Data acquisition method, device and equipment of autonomous underwater vehicle and medium

Abstract

The application discloses a data collection method, device and equipment of an autonomous underwater vehicle and a medium, relates to the technical field of network data collection, and comprises the following steps: acquiring distance information of an autonomous underwater vehicle and a target sensor node, and determining signal-to-noise ratios of various communication modes; determining a target communication mode and a corresponding target transmission mode from the various communication modes based on the signal-to-noise ratios and the distance information; collecting environmental parameters, and planning a target path of the autonomous underwater vehicle by using a preset reward function and the environmental parameters, so that the autonomous underwater vehicle runs to the target sensor node based on the target path, and collects target data from the target sensor node by using the target communication mode and the target transmission mode. Through the above scheme, the data collection of the autonomous underwater vehicle with low cost and low consumption can be realized.

Description

Technical Field

[0001] This invention relates to the field of network data acquisition technology, and in particular to data acquisition methods, devices, equipment and media for autonomous underwater vehicles. Background Technology

[0002] Data collection in underwater sensor networks is crucial for underwater applications. In traditional underwater sensor networks, acoustics is often used as a communication method to collect sensor data. However, due to the high power consumption, large latency, and low transmission speed of underwater acoustic communication, underwater sensor networks with limited power characteristics are not suitable for uploading large amounts of data.

[0003] In existing technologies, autonomous underwater vehicles (AUVs) are used for sensor data collection. Utilizing the mobility of AUVs for data collection can significantly reduce the energy consumption of sensor nodes and extend network lifespan. While AUVs travel to sensor nodes according to a preset path, underwater conditions are complex and variable. If the preset path is not realistic, AUVs may require substantial energy consumption and cost to complete data collection.

[0004] In summary, how to achieve low-cost, low-consumption data collection by autonomous underwater vehicles is a problem that needs to be solved in this field. Summary of the Invention

[0005] In view of this, the purpose of this invention is to provide a data acquisition method, apparatus, device, and medium for autonomous underwater vehicles, enabling low-cost and low-consumption data collection by autonomous underwater vehicles. The specific solution is as follows:

[0006] In a first aspect, this application discloses a data acquisition method for an autonomous underwater vehicle, comprising:

[0007] Acquire distance information between the autonomous underwater vehicle and the target sensor node, and determine the signal-to-noise ratio of each communication method;

[0008] Based on the signal-to-noise ratio and the distance information, the target communication method and the corresponding target transmission mode are determined from each of the communication methods;

[0009] Environmental parameters are collected, and a target path for the autonomous underwater vehicle is planned using a preset reward function and the environmental parameters. The autonomous underwater vehicle then travels to the target sensor node based on the target path and collects target data from the target sensor node using the target communication method and the target transmission mode.

[0010] Optionally, determining the signal-to-noise ratio of each communication method includes:

[0011] A first received power and a first ambient noise are determined for optical communication, and a first signal-to-noise ratio for optical communication is determined using the first received power and the first ambient noise.

[0012] A second received power and a second ambient noise are determined for the acoustic communication, and a second signal-to-noise ratio for the acoustic communication is determined using the second received power and the second ambient noise.

[0013] Optionally, determining the target communication method and corresponding target transmission mode from each of the communication methods based on the signal-to-noise ratio and the distance information includes:

[0014] Determine whether the distance information is less than a preset threshold; if it is less, determine whether the first signal-to-noise ratio is greater than the minimum signal-to-noise ratio of the optical communication.

[0015] If the value is greater than the target value, then the optical communication is determined as the target communication method, and the transmission mode of the optical communication is determined.

[0016] Optionally, after determining whether the first signal-to-noise ratio is greater than the minimum signal-to-noise ratio of the optical communication, the method further includes:

[0017] If it is not greater than, then the acoustic communication is determined to be the target communication method, and the target transmission mode is determined based on the relationship between distance information, the second signal-to-noise ratio and the threshold interval.

[0018] Optionally, the step of collecting environmental parameters and planning the target path of the autonomous underwater vehicle using a preset reward function and the environmental parameters includes:

[0019] Environmental parameters are collected, and the target acceleration is determined using the environmental parameters and the target acceleration model to obtain the target acceleration, so as to plan the target path based on the target acceleration.

