Multi-agent cluster formation control method and device based on navigation following

Abstract

The invention provides a multi-agent cluster formation control method and device based on pilot following, and relates to the technical field of cluster control, and the method comprises the steps: obtaining first position information and first speed information sent by a plurality of agents in a multi-agent cluster; acquiring self real-time second position information and second speed information; determining an adjacent agent according to the first position information and the second position information, wherein the distance between the adjacent agent and the target agent is smaller than a preset communication distance; determining a formation role of the target agent in the multi-agent cluster, wherein the formation role comprises a navigator role and a follower role; and calculating a motion track according to the formation role and based on the first position information, the first speed information, the second position information and the second speed information. According to the invention, a cluster formation control problem caused by a communication distance can be solved.

Description

Technical Field

[0001] The present application relates to the technical field of cluster control, and in particular to a multi-agent cluster formation control method and device based on pilot-following. Background Art

[0002] Multi-agent swarm is a form of multi-agent swarm, which reflects the high degree of collaboration and distributed decision-making ability between agents. A system composed of autonomous or semi-autonomous equipment such as drones, unmanned ships, and unmanned vehicles can communicate and share data in real time through the network, and then coordinate actions to complete various complex tasks. The core advantage of this type of swarm system lies in the autonomy and flexibility of each agent. Agents can respond independently in the local environment and cooperate with other agents to achieve the optimization goal of the overall system. Application scenarios cover military, search and rescue, logistics and transportation, environmental monitoring and other fields.

[0003] In the collaborative operation of multi-agent clusters, formation control is one of the key technologies to achieve efficient collaboration. Through reasonable formation control, the agents in the cluster can maintain a specific formation, thereby improving the efficiency and safety of task execution. Formation control not only ensures the effective distance between agents and avoids collisions, but also makes each agent more orderly and accurate when performing collaborative search, search and rescue tasks through reasonable division of labor and information sharing. At the same time, formation control also helps the cluster to deal with emergencies in complex environments, ensuring the overall stability of the cluster and the successful completion of tasks.

[0004] In a multi-agent swarm, followers usually need to communicate with the leader to obtain its motion state information to ensure the overall coordination of the formation. However, when the communication capability is limited, especially when the follower is at the tail or edge of the swarm and far away from the leader, the communication link may be interrupted or unstable, resulting in the follower being unable to obtain the leader's motion information in time. In this case, the traditional direct communication-based pilot-following method may no longer be applicable. Therefore, a method is needed to solve the cluster formation control problem caused by the communication distance. Summary of the invention

[0005] The present application provides a multi-agent cluster formation control method and device based on pilot-following, which can solve the cluster formation control problem caused by communication distance.

[0006] In a first aspect of the present application, a multi-agent cluster formation control method based on pilot-following is provided, and the method is applied to a target agent, comprising:

[0007] Obtaining first position information and first speed information sent by multiple agents in a multi-agent cluster;

[0008] Collecting real-time second position information and second speed information of the device;

[0009] Determine a neighboring intelligent body according to the first location information and the second location information, wherein the distance between the neighboring intelligent body and the target intelligent body is less than a preset communication distance;

[0010] Determine a formation role of the target agent in the multi-agent cluster, wherein the formation role includes a leader role and a follower role;

[0011] A motion trajectory is calculated according to the formation role and based on the first position information, the first speed information, the second position information, and the second speed information.

[0012] Optionally, calculating the motion trajectory according to the formation role and based on the first position information, the first speed information, the second position information, and the second speed information specifically includes:

[0013] If it is determined that the formation role is the follower, obtaining the number of elements of the plurality of neighboring agents;

[0014] The motion trajectory at the current moment is calculated according to the number of elements and the first position information, specifically by the following formula:

[0015]

[0016] Among them, r i des (t) is the motion trajectory at the current moment, dim(N i ) is the number of elements, q j (t) is the first position information.

[0017] Optionally, after calculating the motion trajectory at the current moment according to the number of elements and the first position information, the method further includes:

[0018] Based on the first position information and the first speed information, the motion trajectory at the next moment is calculated, specifically by the following formula:

[0019]

[0020] Among them, r i des (t+1) is the motion trajectory of the next moment, dim(N i ) is the number of elements, q j (t) is the first position information, p j (t) is the first speed information, and dt is a time step.

[0021] Optionally, the calculating the motion trajectory according to the formation role and based on the first position information, the first speed information, the second position information, and the second speed information specifically further includes:

[0022] If it is determined that the formation role is the navigator, obtaining the navigator's reference trajectory and the first position information at the current moment;

[0023] Based on the navigator reference trajectory at the current moment and the first position information, the motion trajectory at the current moment is calculated, specifically by the following formula:

[0024]

[0025] Among them, r i des (t) is the motion trajectory at the current moment, dim(N i ) is the number of elements of the multiple neighboring agents, q j (t) is the first position information, r i (t) is the reference trajectory of the navigator at the current moment.

