Unmanned aerial vehicle cluster autonomous decision-making method and system integrating Beidou enhancement service and multi-source perception

Abstract

The invention discloses an unmanned aerial vehicle cluster autonomous decision-making method and system fusing Beidou enhancement service and multi-source perception, and the method comprises the steps: enabling each unmanned aerial vehicle to receive a satellite-based enhancement signal, carrying out the real-time calculation of the satellite-based enhancement signal through employing a precise single-point positioning technology, and obtaining precise PVT information; each unmanned aerial vehicle synchronously collects sensor information, carries out space-time alignment on the sensor information and the precise PVT information, and processes local sensing features and wide-area geographic information by using an information fusion model to generate a global environment situation tensor; inputting the global environment situation tensor into a deep reinforcement learning strategy network to obtain a task instruction set; carrying out consensus confirmation on key instructions in the task instruction set by utilizing a Beidou global short message to obtain a task instruction after consensus; and each unmanned aerial vehicle performs collaborative operation based on the task instruction after consensus, performs real-time fusion on new perception data generated in the execution process and precise PVT information, and inputs the fused data into the information fusion model again to complete an autonomous decision closed loop.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of unmanned system cluster control and artificial intelligence, and particularly relates to a Beidou enhanced service and multi-source perception integrated unmanned aerial vehicle cluster autonomous decision method and system. BACKGROUND

[0002] With the development of unmanned aerial vehicle cluster technology, its application in the fields of emergency rescue, environmental monitoring, etc. is increasingly in-depth. However, in remote areas, oceans or complex mountains without ground network coverage, the cluster system faces severe challenges: first, the positioning accuracy is insufficient, and the traditional positioning means such as GPS has a precision of meters, which is difficult to meet the demand of fine cooperative operation; second, the communication link is interrupted, so that the cooperative decision within the cluster and with the rear cannot be made; third, the perception and decision lack a unified high-precision space-time reference, resulting in distorted information fusion and decreased decision quality.

[0003] The Beidou-3 global satellite navigation system provides services such as satellite-based augmentation and global short message, which provides a unique infrastructure to solve the above problems. However, the current application of Beidou technology in the field of unmanned aerial vehicles is mostly limited to single positioning or communication functions, and it has not been deeply integrated into the intelligent decision-making closed loop of unmanned systems, and has not fully tapped its potential as a "spatial information hub".

[0004] Therefore, there is an urgent need for an innovative solution that can systematically integrate Beidou cutting-edge services with cutting-edge artificial intelligence decision-making technology to unlock the advanced autonomous capabilities of unmanned aerial vehicle clusters in extreme environments. SUMMARY

[0005] The present application aims to solve the problems of the prior art and provides the following solution: A Beidou enhanced service and multi-source perception integrated unmanned aerial vehicle cluster autonomous decision method, comprising the following steps: Each unmanned aerial vehicle in the unmanned aerial vehicle cluster receives a satellite-based augmentation signal and uses precise point positioning technology to solve the satellite-based augmentation signal in real time to obtain precise PVT information; Each unmanned aerial vehicle in the unmanned aerial vehicle cluster synchronously collects sensor information and aligns the precise PVT information in space-time, and simultaneously uses an information fusion model to process local perception features and wide-area geographic information to generate a global environment situation tensor with space-time confidence; The global environment situation tensor is input into a pre-trained deep reinforcement learning strategy network to obtain a task instruction set; The key instructions in the task instruction set are confirmed by consensus using Beidou global short message to obtain the consensus task instructions; Each UAV performs collaborative operations based on the consensus-based mission instructions, and integrates the new perception data generated during the execution process with the precise PVT information in real time, and then inputs it back into the information fusion model to complete the autonomous decision-making closed loop.

