Operation planning algorithm and system of underwater unmanned submersible based on artificial intelligence

Abstract

The present invention discloses an underwater unmanned vehicle operation planning algorithm and system based on artificial intelligence, and relates to the technical field of underwater vehicles. The technical key points of the scheme are: the energy consumption factor is calculated by the speed and steering angle of the underwater unmanned vehicle relative to the water flow; the node with the smallest heuristic function value is selected as the current node, until the current node is the target node, and the shortest path is generated by backtracking; the angle between adjacent nodes is calculated by point product and vector length, and compared with the angle threshold to determine whether smoothing is required; for the smoothed path, the speed of the underwater unmanned vehicle is recorded, and the speed fluctuation coefficient of the underwater unmanned vehicle is calculated, and according to the speed fluctuation coefficient, the position and number of arc nodes are automatically adjusted by an artificial intelligence algorithm to optimize the path. The present invention can reduce energy consumption, extend the operation time, and improve the safety of the vehicle.

Description

Technical Field

[0001] The present invention relates to the technical field of underwater submersibles, and in particular to an operation planning algorithm and system for underwater unmanned submersibles based on artificial intelligence. Background Art

[0002] With the continuous development and utilization of marine resources, underwater unmanned vehicles (hereinafter referred to as "underwater vehicles") are increasingly used in the fields of ocean exploration, environmental monitoring, and seabed topography mapping. In order to improve the operating efficiency, safety, and autonomy of underwater vehicles, artificial intelligence (AI)-based underwater vehicle operation planning algorithms and systems have become a hot topic of current research.

[0003] In the Chinese invention application with application publication number CN113074730A, an underwater path planning method and system are disclosed. These factors are fully considered, and a cost function for the underwater environment is designed in combination with the kinematic characteristics of the underwater vehicle, the influence of water flow, the operating speed and operating time of the underwater vehicle. When optimizing the trajectory, the BSpline algorithm is used in combination with the speed of the water flow and the smoothness of the trajectory to generate a safe, dynamically feasible trajectory, which is more suitable for path planning in an underwater environment. Visual SLAM is used for underwater mapping, which is cheaper and easier to obtain than sonar, and has a lower cost.

[0004] In view of the above invention, the prior art has the following deficiencies:

[0005] 1. Since the steering angle and steering speed are not taken into consideration in the planning, the submersible may consume too much energy when performing complex steering tasks. The steering process has a direct impact on the energy consumption of the submersible, especially in complex seabed environments where frequent or sharp turns are required. Ignoring these factors not only reduces the operating efficiency of the submersible, but may also limit its ability to continue operating;

[0006] 2. Path planning algorithms that do not take into account steering angles and steering speeds may cause the vehicle to exhibit unstable behavior during navigation. Sharp turns or inappropriate steering speeds may cause the vehicle to lose balance, especially in the presence of currents, obstacles or other complex ocean conditions. This not only threatens the safety of the vehicle, but may also affect the quality and accuracy of mission completion. Summary of the invention

[0007] In view of the shortcomings of the prior art, the present invention provides an underwater unmanned vehicle operation planning algorithm and system based on artificial intelligence. By comprehensively considering the relative speed of the underwater unmanned vehicle to the water flow and the turning angle, it can reduce energy consumption, extend the operation time, reduce unnecessary turns and speed fluctuations, and improve the safety of the vehicle.

[0008] To achieve the above objectives, the present invention is implemented through the following technical solutions: an artificial intelligence-based underwater unmanned submersible operation planning algorithm includes the following steps:

[0009] The speed of the underwater unmanned submersible vehicle relative to the water flow is calculated by using the speed of the underwater unmanned submersible vehicle and the water flow speed, and the energy consumption factor is calculated in combination with the steering angle of the underwater unmanned submersible vehicle;

[0010] Initialize the node storage table, node set and list of nodes to be processed, select the node with the smallest heuristic function value from the list of nodes to be processed as the current node, until the current node is the target node, and backtrack to generate the shortest path;

[0011] The vector between the adjacent nodes is calculated through the coordinates of two adjacent nodes, the angle between the adjacent nodes is calculated through the dot product and the vector length, and whether smoothing is required is determined by comparing the angle between the adjacent nodes with the angle threshold;

[0012] For the smoothed path, the speed of the underwater unmanned vehicle is recorded, and the speed fluctuation coefficient of the underwater unmanned vehicle is calculated. Based on the speed fluctuation coefficient, the position and number of arc nodes are automatically adjusted through an artificial intelligence algorithm to optimize the path.