[0026] Optionally, after calculating the motion trajectory at the current moment based on the navigator reference trajectory at the current moment and the first position information, the method further includes:

[0027] Based on the navigator's reference trajectory at the next moment, the first position information, and the first speed information, the motion trajectory at the next moment is calculated, specifically by the following formula:

[0028]

[0029] Among them, r i des (t+1) is the motion trajectory of the next moment, dim(N i ) is the number of elements, q j (t) is the first position information, p j (t) is the first speed information, r i (t+1) is the reference trajectory of the navigator at the next moment, and dt is a time step.

[0030] Optionally, after calculating the motion trajectory according to the formation role and based on the first position information, the first speed information, the second position information, and the second speed information, the method further includes:

[0031] Based on the motion trajectory at the current moment and the motion trajectory at the next moment, the control input of the target agent is generated, and the control input is specifically as follows:

[0032]

[0033] Among them, u i (t) is the control input, α and β are control parameters, r i des (t) is the motion trajectory at the current moment, r i des (t+1) is the motion trajectory at the next moment, q i (t) is the second position information, p j (t) is the second speed information, and dt is a time step.

[0034] Optionally, determining a neighboring agent according to the first location information specifically includes:

[0035] Determine the distance between the target agent and other agents according to the first position information and the second position information;

[0036] Acquire a first communication distance of the target intelligent agent and a second communication distance of the other intelligent agents;

[0037] Determining a magnitude relationship between the first communication distance and the second communication distance;

[0038] If it is determined that the first communication distance is smaller than the second communication distance, determining whether the distance between the target agent and other agents is smaller than the first communication distance;

[0039] If it is determined that the distance between the target agent and other agents is less than the first communication distance, the other agents are determined to be the neighboring agents.

[0040] In a second aspect of the present application, a multi-agent cluster formation control device based on pilot-following is provided, wherein the device is a target agent, and includes an acquisition module, a processing module, and a judgment module, wherein:

[0041] The acquisition module is used to acquire first position information and first speed information sent by multiple agents in the multi-agent cluster;

[0042] The acquisition module is used to collect the second position information and the second speed information of the second device in real time;

[0043] The processing module is used to determine a neighboring intelligent body according to the first location information and the second location information, wherein the distance between the neighboring intelligent body and the target intelligent body is less than a preset communication distance;

[0044] The judgment module is used to determine the formation role of the target agent in the multi-agent cluster, and the formation role includes a leader role and a follower role;

[0045] The processing module is used to calculate a motion trajectory according to the formation role and based on the first position information, the first speed information, the second position information and the second speed information.

[0046] Optionally, the acquisition module is used to acquire the number of elements of the plurality of neighboring agents if it is determined that the formation role is the follower;

[0047] The processing module is used to calculate the motion trajectory at the current moment according to the number of elements and the first position information, specifically by the following formula:

[0048]

[0049] Among them, r i des (t) is the motion trajectory at the current moment, dim(N i ) is the number of elements, q j (t) is the first position information.

[0050] Optionally, the processing module is used to calculate the motion trajectory at the next moment based on the first position information and the first speed information, specifically by the following formula:

[0051]

[0052] Among them, r i des (t+1) is the motion trajectory of the next moment, dim(N i ) is the number of elements, q j (t) is the first position information, p j (t) is the first speed information, and dt is a time step.

[0053] Optionally, the acquisition module is used to acquire the reference trajectory of the navigator at the current moment and the first position information if it is determined that the formation role is the navigator;

[0054] The processing module is used to calculate the motion trajectory at the current moment based on the navigator reference trajectory at the current moment and the first position information, specifically by the following formula:

[0055]

[0056] Among them, r i des (t) is the motion trajectory at the current moment, dim(N i ) is the number of elements of the multiple neighboring agents, q j (t) is the first position information, r i (t) is the reference trajectory of the navigator at the current moment.

[0057] Optionally, the processing module is used to calculate the motion trajectory at the next moment based on the navigator reference trajectory at the next moment, the first position information, and the first speed information, specifically by the following formula:

[0058]

[0059] Among them, r i des (t+1) is the motion trajectory of the next moment, dim(N i ) is the number of elements, q j (t) is the first position information, p j (t) is the first speed information, r i (t+1) is the reference trajectory of the navigator at the next moment, and dt is a time step.

[0060] Optionally, the processing module is used to generate a control input of the target agent based on the motion trajectory at the current moment and the motion trajectory at the next moment, and the control input is specifically as follows:

[0061]

[0062] Among them, u i (t) is the control input, α and β are control parameters, r i des (t) is the motion trajectory at the current moment, r i des (t+1) is the motion trajectory at the next moment, q i (t) is the second position information, p j (t) is the second speed information, and dt is a time step.

[0063] Optionally, the judgment module is used to determine the distance between the target agent and other agents according to the first position information and the second position information;

[0064] The acquisition module is used to acquire the first communication distance of the target intelligent agent and the second communication distance of the other intelligent agents;

[0065] The judging module is used to judge the magnitude relationship between the first communication distance and the second communication distance;

[0066] The judging module is configured to judge whether the distance between the target agent and other agents is less than the first communication distance if it is determined that the first communication distance is less than the second communication distance;

[0067] The judgment module is used to determine that the other intelligent agent is the neighboring intelligent agent if it is determined that the distance between the target intelligent agent and the other intelligent agent is less than the first communication distance.

