DTRBA* risk trajectory planning method and system for underwater vehicle

Abstract

The application discloses a DTRBA* risk path planning method and system for underwater vehicles, and the method comprises the following steps: performing safety evaluation and concealment evaluation on a target planning area according to marine environment data and vehicle data, and comprehensively obtaining a three-dimensional space comprehensive risk evaluation result of the target planning area by comprehensively processing three-dimensional space risk evaluation results obtained through the safety evaluation and the concealment evaluation; projecting the three-dimensional space comprehensive risk evaluation result of the target planning area onto a two-dimensional plane, performing path planning by using a DTRBA* algorithm to obtain all path point information on an X-Y direction two-dimensional path, and then finding a best height in a Z direction to generate a three-dimensional path, and finally obtaining a three-dimensional space complete path of the target planning area through path smoothing processing. The application aims to realize comprehensive path planning of underwater vehicles in complex marine environments, and the path planning has safety, concealment, smoothness and high efficiency.

Description

Technical Field

[0001] This invention relates to the field of underwater unmanned vehicle technology, specifically to a DTRBA* risk trajectory planning method and system for underwater vehicles. Background Technology

[0002] As the core of an underwater vehicle's intelligent navigation system, path planning technology plays a crucial role in finding paths that meet multiple objectives such as safety, efficiency, and low energy consumption in complex environments. It directly determines mission success rate and equipment operational safety. Inadequate path planning can lead not only to collisions with obstacles such as reefs, causing equipment damage and marine pollution, but also to a surge in energy consumption, shortening the vehicle's range and limiting operational capabilities.

[0003] Marine meteorological environment is one of the key factors affecting the navigation safety and path efficiency of underwater vehicles. In actual operations, marine meteorological environment encompasses parameters such as wave level, current velocity, water temperature gradient, salinity gradient, and sudden meteorological events (such as short-term strong currents and underwater eddies). For example, wind and waves of force 4 or higher can cause disturbances at a depth of 10-20 meters underwater through water conduction, leading to a 15%-20% decrease in the attitude control accuracy of underwater vehicles; underwater current velocities exceeding 1.5 m / s can cause the actual trajectory of underwater vehicles to deviate from the planned path by more than 30%, and increase propulsion energy consumption by an additional 40%-60%; salinity gradients can interfere with acoustic navigation signals, leading to increased positioning errors and indirectly increasing the risk of collision. These meteorological environmental factors need to be quantitatively assessed and transformed into risk indicators that can guide path planning in order to ensure the safety and feasibility of the path.

[0004] Traditional path planning algorithms are mainly divided into traditional search algorithms, sampling-based algorithms, and bio-inspired algorithms, but none of them have established a systematic marine meteorological environment assessment mechanism, and they lack the core logic of "grid risk value generation - risk value fusion planning," resulting in a disconnect between path planning and the actual marine environment. In addition, existing improved path planning algorithms are mostly derived from the fields of UAVs or small underwater robots, and do not fully consider the coupling effect between the characteristics of underwater vehicles and the marine meteorological environment: underwater vehicles are equipped with main thrusters and vertical and lateral auxiliary thrusters, making motion constraints more complex, their attitude stability more sensitive to changes in the meteorological environment, and they need to combine electronic chart data and meteorological forecast data for cross-regional navigation planning; while existing algorithms often ignore the whole process logic of "meteorological assessment - risk quantification - path fusion," focusing only on spatial path generation, without incorporating dynamic updates and constraint mechanisms for meteorological risk values, resulting in poor path continuity and weak risk resistance under complex weather conditions, and failing to meet the multi-condition operation requirements of underwater vehicles.

[0005] In summary, existing path planning algorithms have two major shortcomings: first, the lack of a quantitative assessment system for the marine meteorological environment makes it impossible to generate meteorological risk values ​​for each grid area, resulting in a lack of environmental risk constraints in path planning; second, deficiencies exist in dynamic adaptability to complex three-dimensional underwater environments, multi-condition adaptability of large vehicles, multi-objective optimization balance, and planning efficiency. These shortcomings collectively make it difficult for existing algorithms to meet the actual operational needs of underwater vehicles, necessitating a path planning method that first assesses the marine environment to generate risk values, and then integrates these risk values ​​to achieve safe and efficient planning. Summary of the Invention

[0006] The technical problem to be solved by the present invention is to provide a DTRBA* risk trajectory planning method and system for underwater vehicles, which addresses the above-mentioned problems in the prior art. The present invention aims to achieve comprehensive path planning for underwater vehicles in complex marine environments, which combines safety, stealth, smoothness and efficiency.

[0007] To solve the above-mentioned technical problems, the technical solution adopted by the present invention is as follows: A DTRBA* risk trajectory planning method for underwater vehicles includes the following steps: conducting safety and concealment assessments of the target planning area based on marine environmental data and vehicle data; integrating the three-dimensional spatial risk assessment results obtained from the safety and concealment assessments to obtain a comprehensive three-dimensional spatial risk assessment result for the target planning area; projecting the comprehensive three-dimensional spatial risk assessment result of the target planning area onto a two-dimensional plane; using the DTRBA* algorithm for path planning to obtain information on all path points on the two-dimensional paths in the X and Y directions; finding the optimal height for all path points on the two-dimensional paths in the X and Y directions in the Z direction to generate a three-dimensional path; and then obtaining the complete three-dimensional spatial path of the target planning area through path smoothing processing.