[0013] Furthermore, the speed of the underwater unmanned submersible vehicle relative to the water flow is calculated by the water flow speed at the current position of the underwater unmanned submersible vehicle and the speed of the underwater unmanned submersible vehicle when turning. The calculation formula is as follows:

[0014]

[0015] Among them, V rel V represents the relative speed of the underwater unmanned vehicle relative to the water flow. AUV Indicates the speed of the underwater unmanned vehicle, V water represents the water flow velocity, and α represents the angle between the water flow direction and the speed direction of the underwater unmanned submersible.

[0016] Furthermore, the energy consumption factor is calculated through the relative speed and steering angle of the underwater unmanned submersible vehicle to the water flow after dimensionless processing. The calculation formula is as follows:

[0017] e(n)=C*V rel 2 *sin 2 θ*T

[0018] Where e(n) represents the energy consumption factor, C represents the energy consumption coefficient, C>0, V relrepresents the relative speed of the underwater unmanned submersible vehicle relative to the water flow, θ represents the turning angle of the underwater unmanned submersible vehicle, and T represents the turning time.

[0019] Furthermore, a node storage table is initialized to record the information of each node's parent node, a node set is initialized to store the nodes that have been visited, a list of nodes to be processed is initialized, and they are sorted according to the heuristic function value. The heuristic function f(n) is:

[0020] f(n)=g(n)+h(n)+e(n)

[0021] Among them, g(n) represents the actual distance from the starting point to the current node, h(n) represents the estimated distance from the current node to the target point, and e(n) represents the energy consumption factor.

[0022] Furthermore, the node with the smallest heuristic function value is selected from the list of nodes to be processed as the current node. If the current node is the target node, the algorithm ends and backtracks to find the shortest path. Otherwise, the current node is marked as visited and removed from the list of nodes to be processed.

[0023] Furthermore, for each adjacent node of the current node, perform the following operations:

[0024] If the adjacent node is already in the set of visited nodes, skip the node, calculate the heuristic function value of the adjacent node, and compare it with the corresponding value in the list of nodes to be processed:

[0025] If the adjacent node is not in the list of nodes to be processed, add it and update the node storage table;

[0026] If the adjacent node is already in the list of nodes to be processed, and the heuristic function value of the adjacent node is less than the corresponding value in the list of nodes to be processed, the information in the node storage table is updated.

[0027] Furthermore, the vector between adjacent nodes is calculated through the coordinates of two adjacent nodes. The calculation formula is as follows:

[0028]

[0029] in, A vector that represents the node with coordinates (x1, y1, z1) pointing to the node with coordinates (x2, y2, z2);

[0030] The angle between adjacent nodes is calculated by dot product and vector length. The calculation formula is as follows:

[0031]

[0032] in, and are two vectors between adjacent nodes, and “·” represents the dot product operation. and Indicates the length of a vector.

[0033] Furthermore, by comparing the angle between adjacent nodes with the angle threshold, it is determined whether smoothing is required, specifically including:

[0034] When the angle between adjacent nodes is less than or equal to the angle threshold, no processing is required;

[0035] When the angle between adjacent nodes is greater than the angle threshold, smoothing is required;

[0036] Insert additional arc nodes between the node that needs to be smoothed and the adjacent node, update the node storage table, record the parent node and other information of the newly inserted arc node, and update the visited node set and the list of nodes to be processed.

[0037] Furthermore, for the smoothed path, the speed of the underwater unmanned vehicle is recorded, and the speed fluctuation coefficient of the underwater unmanned vehicle is calculated. The calculation formula is as follows:

[0038]

[0039] Where Cv is the speed fluctuation coefficient, V avg represents the average speed, V i Represents the speed value at the i-th time point, i=1,2,…,N, N is a positive integer.

