the cluster area is as follows:
[0118] The subtask location information at the right edge of the cluster region is as follows:
[0119] in, For the location information of the regional center, The number of subtasks on each edge, where i is the i-th subtask.
[0120] Based on the number and location information of subtasks, the set of subtasks is determined as follows:
[0121] In one possible implementation, the method further includes: When multiple agents have the same performance information, the agent closest to the subtask is selected as the execution target.
[0122] Specifically, during the task auction process, if two target agents bid the same price for the same task, it indicates a conflict in subtask allocation. In this case, the agent closer to the subtask target can be selected as the execution target.
[0123] In one possible implementation, the method further includes: By using performance information and the location of each subtask, the patrol route of the execution object can be determined, so as to determine the movement route of each execution object to perform the target task, thereby enabling the timely determination of emergency response plans in the event of an emergency.
[0124] Figure 5 This is a schematic diagram of the structure of a cluster control device provided in this disclosure. Figure 5 As shown, the device 500 includes: a first determining module 510, an acquiring module 520, a second determining module 530, and a control module 540.
[0125] The first determining module 510 is used to determine the number and location of subtasks required to execute the target task; The acquisition module 520 is used to acquire, for any one of the subtasks, the performance information of each intelligent agent participating in the subtask; one intelligent agent corresponds to a device in the cluster; The second determining module 530 is used to determine the execution object corresponding to each subtask, wherein the execution object is the intelligent agent with the highest global efficiency. The control module 540 is used to control each of the execution objects to execute their respective sub-tasks.
[0126] Optionally, the first determining module is used to: Based on the preset first constraint, determine the minimum number of subtasks that satisfy the first constraint and the corresponding task positions; The first constraint includes one or more of the following: The boundary coverage rate of the area where the cluster is located is greater than or equal to the boundary coverage rate threshold. The area coverage rate of the region where the cluster is located is greater than or equal to the area coverage rate threshold. The number of rounds in which each of the aforementioned intelligent agents continuously executes the sub-task is greater than or equal to a first threshold. Each of the aforementioned intelligent agents shall perform the task at least once.
[0127] Optionally, the acquisition module is used for: The performance information is obtained by the distributed transmission of each of the intelligent agents; the performance information is determined by the intelligent agents based on the cost and benefit of each intelligent agent performing the sub-task.
[0128] Optionally, the second determining module is used to: Based on the preset second constraint, a target intelligent agent that satisfies the second constraint is determined; Based on the distributed auction rules, the agent with the highest global performance among the target agents is determined as the execution object; The second constraint includes one or more of the following: The distance between the target agent and each of the subtasks is less than a second threshold, and the second threshold is positively correlated with the side length of the region where the cluster is located. The total energy consumed by the target agent in executing each of the sub-tasks is greater than a third threshold, and the third threshold is positively correlated with the energy consumed by the target agent in executing each of the sub-tasks.
[0129] Optionally, the acquisition module is used for: Based on the location information of each target intelligent agent and the task position of each subtask, the distance between each target intelligent agent and each subtask is determined. Based on the energy consumed by each target agent in executing each sub-task and the distance, determine the energy required for each target agent to move to each sub-task; Based on the energy consumed by each target agent in executing each subtask and the energy required to move to each subtask, the total energy consumed by each target agent in executing each subtask is determined. Based on the total energy and the distance, the cost for each target agent to perform each subtask is determined.
[0130] Optionally, the device further includes: The third determining module is used to determine the agent closest to the subtask as the execution object when the performance information of multiple agents is the same.
[0131] This application also provides an electronic device for executing the above-described cluster control method. Please refer to... Figure 6 It illustrates a schematic diagram of an electronic device provided by some embodiments of this application. For example... Figure 6 As shown, the electronic device 6 includes: a processor 600, a memory 601, a bus 602, and a communication interface 603. The processor 600, the communication interface 603, and the memory 601 are connected via the bus 602. The memory 601 stores a computer program that can run on the processor 600. When the processor 600 runs the computer program, it executes the cluster control method provided in any of the foregoing embodiments of this application.
[0132] The memory 601 may include high-speed random access memory (RAM) or non-volatile memory, such as at least one disk storage device. Communication between the device network element and at least one other network element is achieved through at least one communication interface 603 (which can be wired or wireless), such as the Internet, wide area network, local area network, metropolitan area network, etc.