[0020] Optionally, before collecting environmental parameters and using the environmental parameters and the target acceleration to determine the target acceleration using a model, so as to plan the target path based on the target acceleration, the method further includes:

[0021] The initial acceleration determination model is iteratively trained using training environment parameters to obtain the target acceleration determination model;

[0022] Accordingly, the iterative training of the initial acceleration determination model using training environment parameters to obtain the target acceleration determination model includes:

[0023] The model is used to determine the current acceleration by using training environment parameters and the current acceleration, and the current acceleration is scored using the preset reward function to obtain the action value corresponding to the current acceleration;

[0024] Based on the action value, the parameters of the current acceleration determination model are adjusted to obtain the next acceleration determination model. Then, the process jumps back to the step of obtaining the current acceleration using the training environment parameters and the current acceleration determination model, until a target acceleration determination model that can output acceleration that meets the target requirements is obtained.

[0025] Optionally, before acquiring the current distance information between the autonomous underwater vehicle and the target sensor node, and determining the signal-to-noise ratio of each communication method, the method further includes:

[0026] Select the target sensor nodes whose acquisition status is not acquired from a number of sensor nodes;

[0027] Accordingly, after acquiring target data from the target sensor node using the target communication method and the target transmission mode, the process further includes:

[0028] Adjust the acquisition status of the target sensor node to "acquisition completed".

[0029] Secondly, this application discloses a data acquisition device for an autonomous underwater vehicle, comprising:

[0030] The signal-to-noise ratio determination module is used to acquire distance information between the autonomous underwater vehicle and the target sensor node, and to determine the signal-to-noise ratio of each communication method.

[0031] The transmission mode determination module is used to determine the target communication mode and the corresponding target transmission mode from each of the communication modes based on the signal-to-noise ratio and the distance information;

[0032] The data acquisition module is used to collect environmental parameters and plan the target path of the autonomous underwater vehicle using a preset reward function and the environmental parameters, so that the autonomous underwater vehicle can run to the target sensor node based on the target path and collect target data from the target sensor node using the target communication method and the target transmission mode.

[0033] Thirdly, this application discloses an electronic device, including:

[0034] Memory, used to store computer programs;

[0035] A processor is used to execute the computer program to implement the steps of the aforementioned disclosed data acquisition method for an autonomous underwater vehicle.

[0036] Fourthly, this application discloses a computer-readable storage medium for storing a computer program; wherein, when the computer program is executed by a processor, it implements the steps of the aforementioned data acquisition method for an autonomous underwater vehicle.

[0037] As can be seen, this application acquires the distance information between the autonomous underwater vehicle (AUV) and the target sensor node, and determines the signal-to-noise ratio (SNR) of each communication method; based on the SNR and the distance information, it determines the target communication method and the corresponding target transmission mode from each of the communication methods; it collects environmental parameters, and uses a preset reward function and the environmental parameters to plan the target path of the AUV, so that the AUV can run to the target sensor node based on the target path, and collect target data from the target sensor node using the target communication method and the target transmission mode. Therefore, this application can determine a more suitable target communication method and corresponding target transmission mode for the current environment based on the SNR and distance information. This allows for faster data transmission between the AUV and the target sensor node; real-time collection of environmental parameters makes the planned path more consistent with the current situation; and the preset reward function allows the AUV to complete the movement from its current position to the target sensor node with minimal energy consumption, thereby reducing data acquisition costs. Attached Figure Description

[0038] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0039] Figure 1 This is a flowchart of a data acquisition method for an autonomous underwater vehicle disclosed in this application;

[0040] Figure 2 This application discloses a specific data acquisition method for an autonomous underwater vehicle.

[0041] Figure 3 This is a flowchart of another specific data acquisition method for an autonomous underwater vehicle disclosed in this application;

[0042] Figure 4 This is a specific data collection diagram disclosed in this application;

[0043] Figure 5 This is a schematic diagram of the data acquisition device structure of an autonomous underwater vehicle disclosed in this application;

[0044] Figure 6 This is a structural diagram of an electronic device disclosed in this application. Detailed Implementation

[0045] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present invention.

[0046] Data collection in underwater sensor networks is crucial for underwater applications. In traditional underwater sensor networks, acoustics is often used as a communication method to collect sensor data. However, due to the high power consumption, large latency, and low transmission speed of underwater acoustic communication, underwater sensor networks with limited power characteristics are not suitable for uploading large amounts of data.

[0047] In existing technologies, autonomous underwater vehicles (AUVs) are used for sensor data collection. Utilizing the mobility of AUVs for data collection can significantly reduce the energy consumption of sensor nodes and extend network lifespan. While AUVs travel to sensor nodes according to a preset path, underwater conditions are complex and variable. If the preset path is not realistic, AUVs may require substantial energy consumption and incur significant costs to complete data collection.