[0006] Preferably, the satellite-based augmentation signal is: in, Indicates receiver r For satellite s In frequency i pseudorange observations on Indicates the geometric distance between the receiver and the satellite. c Represents the speed of light. Indicates receiver clock bias. Indicates satellite clock bias, Indicates tropospheric delay, Indicates ionospheric delay, Indicates the receiver is at frequency i On pseudo-range hardware delay, Indicates the satellite's frequency i On pseudo-range hardware delay, This represents pseudorange observation noise and multipath error. Indicates receiver r For satellite s In frequency i Carrier phase observations on Represents frequency i carrier wavelength, Indicates the ambiguity of the integer period. Indicates receiver r In frequency i Phase hardware delay on, Indicates satellite s In frequency i Phase hardware delay on, This represents carrier phase observation noise and multipath error.

[0007] Preferably, the information fusion model includes: in, The attention score represents the spatiotemporal reliability. Q This represents the query vector in the attention mechanism. This represents the learnable weight matrix. Indicates from the i The semantic vector of each information source The dimension of the key vector. λ This represents the preset weighting coefficient. indicates the spatiotemporal reliability corresponding to the i first information source.

[0008] Preferably, the method for performing the consensus confirmation comprises: the leader node or the decision node Cmd performs a standardized serialization process, and then uses an anti-collision cryptographic hash function to calculate a fixed-length digital fingerprint, obtaining a hash digest H cmd ; encapsulates the hash digest H cmd , the unique task number Task ID , and the key spatiotemporal parameters obtained by Beidou precise positioning into a lightweight consensus request data packet Pkt req , and then the leader node broadcasts the consensus request data packet Pkt req to all follower nodes in the cluster and the remote command center through the Beidou No. 3 RDSS short message service; After receiving the consensus request data packet Pkt re , the follower nodes or the command center perform a local verification step to obtain a confirmation message Msgack ; The leader node listens to and collects the confirmation messages T from other nodes within a preset time window Δ Msgack , and when the number of valid confirmation messages received M satisfies a preset condition, it is determined that consensus is reached.

[0009] Preferably, the local verification step comprises: obtaining the complete task instruction Cmd' ; using an anti-collision cryptographic hash function to calculate the hash value Cmd' H Cmd’ of the complete task instruction ; H cmd comparing the received hash digest H Cmd’ with the locally calculated hash value H cmd ; H Cmd’ , it is determined that the instructions are consistent and have not been tampered with. ​If the command is found to be consistent and has not been tampered with, a confirmation message is sent in response via BeiDou short message. Msgack The confirmation message Msgack Includes the unique task number Task ID and confirmation signal ACK .

[0010] The present invention also provides an autonomous decision-making system for unmanned aerial vehicle (UAV) swarms that integrates BeiDou enhanced services and multi-source perception. The system applies the above-mentioned method and includes: an information acquisition module, an information processing module, a task instruction generation module, a consensus confirmation module, and an execution feedback module. In the information acquisition module, each UAV in the UAV cluster receives satellite-based augmentation signals and uses precise point positioning technology to perform real-time calculations on the satellite-based augmentation signals to obtain precise PVT information. In the information processing module, each UAV in the UAV cluster synchronously collects sensor information and aligns it with the precise PVT information in time and space. At the same time, the information fusion model is used to process local perception features and wide-area geographic information to generate a global environmental situation tensor with time and space confidence. The task instruction generation module is used to input the global environment situation tensor into a pre-trained deep reinforcement learning policy network to obtain a task instruction set. The consensus confirmation module uses BeiDou global short message service to confirm the key instructions in the task instruction set to obtain the consensus-received task instructions. In the execution feedback module, each UAV performs collaborative operations based on the consensus-based task instructions, and integrates the new perception data generated during the execution process with the precise PVT information in real time, and then inputs it back into the information fusion model to complete the autonomous decision-making closed loop.