[0008] Optionally, the security assessment includes: S101. Determine the value range of each indicator in the marine environmental data and vehicle data required for safety assessment. The marine environmental data required for safety assessment includes some or all of the following: ocean current velocity, density gradient intensity, vortex diameter, vortex velocity, seabed topography risk, and density gradient risk. The vehicle data required for safety assessment includes some or all of the following: vehicle diving depth, vehicle turning radius, vehicle turning time, and vehicle equipment accuracy. S102. The values ​​of each indicator in the marine environmental data and vehicle data required for safety assessment shall be normalized according to the determined value range: ; in, For the first The normalized values ​​of each indicator. The original value of the indicator. and These are the minimum and maximum values ​​of the indicator, respectively. and These are the minimum and maximum values ​​of the stable range of the indicator, respectively. S103. Calculate the membership degree of each index using the preset membership function after normalization: ; in, For the first The indicator belongs to the first Membership degree of each risk level; and The first The upper and lower bounds of the trapezoidal membership function corresponding to each risk level. For the first The standard value of the trapezoidal membership function corresponding to each risk level; S104. Based on the calculated membership degree, according to Calculate indicator weights ,in Number of risk levels; S105. Assign membership degrees and weights to each indicator. The security assessment vector is obtained by performing index fusion calculation: ; ; in, For the first The safety probability of each risk level. ; The total number of indicators. , For the first The weight of each indicator, For security assessment vectors, ~ They are respectively number 1 to The safety probability of each risk level; S106. Calculate the security risk value obtained from the security assessment according to the following formula: ; in, This represents the security risk value.

[0009] Optionally, the stealth assessment includes: S201. Obtain a sensory matrix of aircraft data constructed from the correlation between the indicators of the aircraft data required for the stealth assessment. The rows and columns of the sensory matrix of the marine environment data include the indicators of each marine environment data. The rows and columns of the sensory matrix of the aircraft data include the indicators of each aircraft data. The indicators of the marine environment data required for the stealth assessment include some or all of the following: seawater temperature, waves, rainfall, seabed topography, internal waves, sound propagation loss, marine environmental noise, and marine reverberation. The indicators of the aircraft data required for the stealth assessment include some or all of the following: aircraft diving depth, aircraft shape parameters, aircraft material reflectivity, and aircraft exposure rate. S202. Perform consistency processing using the analytic hierarchy process on the perception matrix of marine environmental data and the perception matrix of vehicle data respectively to obtain the consistency judgment matrix of marine elements and the consistency judgment matrix of vehicle elements. S203. Combining the consistency judgment matrix of marine elements and the consistency judgment matrix of aircraft elements, the weights of each indicator of marine environmental data and aircraft data are calculated using the analytic hierarchy process. S204. The marine environmental data and vehicle data required for the concealment assessment are combined with the weights of each indicator of the marine environmental data and vehicle data to obtain a membership vector through fuzzy comprehensive analysis. Based on the membership vector and the preset weight coefficients of marine elements and vehicle elements, a secondary fuzzy comprehensive index fusion calculation is performed and normalized to obtain the concealment assessment vector. The concealment risk value of the three-dimensional spatial grid points is obtained by using the maximum value method on the concealment assessment vector.

[0010] Optionally, step 204 includes: S301. Normalize the marine environmental data and vehicle data required for the stealth assessment: ; in, Let be the normalized value of the i-th indicator. The original value of the indicator. and These are the minimum and maximum values ​​of the indicator, respectively. and These are the minimum and maximum values ​​of the stable range of the indicator, respectively. S302. Calculate the membership degree of each index using a preset membership function after normalization: ; in, For the k-th element The indicator belongs to the first Membership degree of each risk level; , respectively representing marine elements and aircraft elements, corresponding to marine environmental data and aircraft data required for stealth assessment; and The first The upper and lower limits of each indicator. For the first Standard values ​​for each indicator; S303. For ocean elements and vehicle elements, calculate the membership vector using fuzzy comprehensive calculation according to the following formula: ; ; in, Let be the safety probability of the j-th risk level among the k-th elements. , Number of risk levels; The total number of indicators. , For the first The weight of the i-th indicator among the elements. Let be the membership vector of the k-th element. ~ The first The first of the following elements The safety probability of each risk level; S304. Based on the membership vector and the preset weight coefficients of marine elements and vehicle elements, a secondary fuzzy comprehensive index fusion calculation is performed and normalized to obtain the concealment evaluation vector: ; ; in, For the first The probability of concealment level for each risk level indicator. For factor weights, For the concealment assessment vector, ~ They are respectively number 1 to The probability of concealment level for each risk level indicator; S305. The concealment risk value of the three-dimensional spatial grid points is obtained by using the maximum value method on the concealment assessment vector: ; in, The hidden risk value of the three-dimensional spatial grid points. This indicates taking the maximum value of each element in the concealment evaluation vector within the grid point area.