[0040] The operation planning system of underwater unmanned submersible based on artificial intelligence includes: path planning module, path smoothing processing module and path optimization module; among which,

[0041] The path planning module calculates the speed of the underwater unmanned vehicle relative to the water flow through the speed of the underwater unmanned vehicle and the water flow speed, and calculates the energy consumption factor in combination with the steering angle of the underwater unmanned vehicle; initializes the node storage table, node set and list of nodes to be processed, selects the node with the smallest f(n) value from the list of nodes to be processed as the current node, until the current node is the target node, and backtracks to generate the shortest path;

[0042] The path smoothing processing module calculates the vector between adjacent nodes through the coordinates of two adjacent nodes, calculates the angle between adjacent nodes through dot product and vector length, and determines whether smoothing is required by comparing the angle between adjacent nodes with the angle threshold;

[0043] The path optimization module records the speed of the underwater unmanned vehicle for the smoothed path and calculates the speed fluctuation coefficient of the underwater unmanned vehicle. Based on the speed fluctuation coefficient, the artificial intelligence algorithm is used to automatically adjust the position and number of arc nodes to optimize the path.

[0044] The present invention provides an underwater unmanned submersible operation planning algorithm and system based on artificial intelligence, which has the following beneficial effects:

[0045] (1) The calculation of the energy consumption factor enables the submersible to more accurately estimate its energy consumption under specific conditions. In a complex and changeable underwater environment, the speed and direction of the water flow may change at any time. By real-time monitoring and calculating the energy consumption factor, the submersible can adapt to environmental changes in real time and adjust its speed and steering strategy, which can reduce energy consumption, extend operating time, and improve overall energy efficiency.

[0046] (2) By initializing the node storage table, node set, and list of nodes to be processed, and combining the strategy of selecting the node with the smallest f(n) value as the current node, the shortest path from the starting point to the target point can be generated, which can not only improve the operating efficiency of the AUV but also reduce energy consumption.

[0047] (3) By calculating the angle between adjacent nodes and comparing it with the threshold, the sharp angles and unnecessary turning points in the path can be identified and smoothed, which helps to generate a smoother, continuous and efficient path, making the vehicle more stable during operation and reducing the posture changes or speed fluctuations of the vehicle that may be caused by sharp turns.

[0048] (4) By optimizing the path and reducing unnecessary turns and speed fluctuations, the SCU can complete its mission more efficiently. Reducing speed fluctuations means that the SCU can operate more stably, thereby improving its overall operating efficiency. Excessive speed fluctuations may cause the SCU to behave unstable when turning and may even cause an accident. By optimizing the path and reducing speed fluctuations, this risk can be significantly reduced and the safety of the SCU can be improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] Figure 1 This is a schematic diagram of the steps of the operation planning algorithm of the underwater unmanned submersible based on artificial intelligence of the present invention;

[0050] Figure 2 This is a schematic diagram of the structure of the operation planning system of the underwater unmanned submersible based on artificial intelligence of the present invention. DETAILED DESCRIPTION

[0051] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0052] See also Figure 1 The present invention provides an operation planning algorithm for an underwater unmanned submersible based on artificial intelligence, comprising the following steps:

[0053] Step 1: Calculate the speed of the underwater unmanned submersible relative to the water flow through the speed of the underwater unmanned submersible and the speed of the water flow, and calculate the energy consumption factor in combination with the steering angle of the underwater unmanned submersible;

[0054] The step 1 includes the following contents:

[0055] Step 101: obtaining the water flow speed and direction at the current position of the underwater unmanned submersible through a sensor, and obtaining the speed and steering angle of the underwater unmanned submersible when turning;

[0056] Step 102: Calculate the speed of the underwater unmanned vehicle relative to the water flow through vector synthesis. The calculation formula is as follows:

[0057]

[0058] Among them, V rel V represents the relative speed of the underwater unmanned vehicle relative to the water flow. AUV Indicates the speed of the underwater unmanned vehicle, V water represents the water flow velocity, α represents the angle between the water flow direction and the underwater unmanned submersible vehicle velocity direction;

[0059] It should be noted that if the underwater unmanned vehicle and the water flow are in the same direction, V rel =V AUV -V water or V rel =V AUV +V water , if they are not in the same direction, vector synthesis is required;

[0060] Step 103: The energy consumption factor is calculated by converting the relative speed of the underwater unmanned vehicle to the water flow and the steering angle into dimensionless form. The calculation formula is as follows:

[0061] e(n)=C*V rel 2 *sin 2θ*T

[0062] Where e(n) represents the energy consumption factor, C represents the energy consumption coefficient, C>0, V rel represents the relative speed of the underwater unmanned vehicle relative to the water flow, θ represents the turning angle of the underwater unmanned vehicle, and T represents the turning time;

[0063] It should be noted that the energy consumption coefficient is a constant determined by experiments or simulations, and depends on factors such as the shape, size, propulsion system efficiency, and water flow conditions of the submersible. The turning time is calculated based on the turning angular velocity ω and the target turning angle θ: T = θ / ω;

[0064] When using, combine the contents of step 101 to step 103:

[0065] The calculation of energy consumption factors enables the submersible to more accurately estimate its energy consumption under specific conditions. In a complex and changeable underwater environment, the speed and direction of water flow may change at any time. By real-time monitoring and calculation of energy consumption factors, the submersible can adapt to environmental changes in real time, adjust speed and steering strategies, reduce energy consumption, extend operating time, and improve overall energy efficiency.

[0066] Step 2: Initialize the node storage table, node set and list of nodes to be processed, select the node with the smallest f(n) value from the list of nodes to be processed as the current node, until the current node is the target node, and backtrack to generate the shortest path;

[0067] The step 2 includes the following contents:

[0068] Step 201: Detect obstacles in the surrounding environment through sensors (such as sonar, lidar, etc.) and determine the location of the obstacles;

[0069] Step 202: Initialize a node storage table to record information such as the parent node of each node, initialize a node set to store visited nodes, initialize a list of nodes to be processed, and sort them according to the heuristic function value;

[0070] It should be noted that a node represents a possible position or state in the path planning space. In the path planning scenario of an underwater unmanned vehicle, each node represents a potential position or path point of the underwater unmanned vehicle in the underwater environment;

[0071] Step 203: Define a heuristic function f(n):

[0072] f(n)=g(n)+h(n)+e(n)

[0073] Among them, g(n) represents the actual distance from the starting point to the current node, h(n) represents the estimated distance from the current node to the target point, and e(n) represents the energy consumption factor;

[0074] Step 204: Select the node with the smallest f(n) value from the list of nodes to be processed as the current node. If the current node is the target node, the algorithm ends and backtracks to find the shortest path. Otherwise, mark the current node as visited and remove it from the list of nodes to be processed.

[0075] Step 205: For each adjacent node of the current node, perform the following operations:

[0076] If the adjacent node is already in the set of visited nodes, skip the node, calculate the g(n) value of the adjacent node (the actual distance from the starting point to the node), calculate the h(n) value of the adjacent node (the estimated distance from the node to the target point), calculate the e(n) value of the adjacent node, calculate the f(n) value of the adjacent node, and compare it with the corresponding value in the list of nodes to be processed:

[0077] If the adjacent node is not in the list of nodes to be processed, add it and update the node storage table;

[0078] If the adjacent node is already in the list of nodes to be processed, and the f(n) value of the adjacent node is less than the corresponding value in the list of nodes to be processed, the information in the node storage table is updated.

[0079] It should be noted that if the adjacent node is not in the list of nodes to be processed, the algorithm will add the adjacent node and its f(n) value, g(n) value and other related information to the list of nodes to be processed, and update the node storage table to record the parent node and other related information of the adjacent node. If the adjacent node is already in the list of nodes to be processed, but the calculated f(n) value is less than the value stored in the list, the algorithm will update the corresponding information in the list of nodes to be processed and the node storage table to reflect a better path selection.

[0080] When using, combine the contents in step 201 to step 205:

[0081] By initializing the node storage table, node set, and list of nodes to be processed, and combining the strategy of selecting the node with the smallest f(n) value as the current node, the shortest path from the starting point to the target point can be generated, which can not only improve the operating efficiency of the AUV, but also reduce energy consumption.