[0011] Preferably, the satellite-based augmentation signal is: in, Indicates receiver r For satellite s In frequency i pseudorange observations on Indicates the geometric distance between the receiver and the satellite. c Represents the speed of light. Indicates receiver clock bias. Indicates satellite clock bias, Indicates tropospheric delay, Indicates ionospheric delay, Indicates the receiver is at frequency i On pseudo-range hardware delay, Indicates the satellite's frequencyi On pseudo-range hardware delay, This represents pseudorange observation noise and multipath error. Indicates receiver r For satellite s In frequency i Carrier phase observations on Represents frequency i carrier wavelength, Indicates the ambiguity of the integer period. Indicates receiver r In frequency i Phase hardware delay on, Indicates satellite s In frequency i Phase hardware delay on, This represents carrier phase observation noise and multipath error.

[0012] Preferably, the information fusion model includes: in, The attention score represents the spatiotemporal reliability. Q This represents the query vector in the attention mechanism. This represents the learnable weight matrix. Indicates from the i The semantic vector of each information source This represents the dimension of the key vector. λ This represents the preset weighting coefficient. Indicates the first i The spatiotemporal reliability of each information source.

[0013] Preferably, the workflow of the consensus confirmation module includes: The leader node or decision-making node will receive the task instructions awaiting consensus. Cmd The data is then standardized and serialized, followed by computation using a collision-resistant cryptographic hash function to generate a fixed-length digital fingerprint, resulting in a hash digest. H cmd ; The hash digest H cmd Unique task number Task ID The key spatiotemporal parameters obtained from BeiDou precise positioning are encapsulated into a lightweight consensus request data packet. Pkt req Subsequently, the leadership node transmits the consensus request data packet via the BeiDou-3 RDSS short message service. Pkt req Broadcast to all follower nodes in the cluster and the remote command center; The follower node or the command center receives the consensus request data packet Pkt re After that, a local verification step is performed to obtain a confirmation message Msgack The leader node listens to and collects the confirmation messages from other nodes within a preset time window Δ T Msgack When the number of valid confirmation messages received satisfies a preset condition, it is determined that consensus is reached. M

[0014] Preferably, in the consensus confirmation module, the local verification step comprises: Obtaining a complete task instruction Cmd' Calculating a hash value of the complete task instruction using an anti-collision encryption hash function Cmd' H Cmd’ Comparing the received hash digest H cmd with the locally calculated hash value H Cmd’ and only if H cmd = H Cmd’ it is determined that the instruction is consistent and has not been tampered with; If it is determined that the instruction is consistent and has not been tampered with, a confirmation message is returned through a Beidou short message, the confirmation message Msgack contains the unique task number Msgack and a confirmation signal Task ID ACK

[0015] Compared with the prior art, the present application has the following beneficial effects: ​​​​​​​​The application enables the unmanned aerial vehicle cluster to maintain centimeter-level high-precision positioning and reliable communication in any area without ground network coverage in the world by deeply fusing the satellite-based augmentation of Beidou-3 system and global short message communication capability, and significantly improves the environmental adaptability of the system; the multi-source perception fusion mechanism based on unified space-time reference deeply couples the positioning accuracy and perception data, so that the decision-making process such as path planning and target identification is established on the basis of accurate space-time data, and the accuracy and reliability of the decision-making are greatly improved; the innovatively designed lightweight consensus protocol makes full use of the characteristics of Beidou short message to ensure the smoothness of the core instruction chain in the extreme communication environment, and endows the system with strong anti-interference and fault tolerance capability; the application deeply integrates the characteristic services of the independent Beidou system of China, forms a system-level solution with unique technology and significant threshold, and has important popularization and application value in key fields such as emergency rescue. BRIEF DESCRIPTION OF DRAWINGS

[0016] In order to more clearly illustrate the technical solutions of the present application, the following briefly introduces the drawings needed to be used in the embodiments. Obviously, the drawings described in the following embodiments are only some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained without creative labor.