[0011] Optionally, the step of integrating the three-dimensional spatial risk assessment results obtained from the security assessment and concealment assessment to obtain the comprehensive three-dimensional spatial risk assessment result of the target planning area includes: S401. The three-dimensional spatial risk assessment results obtained from the security assessment and the concealment assessment are weighted and fused to obtain a comprehensive assessment vector: ; in, To comprehensively evaluate the vector, and These are the weights for security assessment and stealth assessment, respectively. Let the safety assessment vector represent the three-dimensional spatial risk assessment result obtained from the safety assessment. Let be the security assessment vector representing the three-dimensional spatial risk assessment result obtained from the concealment assessment; S402. The maximum value method is used to obtain the comprehensive risk value of each grid point representing the three-dimensional spatial comprehensive risk assessment result of the target planning area for the comprehensive assessment vector: ; in, The comprehensive risk value of the grid points. This indicates taking the maximum value of each element in the comprehensive evaluation vector within the grid point region.

[0012] Optionally, the step of projecting the three-dimensional spatial comprehensive risk assessment results of the target planning area onto a two-dimensional plane and using the DTRBA* algorithm for path planning to obtain all path point information on the two-dimensional path in the X and Y directions includes: S501. The three-dimensional spatial comprehensive risk assessment results of the target planning area, which is composed of a three-dimensional comprehensive risk matrix, are linearly normalized to the interval [0,1] to obtain a new three-dimensional normalized matrix. S502. Project the three-dimensional normalized matrix onto a two-dimensional plane along the Z-axis. S503. Project the three-dimensional starting point and the three-dimensional ending point onto the two-dimensional plane to obtain the two-dimensional starting point and the two-dimensional ending point; S504. Simultaneously initiate two A* search processes from the two-dimensional starting point and the two-dimensional ending point respectively. One A* search process performs a forward search, and the other performs a backward search. The forward search uses the two-dimensional starting point as the starting node and the two-dimensional ending point as the target node, while the backward search uses the two-dimensional ending point as the starting node and the two-dimensional starting point as the target node. The A* search process uses the node cost function shown in the following formula to search for the optimal node: ; in, For grid points The node cost, and These are the weighting coefficients. The three-dimensional normalized matrix is ​​projected onto the two-dimensional plane along the Z-axis and then placed at the grid points. Comprehensive risks at the location Let s be the distance between grid point s and the target node. During the search process, any A* search process will determine in real time whether the current node has appeared in the searched node set of another A* search process. If the current node has appeared in the searched node set of another A* search process, the search of the two A* search processes will be stopped. The current node will be taken as the intersection node. Based on the intersection node, the process will backtrack to the two-dimensional starting point and the two-dimensional ending point in the forward and reverse directions respectively. The path points obtained by backtracking will be spliced ​​to obtain the complete path point information on the optimal two-dimensional path in the X and Y directions.

[0013] Optionally, when searching for the optimal height of all path points on the two-dimensional path in the X and Y directions in the Z direction to generate a three-dimensional path, the following steps are taken: for each path point on the two-dimensional path in the X and Y directions, the three-dimensional comprehensive risk value at different depths in the Z direction is obtained in the three-dimensional spatial comprehensive risk assessment result of the target planning area composed of a three-dimensional comprehensive risk matrix, and the depth with the smallest three-dimensional comprehensive risk value is selected as the optimal height of the path point on the two-dimensional path in the X and Y directions in the Z direction.

[0014] The present invention also provides a DTRBA* risk trajectory planning system for underwater vehicles, including an interconnected microprocessor and a memory, wherein the microprocessor is programmed or configured to execute the DTRBA* risk trajectory planning method for underwater vehicles.

[0015] The present invention also provides a computer-readable storage medium storing a computer program or instructions that are programmed or configured to execute the DTRBA* risk trajectory planning method for underwater vehicles via a processor.

[0016] The present invention also provides a computer program product, including a computer program or instructions that are programmed or configured to execute the DTRBA* risk trajectory planning method for underwater vehicles via a processor.

[0017] Compared with existing technologies, the present invention mainly achieves the following beneficial effects: The method of the present invention includes conducting a safety assessment and a concealment assessment of the target planning area; integrating the three-dimensional spatial risk assessment results obtained from the safety assessment and concealment assessment to obtain a comprehensive three-dimensional spatial risk assessment result of the target planning area; projecting the comprehensive three-dimensional spatial risk assessment result of the target planning area onto a two-dimensional plane; using the DTRBA* algorithm for path planning to obtain all path point information on the two-dimensional path in the X and Y directions; and finding the optimal height in the Z direction to generate a three-dimensional path. The method of the present invention obtains a complete three-dimensional spatial path of the target planning area through path smoothing processing. Based on the comprehensive navigation risk assessment of the marine environment and the vehicle's own elements, the method realizes the path planning of large underwater unmanned vehicles through the risk-integrated DTRBA* algorithm. It can plan a comprehensive path with safety, concealment, smoothness and efficiency in complex environments, thus providing a new solution for the path planning of large underwater vehicles in complex marine environments. Attached Figure Description

[0018] Figure 1 This is a schematic diagram of the basic process of the method in an embodiment of the present invention.

[0019] Figure 2 This is a schematic diagram of the security assessment process in an embodiment of the present invention.

[0020] Figure 3 This is a schematic diagram illustrating the results of a security assessment in an embodiment of the present invention.

[0021] Figure 4 This is a schematic diagram of the concealment assessment process in an embodiment of the present invention.

[0022] Figure 5 This is a schematic diagram illustrating the results of the concealment assessment in an embodiment of the present invention.

[0023] Figure 6 This is a schematic diagram of the process of three-dimensional spatial comprehensive risk assessment in an embodiment of the present invention.