[0068] In the third aspect of the present application, an electronic device is provided, including a processor, a memory, a user interface and a network interface, the memory is used to store instructions, the user interface and the network interface are both used to communicate with other devices, and the processor is used to execute the instructions stored in the memory so that the electronic device executes any one of the methods described above.

[0069] In a fourth aspect of the present application, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores instructions, and when the instructions are executed, any of the methods described above is executed.

[0070] In summary, one or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages:

[0071] 1. This application can solve the problem of cluster formation control caused by communication distance, mainly because it realizes local control through information exchange between neighboring agents, rather than relying on global communication. By collecting the position and speed information of itself and neighboring agents in real time, and dynamically adjusting the motion trajectory according to the relative distance between the agent and the neighboring agents, the solution avoids the impact of long-distance communication interruption. In addition, the system performs differentiated control according to the role of each agent (navigator or follower), so that even if the communication range is limited, each agent in the cluster can still perform effective formation and collaboration in the local environment, achieving overall coordination and reliability of task execution.

[0072] 2. By dynamically calculating the motion trajectory based on the information of neighboring agents, the formation control accuracy of the multi-agent cluster in the local environment can be significantly improved. For the agents in the follower role, the motion trajectory of the current moment and the next moment is calculated, which not only enables the agent to adjust its own position according to the average position of the surrounding agents, but also takes into account the speed information to predict the future position. This ensures that even when the communication distance is limited, the agents can still effectively coordinate and adjust the movement, thereby maintaining the overall stability and formation effect of the cluster. This strategy of local calculation and dynamic adjustment improves the cluster's ability to adapt to environmental changes and enhances the autonomy and reliability of the formation.

[0073] 3. By considering the leader's reference trajectory to adjust the leader's motion trajectory, it ensures that followers in a multi-agent cluster can move more accurately in sync. For the leader role, the current moment's motion trajectory combines the leader's own reference trajectory with the position of neighboring agents, so that the leader can not only guide the followers, but also adapt to the overall dynamics of the cluster. By calculating the motion trajectory at the next moment, all agents can plan their motion paths in advance, further improving the coordination and stability of the formation. This method enhances the cluster's autonomous adjustment capabilities, enables agents to more accurately maintain formations in complex environments, and improves the execution effect and safety of cluster tasks. BRIEF DESCRIPTION OF THE DRAWINGS

[0074] Figure 1 It is a flowchart of a multi-agent cluster formation control method based on pilot-following disclosed in an embodiment of the present application;

[0075] Figure 2 It is a structural schematic diagram of a control algorithm disclosed in an embodiment of the present application;

[0076] Figure 3 It is a module schematic diagram of a multi-agent cluster formation control device based on pilot-following disclosed in an embodiment of the present application;

[0077] Figure 4 It is a structural schematic diagram of an electronic device disclosed in an embodiment of the present application.

[0078] Explanation of the reference numerals: 301, acquisition module; 302, processing module; 303, judgment module; 401, processor; 402, communication bus; 403, user interface; 404, network interface; 405, memory. DETAILED DESCRIPTION

[0079] In order to enable technicians in this field to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below in conjunction with the drawings in the embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this application, not all of the embodiments.

[0080] In the description of the embodiments of the present application, words such as "for example" or "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "for example" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "for example" or "for example" is intended to present related concepts in a specific way.

[0081] In the description of the embodiments of the present application, the meaning of the term "multiple" refers to two or more. For example, multiple systems refer to two or more systems, and multiple screen terminals refer to two or more screen terminals. In addition, the terms "first" and "second" are used for descriptive purposes only and cannot be understood as indicating or implying relative importance or implicitly indicating the indicated technical features. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. The terms "include", "comprise", "have" and their variations all mean "including but not limited to", unless otherwise specifically emphasized.

[0082] The present invention proposes a solution to the formation control problem caused by communication distance limitation in multi-agent clusters. The traditional pilot-following method relies on direct communication between the follower and the pilot. However, in practical applications, especially the followers at the tail or edge of the cluster, may not be able to maintain stable communication with the pilot due to the long distance, resulting in formation disorder. To this end, the present invention adopts a distributed control strategy, combined with local sensor information and data sharing of neighboring individuals, to ensure that the cluster can still maintain a stable formation and efficient collaboration under limited communication conditions, thereby improving the overall efficiency and safety of task execution.

[0083] This embodiment discloses a multi-agent cluster formation control method based on pilot-following. Figure 1 , including the following steps S110-S150:

[0084] S110, obtaining first position information and first speed information sent by multiple agents in a multi-agent cluster.

[0085] A multi-agent cluster formation control method based on pilot-following disclosed in the present application is applied to a target agent, where the target agent is any one of the multiple agents included in the multi-agent cluster.