[0017] Figure 1 The method flowchart of the embodiment of the present application. DETAILED DESCRIPTION

[0018] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some embodiments of the present application, not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0019] In order to make the above-mentioned purposes, features and advantages of the present application more obvious and easy to understand, the present application will be further described in detail below with reference to the drawings and specific embodiments.

[0020] Embodiment one In this embodiment, as shown in the figure, a method for unmanned aerial vehicle cluster autonomous decision-making by fusing Beidou augmentation service and multi-source perception includes the following steps: Figure 1 S1. Each unmanned aerial vehicle in the unmanned aerial vehicle cluster receives satellite-based augmentation signals, and uses precise point positioning technology to solve the satellite-based augmentation signals in real time to obtain precise PVT information. S2. Each unmanned aerial vehicle in the unmanned aerial vehicle cluster receives multi-source perception data, and uses the multi-source perception data to assist in solving the satellite-based augmentation signals.

[0021] In this embodiment, each unit in the UAV swarm uses an airborne BeiDou-3 receiver to receive PPP-B2b and / or Galileo HAS satellite-based augmentation signals. Through precise point positioning technology, it calculates and obtains absolute coordinates at the centimeter to decimeter level in real time. This high-precision position, velocity, and time information is used as a unified spatiotemporal reference to provide accurate spatiotemporal labels for all sensing data and subsequent decision-making.

[0022] The satellite-based augmentation signal is: in, Indicates receiver r For satellite s In frequency i pseudorange observations on Indicates the geometric distance between the receiver and the satellite. c Represents the speed of light. Indicates receiver clock bias. Indicates satellite clock bias, Indicates tropospheric delay, Indicates ionospheric delay, Indicates the receiver is at frequency i On pseudo-range hardware delay, Indicates the satellite's frequency i On pseudo-range hardware delay, This represents pseudorange observation noise and multipath error. Indicates receiver r For satellite s In frequency i Carrier phase observations on Represents frequency i carrier wavelength, Indicates the ambiguity of the integer period. Indicates receiver r In frequency i Phase hardware delay on, Indicates satellite s In frequency i Phase hardware delay on, This represents carrier phase observation noise and multipath error. Parameter estimation is performed using Kalman filtering, and the receiver's precise coordinates are calculated in real time to obtain accurate PVT information, providing a unified and high-precision spatiotemporal reference for each step of perception and decision-making.

[0023] S2. Each UAV in the UAV swarm synchronously collects sensor information and aligns it with precise PVT information in time and space. At the same time, the information fusion model is used to process local perception features and wide-area geographic information to generate a global environmental situation tensor with time and space confidence.

[0024] In this embodiment, the information fusion model based on spatio-temporal attention mechanism introduces spatio-temporal weight factor on the original attention mechanism: Let the semantic feature vector set from K information sources be The corresponding Beidou positioning information (precision factor, signal-to-noise ratio) constitutes a spatio-temporal reliability vector The information fusion model includes: calculating the attention score fused with spatio-temporal reliability: Wherein, represents the final calculated attention score fused with content relevance and spatio-temporal reliability; Q represents the query vector in the attention mechanism; represents a learnable weight matrix used to project the input feature to the "key" space; represents the semantic vector from the i-th information source; i represents the dimension of the key vector; represents the standard scaled dot product attention calculation, which is used to evaluate the relevance of the query and the content of the i-th information source; represents a preset weight coefficient used to balance the content relevance score and the spatio-temporal reliability score; i represents the spatio-temporal reliability corresponding to the i-th information source, which is a real number; λ represents the introduced spatio-temporal reliability compensation term, which aims to increase the additional attention score for data sources with higher positioning accuracy and better signal. This design makes the model not only pay attention to the relevance of information content when fusing, but also prefer to trust the perception data with higher positioning accuracy and better spatio-temporal quality. i S3. Input the global environmental situation tensor into a pre-trained deep reinforcement learning strategy network to obtain a task instruction set. In this embodiment, the global environmental situation tensor is input into a pre-trained deep reinforcement learning strategy network. Based on the understanding of the spatio-temporal situation, the strategy network outputs one or more high-level, abstract task instruction sets, which include: task type, target area and its spatio-temporal constraints.