[0024] Figure 7 This is a schematic diagram of the three-dimensional spatial comprehensive risk assessment results in an embodiment of the present invention.

[0025] Figure 8 This is a schematic diagram of the path planning process using the DTRBA* algorithm in an embodiment of the present invention.

[0026] Figure 9 This is a two-dimensional path obtained by using the DTRBA* algorithm for path planning in an embodiment of the present invention.

[0027] Figure 10 This is a schematic diagram of the process for generating a three-dimensional path in an embodiment of the present invention.

[0028] Figure 11 This is a schematic diagram of the path smoothing process in an embodiment of the present invention.

[0029] Figure 12 This refers to the complete three-dimensional spatial path of the target planning area obtained in this embodiment of the invention. Detailed Implementation

[0030] To enable those skilled in the art to better understand the technical solution of the present invention, the technical solution of the present invention will be further described in detail below with reference to the accompanying drawings in the embodiments of the present invention.

[0031] like Figure 1 As shown, the DTRBA* risk trajectory planning method for underwater vehicles in this embodiment includes the following steps: S1. Based on marine environmental data and vehicle data, conduct safety and concealment assessments of the target planning area, and integrate the three-dimensional spatial risk assessment results obtained from the safety and concealment assessments to obtain the comprehensive three-dimensional spatial risk assessment result of the target planning area. S2, the three-dimensional spatial comprehensive risk assessment results of the target planning area are projected onto a two-dimensional plane, and the DTRBA* algorithm is used to perform path planning to obtain all path point information on the two-dimensional path in the X and Y directions; S3 involves finding the optimal height for all path points on the two-dimensional path in the X and Y directions in the Z direction to generate a three-dimensional path. Then, path smoothing is applied to obtain the complete three-dimensional spatial path for the target planning area. This embodiment, based on a comprehensive risk assessment of the marine environment and the vehicle's own characteristics, utilizes the risk-integrated DTRBA* algorithm to achieve path planning for large underwater unmanned vehicles. It can plan comprehensive paths that combine safety, stealth, smoothness, and efficiency in complex environments, providing a new solution for path planning of large underwater vehicles in complex marine environments. It can quickly plan a sufficiently safe, stealthy, and smooth navigable path.

[0032] Safety assessments can utilize the results of existing safety assessments of the aircraft's systems, manually entered safety assessments, or other required safety assessment results, as needed. As an optional implementation method, such as... Figure 2 As shown, the security assessment in this embodiment includes: S101. Determine the value ranges of each indicator in the marine environmental data and vehicle data required for the safety assessment. The marine environmental data required for the safety assessment includes some or all of the following: ocean current velocity, density stratification intensity, vortex diameter, vortex velocity, seabed topography risk, and density gradient risk. The vehicle data required for the safety assessment includes some or all of the following: vehicle diving depth, vehicle turning radius, vehicle turning time, and vehicle equipment accuracy. In this embodiment, the value ranges of the above indicators are as follows: vehicle turning radius (3.5-6m), vehicle turning time (8-15s), vehicle equipment longitude (0.6-1), ocean current velocity (0-10 knots), density stratification intensity (0-1), vortex diameter (0-300km), vortex velocity (0-1m / s), seabed topography risk (0-1), and density gradient risk (1-6). S102. The values ​​of each indicator in the marine environmental data and vehicle data required for safety assessment shall be normalized according to the determined value range: ; in, For the first The normalized values ​​of each indicator. The original value of the indicator. and These are the minimum and maximum values ​​of the indicator, respectively. and These are the minimum and maximum values ​​of the stable range of the indicator, respectively; if the given indicator value is null (NaN), then the minimum value of the corresponding range of the indicator is used instead. S103. Calculate the membership degree of each index using the preset membership function after normalization: ; in, For the first The indicator belongs to the first Membership degree of each risk level; and The first The upper and lower bounds of the trapezoidal membership function corresponding to each risk level. For the first The standard value of the trapezoidal membership function corresponding to each risk level; in this embodiment, the over-standard weight method is used to calculate the weight vector of the indicator and normalize it to obtain the indicator weight vector. Over-standard weight is a method of characterizing the indicator value exceeding the standard value. The more dangerous the parameter, the greater the weight should be, which can be determined by the membership function. S104. Based on the calculated membership degree, according to Calculate indicator weights ,in The number of risk levels; This method transforms qualitative evaluation into quantitative evaluation based on the membership theory of fuzzy mathematics. That is, it uses fuzzy mathematics to make an overall evaluation of things or objects that are constrained by multiple factors. It has the characteristics of clear results and strong systematicity, and can better solve fuzzy and difficult-to-quantify problems. It is suitable for solving various non-deterministic problems. S105. Assign membership degrees and weights to each indicator. The security assessment vector is obtained by performing index fusion calculation: ; ; in, For the first The safety probability of each risk level. ; The total number of indicators. , For the first The weight of each indicator, For security assessment vectors, ~ They are respectively number 1 to The safety probability of each risk level; S106. Calculate the security risk value obtained from the security assessment according to the following formula: ; in, This represents the security risk value.

[0033] Figure 3 This is a schematic diagram illustrating the security assessment results in this embodiment, as shown below. Figure 3 As shown, in this embodiment, the index fusion calculation and normalization are performed by fuzzy comprehensive method to obtain the security assessment vector and calculate the expected value as the security risk value. There are 6 risk levels, ranging from 1 to 6, which are low risk, relatively low risk, medium-low risk, medium-high risk, relatively high risk and high risk, respectively. The two-dimensional area defined by longitude and latitude expresses the risk level of the security risk value at different locations in the target planning area.

