Second-order multi-agent consistency processing method and storage medium based on ZYNQ

Abstract

The present application relates to the technical field of distributed processing of multiple intelligent agents, and discloses a second-order multi-agent consistency processing method and storage medium based on ZYNQ, which establishes a directed network G composed of N intelligent agents; collects the first-order state and second-order state information of the #imgabs0#th intelligent agent; exchanges information with the state information stored in the DDR through a communication module, and in the case where the first-order information sensor is damaged, the #imgabs1#th intelligent agent only sends the second-order information to the neighbor #imgabs2# and receives the sampled information sent from the neighbor #imgabs3#; when the data is received, the IP core in the intelligent agent #imgabs4# calls the DDR through the bus, including its own first-order and second-order state information, the sampled second-order state information from the neighbor, and the control parameters. k 1 ，k 2 and control the step size, and then perform consistency processing according to the average rule. This can enable the intelligent system to achieve state consistency.

Description

Technical Field

[0001] The present application relates to the technical field of distributed processing of multiple agents, for example, to a second-order multi-agent consistency processing method and storage medium based on ZYNQ. Background Art

[0002] As an important branch of distributed artificial intelligence, multi-agent systems have attracted extensive research interests. They are increasingly used in fields such as drones, sensor networks, and industrial production. In multi-agent systems, the consistency problem is its foundation, especially the second-order consistency problem, which is to make their second-order states (such as speed and position) tend to be consistent through the interaction between agents, which is crucial to solving complex cluster processing problems.

[0003] However, in practical applications, due to technical limitations or environmental interference, such as in deep sea or deep space exploration, it is difficult for agents to directly obtain second-order information about their neighbors, which makes it difficult for the entire agent system to be in a common state.

[0004] It should be noted that the information disclosed in the above background technology section is only used to enhance the understanding of the background of the present application, and therefore may include information that does not constitute the prior art known to ordinary technicians in the field. Summary of the invention

[0005] In order to provide a basic understanding of some aspects of the disclosed embodiments, a brief summary is given below. The summary is not an extensive review, nor is it intended to identify key / critical elements or delineate the scope of protection of these embodiments, but rather serves as a prelude to the detailed description that follows.

[0006] The present disclosure provides a second-order multi-agent consistency processing method based on ZYNQ, the method comprising:

[0007] Establish a directed network G consisting of N agents, where the topology of the directed network G has at least one spanning tree, and the Laplace matrix is L ;

[0008] Collection The first-order state and second-order state information of each agent is used to obtain the corresponding sampling data and Stored in DDR;

[0009] The state information stored in DDR is exchanged through the communication module. Considering the damage of the first-order information sensor, the Agents only send second-order state information To Neighbors and receive messages from neighbors The sampling information sent;

[0010] When the data is received, the agent The IP core in the bus calls the DDR including its own first-order and second-order status information and , sampled second-order state information from neighbors , and control parameters , and control step length ,Then the consistency is processed according to the average rule, where T is the number of sampling times;

[0011] Agent Based on the processing signal obtained by the consistency processing, the self-state information is updated.

[0012] In some embodiments, , ,in represents an n-dimensional real vector, The convergence speed is , T is the number of sampling times, control parameter , Satisfaction Matrix There is one eigenvalue of multiplicity 1, and all other eigenvalues ​​are inside the unit circle.

[0013] In some embodiments, Satisfy the formula ,in yes N dimensional identity matrix.

[0014] In some embodiments, the method further comprises:

[0015] Considering the influence of communication noise, the first-order information of the agent is affected by additive Gaussian white noise with a mean value of w during transmission. Actual received from neighbors The information is , , For the The second-order state information of each agent, For the agent in the case of high-speed white noise that obeys a normal distribution with mean w Stores the received first-order information.

[0016] In some embodiments, the control protocol corresponding to the consistency processing according to the average rule , satisfying the formula:

[0017] , =1,…,N, where is the Laplace matrix L Line Elements of a column.