[0025] S4. Use Beidou global short message to reach consensus on the key instructions in the task instruction set to obtain the consensus task instruction.

[0026] In this embodiment, the method for consensus confirmation includes:

[0027] The leader node or decision node will the task instruction to be consensus

[0028] In this embodiment, the method for consensus confirmation includes: The leader node or decision node will the task instruction to be consensus Cmd ​The process involves standardizing and serializing the data, followed by computation using a collision-resistant cryptographic hash function (such as SHA-256) to generate a fixed-length digital fingerprint, thus obtaining the hash digest. H cmd : Here, Hash represents a cryptographic hash function. (This is a summary.) H cmd As a task instruction Cmd It is the only and unalterable representative.

[0029] hash digest H cmd Unique task number Task ID And key spatiotemporal parameters obtained from BeiDou precise positioning (such as the reference time for the command to take effect). T valid and center point coordinates P center Encapsulate it into a lightweight consensus request data packet. Pkt req : , Subsequently, the leader node transmits the consensus request data packet via the BeiDou-3 RDSS short message service. Pkt req Broadcast to all follower nodes in the cluster and the remote command center.

[0030] Follower nodes or command centers receive consensus request data packets Pkt re Then, perform the local verification step and receive a confirmation message. Msgack The local verification steps include: (1) obtaining complete task instructions. Cmd' Specifically, complete mission instructions are received through a separate, higher-bandwidth communication link (such as a line-of-sight data link or Tiantong satellite broadband). Cmd' or unique task number Task ID and center point coordinates P center Derive the expected task instructions from the pre-built task strategy library. Cmd' (2) Use a collision-resistant cryptographic hash function to compute the complete task instructions. Cmd' hash value H Cmd’ : (3) Compare the received hash digests H cmd Hash value calculated locally H Cmd’ If and only ifH cmd = H Cmd’ If the command is consistent and has not been tampered with, then a confirmation message is sent via BeiDou short message. Msgack Confirmation message Msgack It is a message sent via BeiDou short message service that contains at least a unique mission number. Task ID and confirmation signal ACK The structured acknowledgment message is a type of message where ACK is a positive response signal indicating "verification passed, acknowledgement received".

[0031] The leader node in the preset time window Δ T Internally, it listens for and collects confirmation messages from other nodes. Msgack When the number of valid confirmation messages received M If the preset conditions are met, a consensus is considered to have been reached. The preset conditions are: in, N This indicates the total number of nodes in the cluster, with the leader node itself counted as 1 acknowledgment. This indicates rounding up. This condition is equivalent to implementing most principles of distributed systems, allowing for rounding down to the nearest integer. The cluster detects node failures or malicious behavior. Once consensus is reached, the leader node broadcasts a task activation command, and all cluster members synchronously begin executing the task. Cmd .

[0032] S5. Each UAV performs collaborative operations based on the consensus-based mission instructions, and integrates the new perception data generated during the execution process with the precise PVT information in real time, and then inputs it back into the information fusion model to complete the autonomous decision-making closed loop.

[0033] Example 2 In this embodiment, an autonomous decision-making system for UAV swarms that integrates BeiDou enhanced services and multi-source perception includes: an information acquisition module, an information processing module, a task instruction generation module, a consensus confirmation module, and an execution feedback module.

[0034] In the information acquisition module, each UAV in the UAV cluster receives satellite-based augmentation signals and uses precise point positioning technology to perform real-time calculations on the satellite-based augmentation signals to obtain precise PVT information.