[0082] Step 3: Calculate the vector between adjacent nodes through the coordinates of two adjacent nodes, calculate the angle between adjacent nodes through dot product and vector length, and compare the angle between adjacent nodes with the angle threshold to determine whether smoothing is required;

[0083] The step three includes the following contents:

[0084] Step 301: Obtain the three-dimensional coordinates of the nodes, and calculate the vector between the adjacent nodes through the coordinates of two adjacent nodes. The calculation formula is as follows:

[0085]

[0086] in, A vector that represents the node with coordinates (x1, y1, z1) pointing to the node with coordinates (x2, y2, z2);

[0087] Step 302: Calculate the angle between adjacent nodes by dot product and vector length. The calculation formula is as follows:

[0088]

[0089] in, and are two vectors between adjacent nodes, and “·” represents the dot product operation. and Indicates the length of a vector;

[0090] Step 303: presetting an angle threshold, and comparing the angle between adjacent nodes with the angle threshold to determine whether smoothing is required, specifically including:

[0091] When the angle between adjacent nodes is less than or equal to the angle threshold, it means that there is no large angle change in the current path segment, which meets the minimum turning radius requirement of the stealth vehicle and no processing is required;

[0092] When the angle between adjacent nodes is greater than the angle threshold, it means that the current path segment has a large angle change, which does not meet the minimum turning radius requirement of the stealth vehicle and needs to be smoothed;

[0093] Step 304: insert an additional arc node between the node to be smoothed and the adjacent node, update the node storage table, record the parent node and other information of the newly inserted arc node, and update the visited node set and the list of nodes to be processed to reflect the changes in the path.

[0094] When used, combine the contents of step 301 to step 304:

[0095] By calculating the angles between adjacent nodes and comparing them with the threshold, sharp angles and unnecessary turning points in the path can be identified and smoothed, which helps to generate a smoother, continuous and efficient path, making the vehicle more stable during operation and reducing the changes in the vehicle's posture or speed fluctuations that may be caused by sharp turns.

[0096] Step 4: For the smoothed path, record the speed of the underwater unmanned vehicle and calculate the speed fluctuation coefficient of the underwater unmanned vehicle. According to the speed fluctuation coefficient, the position and number of arc nodes are automatically adjusted through the artificial intelligence algorithm to optimize the path;

[0097] The step 4 includes the following contents:

[0098] Step 401: For the smoothed path, record the speed of the underwater unmanned vehicle and calculate the speed fluctuation coefficient of the underwater unmanned vehicle. The calculation formula is as follows:

[0099]

[0100] Where Cv is the speed fluctuation coefficient, V avg represents the average speed, V i represents the speed value at the i-th time point, i=1,2,…,N, N is a positive integer;

[0101] It should be noted that when the speed fluctuation coefficient is higher, it means that the speed fluctuation is greater and the smoothing effect of the smoothed path is worse. Conversely, when the speed fluctuation coefficient is lower, it means that the speed fluctuation is smaller and the smoothing effect of the smoothed path is better.

[0102] Step 402: According to the speed fluctuation coefficient, the position and number of arc nodes are automatically adjusted by an artificial intelligence algorithm (genetic algorithm) to optimize the path, specifically including:

[0103] Step 4021: define decision variables, which include the position (such as x, y, z coordinates) and number of arc nodes, randomly generate an initial population of multiple individuals, each of which represents a possible solution, that is, the position and number of a set of arc nodes, and for each individual (solution), calculate its corresponding speed fluctuation coefficient and use it as the fitness value. The smaller the fitness value, the closer the individual is to the optimal solution;

[0104] Step 4022: select individuals from the current population according to the fitness value. Common selection strategies include roulette selection, tournament selection, etc. The selected individuals will have the opportunity to participate in subsequent crossover and mutation operations; randomly select two parent individuals for crossover operation, and exchange some genes of the two parent individuals according to the selected crossover mode (such as single-point crossover, multi-point crossover, etc.) to generate new offspring individuals; perform mutation operation on the newly generated offspring individuals or some individuals in the population, and randomly select a gene for mutation, such as changing its value or introducing a new gene. The mutation operation can increase the diversity of the population and help to find new and better solutions;

[0105] Step 4023: Repeat the selection, crossover and mutation operations to generate a new population, evaluate each individual in the new population, and calculate its fitness value, select some excellent individuals according to the fitness value to enter the next generation population, and repeat the above steps until the termination condition is met (such as reaching the maximum number of iterations, fitness value convergence, etc.);

[0106] Step 4024: When the termination condition is met, the iterative evolution process is stopped, and the individual with the best fitness value in the current population is output as the optimal solution, that is, the optimized arc node position and number.

