An unmanned submersible cluster uncontrolled self-operation task execution system and method

Abstract

The application discloses an unmanned submersible cluster non-control self-operation task execution system and method, which comprises a plurality of resource-carrying autonomous underwater vehicles (AUVs), each of which is provided with an edge computing module, a multi-modal perception module, a communication module and a resource configuration module, and each of the resource-carrying autonomous underwater vehicles corresponds to a group of target identification information, and the target identification information comprises target frequency and target confidence, wherein the multi-modal perception module is provided with a passive sonar array, a multi-beam sonar (MBS), an inertial measurement unit (IMU) and a depth sensor, and is used for acquiring perception data, and the perception data comprises target voiceprint feature vectors, target relative distances, velocity vectors and environmental parameters. The unmanned submersible cluster non-control self-operation task execution system and method improve the adaptability of the cluster to complex underwater environments, and realize resource optimization configuration and efficient task execution.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of underwater unmanned equipment cluster control, and particularly relates to an unmanned underwater vehicle cluster control-free self-operation task execution system and method. BACKGROUND

[0002] Autonomous underwater vehicle (AUV) clusters have important application value in military underwater attack tasks, but the complexity of the underwater environment poses a serious challenge to their collaborative capabilities. The existing technology has the following limitations: centralized control systems rely on real-time instructions from ground stations or mother ships, which have poor adaptability in underwater environments with high delay and low bandwidth (<5 Kbps), and communication interruptions can lead to task failure; existing AUV systems (such as Sailfish-324) focus on detection and monitoring, lack attack functions and dynamic task management capabilities, and cannot cope with high-adversary scenarios; when facing changes in target mobility and individual AUV failures, the cluster has difficulty adjusting strategies in real time, and the task robustness is insufficient. Therefore, there is an urgent need for an AUV cluster system that can be completely autonomous after launch, adapt to low-bandwidth communication, and dynamic adversarial environments. SUMMARY

[0003] To solve the technical problems in the background art, the present application proposes an unmanned underwater vehicle cluster control-free self-operation task execution system and method.

[0004] The unmanned underwater vehicle cluster control-free self-operation task execution system proposed by the present application comprises: a plurality of resource-carrying autonomous underwater vehicles AUV, each resource-carrying autonomous underwater vehicle AUV is configured with an edge computing module, a multi-modal perception module, a communication module and a resource configuration module, each resource-carrying autonomous underwater vehicle AUV corresponds to a set of target identification information, the target identification information includes target frequency and target confidence, wherein,

[0005] The multi-modal perception module is configured with a passive sonar array, a multi-beam sonar MBS, an inertial measurement unit IMU and a depth sensor, and is used to obtain perception data, the perception data including target voiceprint feature vectors, target relative distances, velocity vectors and environmental parameters;

[0006] The edge computing module is used to receive the perception data, process the perception data, and output a task allocation vector, an attack instruction sequence and a trajectory planning matrix based on the processed perception data and the target identification information to drive the resource configuration module to execute corresponding tasks;

[0007] The communication module is used to periodically obtain the state vector of the current resource-carrying autonomous underwater vehicle AUV and the state matrix of the neighboring resource-carrying autonomous underwater vehicle AUV, and after signal demodulation, CRC check and data alignment processing, a cluster global state graph is generated and synchronized to the edge computing module to support decision planning.

[0008] A resource configuration module is configured to record the type and number of equipment of the current AUV carrying resource configuration, and use the corresponding equipment according to the driving instruction of the edge computing module.

[0009] Preferably, the edge computing module comprises:

[0010] A target identification sub-module is configured to map the voiceprint feature vector to a target type probability distribution T based on a pre-trained MobileNet model, to output a confidence matrix C.

[0011] A trajectory prediction sub-module is configured to process the relative distance and velocity vector by using a Kalman filtering algorithm, to generate a three-dimensional position prediction matrix P at a future time t.

[0012] A decision planning sub-module is configured to solve an optimal task allocation vector A by using a particle swarm optimization algorithm based on the confidence matrix C, the relative distance, the velocity vector, and the environmental parameters.

[0013] Preferably, the state vector of the current AUV carrying resource includes an AUV identifier ID, a position vector, an energy state, an attack resource vector, and a task allocation identifier, wherein each AUV carrying resource corresponds to a unique AUV identifier ID.