[0035] The satellite-based augmentation signal is: in, Indicates receiver r For satellite spseudo-range observation on frequency i , denotes a geometric distance between the receiver and the satellite, c denotes the speed of light, denotes the receiver clock bias, denotes the satellite clock bias, denotes the tropospheric delay, denotes the ionospheric delay, denotes the receiver hardware delay on frequency i , denotes the satellite hardware delay on frequency i , denotes the pseudo-range observation noise and multipath error, denotes the receiver r to the satellite s on frequency i , denotes the carrier wavelength of frequency i , denotes the integer ambiguity, denotes the receiver r phase hardware delay on frequency i , denotes the satellite s phase hardware delay on frequency i , denotes the carrier phase observation noise and multipath error.

[0036] In the information processing module, each UAV in the UAV cluster synchronously collects sensor information and aligns the local perception features and wide-area geographic information with the precise PVT information in space-time, and generates a global environment situation tensor with space-time confidence by using an information fusion model.

[0037] The information fusion model includes: wherein, denotes the space-time reliability attention score, Q denotes the query vector in the attention mechanism, denotes the learnable weight matrix, denotes the semantic vector from the i-th information source, i denotes the dimension of the key vector, denotes the preset weight coefficient, λ denotes the space-time reliability corresponding to the i-th information source. i

[0038] ​​The task instruction generation module is used to input the global environment situation tensor into a pre-trained deep reinforcement learning policy network to obtain the task instruction set.

[0039] The consensus confirmation module uses BeiDou global short message service to confirm the key instructions in the task instruction set and obtain the consensus-based task instructions.

[0040] The consensus confirmation module's workflow includes: the leader node or decision node submits the task instructions to be agreed upon. Cmd The data is then standardized and serialized, followed by computation using a collision-resistant cryptographic hash function to generate a fixed-length digital fingerprint, resulting in a hash digest. H cmd ; hash digest H cmd Unique task number Task ID The key spatiotemporal parameters obtained from BeiDou precise positioning are encapsulated into a lightweight consensus request data packet. Pkt req Subsequently, the leading node transmits the consensus request data packet via the BeiDou-3 RDSS short message service. Pkt req Broadcast to all follower nodes in the cluster and the remote command center; follower nodes or the command center, upon receiving the consensus request data packet... Pkt re Then, perform the local verification step and receive a confirmation message. Msgack The leadership node is within the preset time window Δ T Internally, it listens for and collects confirmation messages from other nodes. Msgack When the number of valid confirmation messages received M If the preset conditions are met, a consensus is considered to have been reached.

[0041] In the consensus confirmation module, the local verification steps include: obtaining the complete task instructions. Cmd' Use a collision-resistant cryptographic hash function to compute the complete task instructions. Cmd' hash value H Cmd’ Compare the received hash digests. H cmd Hash value calculated locally H Cmd’ If and only if H cmd = H Cmd’ If the command is found to be consistent and unaltered, a confirmation message is sent via BeiDou short message service. Msgack Confirmation message Msgack Includes a unique task numberTask ID and acknowledgement signal ACK .

[0042] In the execution feedback module, each unmanned aerial vehicle performs cooperative work based on the consensus task instruction, and real-time fusion is performed on new perception data generated in the execution process and precise PVT information, and the new perception data and the precise PVT information are input into the information fusion model again to complete an autonomous decision closed loop.

[0043] The above-described embodiments are only used to describe the preferred modes of the present application, and are not used to limit the scope of the present application. Without departing from the design spirit of the present application, various modifications and improvements to the technical solutions of the present application made by those skilled in the art shall fall within the protection scope determined by the claims of the present application.