[0034] The stealth assessment can utilize the stealth assessment results of existing systems within the aircraft, manually input stealth assessment results, or other required stealth assessment results, as needed. As an optional implementation method, such as... Figure 4 As shown, the concealment assessment in this embodiment includes: S201. Obtain a sensory matrix of aircraft data constructed from the correlation between the indicators of the aircraft data required for the stealth assessment. The rows and columns of the sensory matrix of the marine environment data include the indicators of each marine environment data. The rows and columns of the sensory matrix of the aircraft data include the indicators of each aircraft data. The indicators of the marine environment data required for the stealth assessment include some or all of the following: seawater temperature, waves, rainfall, seabed topography, internal waves, sound propagation loss, marine environmental noise, and marine reverberation. The indicators of the aircraft data required for the stealth assessment include some or all of the following: aircraft diving depth, aircraft shape parameters, aircraft material reflectivity, and aircraft exposure rate. S202. Perform consistency processing using the analytic hierarchy process on the perception matrix of marine environmental data and the perception matrix of vehicle data respectively to obtain the consistency judgment matrix of marine elements and the consistency judgment matrix of vehicle elements. S203. Combining the consistency judgment matrix of marine elements and the consistency judgment matrix of aircraft elements, the weights of each indicator of marine environmental data and aircraft data are calculated using the analytic hierarchy process. S204. The marine environmental data and vehicle data required for the concealment assessment are combined with the weights of each indicator of the marine environmental data and vehicle data to obtain a membership vector through fuzzy comprehensive analysis. Based on the membership vector and the preset weight coefficients of marine elements and vehicle elements, a secondary fuzzy comprehensive index fusion calculation is performed and normalized to obtain the concealment assessment vector. The concealment risk value of the three-dimensional spatial grid points is obtained by using the maximum value method on the concealment assessment vector.

[0035] In this embodiment, step 204 includes: S301. Normalize the marine environmental data and vehicle data required for the stealth assessment: ; in, Let be the normalized value of the i-th indicator. The original value of the indicator. and These are the minimum and maximum values ​​of the indicator, respectively. and These are the minimum and maximum values ​​of the stable range of the indicator, respectively. S302. Calculate the membership degree of each index using a preset membership function after normalization: ; in, For the k-th element The indicator belongs to the first Membership degree of each risk level; , respectively representing marine elements and aircraft elements, corresponding to marine environmental data and aircraft data required for stealth assessment; and The first The upper and lower limits of each indicator. For the first Standard values ​​for each indicator; S303. For ocean elements and vehicle elements, calculate the membership vector using fuzzy comprehensive calculation according to the following formula: ; ; in, Let be the safety probability of the j-th risk level among the k-th elements. , Number of risk levels; The total number of indicators. , For the first The weight of the i-th indicator among the elements. Let be the membership vector of the k-th element. ~ The first The first of the following elements The safety probability of each risk level can be set; the weights of marine elements and vehicle elements can be set to 0.5 each. S304. Based on the membership vector and the preset weight coefficients of marine elements and vehicle elements, a secondary fuzzy comprehensive index fusion calculation is performed and normalized to obtain the concealment evaluation vector: ; ; in, For the first The probability of concealment level for each risk level indicator. For factor weights, For the concealment assessment vector, ~ They are respectively number 1 to The probability of concealment level for each risk level indicator; S305. The concealment risk value of the three-dimensional spatial grid points is obtained by using the maximum value method on the concealment assessment vector: ; in, The hidden risk value of the three-dimensional spatial grid points. This indicates taking the maximum value of each element in the concealment evaluation vector within the grid point area.

[0036] In this embodiment, during the concealment assessment, the initial perception matrix is ​​obtained by expert evaluation. Then, the initial perception matrix is ​​standardized using the analytic hierarchy process (AHP). Next, combined with the consistency judgment matrix, the AHP is applied to calculate the weight vector of each indicator. The AHP refers to treating a complex multi-objective decision problem as a system, decomposing the objective into multiple objectives or criteria, and then further decomposing them into several levels of multiple indicators (or criteria, constraints). The hierarchical single ranking (weights) and overall ranking are calculated using a qualitative indicator fuzzy quantification method to achieve optimal decision-making for multiple objectives (multiple indicators) and multiple options. Figure 5 This is a schematic diagram illustrating the results of the concealment assessment in this embodiment, as shown below. Figure 5 As shown, in this embodiment, there are 6 risk levels, ranging from 1 to 6, which are also divided into low risk, relatively low risk, medium-low risk, medium-high risk, relatively high risk, and high risk. Their connotations are high concealment, relatively high concealment, medium-high concealment, medium-low concealment, relatively low concealment, and low concealment, respectively. The two-dimensional area defined by longitude and latitude expresses the risk level of concealment risk value at different locations in the target planning area.