[0107] It should be noted that the optimized path should be verified in the actual environment to ensure that the crawler can run stably along the new path, and observe whether the speed fluctuation coefficient meets the requirements. If it does not meet the requirements, the parameters of the genetic algorithm (such as population size, crossover rate, mutation rate, etc.) can be adjusted and the optimization process can be restarted.

[0108] When used, combine the contents of step 401 to step 402:

[0109] By optimizing the path and reducing unnecessary turns and speed fluctuations, the SCUBA can complete its mission more efficiently. Reducing speed fluctuations means that the SCUBA can operate more stably, thereby improving its overall operating efficiency. Excessive speed fluctuations may cause the SCUBA to behave unstable when turning and may even cause an accident. By optimizing the path and reducing speed fluctuations, this risk can be significantly reduced and the safety of the SCUBA can be improved.

[0110] See also Figure 2 The present invention also provides an operation planning system for an underwater unmanned submersible based on artificial intelligence, including: a path planning module, a path smoothing processing module and a path optimization module; wherein,

[0111] The path planning module calculates the speed of the underwater unmanned vehicle relative to the water flow through the speed of the underwater unmanned vehicle and the water flow speed, and calculates the energy consumption factor in combination with the steering angle of the underwater unmanned vehicle; initializes the node storage table, node set and list of nodes to be processed, selects the node with the smallest f(n) value from the list of nodes to be processed as the current node, until the current node is the target node, and backtracks to generate the shortest path;

[0112] The path smoothing processing module calculates the vector between adjacent nodes through the coordinates of two adjacent nodes, calculates the angle between adjacent nodes through dot product and vector length, and determines whether smoothing is required by comparing the angle between adjacent nodes with the angle threshold;

[0113] The path optimization module records the speed of the underwater unmanned vehicle for the smoothed path and calculates the speed fluctuation coefficient of the underwater unmanned vehicle. Based on the speed fluctuation coefficient, the artificial intelligence algorithm is used to automatically adjust the position and number of arc nodes to optimize the path.

[0114] In the application, the several formulas involved are all calculated by removing dimensions and taking their numerical values. The formula is a formula of the most recent real situation obtained by collecting a large amount of data and performing software simulation. The coefficients in the formula are set by technicians in this field according to actual conditions.

[0115] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination thereof. When implemented by software, the above embodiments may be implemented in whole or in part in the form of a computer program product. A person of ordinary skill in the art may appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein may be implemented in combination with electronic hardware, computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution.

[0116] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, and may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0117] The above description is only a specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application.

Claims

1. An artificial intelligence-based underwater unmanned submersible vehicle operation planning algorithm, characterized by: The following steps are involved: The speed of the underwater unmanned submersible vehicle relative to the water flow is calculated by using the speed of the underwater unmanned submersible vehicle and the water flow speed, and the energy consumption factor is calculated in combination with the steering angle of the underwater unmanned submersible vehicle; Initialize the node storage table, node set and list of nodes to be processed, select the node with the smallest heuristic function value from the list of nodes to be processed as the current node, until the current node is the target node, and backtrack to generate the shortest path; The heuristic function is f(n): f(n)=g(n)+h(n)+e(n) Among them, g(n) represents the actual distance from the starting point to the current node, h(n) represents the estimated distance from the current node to the target point, and e(n) represents the energy consumption factor; The vector between the adjacent nodes is calculated through the coordinates of two adjacent nodes, the angle between the adjacent nodes is calculated through the dot product and the vector length, and whether smoothing is required is determined by comparing the angle between the adjacent nodes with the angle threshold; For the smoothed path, the speed of the underwater unmanned vehicle is recorded, and the speed fluctuation coefficient of the underwater unmanned vehicle is calculated. According to the speed fluctuation coefficient, the position and number of arc nodes are automatically adjusted through the artificial intelligence algorithm to optimize the path; The speed of the underwater unmanned submersible relative to the water flow is calculated by the water flow speed at the current position of the underwater unmanned submersible and the speed of the underwater unmanned submersible when turning. The calculation formula is as follows: Among them, V rel V represents the relative speed of the underwater unmanned vehicle relative to the water flow. AUV Indicates the speed of the underwater unmanned vehicle, V water represents the water flow velocity, α represents the angle between the water flow direction and the underwater unmanned submersible vehicle velocity direction; The energy consumption factor is calculated by the relative speed and steering angle of the underwater unmanned submersible to the water flow after dimensionless processing. The calculation formula is as follows: e(n)=C*V rel 2 *sin 2 θ*T Where e(n) represents the energy consumption factor, C represents the energy consumption coefficient, C>0, V rel represents the relative speed of the underwater unmanned submersible vehicle relative to the water flow, θ represents the turning angle of the underwater unmanned submersible vehicle, and T represents the turning time.