Claims

1. A method for autonomous decision-making of a UAV cluster by fusing Beidou enhanced services and multi-source perception, characterized in that, The method comprises the following steps: Each unmanned aerial vehicle in the unmanned aerial vehicle cluster receives a satellite-based augmentation signal and uses precise point positioning technology to solve the satellite-based augmentation signal in real time to obtain precise PVT information; Each unmanned aerial vehicle in the unmanned aerial vehicle cluster synchronously collects sensor information and performs space-time alignment with the precise PVT information, simultaneously uses an information fusion model to process local perception features and wide-area geographic information, and generates a global environment situation tensor with space-time confidence; The global environment situation tensor is input into a pre-trained deep reinforcement learning strategy network to obtain a task instruction set; The key instructions in the task instruction set are consensus-confirmed by using a Beidou global short message to obtain consensus task instructions; Each unmanned aerial vehicle performs collaborative work based on the consensus task instructions, and real-time fuses new perception data generated in the execution process with the precise PVT information, and inputs again into the information fusion model to complete the autonomous decision-making closed loop.

2. The method of claim 1, wherein the method further comprises: The satellite-based augmentation signal is: in, Indicates receiver r For satellite s In frequency i pseudorange observations on Indicates the geometric distance between the receiver and the satellite. c Represents the speed of light. Indicates receiver clock bias. Indicates satellite clock bias, Indicates tropospheric delay, Indicates ionospheric delay, Indicates the receiver is at frequency i On pseudo-range hardware delay, Indicates the satellite's frequency i On pseudo-range hardware delay, This represents pseudorange observation noise and multipath error. Indicates receiver r For satellite s In frequency i Carrier phase observations on Represents frequency i carrier wavelength, Indicates the ambiguity of the integer period. Indicates receiver r In frequency i Phase hardware delay on, Indicates satellite s In frequency i Phase hardware delay on, This represents carrier phase observation noise and multipath error.

3. The method of claim 1, wherein the method further comprises: The information fusion model comprises: in, The attention score represents the spatiotemporal reliability. Q This represents the query vector in the attention mechanism. This represents the learnable weight matrix. Indicates from the i The semantic vector of each information source The dimension of the key vector. λ This represents the preset weighting coefficient. Indicates the first i The spatiotemporal reliability of each information source.

4. The method of claim 1, wherein the method further comprises: The method for performing the consensus confirmation comprises: The leader node or decision node will instruct the task to be consensus Cmd Standardized serialization processing is performed, and then a collision-resistant cryptographic hash function is used for calculation to generate a fixed-length digital fingerprint, obtaining a hash digest H cmd ; The hash digest H cmd , a unique task number Task ID , and a key space-time parameter obtained by Beidou precise positioning are encapsulated into a lightweight consensus request data packet Pkt req Subsequently, the leader node broadcasts the consensus request data packet Pkt req to all follower nodes in the cluster and the remote command center through the Beidou No. 3 RDSS short message service. The follower node or the command center receives the consensus request data packet Pkt re After that, a local verification step is performed, resulting in a confirmation message Msgack ; The leadership node is within a preset time window Δ T Internally, it listens for and collects the confirmation messages from other nodes. Msgack When the number of valid confirmation messages received M If the preset conditions are met, a consensus is considered to have been reached.

5. The method of claim 4, wherein the method further comprises: The local verification step in the consensus confirmation module comprises: Acquire complete task instructions Cmd’ ; computing the hash value of the complete task instruction using a collision-resistant cryptographic hash function Cmd’ H Cmd’ ;​ comparing the received hash digest H cmd with the locally computed hash value H Cmd’ if and only if H cmd = H Cmd’ the instructions are both consistent and unaltered. If the instruction is consistent and not tampered, a confirmation message is sent back through the Beidou short message Msgack , the confirmation message Msgack contains the unique task number Task ID and the confirmation signal ACK .