[0018] In some embodiments, the agent Based on the processed signal obtained by consistency processing, update its own state information to meet the formula:

[0019] ,

[0020] ,

[0021] in, For intelligent agents Updated first-order status information, For intelligent agents Updated second-order status information.

[0022] In some embodiments, the method may further include:

[0023] After updating its own state information, if the task is not completed, it collects the first-order state and second-order state information of other agents, obtains the corresponding sampling data and stores it in DDR.

[0024] An embodiment of the present disclosure provides a storage medium storing program instructions, which, when run, execute the second-order multi-agent consistency processing method based on ZYNQ in the above embodiment.

[0025] The second-order multi-agent consistency processing method and storage medium based on ZYNQ provided in the embodiments of the present disclosure can achieve the following technical effects:

[0026] By establishing a directed network G composed of N intelligent agents; collecting The first-order state and second-order state information of each intelligent agent; the state information stored in the DDR is exchanged through the communication module. Considering the damage of the first-order information sensor, the Agents only send second-order information to their neighbors and receive messages from neighbors The sampling information sent; when the data is received, the agent The IP core in the bus calls the DDR, including its own first-order and second-order state information, and the sampled second-order state information from the neighbor. And control parameters , And control the step size, and then perform consistency processing according to the average rule. This can enable the intelligent system to achieve state consistency.

[0027] The above general description and the following description are exemplary and explanatory only and are not intended to limit the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] One or more embodiments are exemplarily described by corresponding drawings, which do not limit the embodiments. Elements with the same reference numerals in the drawings are shown as similar elements, and the drawings do not constitute a scale limitation, and wherein:

[0029] Figure 1 It is a flowchart of a second-order multi-agent consistency processing method based on ZYNQ provided in an embodiment of the present disclosure;

[0030] Figure 2 It is a flowchart of another second-order multi-agent consistency processing method based on ZYNQ provided in an embodiment of the present disclosure;

[0031] Figure 3 It is a hardware architecture diagram provided by an embodiment of the present disclosure;

[0032] Figure 4 It is a structural diagram of a second-order multi-agent consistency processing system based on ZYNQ provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0033] In order to be able to understand the features and technical contents of the embodiments of the present disclosure in more detail, the implementation of the embodiments of the present disclosure is described in detail below in conjunction with the accompanying drawings. The attached drawings are for reference only and are not used to limit the embodiments of the present disclosure. In the following technical description, for the convenience of explanation, a full understanding of the disclosed embodiments is provided through multiple details. However, one or more embodiments can still be implemented without these details. In other cases, to simplify the drawings, well-known structures and devices can be simplified for display.

[0034] The terms "first", "second", etc. in the embodiments of the present disclosure are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the terms used in this way can be interchanged where appropriate, so as to describe the embodiments of the present disclosure described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions.

[0035] Unless otherwise stated, the term "plurality" means two or more.

[0036] In the embodiment of the present disclosure, the character " / " indicates that the preceding and following objects are in an "or" relationship. For example, A / B indicates: A or B.

[0037] The term "and / or" is a description of the association relationship between objects, indicating that three relationships can exist. For example, A and / or B means: A or B, or, A and B.

[0038] The term "correspondence" may refer to an association relationship or a binding relationship. The correspondence between A and B means that there is an association relationship or a binding relationship between A and B.

[0039] The following is an explanation of the ZYNQ-based second-order multi-agent consistency processing method and storage medium provided in the embodiments of the present disclosure in conjunction with the accompanying drawings.

[0040] Figure 1 It is a flow chart of a second-order multi-agent consistency processing method based on ZYNQ provided in an embodiment of the present disclosure.