[0048] Therefore, this application provides a data acquisition scheme for autonomous underwater vehicles, which can achieve low-cost and low-consumption data collection by autonomous underwater vehicles.

[0049] See Figure 1 As shown in the figure, this application discloses a data acquisition method for an autonomous underwater vehicle, including:

[0050] Step S11: Obtain the distance information between the autonomous underwater vehicle and the target sensor node, and determine the signal-to-noise ratio of each communication method.

[0051] Understandably, it is necessary to obtain the coordinate information of the target sensor node and, using the local observation capabilities of the autonomous underwater vehicle (AUV), obtain the coordinate information of the AUV. Based on the coordinate information of the target sensor node and the coordinate information of the AUV, the distance between the AUV and the target sensor node is calculated. It is also necessary to calculate the signal-to-noise ratio of each communication method. Due to the instability of magnetic communication, acoustic communication and optical communication are used as the multi-mode communication methods of the AUV.

[0052] In this embodiment, before acquiring the current distance information between the autonomous underwater vehicle (AUV) and the target sensor node and determining the signal-to-noise ratio of each communication method, the method further includes: filtering out target sensor nodes whose acquisition status is "not collected" from a number of sensor nodes. In the state space, since multiple AUVs cooperate to collect data to improve efficiency, the collected sensor node information is crucial for each AUV to determine its trajectory in a distributed manner. In the data collection scenario, the AUV can observe the motion status of other AUVs and the collection status of all sensor nodes. If a sensor node is within close range of any AUV and has already had its data collected by that AUV, its acquisition status is determined to be "collected"; otherwise, it is determined to be "not collected." Therefore, the target sensor node should be a sensor node whose acquisition status is "not collected."

[0053] Step S12: Based on the signal-to-noise ratio and the distance information, determine the target communication method and the corresponding target transmission mode from each of the communication methods.

[0054] In this embodiment, different communication methods and transmission modes can be used for data transmission. To better enable the autonomous underwater vehicle (AUV) to collect data from the target sensor nodes, in addition to determining the target communication method, the corresponding target transmission mode also needs to be determined. This accelerates data transmission, saves transmission time, improves data transmission efficiency, and ultimately reduces the AUV's energy consumption. To allow the AUV to optimize its energy consumption performance through appropriate transmission methods and modes, the multi-mode transmission selection problem of the AUV is represented as an integral linear programming problem, as shown below:

[0055]

[0056]

[0057] In the formula, The resistance of the autonomous underwater vehicle i as it travels in the ocean current is proportional to the square of its velocity, and t represents time. The transmission energy consumption of autonomous underwater vehicle i under communication mode s and transmission mode y, x s Indicates whether the current communication mode of the autonomous underwater vehicle i is s.

[0058] Step S13: Collect environmental parameters and use a preset reward function and the environmental parameters to plan the target path of the autonomous underwater vehicle, so that the autonomous underwater vehicle can run to the target sensor node based on the target path, and collect target data from the target sensor node using the target communication method and the target transmission mode.

[0059] In this embodiment, after collecting target data from the target sensor node using the target communication method and the target transmission mode, the method further includes: adjusting the acquisition status of the target sensor node to "acquired". It is understood that when the target sensor node has completed data transmission with the autonomous underwater vehicle (AUV), its acquisition status should be adjusted to "acquired" to comprehensively control the movement paths of each AUV and better coordinate the AUVs. It should be noted that the AUV's movement to the target sensor node can be, for example, to a preset range or preset area of ​​the target sensor node. This embodiment combines transmission selection and path planning within the same protocol, which focuses on maximizing the efficiency of data collection, energy utilization, and transmission.

[0060] As can be seen, this application acquires the distance information between the autonomous underwater vehicle (AUV) and the target sensor node, and determines the signal-to-noise ratio (SNR) of each communication method; based on the SNR and the distance information, it determines the target communication method and the corresponding target transmission mode from each of the communication methods; it collects environmental parameters, and uses a preset reward function and the environmental parameters to plan the target path of the AUV, so that the AUV can run to the target sensor node based on the target path, and collect target data from the target sensor node using the target communication method and the target transmission mode. Therefore, this application can determine a more suitable target communication method and corresponding target transmission mode for the current environment based on the SNR and distance information. This allows for faster data transmission between the AUV and the target sensor node; real-time collection of environmental parameters makes the planned path more consistent with the current situation; and the preset reward function allows the AUV to complete the movement from its current position to the target sensor node with minimal energy consumption, thereby reducing data acquisition costs.