6. An unmanned aerial vehicle cluster autonomous decision system fusing Beidou enhanced service and multi-source perception, the system applying the method of any one of claims 1-5. Comprise: An information acquisition module, an information processing module, a task instruction generation module, a consensus confirmation module, and an execution feedback module; In the information acquisition module, each unmanned aerial vehicle in the unmanned aerial vehicle cluster receives a satellite-based augmentation signal and uses precise point positioning technology to solve the satellite-based augmentation signal in real time to obtain precise PVT information; In the information processing module, each unmanned aerial vehicle in the unmanned aerial vehicle cluster synchronously collects sensor information and performs space-time alignment with the precise PVT information, simultaneously uses an information fusion model to process local perception features and wide-area geographic information, and generates a global environment situation tensor with space-time confidence; The task instruction generation module is configured to input the global environment situation tensor into a pre-trained deep reinforcement learning strategy network to obtain a task instruction set; The consensus confirmation module uses a Beidou global short message to perform consensus confirmation on key instructions in the task instruction set to obtain consensus task instructions; In the execution feedback module, each unmanned aerial vehicle performs collaborative work based on the consensus task instructions, and real-time fuses new perception data generated in the execution process with the precise PVT information, and inputs again into the information fusion model to complete the autonomous decision-making closed loop.

7. The unmanned aerial vehicle cluster autonomous decision system of claim 6, wherein, The satellite-based augmentation signal is: wherein denotes the receiver r to the satellite s at frequency i , the pseudorange observation, denotes the geometric distance between the receiver and the satellite, c denotes the speed of light, denotes the receiver clock bias, denotes the satellite clock bias, denotes the tropospheric delay, denotes the ionospheric delay, denotes the receiver pseudorange hardware delay at frequency i , denotes the satellite pseudorange hardware delay at frequency i , denotes the pseudorange observation noise and multipath error, denotes the receiver r to the satellite s at frequency i , the carrier phase observation, denotes the carrier wavelength at frequency i , denotes the integer ambiguity, denotes the receiver r phase hardware delay at frequency i , denotes the satellite s phase hardware delay at frequency i , denotes the carrier phase observation noise and multipath error.

8. The unmanned aerial vehicle cluster autonomous decision system of claim 6, wherein, The information fusion model comprises: in, The attention score represents the spatiotemporal reliability. Q This represents the query vector in the attention mechanism. This represents the learnable weight matrix. Indicates from the i The semantic vector of each information source The dimension of the key vector. λ This represents the preset weighting coefficient. Indicates the first i The spatiotemporal reliability of each information source.

9. The unmanned aerial vehicle cluster autonomous decision system of claim 6, wherein, The workflow of the consensus confirmation module comprises: The leader node or decision node will instruct the task to be consensus Cmd Standardized serialization processing is performed, and then a collision-resistant cryptographic hash function is used for calculation to generate a fixed-length digital fingerprint, obtaining a hash digest H cmd ; The hash digest H cmd The unique task number Task ID And the key space-time parameters obtained by the Beidou precise positioning are encapsulated into a lightweight consensus request data packet Pkt req Subsequently, the leader node broadcasts the consensus request data packet Pkt req To all follower nodes in the cluster and the remote command center through the Beidou No. 3 RDSS short message service. The follower node or the command center receives the consensus request data packet Pkt re After that, a local verification step is performed, resulting in a confirmation message Msgack ; The leadership node is within a preset time window Δ T Internally, it listens for and collects the confirmation messages from other nodes. Msgack When the number of valid confirmation messages received M If the preset conditions are met, a consensus is considered to have been reached.

10. The unmanned aerial vehicle cluster autonomous decision system of claim 9, wherein, In the consensus confirmation module, the local verification step comprises: Acquire complete task instructions Cmd’ ; computing the hash value of the complete task instruction using a collision-resistant cryptographic hash function Cmd’ H Cmd’ ;​ comparing the received hash digest H cmd with the locally computed hash value H Cmd’ if and only if H cmd = H Cmd’ the instructions are determined to be consistent and unaltered. If the instruction is determined to be consistent and not tampered, a confirmation message is sent back through the Beidou short message Msgack , the confirmation message Msgack contains the unique task number Task ID and the confirmation signal ACK .

Images