[0086] In a multi-agent cluster, the cluster consists of n agents, represented by a set E = {1, 2, 3, ..., n}, where some agents are leaders and others are followers. The dynamic model of each agent is represented by the following equation:

[0087]

[0088] Where, the subscript i=1,2,…,n represents the i-th agent, q i represents the position vector, p i represents the velocity vector, u i represents the control input vector.

[0089] S120, collecting real-time second position information and second speed information of the device.

[0090] The multi-agent swarm formation adopts distributed control. Each agent has an independent controller. The control algorithm runs on the controller. The control algorithm structure of each agent is the same. Figure 2 ,The control algorithm mainly consists of three parts: real-time information acquisition module, ,online trajectory generation module and real-time position control module.

[0091] The real-time information acquisition module is responsible for collecting the position and speed information of the intelligent agent and its neighboring intelligent agents in real time, and sending the position and speed information of the neighboring intelligent agents to the online trajectory generation module, and sending the position and speed information of its own intelligent agent to the real-time position control module.

[0092] S120, determining a neighboring agent according to the first position information and the second position information.

[0093] In one possible implementation, determining neighboring intelligent agents based on the first position information specifically includes: determining the distance between the target intelligent agent and other intelligent agents based on the first position information and the second position information; obtaining the first communication distance of the target intelligent agent and the second communication distance of the other intelligent agents; determining the relationship between the first communication distance and the second communication distance; if it is determined that the first communication distance is smaller than the second communication distance, determining whether the distance between the target intelligent agent and other intelligent agents is smaller than the first communication distance; if it is determined that the distance between the target intelligent agent and other intelligent agents is smaller than the first communication distance, determining that the other intelligent agents are neighboring intelligent agents.

[0094] Specifically, the target agent obtains the location information (first location information) of other agents through the communication module, that is, the q j , collect its own real-time location informationq i , using the Euclidean distance formula, calculate the distance between the target agent i and other agents j: d ij =||q i -qj ||, where d ij Represents the physical distance between the target agent and other agents.

[0095] The target agent has its own communication range, called the first communication distance, which indicates the maximum distance that the target agent can directly communicate with other agents. It also obtains the communication range of other agents, called the second communication distance. By comparing the first communication distance of the target agent with the second communication distance of other agents, it is determined whether the communication range of the target agent is smaller or the communication range of other agents is smaller.

[0096] If the first communication distance is less than the second communication distance, it is further checked whether the physical distance between the target agent and the other agents is less than the first communication distance of the target agent. If it is less than, it means that the target agent can communicate with other agents and can be considered as a neighboring agent. Or if it is greater than the second communication distance, it is further checked whether the physical distance between the target agent and the other agents is less than the second communication distance of the target agent.

[0097] Each agent sends its own position and speed information to neighboring agents, and receives position and speed information from neighboring agents. Based on the above principle, the set of neighboring agents of the target agent is expressed as:

[0098] N i ={j∈E:||q i -q j ||≤min{d i ,d j}}

[0099] Among them, N i represents a set of neighboring agents, E represents a multi-agent cluster, q i is the second position information, q j is the first position information, d i is the first communication distance, d j is the second communication distance.

[0100] S140, determining the formation role of the target agent in the multi-agent cluster.

[0101] If the target agent takes the leadership role in the cluster, it provides direction and speed information. The leader determines its own motion state independently and does not rely on other agents. Other agents rely on the position and speed information provided by the leader or neighboring agents for motion control. Other agents communicate with the leader or neighboring followers, and the followers adjust their own motion trajectories.

[0102] Assume that the reference trajectory of the entire cluster is r(t), where t represents time. The reference trajectory of each leader forms a fixed deviation from r(t). Assume that the sth agent is the leader, then its reference trajectory is represented by r s (t) = r(t) + b s , where s∈E L , b s is a known constant, E L The leader forms a set. The leader has a known reference trajectory, and the followers do not have a reference trajectory. There can be multiple leaders, and each leader's b s The constants are different.

[0103] S150, calculating a motion trajectory according to the formation role and based on the first position information, the first speed information, the second position information and the second speed information.

[0104] The online trajectory generation module is responsible for generating the target tracking trajectory of the intelligent agent online and sending the target tracking trajectory to the real-time position control module. The target tracking trajectory calculation and generation methods of the leader and follower are different.

[0105] For the target agent, its control module determines the formation role of the current agent in the cluster. If it is determined to be a follower, it needs to adjust its own motion trajectory according to the information of the neighboring agents. The target agent obtains the location information of the neighboring agents through the communication module. By calculating or recording, the target agent can obtain the number of elements in the neighboring agent set, that is, the number of neighboring agents. When the target agent acts as a follower, it needs to calculate its expected motion trajectory according to the location information of the neighboring agents. The specific calculation formula is:

[0106]

[0107] Among them, r i des (t) is the motion trajectory at the current moment, dim(N i ) is the number of elements, q j (t) is the first position information.