[0133] Bus 602 can be an ISA bus, PCI bus, or EISA bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. The memory 601 is used to store programs. After receiving an execution instruction, the processor 600 executes the program. The cluster control method disclosed in any of the foregoing embodiments of this application can be applied to the processor 600, or implemented by the processor 600.
[0134] The processor 600 may be an integrated circuit chip with signal processing capabilities. In implementation, each step of the above method can be completed by the integrated logic circuitry in the hardware of the processor 600 or by instructions in software form. The processor 600 may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it may also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), an off-the-shelf programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this application. The general-purpose processor may be a microprocessor or any conventional processor. The steps of the methods disclosed in the embodiments of this application can be directly embodied in the execution of a hardware decoding processor, or executed by a combination of hardware and software modules in the decoding processor. The software modules may reside in random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, or other mature storage media in the art. The storage medium is located in memory 601. Processor 600 reads the information in memory 601 and, in conjunction with its hardware, completes the steps of the above method.
[0135] The electronic device provided in this application embodiment and the cluster control method provided in this application embodiment are based on the same inventive concept and have the same beneficial effects as the methods they adopt, operate or implement.
[0136] This application also provides a computer-readable storage medium corresponding to the cluster control method provided in the foregoing embodiments. The computer-readable storage medium shown can be an optical disc, on which a computer program is stored. When the computer program is run by a processor, it executes the cluster control method provided in any of the foregoing embodiments.
[0137] It should be noted that examples of the computer-readable storage medium may also include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other optical and magnetic storage media, which will not be elaborated here.
[0138] The computer-readable storage medium provided in the above embodiments of this application and the cluster control method provided in the embodiments of this application are based on the same inventive concept and have the same beneficial effects as the methods adopted, run or implemented by the applications stored therein.
[0139] This application also provides a computer program product 700, such as... Figure 7 As shown. This computer program product carries a computer program 701. The instructions included in the program code can be used to execute the steps of the cluster control method described in the above method embodiments. For details, please refer to the above method embodiments, which will not be repeated here.
[0140] The aforementioned computer program product can be implemented through hardware, software, or a combination thereof. In one optional embodiment, the computer program product is specifically embodied in a computer storage medium; in another optional embodiment, the computer program product is specifically embodied in a software product, such as a software development kit (SDK), etc.
[0141] The basic principles of this disclosure have been described above with reference to specific embodiments. However, it should be noted that the advantages, benefits, and effects mentioned in this disclosure are merely examples and not limitations, and should not be considered as essential features of each embodiment of this disclosure. Furthermore, the specific details disclosed above are for illustrative and facilitative purposes only, and are not limitations. These details do not limit the scope of this disclosure to the necessity of employing the aforementioned specific details for implementation.
[0142] The block diagrams of devices, apparatuses, devices, and systems disclosed herein are merely illustrative examples and are not intended to require or imply that they must be connected, arranged, or configured in the manner shown in the block diagrams. As those skilled in the art will recognize, these devices, apparatuses, devices, and systems can be connected, arranged, and configured in any manner. Words such as “comprising,” “including,” “having,” etc., are open-ended terms meaning “including but not limited to,” and are used interchangeably with them. The terms “or” and “and” as used herein refer to the terms “and / or,” and are used interchangeably with them unless the context clearly indicates otherwise. The term “such as” as used herein refers to the phrase “such as but not limited to,” and is used interchangeably with it.
[0143] Additionally, as used herein, the "or" used in a list of items beginning with "at least one" indicates a separate list, such that a list of, for example, "at least one of A, B, or C" means A or B or C, or AB or AC or BC, or ABC (i.e., A and B and C). Furthermore, the word "exemplary" does not imply that the described example is preferred or better than other examples.
[0144] It should also be noted that in the systems and methods of this disclosure, the components or steps can be decomposed and / or recombined. These decompositions and / or recombinations should be considered as equivalent solutions to this disclosure.