[0061] See Figure 2 As shown in the figure, this application discloses a specific data acquisition method for an autonomous underwater vehicle, including:

[0062] Step S21: Obtain the distance information between the autonomous underwater vehicle and the target sensor node.

[0063] Step S22: Determine the first received power and the first ambient noise of the optical communication, and use the first received power and the first ambient noise to determine the first signal-to-noise ratio of the optical communication.

[0064] In this embodiment, the formula for determining the first signal-to-noise ratio γ0 of optical communication is as follows:

[0065]

[0066] In the formula, S0 represents the first received power of optical communication, and N0 represents the first ambient noise of optical communication.

[0067] For optical communication, the first received power can be expressed as: Where, p r,s Let ε represent the conversion efficiency from optical signal to electrical signal, and d represent the distance d between the autonomous underwater vehicle i and the target sensor j. ij The degree of water turbidity is an important factor affecting the quality of underwater optical communication, which is related to the extinction coefficient c(λ). Here, λ represents the wavelength of light, and c(λ) is determined by the absorption coefficient a(λ) and the scattering coefficient b(λ), i.e., c(λ) = a(λ) + b(λ).

[0068] For the first ambient noise N0 in optical communication, shot noise is generally considered to be... and thermal noise It is a noise source, that is

[0069] Step S23: Determine the second received power and the second ambient noise of the acoustic communication, and use the second received power and the second ambient noise to determine the second signal-to-noise ratio of the acoustic communication.

[0070] In this embodiment, the second signal-to-noise ratio γ of the acoustic communication is determined. a The formula is shown below:

[0071]

[0072] In the formula, S a N represents the second received power in acoustic communication. a The second ambient noise represents acoustic communication.

[0073] Among them, the second receiving power of acoustic communication P s Indicates the sound transmission power, d ij A(d) represents the distance information between autonomous underwater vehicle i and target sensor node j. ij f) represents path loss, which has the following form: u represents the propagation factor, and a(f) is the absorption coefficient related to the frequency of the acoustic signal.

[0074] For acoustic communication, the second environmental noise N a The main consideration is water flow noise N. c Ship noise N s Wind noise N w and heat dry N t Therefore, the second environmental noise for acoustic communication is represented as N.a =N c +N s +N w +N t .

[0075] Step S24: Determine the target communication method and the corresponding target transmission mode from each of the communication methods based on the signal-to-noise ratio and the distance information.

[0076] In this embodiment, determining the target communication method and the corresponding target transmission mode from each of the communication methods based on the signal-to-noise ratio and the distance information includes: determining whether the distance information is less than a preset threshold; if it is less, determining whether the first signal-to-noise ratio is greater than the minimum signal-to-noise ratio of the optical communication; if it is greater, determining the optical communication as the target communication method and determining the transmission mode of the optical communication.

[0077] In this embodiment, after determining whether the first signal-to-noise ratio is greater than the minimum signal-to-noise ratio of the optical communication, the method further includes: if it is not greater than the minimum signal-to-noise ratio of the optical communication, determining the acoustic communication as the target communication method, and determining the target transmission mode based on the relationship between the distance information, the second signal-to-noise ratio, and the threshold interval.

[0078] It is understandable that if the distance information d ij If the threshold value Γ exceeds the optical transmission range (i.e., the preset threshold), then acoustic communication is the target communication method. Further target transmission modes require distance information d. ij Second signal-to-noise ratio γ a and threshold interval φ a The relationship between the three is determined, and when the relationship between the three satisfies the preset conditions, the transmission mode y is the target transmission mode. The preset conditions are as follows:

[0079]

[0080] If the distance information d ij If the signal-to-noise ratio γ0 is less than the threshold of the optical transmission range Γ, it is necessary to determine whether the first signal-to-noise ratio γ0 is greater than the minimum signal-to-noise ratio S of optical communication. min If it is greater than , then optical communication is the target communication method; if it is not greater than , then acoustic communication is the target communication method, and the transmission mode is y = min(m).

[0081] This embodiment proposes a novel multimode transmission selection algorithm to achieve high-quality transmission services for underwater data acquisition. The optimization of transmission mode and method selection is expressed as an integral linear programming (ILP) problem, and then the solution is obtained by considering the impact of the autonomous underwater vehicle's trajectory, distance, and water turbidity on the signal-to-noise ratio.

[0082] Step S25: Collect environmental parameters and use a preset reward function and the environmental parameters to plan the target path of the autonomous underwater vehicle, so that the autonomous underwater vehicle can run to the target sensor node based on the target path, and collect target data from the target sensor node using the target communication method and the target transmission mode.