[0041] like Figure 1 As shown, the second-order multi-agent consistency processing method based on ZYNQ may include:

[0042] S01, establish a directed network G consisting of N intelligent agents, where the topological structure of the directed network G has at least one spanning tree, and the Laplace matrix is L ;

[0043] S02, collection The first-order state and second-order state information of each agent is used to obtain the corresponding sampling data and And stored in DDR;

[0044] S03, the state information stored in the DDR is exchanged through the communication module. Considering the damage of the first-order information sensor, The agent only sends second-order state information To Neighbors and receive messages from neighbors The sampling information sent;

[0045] S04, when the data is received, the agent The IP core in the bus calls the DDR including its own first-order and second-order status information and , sampled second-order state information from neighbors , and control parameters , and control step length ,Then the consistency is processed according to the average rule, where T is the number of sampling times;

[0046] S05, Agent Based on the processing signal obtained by the consistency processing, the self-state information is updated.

[0047] In the present disclosure, the consistency processing of the first-order state and second-order state information of the intelligent agent is performed based on the ZYNQ platform, which can complete the distributed deployment of the algorithm on multiple ZYNQ platforms and has high system performance and scalability, thereby enabling the intelligent agent system to achieve state consistency.

[0048] In some embodiments, , ， ,in represents an n-dimensional real vector, The convergence speed is , T is the number of sampling times, control parameter , Satisfaction Matrix has an eigenvalue of multiplicity 1, and all other eigenvalues ​​are inside the unit circle, where It is an expression of the convergence speed of an algorithm and is defined as It means that g(x) is the bound of f(x), which in this article means that the algorithm converges to 1 / T.

[0049] In some embodiments, Satisfy the formula ,in yes N dimensional identity matrix.

[0050] In some embodiments, Figure 1 The method may also include:

[0051] Considering the influence of communication noise, the first-order information of the agent is affected by additive Gaussian white noise with a mean value of w during transmission. Actual received from neighbors The information is , , For the The second-order state information of each agent, For the agent in the case of high-speed white noise that obeys a normal distribution with mean w Stores the received first-order information.

[0052] In some embodiments, the control protocol corresponding to the consistency processing according to the average rule , satisfying the formula:

[0053] , =1,…,N, where is the Laplace matrix L Line The elements of the column, based on this control protocol, do not require division operations, and can make the states of multiple agents tend to a weighted average result.

[0054] In some embodiments, the agent Based on the processed signal obtained by consistency processing, update its own state information to meet the formula:

[0055] ，

[0056] ,

[0057] in, For intelligent agents Updated first-order status information, For intelligent agents Updated second-order status information.

[0058] In some embodiments, Figure 1 The method may also include:

[0059] After updating its own state information, if the task is not completed, it collects the first-order state and second-order state information of other agents, obtains the corresponding sampling data and stores it in DDR.

[0060] Figure 2 is a flow chart of another second-order multi-agent consistency processing method based on ZYNQ provided in an embodiment of the present disclosure, Figure 3 This is a hardware architecture diagram provided by the embodiment of the present disclosure, combined with Figure 2 and Figure 3 ,right Figure 1 The second-order multi-agent consensus processing method based on ZYNQ is further described in .

[0061] Step 1: Initialize data

[0062] We are established by Agents form a directed network , its topological structure has at least one spanning tree, and the Laplace matrix is . No. ( =1,2,3…N) agents’ initial state first-order and second-order information are , , set the control parameters and control step size. Control step size is a positive decreasing sequence, satisfying ,T is the number of sampling times, control parameter , Satisfaction Matrix has an eigenvalue of multiplicity 1, and all other eigenvalues ​​are inside the unit circle, where

[0063] .

[0064] Step 2: Agent state data sampling and storage

[0065] No. ( =1,2,3…N) Each agent samples its first-order state and second-order state information to obtain sampled data and Stored in DDR.

[0066] Step 3: Send data to neighbors and receive

[0067] The agent exchanges information with the state information stored in the DDR through the communication module. We consider the case where the first-order information sensor is damaged. ( =1,2,3…N) Agents can send only second-order information To Neighbors ( =1,2,3…N, ≠ ) and receive messages from neighbors Considering the influence of communication noise, we can assume that the first-order information of the agent is affected by additive Gaussian white noise with a mean of 0 during transmission, and the actual information received from the neighbor is , , is a high-speed white noise that obeys a normal distribution with a mean of 0, and the agent stores the received first-order information. In other words, the above w can be 0.