[0037] like Figure 6 As shown, in this embodiment, the comprehensive three-dimensional spatial risk assessment results of the target planning area obtained by integrating the three-dimensional spatial risk assessment results obtained from the security assessment and the concealment assessment include: S401. The three-dimensional spatial risk assessment results obtained from the security assessment and the concealment assessment are weighted and fused to obtain a comprehensive assessment vector: ; in, To comprehensively evaluate the vector, and These are the weights for security assessment and stealth assessment, respectively. Let the safety assessment vector represent the three-dimensional spatial risk assessment result obtained from the safety assessment. Let be the security assessment vector representing the three-dimensional spatial risk assessment result obtained from the concealment assessment; S402. The maximum value method is used to obtain the comprehensive risk value of each grid point representing the three-dimensional spatial comprehensive risk assessment result of the target planning area for the comprehensive assessment vector: ; in, The comprehensive risk value of the grid points. This indicates taking the maximum value of each element in the comprehensive evaluation vector within the grid point region. Figure 7This is a schematic diagram of the three-dimensional spatial comprehensive risk assessment results in this embodiment. There are 6 risk levels, ranging from 1 to 6, which are low risk, relatively low risk, medium-low risk, medium-high risk, relatively high risk, and high risk, respectively. The two-dimensional area defined by longitude and latitude expresses the risk level of the comprehensive risk value at different locations in the target planning area.

[0038] like Figure 8 As shown, in this embodiment, the three-dimensional spatial comprehensive risk assessment results of the target planning area are projected onto a two-dimensional plane, and the DTRBA* algorithm (Dynamic Time-Varying Risk A* algorithm) is used for path planning to obtain all path point information on the two-dimensional path in the X and Y directions, including: S501. The three-dimensional spatial comprehensive risk assessment results of the target planning area, which is composed of a three-dimensional comprehensive risk matrix, are linearly normalized to the interval [0,1] to obtain a new three-dimensional normalized matrix. S502. Project the three-dimensional normalized matrix onto a two-dimensional plane along the Z-axis. S503. Project the three-dimensional starting point and the three-dimensional ending point onto the two-dimensional plane to obtain the two-dimensional starting point and the two-dimensional ending point; S504. Simultaneously initiate two A* search processes from the two-dimensional starting point and the two-dimensional ending point respectively. One A* search process performs a forward search, and the other performs a backward search. The forward search uses the two-dimensional starting point as the starting node and the two-dimensional ending point as the target node, while the backward search uses the two-dimensional ending point as the starting node and the two-dimensional starting point as the target node. The A* search process uses the node cost function shown in the following formula to search for the optimal node: ; in, For grid points The node cost, and These are the weighting coefficients. The three-dimensional normalized matrix is ​​projected onto the two-dimensional plane along the Z-axis and then placed at the grid points. Comprehensive risks at the location In this embodiment, the risk cost weight is set to represent the distance between grid point s and the target node. And distance weights: ; During the search process, any A* search process continuously checks whether the current node has already appeared in the searched node set of another A* search process. If the current node has appeared in the searched node set of another A* search process, both A* search processes stop searching. The current node is taken as the intersection node, and backtracking is performed in both the forward and reverse directions from the intersection node to the two-dimensional starting point and the two-dimensional ending point, respectively. The backtracked path points are then concatenated to obtain the complete path point information of the optimal two-dimensional path in the X and Y directions. When a node extending in any direction appears in the visited set on the opposite side or is less than or equal to 2 grids away from the node on the opposite side, the search immediately stops, and the forward and reverse paths are concatenated using the intersection point as the connection point to obtain the optimal two-dimensional path Path_2D on the grid. Figure 9 This is the two-dimensional path obtained by path planning using the DTRBA* algorithm in this embodiment. The points on this two-dimensional path are the path points on the two-dimensional path in the X and Y directions. In this embodiment, the code execution time is 7.26 seconds, and the total length of the two-dimensional path in the X and Y directions is 150.58 kilometers.

[0039] In this embodiment, when finding the optimal height in the Z direction for all path points on the two-dimensional path in the X and Y directions to generate a three-dimensional path, it includes, for each path point on the two-dimensional path in the X and Y directions, obtaining its three-dimensional comprehensive risk value at different depths in the Z direction from the three-dimensional spatial comprehensive risk assessment results of the target planning area composed of a three-dimensional comprehensive risk matrix, and selecting the depth with the smallest three-dimensional comprehensive risk value as the optimal height of the path point on the two-dimensional path in the X and Y directions in the Z direction. Figure 10 As shown, the path for generating the 3D model includes: S601. Iterate through each two-dimensional grid point in the two-dimensional path in turn; S602. Enumerate all depth layers of this grid point; S603. Calculate the comprehensive cost for each candidate 3D point. ; S604. Additional constraints (optional); S605. Select the 3D point with the lowest overall cost that satisfies the constraints and add it to the 3D path. S606. In real time, determine whether the current node is the end point of the path. If it is, force the depth to the preset end point depth and output the 3D path. Otherwise, continue traversing. S607. Perform uniqueness deduplication on the 3D path and apply it according to the comprehensive cost. Sort; S608. Use cubic B-spline sampling to smooth the path and obtain a smooth 3D path; S609. Replace the start and end points of the smooth 3D path with the actual departure depth and target depth; S610. Calculate the arrival time based on the three-dimensional true distance of each path segment and the given speed, and generate a sequence of completed waypoints with timestamps. S611, Output two-dimensional route chart (two-dimensional path) and three-dimensional route chart (three-dimensional path), total cost (comprehensive cost) Indicators such as total voyage distance and planned travel time.