[0083] Therefore, this application determines the first ambient noise of optical communication based on shot noise and thermal noise, and determines the first received power of optical communication based on extinction coefficient and distance information, so as to determine the first signal-to-noise ratio of optical communication based on the first received power and the first ambient noise. It also determines the second received power of acoustic communication based on path loss and acoustic transmission power, and determines the second ambient noise of acoustic communication based on water flow noise, ship noise, wind noise, and thermal noise, so as to determine the second signal-to-noise ratio of acoustic communication based on the second received power and the second ambient noise. Because it considers more comprehensive environmental factors, determining the communication method and transmission mode based on the first signal-to-noise ratio of optical communication, the second signal-to-noise ratio of acoustic communication, and distance information is more in line with reality, so as to improve data transmission efficiency.

[0084] See Figure 3 As shown in the embodiments, this application discloses another specific data acquisition method for an autonomous underwater vehicle, including:

[0085] Step S31: Obtain the distance information between the autonomous underwater vehicle and the target sensor node, and determine the signal-to-noise ratio of each communication method.

[0086] Step S32: Based on the signal-to-noise ratio and the distance information, determine the target communication method and the corresponding target transmission mode from each of the communication methods.

[0087] Step S33: Collect environmental parameters, use the environmental parameters and target acceleration determination model to obtain target acceleration, so as to plan a target path based on the target acceleration, so that the autonomous underwater vehicle can run to the target sensor node based on the target path, and collect target data from the target sensor node using the target communication method and the target transmission mode.

[0088] In this embodiment, before collecting environmental parameters and using the environmental parameters and the target acceleration determination model to obtain the target acceleration, so as to plan the target path based on the target acceleration, the method further includes: iteratively training the initial acceleration determination model using training environmental parameters to obtain the target acceleration determination model; correspondingly, iteratively training the initial acceleration determination model using training environmental parameters to obtain the target acceleration determination model includes: obtaining the current acceleration using the training environmental parameters and the current acceleration determination model, and scoring the current acceleration using the preset reward function to obtain the action value corresponding to the current acceleration; adjusting the various parameters of the current acceleration determination model based on the action value to obtain the next acceleration determination model, and then jumping back to the step of obtaining the current acceleration using the training environmental parameters and the current acceleration determination model, until a target acceleration determination model that can output acceleration that meets the target requirements is obtained. The target requirements can be that the number of training iterations reaches a preset number, or that the action value of the output acceleration is sufficiently high.

[0089] Autonomous underwater vehicle i Observation environment To determine its action in time period t That is, the current target acceleration And according to the current target acceleration The autonomous underwater vehicle (AUV) travels to sensor node k to collect data from it. AUV i needs to obtain its own coordinate information. Speed ​​information Heading angle and energy consumption Also considered are the first signal-to-noise ratio for optical communication, the second signal-to-noise ratio for acoustic communication, and environmental parameters such as ocean current speed. The autonomous underwater vehicle (AUV) i observes the above information in every time slot to determine the basis for its next action. In the action space, the actions of AUV i are primarily measured by velocity and direction. These two variables are continuous and are treated here as velocity components in each direction, i.e.

[0090] In this embodiment, during the training phase, a preset reward function is used to determine the action value corresponding to the current acceleration. This involves scoring the current acceleration to obtain its corresponding action value. The preset reward function is defined to maximize the collection rate and minimize energy consumption of the autonomous underwater vehicle (AUV) swarm. The preset reward function consists of two parts: a penalty and a reward. As a penalty, to ensure cooperation among AUVs, each AUV is prohibited from operating outside the USN coverage area or losing connection with all remaining AUVs within its maximum communication range R. For safety, AUVs are also penalized for colliding with obstacles; the penalty value is p. t i As shown below:

[0091]

[0092] The reward primarily considers the autonomous underwater vehicle's collection rate and energy consumption; therefore, the reward function is expressed as:

[0093]

[0094] In the formula, Δc t (k)=c t (k)-c t-1 (k), c t (k) represents the data collection status of sensor node k. This represents the energy consumption from t-1 to t, where ρ1 and ρ2 represent the weighting coefficients for the collection rate and energy consumption; it is understandable that... The value of an action is represented by its action value. The higher the action value, the lower the energy consumed and the better the collection effect of the corresponding current reference acceleration. Therefore, the current target acceleration can be determined based on the action value of each current reference acceleration. For example, the current reference acceleration with the highest action value can be used as the current target acceleration.