[0068] Step 4: Implement the consensus algorithm

[0069] When the data is received, the agent ( =1,2,3…N) The core calls the data in DDR through the bus, including its own first-order and second-order state sampling information and , sampled second-order state information from neighbors , and control parameters , and control step length , and then perform consistency processing according to the average rule:

[0070] , =1,…,N,

[0071] Step 5: Status Update

[0072] The agent updates its own state information through the processing signal obtained by the consensus algorithm:

[0073] ,

[0074] ,

[0075] Determine whether the task is completed. If not, proceed to step 2.

[0076] Combination Figure 4 As shown, the embodiment of the present disclosure provides a second-order multi-agent consistency processing system 400 based on ZYNQ, including a processor 404 and a memory 401. Optionally, the system may also include a communication interface 402 and a bus 403. Among them, the processor 404, the communication interface 402, and the memory 401 can communicate with each other through the bus 403. The communication interface 402 can be used for information transmission. The processor 404 can call the logic instructions in the memory 401 to execute the second-order multi-agent consistency processing method based on ZYNQ of the above embodiment.

[0077] In addition, the logic instructions in the memory 401 described above may be implemented in the form of software functional units and when sold or used as independent products, may be stored in a computer-readable storage medium.

[0078] The memory 401 is a computer-readable storage medium that can be used to store software programs and computer executable programs, such as program instructions / modules corresponding to the method in the embodiment of the present disclosure. The processor 404 executes the functional application and data processing by running the program instructions / modules stored in the memory 401, that is, the second-order multi-agent consistency processing method based on ZYNQ in the above embodiment is implemented.

[0079] The memory 401 may include a program storage area and a data storage area, wherein the program storage area may store an operating system and an application required for at least one function; the data storage area may store data created according to the use of the terminal device, etc. In addition, the memory 401 may include a high-speed random access memory and may also include a non-volatile memory.

Claims

1. A second-order multi-agent consensus processing method based on ZYNQ, characterized in that: The method comprises: Establish a directed network G consisting of N agents, where the topology of the directed network G has at least one spanning tree, and the Laplace matrix is L ; Collection The first-order state and second-order state information of each agent is used to obtain the corresponding sampling data and And stored in DDR; The state information stored in DDR is exchanged through the communication module. Considering the damage of the first-order information sensor, the Agents only send second-order state information To Neighbors and receive messages from neighbors The sampling information sent; When the data is received, the agent The IP core in the bus calls the DDR including its own first-order and second-order status information and , sampled second-order state information from neighbors , and control parameters , and control step length , and then the consistency is processed according to the average rule; Agent Based on the processing signal obtained by the consistency processing, update its own state information; in, The convergence speed is , T is the number of sampling times, control parameter , Satisfaction Matrix There is an eigenvalue with a multiplicity of 1, and the other eigenvalues ​​are all inside the unit circle. When T is 1, , ,in represents an n-dimensional real vector; Satisfy the formula ,in yes N dimensional identity matrix; The control protocol corresponding to the consistency processing according to the average rule , satisfying the formula: , =1,…,N, where is the Laplace matrix L Line Elements of a column; The agent Based on the processed signal obtained by consistency processing, update its own state information to meet the formula: ， ， in, For intelligent agents Updated first-order status information, For intelligent agents Updated second-order status information.

2. The method according to claim 1, characterized in that The method further comprises: Considering the influence of communication noise, the first-order information of the agent is affected by additive Gaussian white noise with a mean value of w during transmission. Actual received from neighbors The information is , , For the The second-order state information of each agent, For the agent in the case of high-speed white noise that obeys a normal distribution with mean w Stores the received first-order information.

3. The method according to claim 1, characterized in that The method further comprises: After updating its own state information, if the task is not completed, it collects the first-order state and second-order state information of other agents, obtains the corresponding sampling data and stores it in DDR.

4. A storage medium storing program instructions, characterized in that: When the program instructions are run, they execute the second-order multi-agent consistency processing method based on ZYNQ as described in any one of claims 1 to 3.

Images