[0040] like Figure 11 The diagram shows a flowchart of path smoothing using B-spline sampling. In this embodiment, a cubic B-spline curve (order k=3, smoothing factor s=3.0) is used for interpolation smoothing. 300-500 interpolation points are uniformly generated within the parameter range [0,1] to obtain the smoothed 3D path Smooth_3D, and the depths of the first and last points are forced to be the actual departure depth and the target depth, respectively. Finally, based on the Havesing formula and depth difference, the true 3D distance of each segment is calculated. Combined with the given speed (knots), the cumulative arrival time of each waypoint in Smooth_3D is marked, generating a complete concealed route with timestamps. Simultaneously, a 2D risk distribution map and a 3D route stereoscopic map (such as...) are output. Figure 12 (As shown), indicators such as total weighted cost, total voyage distance, and planning time.

[0041] In summary, this embodiment of the DTRBA* risk trajectory planning method for underwater vehicles first aims to improve the navigation safety of large underwater unmanned vehicles by proposing a strategy to obtain regional risk values ​​through a three-layer risk assessment using both oceanic and vehicle-specific factors. Secondly, to improve path search efficiency, it proposes a path planning strategy that first uses a bidirectional A* strategy with improved risk costs in a two-dimensional plane for path search, and then transforms the two-dimensional path into a smooth three-dimensional path through conditional constraints and B-spline smoothing. This approach can plan comprehensive paths that combine safety, stealth, smoothness, and efficiency in complex environments, providing a new solution for path planning of large underwater vehicles in complex marine environments.

[0042] Those skilled in the art will understand that the technical solutions provided by this invention can take the form of a method, a system, or a computer program product. Therefore, this invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. For example, this invention can provide a DTRBA* risk trajectory planning system for underwater vehicles, including an interconnected microprocessor and a memory, the microprocessor being programmed or configured to execute the DTRBA* risk trajectory planning method for underwater vehicles. This invention can provide a computer-readable storage medium storing a computer program or instructions programmed or configured to execute the DTRBA* risk trajectory planning method for underwater vehicles via a processor. This invention can provide a computer program product including a computer program or instructions programmed or configured to execute the DTRBA* risk trajectory planning method for underwater vehicles via a processor. Furthermore, this invention can take the form of a computer program product implemented on one or more computer-readable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code. This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 The computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to operate in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The functions specified in one or more boxes. These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable apparatus for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0043] The above description is merely a preferred embodiment of the present invention. The scope of protection of the present invention is not limited to the above embodiments. All technical solutions falling within the scope of the present invention's concept are within the scope of protection of the present invention. It should be noted that for those skilled in the art, any improvements and modifications made without departing from the principles of the present invention should also be considered within the scope of protection of the present invention.

Claims

1. A DTRBA* risk trajectory planning method for underwater vehicles, characterized in that, The process includes the following steps: conducting a safety assessment and a concealment assessment of the target planning area based on marine environmental data and vehicle data; and integrating the three-dimensional spatial risk assessment results obtained from the safety assessment and concealment assessment to obtain a comprehensive three-dimensional spatial risk assessment result for the target planning area. The three-dimensional spatial comprehensive risk assessment results of the target planning area are projected onto a two-dimensional plane. The DTRBA* algorithm is used for path planning to obtain all path point information on the two-dimensional path in the X and Y directions. The optimal height of all path points on the two-dimensional path in the X and Y directions is found in the Z direction to generate a three-dimensional path. Finally, the complete three-dimensional spatial path of the target planning area is obtained through path smoothing.

2. The DTRBA* risk trajectory planning method for underwater vehicles according to claim 1, characterized in that, The security assessment includes: S101. Determine the value range of each indicator in the marine environmental data and vehicle data required for safety assessment. The marine environmental data required for safety assessment includes some or all of the following: ocean current velocity, density gradient intensity, vortex diameter, vortex velocity, seabed topography risk, and density gradient risk. The vehicle data required for safety assessment includes some or all of the following: vehicle diving depth, vehicle turning radius, vehicle turning time, and vehicle equipment accuracy. S102. The values ​​of each indicator in the marine environmental data and vehicle data required for safety assessment shall be normalized according to the determined value range: ； in, For the first The normalized values ​​of each indicator. The original value of the indicator. and These are the minimum and maximum values ​​of the indicator, respectively. and These are the minimum and maximum values ​​of the stable range of the indicator, respectively. S103. Calculate the membership degree of each index using the preset membership function after normalization: ； in, For the first The indicator belongs to the first Membership degree of each risk level; and The first The upper and lower bounds of the trapezoidal membership function corresponding to each risk level. For the first The standard value of the trapezoidal membership function corresponding to each risk level; S104. Based on the calculated membership degree, according to Calculate indicator weights ,in Number of risk levels; S105. Assign membership degrees and weights to each indicator. The security assessment vector is obtained by performing index fusion calculation: ； ； in, For the first The safety probability of each risk level. ; The total number of indicators. , For the first The weight of each indicator, For security assessment vectors, ~ They are respectively number 1 to The safety probability of each risk level; S106. Calculate the security risk value obtained from the security assessment according to the following formula: ； in, This represents the security risk value.