[0014] Preferably, the communication module adopts a broadcast time division multiple access protocol, and broadcasts the state information in a 32-byte standard PDU or a 64-byte extended PDU format, with a bandwidth control of <5Kbps.

[0015] The present application provides an unmanned submersible cluster control-free self-operation task execution method, which is applied to the unmanned submersible cluster control-free self-operation task execution system as described in any one of the above, and the method comprises the following steps:

[0016] S1: obtaining target detection data and state flags corresponding to a plurality of AUVs carrying resources, and controlling the plurality of AUVs to broadcast their target detection data to other AUVs in the cluster for the first time, wherein the target detection data includes target position, target speed, target shape, and target frequency.

[0017] S2: synchronously correcting the target detection data corresponding to the plurality of AUVs carrying resources, and broadcasting the corrected target detection data to the plurality of AUVs carrying resources for the second time.

[0018] S3: one-to-one utility score is calculated for each of the plurality of resource-carrying autonomous underwater vehicles (AUVs), and the plurality of resource-carrying autonomous underwater vehicles (AUVs) are grouped according to the utility score and a preset grouping strategy to obtain a plurality of preset groups, one group corresponding to one execution task;

[0019] S4: the resource-carrying autonomous underwater vehicles (AUVs) in each group are controlled to complete the execution task according to the plurality of preset groups.

[0020] Preferably, the utility score is calculated according to the following formula:

[0021] ;

[0022] wherein, is a distance weight, which can be a preset fixed parameter, emphasizing the importance of proximity to the target; is an action energy weight, which can be a preset fixed parameter, ensuring sustained combat capability; is an attack resource weight, which can be a preset fixed parameter, indicating the sufficiency of ammunition; is an attack resource type weight; is a normalized ammunition vector; is an ammunition item index, a fixed parameter, controlling the coupling degree of ammunition types; is the ratio of the distance of the target to the maximum distance of the same target by the surviving AUVs, is the ratio of the percentage of action energy to the maximum energy; is the utility score of the ith resource-carrying autonomous underwater vehicle (AUV).

[0023] Preferably, the preset grouping strategy specifically includes:

[0024] The plurality of resource-carrying autonomous underwater vehicles (AUVs) are sorted in descending order of the utility score;

[0025] A plurality of preset score thresholds corresponding to the plurality of groups are obtained, and the sorted plurality of resource-carrying autonomous underwater vehicles (AUVs) are divided into groups according to the preset score thresholds to obtain a plurality of groups, wherein the groups include but are not limited to attack groups and decoy groups.

[0026] Preferably, it further includes: calculating a cluster resource value corresponding to the cluster of unmanned underwater vehicles (AUVs) in real time When the cluster resource value is less than a preset termination threshold, the execution task is terminated.

[0027] Preferably, the calculation process of the cluster resource value is specifically as follows:

[0028] ;

[0029] wherein, is an autonomous underwater vehicle AUV carrying resources available; is an autonomous underwater vehicle AUV carrying total resources.

[0030] Preferably, the AUV state flag includes but is not limited to idle, attack, decoy, termination.

[0031] In the present application, the proposed unmanned submarine cluster control-free self-operation task execution system and method. Through distributed sensing, dynamic grouping and cooperative control, efficient underwater task execution is realized. The method comprises: obtaining target detection data of a plurality of AUVs and first broadcasting; the detection data is corrected for spatio-temporal consistency and secondly broadcasted; the utility score is calculated based on distance, energy and resource state, and grouped according to the preset strategy; control each group of AUVs to execute corresponding tasks. The present application significantly improves the adaptability of the cluster to complex underwater environment through multi-round data synchronization and dynamic grouping strategy, realizes the optimal allocation of resources and efficient execution of tasks. BRIEF DESCRIPTION OF DRAWINGS

[0032] Figure 1 The system architecture diagram of the unmanned submarine cluster control-free self-operation task execution system proposed by the present application;

[0033] Figure 2 The working flow diagram of the unmanned submarine cluster control-free self-operation task execution method proposed by the present application. DETAILED DESCRIPTION