[0095] Each autonomous underwater vehicle (AUV) requires communication with other AUVs to obtain global environmental information and the actions of other AUVs. AUVs cooperate to transmit their local observations to each other. For example... Figure 4 The diagram illustrates a specific data collection process. Each autonomous underwater vehicle's acceleration determination model has four neural networks: an Actor network, a Target Actor network, a Critic network, and a Target Critic network. The Critic network evaluates the value of all autonomous underwater vehicles in their current state and actions, i.e., the action value r. t iThe Actor network modifies the probability of the selected action based on the Critic's results, which is the weight value corresponding to the acceleration. In other words, the current acceleration determines the various parameters of the model. The Critic network can update the Target Critic network to evaluate the value of the next state and action of all AUVs. That is, the next acceleration determines the various parameters of the model. The specific training process is as follows:

[0096] 1) Input status information s t The status information s t Including coordinate information of autonomous underwater vehicles Speed ​​of autonomous underwater vehicles With heading angle Collection status c t (k) Collection rate and energy consumption, ocean current velocity And direction, etc.;

[0097] 2) Initialize the Critic network and Actor Network

[0098] 3) The parameters of the Critic network and Actor network are copied to the Target critic network Q' i () and Targetactor network μ' i ();

[0099] 4) Set the preset threshold and time t for the episode;

[0100] 5) For each time t within each episode, perform the following steps:

[0101] 5.1) Autonomous underwater vehicle i performs actions And gain action value The environment updates status information based on the actions of the autonomous underwater vehicle (AUV). t+1 ;5.2) Transfer the data (s) t ,a t ,r t ,s t+1 Store it in the cache pool, let s t ←s t+1 5.3) Sample M data items from the cache pool and calculate the target value. 5.4) Update the Critic network, Actor network, Target critic network, and Target actor network;

[0102] 6) Output: Actions of the autonomous underwater vehicle i

[0103] Therefore, this application considers the coordinate information of the autonomous underwater vehicle (AUV), its speed and heading angle, data collection status, collection rate and energy consumption, and the speed and direction of ocean currents when determining the target acceleration. As a result, the target path obtained is more consistent with the current underwater conditions, and the AUV requires less energy to execute the target path, resulting in lower costs. This application proposes a multi-AUV trajectory planning algorithm based on distributed deep reinforcement learning. This algorithm is specifically designed for underwater data acquisition and considers multi-mode transmission, underwater obstacles, and ocean currents to achieve high acquisition rate and low energy consumption.

[0104] The data collection task of an autonomous underwater vehicle (AUV) is to collect data from underwater sensors by effectively controlling its own speed and direction. For an underwater scenario with N AUVs and K sensor nodes, the goal is to maximize collection efficiency and minimize the energy consumption of the AUVs. The energy consumption of the AUV is determined by its motion energy consumption ∈ […]. m and data transmission energy consumption ∈ c Composed of two parts, for the i-th autonomous underwater vehicle, its energy consumption at time t It is expressed as follows:

[0105]

[0106] Therefore, the total energy consumption of autonomous underwater vehicle i within time t is:

[0107] During data collection, the autonomous underwater vehicle, influenced by ocean currents, traveled at a speed of v. x ,v y ,v z Movement. Since the depth and z-axis velocity of the autonomous underwater vehicle can be obtained through a depth gauge, the model mainly considers the velocity direction of the autonomous underwater vehicle and the ocean current on the plane.

[0108] The model is based on the data collection rate c t and energy efficiency η t The algorithm's performance is evaluated from two aspects: the collection rate c. t Defined as:

[0109]

[0110] Among them, c t (k) indicates whether sensor node K is collected; if collected, c t (k) = 1, otherwise 0.

[0111] Energy efficiency is defined as:

[0112]

[0113] In the formula, c represents the average normalized value of the mobile energy consumption of all autonomous underwater vehicles. t This represents the collection rate of the autonomous underwater vehicle up to time t.

[0114] See Figure 5 As shown in the figure, this application discloses a data acquisition device for an autonomous underwater vehicle, comprising:

[0115] The signal-to-noise ratio determination module 11 is used to acquire the distance information between the autonomous underwater vehicle and the target sensor node, and to determine the signal-to-noise ratio of each communication method.

[0116] The transmission mode determination module 12 is used to determine the target communication mode and the corresponding target transmission mode from each of the communication modes based on the signal-to-noise ratio and the distance information;

[0117] The data acquisition module 13 is used to collect environmental parameters and plan the target path of the autonomous underwater vehicle using a preset reward function and the environmental parameters, so that the autonomous underwater vehicle can run to the target sensor node based on the target path and collect target data from the target sensor node using the target communication method and the target transmission mode.