2. The operation planning algorithm of an underwater unmanned submersible vehicle based on artificial intelligence according to claim 1 is characterized in that: Initialize a node storage table to record the parent node information of each node, initialize a node set to store the nodes that have been visited, initialize a list of nodes to be processed, and sort them according to the heuristic function value.

3. The operation planning algorithm of an underwater unmanned submersible vehicle based on artificial intelligence according to claim 2 is characterized in that: Select the node with the smallest heuristic function value from the list of nodes to be processed as the current node. If the current node is the target node, the algorithm ends and backtracks to find the shortest path. Otherwise, mark the current node as visited and remove it from the list of nodes to be processed.

4. The operation planning algorithm of an underwater unmanned submersible vehicle based on artificial intelligence according to claim 3 is characterized in that: For each neighboring node of the current node, do the following: If the adjacent node is already in the set of visited nodes, skip the node, calculate the heuristic function value of the adjacent node, and compare it with the corresponding value in the list of nodes to be processed: If the adjacent node is not in the list of nodes to be processed, add it and update the node storage table; If the adjacent node is already in the list of nodes to be processed, and the heuristic function value of the adjacent node is less than the corresponding value in the list of nodes to be processed, the information in the node storage table is updated.

5. The operation planning algorithm of an underwater unmanned submersible vehicle based on artificial intelligence according to claim 1 is characterized in that: The vector between two adjacent nodes is calculated by the coordinates of the two adjacent nodes. The calculation formula is as follows: in, A vector that represents the node with coordinates (x1, y1, z1) pointing to the node with coordinates (x2, y2, z2); The angle between adjacent nodes is calculated by dot product and vector length. The calculation formula is as follows: in, and are two vectors between adjacent nodes, "·" represents the dot product operation, and Indicates the length of a vector.

6. The operation planning algorithm of an underwater unmanned submersible vehicle based on artificial intelligence according to claim 5 is characterized in that: By comparing the angle between adjacent nodes with the angle threshold, it is determined whether smoothing is required, including: When the angle between adjacent nodes is less than or equal to the angle threshold, no processing is required; When the angle between adjacent nodes is greater than the angle threshold, smoothing is required; Insert additional arc nodes between the node that needs to be smoothed and the adjacent node, update the node storage table, record the parent node information of the newly inserted arc node, and update the visited node set and the list of nodes to be processed.

7. The operation planning algorithm of an underwater unmanned submersible vehicle based on artificial intelligence according to claim 1 is characterized in that: For the smoothed path, record the speed of the underwater unmanned vehicle and calculate the speed fluctuation coefficient of the underwater unmanned vehicle. The calculation formula is as follows: Where Cv is the speed fluctuation coefficient, V avg represents the average speed, V i Represents the speed value at the i-th time point, i=1,2,…,N, N is a positive integer.

8. An artificial intelligence-based underwater unmanned submersible vehicle operation planning system, used to implement the algorithm described in any one of claims 1 to 7, characterized in that: include: The path planning module calculates the speed of the underwater unmanned submersible vehicle relative to the water flow through the speed of the underwater unmanned submersible vehicle and the water flow speed, and calculates the energy consumption factor in combination with the steering angle of the underwater unmanned submersible vehicle; Initialize the node storage table, node set and list of nodes to be processed, select the node with the smallest f(n) value from the list of nodes to be processed as the current node, until the current node is the target node, and backtrack to generate the shortest path; The path smoothing processing module calculates the vector between adjacent nodes through the coordinates of two adjacent nodes, calculates the angle between adjacent nodes through dot product and vector length, and determines whether smoothing is required by comparing the angle between adjacent nodes with the angle threshold; The path optimization module records the speed of the underwater unmanned vehicle for the smoothed path and calculates the speed fluctuation coefficient of the underwater unmanned vehicle. Based on the speed fluctuation coefficient, the artificial intelligence algorithm is used to automatically adjust the position and number of arc nodes to optimize the path.

Images