[0034] Referring to Figure 1 and Figure 2 The unmanned submarine cluster control-free self-operation task execution system proposed by the present application comprises: a plurality of autonomous underwater vehicles AUVs carrying resources, each autonomous underwater vehicle AUV carrying resources is configured with an edge computing module, a multi-modal sensing module, a communication module and a resource configuration module, each autonomous underwater vehicle AUV carrying resources corresponds to a group of target identification information, the target identification information includes target frequency and target confidence, wherein,

[0035] The multi-modal sensing module is configured with a passive sonar array, a multi-beam sonar MBS, an inertial measurement unit IMU and a depth sensor, and is used for obtaining sensing data, the sensing data including target voiceprint feature vector, target relative distance, velocity vector and environmental parameters;

[0036] The edge computing module is used for receiving sensing data, processing the sensing data, and outputting a task allocation vector, an attack instruction sequence and a trajectory planning matrix based on the processed sensing data and the target identification information to drive the resource configuration module to execute corresponding tasks;

[0037] The communication module is configured to periodically acquire a state vector of a current resource-carrying autonomous underwater vehicle (AUV) and a state matrix of a neighbor resource-carrying autonomous underwater vehicle (AUV), and generate a cluster global state graph through signal demodulation, CRC check and data alignment processing, and synchronize the cluster global state graph to the edge computing module to support decision planning.

[0038] The resource configuration module is configured to record a type of equipment and a number of equipment configured by the current resource-carrying autonomous underwater vehicle (AUV), and use the corresponding equipment according to a driving instruction of the edge computing module.

[0039] In this embodiment, the edge computing module comprises:

[0040] The target identification submodule is configured to map the voiceprint feature vector to a target type probability distribution T based on a pre-trained MobileNet model, to output a confidence matrix C.

[0041] The trajectory prediction submodule is configured to process the relative distance and velocity vector by using a Kalman filtering algorithm, to generate a three-dimensional position prediction matrix P at a future time t.

[0042] The decision planning submodule is configured to solve an optimal task allocation vector A by using a particle swarm optimization algorithm based on the confidence matrix C, the relative distance, the velocity vector and the environmental parameters.

[0043] Specifically, the target state is evaluated using the current MBS image and acoustic signal, and a comprehensive confidence C is generated.

[0044] In this embodiment, the state vector of the current resource-carrying autonomous underwater vehicle (AUV) comprises an AUV identifier ID, a position vector, an energy state, an attack resource vector and a task allocation identifier, wherein each resource-carrying autonomous underwater vehicle (AUV) corresponds to a unique AUV identifier ID.

[0045] In this embodiment, the communication module adopts a broadcast time division multiple access protocol, and broadcasts the state information in a 32-byte standard PDU or a 64-byte extended PDU format, with a bandwidth control of <5Kbps.

[0046] Specifically, the content contained in the PDU format is shown in the following table:

[0047] Field Store (B) Description Data source AUV ID 1 Unique identifier (0-255) System initialization allocation, underwater acoustic communication standard uses broadcast mode, no need for destination address Target distance D 4 Sonar ranging distance (meters, single precision floating point) Existing sonar system (active sonar ranging) Action energy P 1 Action energy percentage (0-100) AUV energy management system Attack resource vector 6 Such as torpedoes, decoys, explosive shells (2 bytes each) AUV attack resource management system Attack resource stock a i,k ]] 2 Attack resource storage value, k is the resource type Initialization full load, calculate after attack Utility score U i ]] 4 Utility score (floating point, 0-1) Local calculation, single precision floating point Target information 8 Compressed sonar features (such as dominant frequency) Existing sonar system (feature extraction) State flag 1 State (0 idle, 1 attack, 2 feint, 3 terminate) AUV state machine CRC check 2 Data integrity check CRC32 algorithm Target ID 2 Target identifier (0-65535) Sonar feature clustering Confidence 4 Target distance confidence (0-1) Sonar signal strength Group confirmation 2 Group confirmation (1 byte target ID, 0-255; 1 byte role, 1 attack, 2 feint) Group calculation

[0048] PDU size: D = 32 bytes.