[0118] As can be seen, this application acquires the distance information between the autonomous underwater vehicle (AUV) and the target sensor node, and determines the signal-to-noise ratio (SNR) of each communication method; based on the SNR and the distance information, it determines the target communication method and the corresponding target transmission mode from each of the communication methods; it collects environmental parameters, and uses a preset reward function and the environmental parameters to plan the target path of the AUV, so that the AUV can run to the target sensor node based on the target path, and collect target data from the target sensor node using the target communication method and the target transmission mode. Therefore, this application can determine a more suitable target communication method and corresponding target transmission mode for the current environment based on the SNR and distance information. This allows for faster data transmission between the AUV and the target sensor node; real-time collection of environmental parameters makes the planned path more consistent with the current situation; and the preset reward function allows the AUV to complete the movement from its current position to the target sensor node with minimal energy consumption, thereby reducing data acquisition costs.

[0119] Furthermore, embodiments of this application also provide an electronic device. Figure 6 This is a structural diagram of an electronic device 20 according to an exemplary embodiment. The content of the diagram should not be construed as limiting the scope of this application.

[0120] Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Specifically, it may include: at least one processor 21, at least one memory 22, a power supply 23, a communication interface 24, an input / output interface 25, and a communication bus 26. The memory 22 stores a computer program, which is loaded and executed by the processor 21 to implement the relevant steps in the data acquisition method for an autonomous underwater vehicle executed by an electronic device as disclosed in any of the foregoing embodiments.

[0121] In this embodiment, the power supply 23 is used to provide operating voltage for various hardware devices on the electronic device; the communication interface 24 can create a data transmission channel between the electronic device and external devices, and the communication protocol it follows can be any communication protocol applicable to the technical solution of this application, and is not specifically limited here; the input / output interface 25 is used to acquire external input data or output data to the outside world, and its specific interface type can be selected according to specific application needs, and is not specifically limited here.

[0122] The processor 21 may include one or more processing cores, such as a quad-core processor or an octa-core processor. The processor 21 may be implemented using at least one hardware form selected from DSP (Digital Signal Processing), FPGA (Field-Programmable Gate Array), and PLA (Programmable Logic Array). The processor 21 may also include a main processor and a coprocessor. The main processor, also known as a CPU (Central Processing Unit), is used to process data in the wake-up state; the coprocessor is a low-power processor used to process data in the standby state. In some embodiments, the processor 21 may integrate a GPU (Graphics Processing Unit), which is responsible for rendering and drawing the content to be displayed on the screen. In some embodiments, the processor 21 may also include an AI (Artificial Intelligence) processor, which is used to handle computational operations related to machine learning.

[0123] In addition, the memory 22, as a carrier for resource storage, can be a read-only memory, random access memory, disk or optical disk, etc. The resources stored on it include operating system 221, computer program 222 and data 223, etc., and the storage method can be temporary storage or permanent storage.

[0124] The operating system 221 manages and controls the various hardware devices and computer programs 222 on the electronic device to enable the processor 21 to perform calculations and processing on the massive amounts of data 223 in the memory 22. The operating system can be Windows, Unix, Linux, etc. The computer program 222, in addition to including a computer program capable of performing the data acquisition method of the autonomous underwater vehicle executed by the electronic device as disclosed in any of the foregoing embodiments, may further include computer programs capable of performing other specific tasks. The data 223 may include data received by the electronic device from external devices, as well as data collected by its own input / output interface 25.

[0125] Furthermore, embodiments of this application also disclose a computer-readable storage medium storing a computer program. When the computer program is loaded and executed by a processor, it implements the method steps performed by an autonomous underwater vehicle during data acquisition as disclosed in any of the foregoing embodiments.

[0126] Finally, it should be noted that in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0127] The above provides a detailed description of the data acquisition method, apparatus, equipment, and medium for an autonomous underwater vehicle provided by the present invention. Specific examples have been used to illustrate the principles and implementation methods of the present invention. The descriptions of the above embodiments are only for the purpose of helping to understand the method and core ideas of the present invention. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of the present invention. Therefore, the content of this specification should not be construed as a limitation of the present invention.