[0108] This formula indicates that the target agent's expected motion trajectory is the average of the positions of all neighboring agents. The current position information of neighboring agents is provided by the communication module, and the target agent receives this information in real time through the communication network. After the target agent receives the position information of all neighboring agents, it uses the above formula to calculate the average of these positions through the internal calculation module. In other words, the next motion trajectory of the target agent will tend to the center position of its neighboring agents. The expected motion trajectory calculated by the target agent through the above formula represents the target position it should go to at the current moment. At this time, the follower agent will adjust its own motion state according to this expected position and gradually move closer to this position.

[0109] Furthermore, after calculating the motion trajectory at the current moment, the target agent then calculates the expected motion trajectory at the next moment. The target agent obtains the current position information q of each agent in its neighboring agent set through the communication module. j (t), which is the position information of the jth neighboring agent at the current time t. The target agent also needs to obtain the speed information p of each agent in the neighboring agent set j (t), that is, the speed information of the jth neighboring agent at the current moment. Then, based on the first position information and the first speed information, the motion trajectory at the next moment is calculated, which is specifically calculated by the following formula:

[0110]

[0111] Among them, r i des (t+1) is the motion trajectory at the next moment, dim(N i ) is the number of elements, q j (t) is the first position information, p j (t) is the first velocity information, and dt is a time step.

[0112] This formula represents the expected motion trajectory r of the target agent at the next time t+1 i des (t+1) is determined by the position and speed information of the neighboring agents. According to the current position and speed information of each neighboring agent, p j (t)·dt is used to predict the position of the neighboring agent at the next moment t+1. Here, dt is the time step, which represents the time interval from the current moment t to the next moment t+1. The expected position of the neighboring agent at the next moment is calculated, and the expected positions of all neighboring agents are averaged. Through this step, the target agent can predict the motion state of the neighboring agent at the next moment, and thus determine the expected motion trajectory that it should follow next.

[0113] In a possible implementation, for the target agent, the control module determines that the current agent role is the navigator. At this time, the agent needs to obtain two key information: the navigator reference trajectory at the current moment. This is the expected trajectory set by the system for the navigator, which is usually provided by the task planning module and is the ideal trajectory that the navigator needs to follow at this moment. The reference trajectory is represented by r s (t) = r(t) + b s The navigator also needs to obtain the location information of each agent in the set of neighboring agents around it from the communication network, that is, the current location of each neighboring agent. The expected motion trajectory of the navigator is calculated by the following formula:

[0114]

[0115] Among them, r i des (t) is the motion trajectory at the current moment, dim(N i ) is the number of elements, q j (t) is the first position information, r i (t) is the reference trajectory of the navigator at the current moment.

[0116] The summation term in the formula reflects the concept of local averaging, that is, the navigator needs to consider not only its own reference trajectory, but also the location information of neighboring agents to calculate its trajectory. Specifically, by interacting with neighboring agents, the navigator can obtain their location information. The number of neighboring agents affects the navigator's perception of the surrounding environment. i )+1) is a weight factor used for normalization, which gives equal weight to the position of each neighboring agent and its own reference trajectory. Here dim(N i ) represents the number of neighboring agents. The form of the weight factor ensures that as the number of neighboring agents increases, the contribution of each agent to the desired motion trajectory will decrease, so as to avoid a certain neighboring agent from having too much influence on the movement of the leader.

[0117] Furthermore, through the local information interaction between agents, the motion trajectory of the agent at the next moment is calculated in combination with the reference trajectory of the navigator. Specifically, the navigator reference trajectory at the next moment is obtained. The navigator reference trajectory is the target trajectory preset by the system, and the navigator needs to follow this trajectory to perform the task. This trajectory may be set in advance by an external system or a global planning algorithm to guide the navigator to move on a specific path. The navigator will obtain the information of its neighboring agents (N iEach navigator uses this local position information to determine the current cluster distribution. By obtaining the speed information of neighboring agents, the navigator can predict the movement trends of these agents in a short period of time. This is crucial for maintaining formation stability and coordination. Based on the navigator's reference trajectory at the next moment, the first position information, and the first speed information, the motion trajectory at the next moment is calculated, specifically using the following formula:

[0118]

[0119] Among them, r i des (t+1) is the motion trajectory at the next moment, dim(N i ) is the number of elements, q j (t) is the first position information, p j (t) is the first speed information, r i (t+1) is the reference trajectory of the navigator at the next moment, and dt is a time step.

[0120] The leader also needs to consider its preset reference trajectory at the next moment. This trajectory is provided by the global planner or upper-level control system to guide the leader to complete a specific task. Introducing the reference trajectory at the next moment into the calculation ensures that the leader can keep moving towards the goal while coordinating with the swarm agent.