[0049] Specifically, before transmission, the AUV cluster completes the following initialization through a ground station:

[0050] 1) Load target information: For moving targets (e.g. enemy ships), load sonar signatures (e.g. propeller noise spectrum, 20-100 Hz). Specify the target's approximate area (radius 5 km) without precise coordinates. Target information is stored in the edge computing module of each AUV, occupying <1 KB memory.

[0051] 2) Each AUV carries multiple types of attack resources and initial quantities, such as: Torpedo (T): high power, attacks ships, each occupies 5 storage units, initial n units (storage value 5n). Decoy (D): interferes with defense, each occupies 2 storage units, initial m units (storage value 2m). Precision Bomb (P): high-precision strike, each occupies 4 storage units, initial k units (storage value 4k). i,k : Current storage value of attack resource type k (k ∈ {T, D, P, …}) of AUV i (unit: storage unit). i,kmax : Maximum storage value of attack resource type k. i : Total attack resource storage value of AUV i, defined as i =∑ k∈{T，D，P，……} a i,k , subject to the total capacity constraint max =∑ k∈{T,D,P，……} a i,kmax .

[0052] 3) Configure communication protocol: Time Division Multiple Access (TDMA) acoustic communication, frame duration T frame =10 seconds. Number of time slots N equals the number of AUVs, such as N=20, time slot duration T slot =T frame / N=10 / 20=0.5 seconds. PDU size: 24 bytes, bandwidth 192 bps.

[0053] 4) Synchronize clock: Each AUV is equipped with a high-precision quartz clock with a drift of <1 ms / h, and the frame start time is synchronized by the ground station.

[0054] 5) Initialize edge computing: Deploy MobileNet model with approximately 4.2M parameters, occupying <10MB storage, for target recognition. Configure A* path planning algorithm with terrain map resolution of 50 meters / pixel. Load Kalman filter algorithm for target trajectory prediction.

[0055] 6) Hardware check: Confirm that the passive sonar (10-100 Hz), MBS (20 kHz, 0.1 meter resolution), IMU (accuracy 0.01°), and depth sensor (accuracy 0.1 meters) are functioning normally. Initial action resource quantity is 100%.

[0056] Specifically, the AUV uses passive sonar to listen to the target's main frequency and active sonar for short-pulse ranging to calculate the target distance d. i =t×1500 / 2 (t is the round-trip time), speed v i =f d ×1500 / (2×20000)(f d (Doppler frequency shift); MBS generates a 3D acoustic image, which is then denoised using Gaussian filtering and input into a MobileNet model. The output is the target type and confidence level C. target If C target If the value is greater than 0.8, the target ID is confirmed.

[0057] It should be noted that when multiple AUVs identify the same target differently, the following steps are performed: extract the target's main frequency f detected by each AUV. j and confidence level C d,j K-means clustering (threshold 10Hz) was used; when the dominant frequency difference was <10Hz, C was selected. d,j The highest ID is used as the unified target ID. consensus Broadcast the corrected target ID to ensure data consistency across the cluster.

[0058] Specifically, ;

[0059] For target ID and main frequency f j K-means clustering was performed on the (PDU target information field) based on C d,j Weighted. If the clock frequency difference is less than 10 Hz, it is unified into a single target ID (take C). d, (j is the highest ID), obtain the consistent target ID. consensus Otherwise, divide the group into subgroups, assign new IDs (0-255, PDU group confirmation field), update the PDU target ID field (16-bit integer), and broadcast the correction results.

[0060] Reference Figure 1 and Figure 2 The present invention proposes an uncontrolled autonomous task execution system for an unmanned submersible swarm, applicable to any of the uncontrolled autonomous task execution systems described above. The method includes the following steps:

[0061] S1: Acquire target detection data and status flags for multiple autonomous underwater vehicles (AUVs) carrying resources, and control multiple AUVs to broadcast their target detection data to other AUVs in the cluster for the first time. The target detection data includes target position, target speed, target shape, and target frequency.

[0062] S2: synchronously correct the target detection data corresponding to the plurality of resource-carrying autonomous underwater vehicles AUVs, and broadcast the corrected target detection data to the plurality of resource-carrying autonomous underwater vehicles AUVs for a second time;

[0063] S3: one-to-one calculate the utility scores of the plurality of resource-carrying autonomous underwater vehicles AUVs, and perform grouping operation on the plurality of resource-carrying autonomous underwater vehicles AUVs according to the utility scores and a preset grouping strategy, to obtain a plurality of preset groups, one group corresponding to one execution task;

[0064] S4: control the resource-carrying autonomous underwater vehicles AUVs under each group to complete the execution task according to the plurality of preset groups.