[0145] Various changes, substitutions, and modifications can be made to the technology described herein without departing from the teachings defined by the appended claims. Furthermore, the scope of the claims of this disclosure is not limited to the specific aspects of the processes, machines, manufactures, events, means, methods, and actions described above. Currently existing or later-developed processes, machines, manufactures, events, means, methods, or actions that perform substantially the same function or achieve substantially the same result as the corresponding aspects described herein can be utilized. Therefore, the appended claims include such processes, machines, manufactures, events, means, methods, or actions within their scope.
[0146] The above description of the disclosed aspects is provided to enable any person skilled in the art to make or use this disclosure. Various modifications to these aspects will be readily apparent to those skilled in the art, and the general principles defined herein may be applied to other aspects without departing from the scope of this disclosure. Therefore, this disclosure is not intended to be limited to the aspects shown herein, but rather to be carried out within the widest scope consistent with the principles and novel features disclosed herein.
[0147] The above description has been given for purposes of illustration and description. Furthermore, this description is not intended to limit the embodiments of this disclosure to the forms disclosed herein. Although numerous exemplary aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, alterations, additions, and sub-combinations therein.
Claims
1. A cluster control method characterized by, The method comprises: determining the number and positions of sub-tasks required for performing a target task; for any one of the sub-tasks, obtaining performance information of each agent participating in the sub-task; one agent corresponds to one device in the cluster; determining an execution object corresponding to each sub-task, the execution object being an agent with the highest global performance; controlling each execution object to perform the corresponding sub-task.
2. The method of claim 1, wherein, If the target task is a vigilance task, the determination of the number and positions of sub-tasks required for performing the target task comprises: based on a preset first constraint condition, determining the minimum number of sub-tasks and the corresponding task positions that satisfy the first constraint condition; wherein the first constraint condition comprises one or more of the following: the boundary coverage of the area where the cluster is located is greater than or equal to a boundary coverage threshold; the area coverage of the area where the cluster is located is greater than or equal to an area coverage threshold; the number of consecutive rounds of each agent performing the sub-task is greater than or equal to a first threshold; each agent performs the task at least once.
3. The method of claim 1, wherein, The obtaining of the performance information of each agent participating in the sub-task comprises: obtaining the performance information distributed by each agent; the performance information is determined by each agent based on the cost of performing the sub-task and the benefit of performing the sub-task.
4. The method of claim 1, wherein, The determination of the execution object corresponding to each sub-task comprises: based on a preset second constraint condition, determining a target agent that satisfies the second constraint condition; based on a distributed auction rule, determining the agent with the highest global performance among the target agents as the execution object; wherein the second constraint condition comprises one or more of the following: the distance between the target agent and each sub-task is less than a second threshold, the second threshold being positively correlated with the length of the area where the cluster is located; the total energy of the target agent performing each sub-task is greater than a third threshold, the third threshold being positively correlated with the consumed energy of the target agent performing each sub-task.
5. The method of claim 4, wherein, The obtaining of the performance information of each agent participating in the sub-task comprises: based on the position information of each target agent and the task positions of each sub-task, determining the distance between each target agent and each sub-task; based on the consumed energy of each target agent performing each sub-task and the distance, determining the energy of each target agent moving to each sub-task; based on the consumed energy of each target agent performing each sub-task and the energy of each target agent moving to each sub-task, determining the total energy of each target agent performing each sub-task; based on the total energy and the distance, determining the cost of each target agent performing each sub-task.
6. The method of claim 1, wherein, The method further comprises: when the performance information of multiple agents is the same, determining the agent closest to the sub-task as the execution object.
7. A cluster control device characterized by comprising: The method comprises: a first determination module for determining the number and positions of sub-tasks required for performing a target task; An acquisition module is configured to acquire, for any one of the subtasks, performance information of each agent participating in the subtask respectively; one of the agents corresponds to one of the devices in the cluster; A second determination module is configured to determine an execution object corresponding to each subtask, the execution object being an agent with the highest global performance; A control module is configured to control each execution object to execute a corresponding subtask respectively.
8. An electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, The processor runs the computer program to implement the method of any one of claims 1-6.
9. A computer readable storage medium having stored thereon a computer program, characterized in that, The program is executed by the processor to implement the method of any one of claims 1-6.
10. A computer program product, characterised in that, The non-volatile computer readable storage medium includes or carries computer readable code, and when the computer readable code runs in the processor of the electronic device, the processor in the electronic device executes the method of any one of claims 1-6.