[0121] In a possible implementation, after calculating the motion trajectory according to the formation role and based on the first position information, the first speed information, the second position information and the second speed information, the control input of the intelligent agent is generated so that the intelligent agent can adjust the motion according to the calculated motion trajectory to achieve precise control of the intelligent agent. The control input is based on the motion trajectory information at the current moment and the next moment, and is combined with the current position and speed state of the intelligent agent for feedback control. Based on the motion trajectory at the current moment and the motion trajectory at the next moment, the control input of the target intelligent agent is generated, and the control input is specifically as follows:

[0122]

[0123] Among them, u i (t) is the control input, α and β are the control parameters, r i des (t) is the motion trajectory at the current moment, r i des (t+1) is the motion trajectory at the next moment, q i (t) is the second position information, p j (t) is the second velocity information, and dt is a time step.

[0124] Control parameters are used to adjust the agent's response to position error and velocity error. They are usually obtained through system design or experimental adjustment. α mainly affects the agent's response to position error and controls the agent's displacement adjustment. β mainly affects the response to velocity error and controls the agent's movement trend and speed.

[0125] r i des (t) is the expected motion trajectory of the agent at the current moment, q i (t) is the actual position information at the current moment. By calculating the error between the expected position and the current actual position, the agent can adjust its position according to this item to make it closer to the expected trajectory. The speed feedback item is the speed at the next moment calculated according to the expected motion trajectory, reflecting the changing trend of the expected speed. By combining the position error and the speed error, the control input can achieve dual adjustment of the position and speed of the agent, so that it can not only quickly approach the expected position, but also ensure that the motion speed meets expectations.

[0126] By adopting the technical solution of the present application, the position information and speed information of the intelligent agent and the neighboring intelligent agents are collected in real time, and the motion trajectory is dynamically adjusted according to the relative distance between the intelligent agent and the neighboring intelligent agents. The solution avoids the impact of long-distance communication interruption. In addition, the system performs differentiated control according to the role of each intelligent agent (leader or follower), so that even if the communication range is limited, each intelligent agent in the cluster can still form an effective formation and cooperate in the local environment, achieving overall coordination and reliability of task execution.

[0127] This embodiment also discloses a multi-agent cluster formation control device based on piloting and following, wherein the device is a target agent, and a reference Figure 3 , including an acquisition module 301, a processing module 302 and a judgment module 303, wherein:

[0128] The acquisition module 301 is used to acquire the first position information and the first speed information sent by multiple agents in the multi-agent cluster.

[0129] The acquisition module 301 is used to collect the second position information and the second speed information of the device in real time.

[0130] The processing module 302 is used to determine a neighboring intelligent agent according to the first location information and the second location information, and the distance between the neighboring intelligent agent and the target intelligent agent is less than a preset communication distance.

[0131] The judgment module 303 is used to determine the formation role of the target agent in the multi-agent cluster, and the formation role includes a leader role and a follower role.

[0132] The processing module 302 is used to calculate the motion trajectory according to the formation role and based on the first position information, the first speed information, the second position information and the second speed information.

[0133] In a possible implementation, the acquisition module 301 is used to acquire the number of elements of multiple neighboring agents if it is determined that the formation role is a follower.

[0134] The processing module 302 is used to calculate the motion trajectory at the current moment according to the number of elements and the first position information, specifically by the following formula:

[0135]

[0136] Among them, r i des (t) is the motion trajectory at the current moment, dim(N i ) is the number of elements, q j (t) is the first position information.

[0137] In a possible implementation, the processing module 302 is used to calculate the motion trajectory at the next moment based on the first position information and the first speed information, specifically by the following formula:

[0138]

[0139] Among them, r i des (t+1) is the motion trajectory at the next moment, dim(N i ) is the number of elements, q j (t) is the first position information, p j (t) is the first velocity information, and dt is a time step.

[0140] In a possible implementation, the acquisition module 301 is configured to acquire the reference trajectory and first position information of the navigator at the current moment if it is determined that the formation role is the navigator.

[0141] The processing module 302 is used to calculate the motion trajectory at the current moment based on the navigator's reference trajectory at the current moment and the first position information, specifically by the following formula:

[0142]

[0143] Among them, r i des (t) is the motion trajectory at the current moment, dim(N i ) is the number of elements of multiple neighboring agents, q j (t) is the first position information, r i(t) is the reference trajectory of the navigator at the current moment.

[0144] In a possible implementation, the processing module 302 is used to calculate the motion trajectory at the next moment based on the navigator reference trajectory at the next moment, the first position information, and the first speed information, specifically by the following formula:

[0145]

[0146] Among them, r i des (t+1) is the motion trajectory at the next moment, dim(N i ) is the number of elements, q j (t) is the first position information, p j (t) is the first speed information, r i (t+1) is the reference trajectory of the navigator at the next moment, and dt is a time step.

[0147] In a possible implementation, the processing module 302 is used to generate a control input of the target agent based on the motion trajectory at the current moment and the motion trajectory at the next moment. The control input is specifically as follows:

[0148]

[0149] Among them, u i (t) is the control input, α and β are the control parameters, r i des (t) is the motion trajectory at the current moment, r i des (t+1) is the motion trajectory at the next moment, q i (t) is the second position information, p j (t) is the second velocity information, and dt is a time step.

[0150] In a possible implementation, the determination module 303 is used to determine the distance between the target agent and other agents according to the first position information and the second position information.