[0065] In this embodiment, the calculation formula of the utility score is:

[0066] ;

[0067] wherein, is a distance weight, which can be a preset fixed parameter, emphasizing the importance of approaching the target; is an action energy weight, which can be a preset fixed parameter, ensuring the continuous combat capability; is an attack resource weight, which can be a preset fixed parameter, indicating the ammunition sufficiency; is an attack resource type weight; is a normalized ammunition vector; is an ammunition item index, a fixed parameter, controlling the coupling degree of ammunition types; is a ratio of the target distance to the maximum distance of the surviving AUVs to the same target, is a ratio of the action energy percentage to the maximum energy; is the utility score of the ith resource-carrying autonomous underwater vehicle AUV, such as, =0.4, =0.3, =0.3.

[0068] Specifically, ;

[0069] wherein, the normalized ammunition vector is based on a i,k (PDU attack resource type vector) a i,kmax (initialization configuration). The normalized ammunition quantity facilitates vector operation. a i,k the inventory of the attack resource k type (such as T: torpedo, D: decoy, P: explosive), a i,kmax the maximum storage value of the attack resource k type, from the PDU attack resource vector field.

[0070] In the embodiment, the preset grouping strategy specifically includes:

[0071] The multiple resource-carrying autonomous underwater vehicles (AUVs) are sorted in descending order of utility scores;

[0072] A preset score threshold corresponding to each group is obtained, and the sorted multiple resource-carrying autonomous underwater vehicles (AUVs) are divided into groups according to the preset score threshold, to obtain multiple groups, including but not limited to an attack group and a decoy group.

[0073] In the embodiment, the cluster resource value corresponding to the unmanned underwater vehicle cluster is calculated in real time When the cluster resource value is less than a preset termination threshold, the execution of the task is terminated.

[0074] In the embodiment, after the attack task is executed, the surviving AUVs calculate the remaining ammunition, compare the attack demand value, re-group based on the remaining ammunition and utility scores, and continue to attack the undamaged targets. The grouping process is repeated. According to the preset AUV state parameters of the system, the self-action resources and total resources are analyzed, a new utility score value is obtained, and the groups are re-grouped. Until the sonar determines that the task is completed or the ui value of the surviving AUVs is insufficient to complete the task, the AUVs are withdrawn according to the preset plan.

[0075] In the embodiment, the cluster resource value is calculated as follows:

[0076]

[0077] wherein, is the available resource-carrying autonomous underwater vehicle (AUV); is the total resource-carrying autonomous underwater vehicle (AUV).

[0078] In the embodiment, the AUV state flags include but are not limited to idle, attack, decoy, and termination.

[0079] Embodiment 1:

[0080] Single target:

[0081] 12 AUVs, target (ID=1), AUV1 measures d1=2000m, v1=0.375m / s, C d,1 =0.9. The number of time slots N=12, the time slot length Tslot=12 / 12=1s. Bandwidth: R AUV =32 / 12=2.667B / s=21.33b / s, R total ​= 12 x 21.33 = 255.96 bps < 5 Kb / s, meet the underwater communication requirements.

[0082] Single target: 12 AUVs, target ID = 1. AUV1: U1 = 0.78, AUV2: U2 = 0.73, AUV3 not broadcast (exclude), AUV4: U4 = 0.75, AUV5: U5 = 0.70, and so on. AUV1 collects PDU, extract the order to [(AUV1, 0.78), (AUV2, 0.73), (AUV4, 0.75), (AUV5, 0.70), …].

[0083] Total resource amount a i = a max , resource vector, maximum storage value a i,kmax System initialization configuration, normalized attack resource amount.

[0084] Example 2:

[0085] Scenario 2 (multiple targets): 8 AUVs, target A (ID = 1), target B (ID = 2), AUV1 measures target A's d1 = 2500 meters, C d,1 = 0.9. Time slot number N = 8, time slot length Tslot = 12 / 8 = 1.5 seconds. Total bandwidth Rtotal = 8 x 21.33 = 170.64 b / s < 5 Kb / s, meet the underwater communication requirements.