Claims

1. A data acquisition method for an autonomous underwater vehicle, characterized in that, include: Acquire distance information between the autonomous underwater vehicle and the target sensor node, and determine the signal-to-noise ratio of each communication method; Based on the signal-to-noise ratio and the distance information, the target communication method and the corresponding target transmission mode are determined from each of the communication methods; Environmental parameters are collected, and a target path for the autonomous underwater vehicle is planned using a preset reward function and the environmental parameters, so that the autonomous underwater vehicle can run to the target sensor node based on the target path, and collect target data from the target sensor node using the target communication method and the target transmission mode; The determination of the signal-to-noise ratio of each communication method includes: A first received power and a first ambient noise are determined for optical communication, and a first signal-to-noise ratio (SNR) for optical communication is determined using the first received power and the first ambient noise; a second received power and a second ambient noise are determined for acoustic communication, and a second SNR for acoustic communication is determined using the second received power and the second ambient noise. The step of determining the target communication method and corresponding target transmission mode from each of the communication methods based on the signal-to-noise ratio and the distance information includes: If the distance information is less than a preset threshold, then it is determined whether the first signal-to-noise ratio is greater than the minimum signal-to-noise ratio of the optical communication; if it is greater, then the optical communication is determined as the target communication method, and the transmission mode of the optical communication is determined. After determining whether the first signal-to-noise ratio is greater than the minimum signal-to-noise ratio of the optical communication, the method further includes: If the value is not greater than the threshold, then the acoustic communication is determined as the target communication method, and the target transmission mode is determined based on the relationship between distance information, the second signal-to-noise ratio, and the threshold interval, and a preset condition; the preset condition is: ； in, For distance information, The second signal-to-noise ratio, y represents the threshold interval and y represents the transmission mode.

2. The data acquisition method for an autonomous underwater vehicle according to claim 1, characterized in that, The process of collecting environmental parameters and using a preset reward function and the environmental parameters to plan the target path of the autonomous underwater vehicle includes: Environmental parameters are collected, and the target acceleration is determined using the environmental parameters and the target acceleration model to obtain the target acceleration, so as to plan the target path based on the target acceleration.

3. The data acquisition method for an autonomous underwater vehicle according to claim 2, characterized in that, Before collecting environmental parameters, using the environmental parameters and the target acceleration determination model to obtain the target acceleration, and planning the target path based on the target acceleration, the process also includes: The initial acceleration determination model is iteratively trained using training environment parameters to obtain the target acceleration determination model; Accordingly, the iterative training of the initial acceleration determination model using training environment parameters to obtain the target acceleration determination model includes: The model is used to determine the current acceleration by using training environment parameters and the current acceleration, and the current acceleration is scored using the preset reward function to obtain the action value corresponding to the current acceleration; Based on the action value, adjust the parameters of the current acceleration determination model to obtain the next acceleration determination model, and then jump back to the step of obtaining the current acceleration using the training environment parameters and the current acceleration determination model, until a target acceleration determination model that can output acceleration that meets the target requirements is obtained.

4. The data acquisition method for an autonomous underwater vehicle according to any one of claims 1 to 3, characterized in that, Before acquiring the current distance information between the autonomous underwater vehicle and the target sensor node, and determining the signal-to-noise ratio of each communication method, the method further includes: Select the target sensor nodes whose acquisition status is not acquired from a number of sensor nodes; Accordingly, after acquiring target data from the target sensor node using the target communication method and the target transmission mode, the process further includes: Adjust the acquisition status of the target sensor node to "acquisition completed".

5. A data acquisition device for an autonomous underwater vehicle, used to implement the steps of the data acquisition method for an autonomous underwater vehicle according to any one of claims 1 to 4, characterized in that, include: The signal-to-noise ratio determination module is used to acquire distance information between the autonomous underwater vehicle and the target sensor node, and to determine the signal-to-noise ratio of each communication method. The transmission mode determination module is used to determine the target communication mode and the corresponding target transmission mode from each of the communication modes based on the signal-to-noise ratio and the distance information; The data acquisition module is used to collect environmental parameters and plan the target path of the autonomous underwater vehicle using a preset reward function and the environmental parameters, so that the autonomous underwater vehicle can run to the target sensor node based on the target path and collect target data from the target sensor node using the target communication method and the target transmission mode.

6. An electronic device, characterized in that, include: Memory, used to store computer programs; A processor for executing the computer program to implement the steps of the data acquisition method for an autonomous underwater vehicle as described in any one of claims 1 to 4.

7. A computer-readable storage medium, characterized in that, Used to store computer programs; wherein, when the computer programs are executed by a processor, they implement the steps of the data acquisition method for an autonomous underwater vehicle as described in any one of claims 1 to 4.

Images