[0151] The acquisition module 301 is used to acquire the first communication distance of the target intelligent agent and the second communication distances of other intelligent agents.

[0152] The judgment module 303 is used to judge the size relationship between the first communication distance and the second communication distance.

[0153] The judgment module 303 is used to judge whether the distance between the target intelligent agent and other intelligent agents is less than the first communication distance if it is determined that the first communication distance is less than the second communication distance.

[0154] The judgment module 303 is used to determine that the other intelligent agent is the neighboring intelligent agent if it is determined that the distance between the target intelligent agent and the other intelligent agent is less than the first communication distance.

[0155] It should be noted that: when the device provided in the above embodiment realizes its function, only the division of the above functional modules is used as an example. In actual application, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In addition, the device and method embodiments provided in the above embodiment belong to the same concept, and the specific implementation process is detailed in the method embodiment, which will not be repeated here.

[0156] This embodiment also discloses an electronic device, referring to Figure 4 The electronic device may include: at least one processor 401 , at least one communication bus 402 , a user interface 403 , a network interface 404 , and at least one memory 405 .

[0157] The communication bus 402 is used to realize the connection and communication between these components.

[0158] The user interface 403 may include a display screen (Display) and a camera (Camera), and the optional user interface 403 may also include a standard wired interface and a wireless interface.

[0159] The network interface 404 may optionally include a standard wired interface or a wireless interface (such as a WI-FI interface).

[0160] Among them, the processor 401 may include one or more processing cores. The processor 401 uses various interfaces and lines to connect various parts in the entire server, and executes various functions of the server and processes data by running or executing instructions, programs, code sets or instruction sets stored in the memory 405, and calling data stored in the memory 405. Optionally, the processor 401 can be implemented in at least one hardware form of digital signal processing (Digital Signal Processing, DSP), field programmable gate array (Field-Programmable Gate Array, FPGA), and programmable logic array (Programmable Logic Array, PLA). The processor 401 can integrate one or more combinations of a central processing unit (Central Processing Unit, CPU), a graphics processing unit (Graphics Processing Unit, GPU) and a modem. Among them, the CPU mainly processes the operating system, user interface and application programs; the GPU is responsible for rendering and drawing the content to be displayed on the display screen; the modem is used to process wireless communications. It can be understood that the above-mentioned modem may not be integrated into the processor 401, and it can be implemented separately through a chip.

[0161] Among them, the memory 405 may include a random access memory (Random Access Memory, RAM), and may also include a read-only memory (Read-Only Memory). Optionally, the memory includes a non-transitory computer-readable storage medium. The memory 405 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 405 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the above-mentioned various method embodiments, etc.; the data storage area may store data involved in the above-mentioned various method embodiments, etc. The memory 405 may also be at least one storage device located away from the aforementioned processor 401. The memory 405 as a computer storage medium may include an operating system, a network communication module, a user interface 403 module, and an application program for a multi-agent cluster formation control method based on pilot following.

[0162] exist Figure 4In the electronic device shown, the user interface 403 is mainly used to provide an input interface for the user and obtain data input by the user; and the processor 401 can be used to call an application program stored in the memory 405 for a multi-agent cluster formation control method based on pilot following. When executed by one or more processors 401, the electronic device executes one or more methods in the above-mentioned embodiments.

[0163] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all described as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the order of the actions described, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required for the present application.

[0164] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0165] In the several embodiments provided in this application, it should be understood that the disclosed devices can be implemented in other ways. For example, the device embodiments described above are only schematic, such as the division of units, which is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some service interfaces, and the indirect coupling or communication connection of devices or units can be electrical or other forms.

[0166] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0167] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0168] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a memory 405, including a number of instructions for a computer device (which can be a personal computer, server or network device, etc.) to perform all or part of the steps of the various embodiments of the present application. The aforementioned memory 405 includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a magnetic disk or an optical disk.

[0169] The present application also discloses a computer-readable storage medium, wherein the computer-readable storage medium stores instructions. When executed by one or more processors 401, the electronic device executes one or more of the methods described in the above embodiments.

[0170] The above is only an exemplary embodiment of the present disclosure, and the scope of the present disclosure cannot be limited thereto. That is, any equivalent changes and modifications made according to the teachings of the present disclosure are still within the scope of the present disclosure. After considering the disclosure of the specification and the truth of practice, it will be easy for those skilled in the art to think of other embodiments of the present disclosure. This application is intended to cover any modification, use or adaptation of the present disclosure, which follows the general principles of the present disclosure and includes common knowledge or customary technical means in the technical field that are not recorded in the present disclosure. The description and examples are regarded as exemplary only, and the scope and spirit of the present disclosure are defined by the claims.

Claims

1. A multi-agent cluster formation control method based on pilot-following, characterized in that: The method is applied to a target agent, comprising: Obtaining first position information and first speed information sent by multiple agents in a multi-agent cluster; Collecting real-time second position information and second speed information of the device; Determine a neighboring intelligent body according to the first location information and the second location information, wherein the distance between the neighboring intelligent body and the target intelligent body is less than a preset communication distance; Determine a formation role of the target agent in the multi-agent cluster, wherein the formation role includes a leader role and a follower role; A motion trajectory is calculated according to the formation role and based on the first position information, the first speed information, the second position information, and the second speed information.