[0086] Multiple targets: 8 AUVs, target A (ID = 1) target B (ID = 2).

[0087] AUV1: U1, A = 0.755, U 1,B = 0.72;

[0088] AUV2: U2, A = 0.746, U 2,B = 0.71;

[0089] AUV3: U 3,A = 0.74, target B not detected;

[0090] AUV4: U 4,A = 0.73, U 4,B = 0.70;

[0091] AUV5: a i,D = 0 exclude.

[0092] AUV6: target A not detected, U 6,B = 0.73;

[0093] AUV7: target A not detected, U 7,B= 0.70;

[0094] AUV8: U 8,A = 0.72, U 8,B = 0.69;

[0095] AUV1 generates two tables, and other AUVs also refer to similar, to generate their respective priority table:

[0096] Target A:

[0097] PriorityTable 1,A = [(AUV1, 0.755, ID = 1), (AUV2, 0.746, ID = 1), (AUV3, 0.74, ID = 1), (AUV4, 0.73, ID = 1), (AUV8, 0.72, ID = 1), (AUV6, 0, ID = 1), (AUV7, 0, ID = 1),...].

[0098] Target B:

[0099] PriorityTable 1,B = [(AUV6, 0.73, ID = 2), (AUV1, 0.72, ID = 2), (AUV2, 0.71, ID = 2), (AUV4, 0.70, ID = 2), (AUV7, 0.70, ID = 2), (AUV8, 0.69, ID = 2), (AUV3, 0, ID = 2),...].

[0100] The above, only for the preferred specific embodiments of the present application, but the scope of protection of the present application is not limited to this, any skilled in the art of the technical personnel in the technical range of the present application disclosed according to the technical solution of the present application and the invention concept to equivalent replacement or change, should be covered in the scope of protection of the present application.

Claims

1. A system for uncontrolled autonomous execution of tasks by a cluster of unmanned underwater vehicles, characterized in that, Comprise: A plurality of autonomous underwater vehicles AUVs, each autonomous underwater vehicle AUV is configured with an edge computing module, a multi-modal perception module, a communication module and a resource configuration module, each autonomous underwater vehicle AUV corresponds to a set of target identification information, the target identification information includes target frequency, target confidence, wherein, The multi-modal perception module is configured with a passive sonar array, a multi-beam sonar MBS, an inertial measurement unit IMU and a depth sensor, and is used for acquiring perception data, the perception data including target voiceprint feature vector, target relative distance, velocity vector and environmental parameter; The edge computing module is used for receiving the perception data, processing the perception data, and outputting a task allocation vector, an attack instruction sequence and a trajectory planning matrix based on the processed perception data and the target identification information to drive the resource configuration module to execute corresponding tasks; The communication module is used for periodically acquiring the current autonomous underwater vehicle AUV state vector and the neighbor autonomous underwater vehicle AUV state matrix, and generating a cluster global state graph after signal demodulation, CRC check and data alignment processing, and synchronizing to the edge computing module to support decision planning; The resource configuration module is used for recording the current autonomous underwater vehicle AUV configuration equipment type and equipment quantity, and using corresponding equipment according to the driving instruction of the edge computing module; The edge computing module is further configured to dynamically group a plurality of autonomous underwater vehicles AUVs carrying resources based on a utility score model, and the utility score calculation formula is: ； wherein, is a distance weight, which can be a pre-set fixed parameter, emphasizing the importance of proximity to the target; is an action energy weight, which can be a pre-set fixed parameter, ensuring sustained combat capability; is an attack resource weight, which can be a pre-set fixed parameter, indicating the sufficiency of ammunition; is an attack resource type weight; is a normalized ammunition vector, representing the ratio vector of the current stock of each type of ammunition to the maximum stock; is an ammunition item index, a fixed parameter, controlling the coupling degree of ammunition types, which is a pre-set fixed parameter, used to adjust the synergistic effect of different ammunition types; is the ratio of the target distance to the maximum distance, is the ratio of the action energy percentage to the maximum energy; is the utility score of the ith autonomous underwater vehicle (AUV).