2. The multi-agent cluster formation control method based on pilot-following according to claim 1 is characterized in that: The calculating the motion trajectory according to the formation role and based on the first position information, the first speed information, the second position information, and the second speed information specifically includes: If it is determined that the formation role is the follower, obtaining the number of elements of the plurality of neighboring agents; The motion trajectory at the current moment is calculated according to the number of elements and the first position information, specifically by the following formula: Among them, r i des (t) is the motion trajectory at the current moment, dim(N i ) is the number of elements, q j (t) is the first position information.

3. The multi-agent cluster formation control method based on pilot-following according to claim 2 is characterized in that: After calculating the motion trajectory at the current moment according to the number of elements and the first position information, the method further includes: Based on the first position information and the first speed information, the motion trajectory at the next moment is calculated, specifically by the following formula: Among them, r i des (t+1) is the motion trajectory of the next moment, dim(N i ) is the number of elements, q j (t) is the first position information, p j (t) is the first speed information, and dt is a time step.

4. The multi-agent cluster formation control method based on pilot-following according to claim 1 is characterized in that: The calculating the motion trajectory according to the formation role and based on the first position information, the first speed information, the second position information, and the second speed information specifically further includes: If it is determined that the formation role is the navigator, obtaining the navigator's reference trajectory and the first position information at the current moment; Based on the navigator reference trajectory at the current moment and the first position information, the motion trajectory at the current moment is calculated, specifically by the following formula: Among them, r i des (t) is the motion trajectory at the current moment, dim(N i ) is the number of elements of the multiple neighboring agents, q j (t) is the first position information, r i (t) is the reference trajectory of the navigator at the current moment.

5. The multi-agent cluster formation control method based on pilot-following according to claim 4 is characterized in that: After calculating the motion trajectory at the current moment based on the navigator reference trajectory at the current moment and the first position information, the method further includes: Based on the navigator's reference trajectory at the next moment, the first position information, and the first speed information, the motion trajectory at the next moment is calculated, specifically by the following formula: Among them, r i des (t+1) is the motion trajectory of the next moment, dim(N i ) is the number of elements, q j (t) is the first position information, p j (t) is the first speed information, r i (t+1) is the reference trajectory of the navigator at the next moment, and dt is a time step.

6. The multi-agent swarm formation control method based on pilot-following according to claim 1 is characterized in that: After calculating the motion trajectory according to the formation role and based on the first position information, the first speed information, the second position information, and the second speed information, the method further includes: Based on the motion trajectory at the current moment and the motion trajectory at the next moment, the control input of the target agent is generated, and the control input is specifically as follows: Among them, u i (t) is the control input, α and β are control parameters, r i des (t) is the motion trajectory at the current moment, r i des (t+1) is the motion trajectory at the next moment, q i (t) is the second position information, p j (t) is the second speed information, and dt is a time step.

7. The multi-agent cluster formation control method based on pilot-following according to claim 1 is characterized in that: The determining of the neighboring agent according to the first location information specifically includes: Determine the distance between the target agent and other agents according to the first position information and the second position information; Acquire a first communication distance of the target intelligent agent and a second communication distance of the other intelligent agents; Determining a magnitude relationship between the first communication distance and the second communication distance; If it is determined that the first communication distance is smaller than the second communication distance, determining whether the distance between the target agent and other agents is smaller than the first communication distance; If it is determined that the distance between the target agent and other agents is less than the first communication distance, the other agents are determined to be the neighboring agents.

8. A multi-agent cluster formation control device based on pilot-following, characterized in that: The device is a target intelligent agent, comprising an acquisition module (301), a processing module (302) and a judgment module (303), wherein: The acquisition module (301) is used to acquire first position information and first speed information sent by multiple agents in a multi-agent cluster; The acquisition module (301) is used to collect the second position information and the second speed information of the device in real time; The processing module (302) is used to determine a neighboring intelligent entity according to the first location information and the second location information, wherein the distance between the neighboring intelligent entity and the target intelligent entity is less than a preset communication distance; The judgment module (303) is used to determine the formation role of the target agent in the multi-agent cluster, and the formation role includes a leader role and a follower role; The processing module (302) is used to calculate a motion trajectory according to the formation role and based on the first position information, the first speed information, the second position information and the second speed information.

9. An electronic device, characterized in that: The electronic device comprises a processor (401), a communication bus (402), a memory (405), a user interface (403), a network interface (404) and a memory (405), wherein the memory (405) is used to store instructions, the user interface (403) and the network interface (404) are both used to communicate with other devices, and the processor (401) is used to execute the instructions stored in the memory (405) so that the electronic device executes the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores instructions, and when the instructions are executed, the method according to any one of claims 1 to 7 is executed.

Images