2. The uncontrolled self-running mission execution system of a cluster of AUVs according to claim 1, wherein, The edge computing module comprises: A target identification sub-module for mapping the voiceprint feature vector to a target type probability distribution T based on a pre-trained MobileNet model to output a confidence matrix C; A trajectory prediction sub-module for processing the relative distance and velocity vector using a Kalman filter algorithm to generate a three-dimensional position prediction matrix P at future time t; A decision planning sub-module for solving an optimal task allocation vector A based on the confidence matrix C, the relative distance, the velocity vector and the environmental parameter through a particle swarm optimization algorithm.

3. The uncontrolled autonomous mission execution system of a cluster of AUVs according to claim 1, wherein, The current autonomous underwater vehicle AUV state vector includes: AUV identifier ID, position vector, energy state, attack resource vector, task allocation identifier, wherein each autonomous underwater vehicle AUV corresponds to a unique AUV identifier ID.

4. The uncontrolled autonomous mission execution system of a cluster of AUVs according to claim 1, wherein, The communication module adopts a broadcast time division multiple access protocol to broadcast state information in 32-byte standard PDU or 64-byte extended PDU format, and the bandwidth control is less than 5Kbps.

5. A method for performing a mission by a cluster of unmanned underwater vehicles without control and self-operation, characterized in that, The method is applied to the unmanned underwater vehicle cluster control-free self-operation task execution system of any one of claims 1-4, and the method comprises the following steps: S1: Obtain the target detection data corresponding to a plurality of autonomous underwater vehicles AUVs and the AUV state flag, and control the plurality of autonomous underwater vehicles AUVs to broadcast the target detection data of the autonomous underwater vehicles AUVs in the cluster for the first time, the target detection data including target position, target speed, target shape and target frequency; S2: synchronously correct the target detection data corresponding to the plurality of autonomous underwater vehicles AUVs, and broadcast the corrected target detection data to the plurality of autonomous underwater vehicles AUVs for a second time; S3: one-to-one corresponding calculation of the utility score of the plurality of autonomous underwater vehicles AUVs, and grouping operation of the plurality of autonomous underwater vehicles AUVs according to the utility score and a preset grouping strategy to obtain a plurality of preset groups, one group corresponding to one execution task; S4: controlling the autonomous underwater vehicles AUVs under each group according to the plurality of preset groups to complete the execution task; The calculation formula of the utility score is: ； wherein, is a distance weight, which can be a pre-set fixed parameter, emphasizing the importance of proximity to the target; is an action energy weight, which can be a pre-set fixed parameter, ensuring the ability to continue combat; is an attack resource weight, which can be a pre-set fixed parameter, indicating the sufficiency of ammunition; is an attack resource type weight; is a normalized ammunition vector, indicating the ratio vector of the current stock of each type of ammunition to the maximum stock; is an ammunition item index, a fixed parameter, controlling the degree of coupling of ammunition types, which is a pre-set fixed parameter, used to adjust the synergistic effect of different ammunition types; is the ratio of the target distance to the maximum distance, is the ratio of the action energy percentage to the maximum energy; is the utility score of the ith autonomous underwater vehicle (AUV).

6. The method of claim 5, wherein, The preset grouping strategy specifically includes: sequencing the plurality of autonomous underwater vehicles AUVs in order from high to low according to the utility score; obtaining a preset score threshold corresponding to the plurality of groups, and dividing the plurality of autonomous underwater vehicles AUVs after sequencing into groups according to the preset score threshold to obtain the plurality of groups, which include but are not limited to attack groups and decoy groups.

7. The method of claim 5, wherein, Also includes: Real-time calculation of cluster resource value corresponding to unmanned submarine cluster When the cluster resource value is less than a preset termination threshold, terminate execution of the task.

8. The method of claim 7, wherein, The cluster resource value The calculation process is specifically: ； wherein, is an available autonomous underwater vehicle AUV; is a total autonomous underwater vehicle AUV; is an attack resource type weight; is a normalized munitions vector representing a ratio vector of a current stock to a maximum stock of each type of munition; is a ratio of an action energy percentage to a maximum energy.

9. The method of claim 5, wherein, The AUV state flag includes but is not limited to idle, attack, decoy, and termination.

Images