3. The DTRBA* risk trajectory planning method for underwater vehicles according to claim 1, characterized in that, The covertness assessment includes: S201. Obtain a sensory matrix of aircraft data constructed from the correlation between the indicators of the aircraft data required for the stealth assessment. The rows and columns of the sensory matrix of the marine environment data include the indicators of each marine environment data. The rows and columns of the sensory matrix of the aircraft data include the indicators of each aircraft data. The indicators of the marine environment data required for the stealth assessment include some or all of the following: seawater temperature, waves, rainfall, seabed topography, internal waves, sound propagation loss, marine environmental noise, and marine reverberation. The indicators of the aircraft data required for the stealth assessment include some or all of the following: aircraft diving depth, aircraft shape parameters, aircraft material reflectivity, and aircraft exposure rate. S202. Perform consistency processing using the analytic hierarchy process on the perception matrix of marine environmental data and the perception matrix of vehicle data respectively to obtain the consistency judgment matrix of marine elements and the consistency judgment matrix of vehicle elements. S203. Combining the consistency judgment matrix of marine elements and the consistency judgment matrix of aircraft elements, the weights of each indicator of marine environmental data and aircraft data are calculated using the analytic hierarchy process. S204. The marine environmental data and vehicle data required for the concealment assessment are combined with the weights of each indicator of the marine environmental data and vehicle data to obtain a membership vector through fuzzy comprehensive analysis. Based on the membership vector and the preset weight coefficients of marine elements and vehicle elements, a secondary fuzzy comprehensive index fusion calculation is performed and normalized to obtain the concealment assessment vector. The concealment risk value of the three-dimensional spatial grid points is obtained by using the maximum value method on the concealment assessment vector.

4. The DTRBA* risk trajectory planning method for underwater vehicles according to claim 3, characterized in that, Step 204 includes: S301. Normalize the marine environmental data and vehicle data required for the stealth assessment: ； in, Let be the normalized value of the i-th indicator. The original value of the indicator. and These are the minimum and maximum values ​​of the indicator, respectively. and These are the minimum and maximum values ​​of the stable range of the indicator, respectively. S302. Calculate the membership degree of each index using a preset membership function after normalization: ； in, For the k-th element The indicator belongs to the first Membership degree of each risk level; , respectively representing marine elements and aircraft elements, corresponding to marine environmental data and aircraft data required for stealth assessment; and The first The upper and lower limits of each indicator. For the first Standard values ​​for each indicator; S303. For ocean elements and vehicle elements, calculate the membership vector using fuzzy comprehensive calculation according to the following formula: ； ； in, Let be the safety probability of the j-th risk level among the k-th elements. , Number of risk levels; The total number of indicators. , For the first The weight of the i-th indicator among the elements. Let be the membership vector of the k-th element. ~ The first The first of the following elements The safety probability of each risk level; S304. Based on the membership vector and the preset weight coefficients of marine elements and vehicle elements, a secondary fuzzy comprehensive index fusion calculation is performed and normalized to obtain the concealment evaluation vector: ； ； in, For the first The probability of concealment level for each risk level indicator. For factor weights, For the concealment assessment vector, ~ They are respectively number 1 to The probability of concealment level for each risk level indicator; S305. The concealment risk value of the three-dimensional spatial grid points is obtained by using the maximum value method on the concealment assessment vector: ； in, The hidden risk value of the three-dimensional spatial grid points. This indicates taking the maximum value of each element in the concealment evaluation vector within the grid point area.

5. The DTRBA* risk trajectory planning method for underwater vehicles according to claim 1, characterized in that, The method of integrating the three-dimensional spatial risk assessment results obtained from the security assessment and concealment assessment to obtain the comprehensive three-dimensional spatial risk assessment result of the target planning area includes: S401. The three-dimensional spatial risk assessment results obtained from the security assessment and the concealment assessment are weighted and fused to obtain a comprehensive assessment vector: ； in, To comprehensively evaluate the vector, and These are the weights for security assessment and stealth assessment, respectively. Let the safety assessment vector represent the three-dimensional spatial risk assessment result obtained from the safety assessment. Let be the security assessment vector representing the three-dimensional spatial risk assessment result obtained from the concealment assessment; S402. The maximum value method is used to obtain the comprehensive risk value of each grid point representing the three-dimensional spatial comprehensive risk assessment result of the target planning area for the comprehensive assessment vector: ； in, The comprehensive risk value of the grid points. This indicates taking the maximum value of each element in the comprehensive evaluation vector within the grid point region.

6. The DTRBA* risk trajectory planning method for underwater vehicles according to claim 1, characterized in that, The process of projecting the three-dimensional spatial comprehensive risk assessment results of the target planning area onto a two-dimensional plane and using the DTRBA* algorithm for path planning to obtain all path point information on the two-dimensional path in the X and Y directions includes: S501. The three-dimensional spatial comprehensive risk assessment results of the target planning area, which is composed of a three-dimensional comprehensive risk matrix, are linearly normalized to the interval [0,1] to obtain a new three-dimensional normalized matrix. S502. Project the three-dimensional normalized matrix onto a two-dimensional plane along the Z-axis. S503. Project the three-dimensional starting point and the three-dimensional ending point onto the two-dimensional plane to obtain the two-dimensional starting point and the two-dimensional ending point; S504. Simultaneously initiate two A* search processes from the two-dimensional starting point and the two-dimensional ending point respectively. One A* search process performs a forward search, and the other performs a backward search. The forward search uses the two-dimensional starting point as the starting node and the two-dimensional ending point as the target node, while the backward search uses the two-dimensional ending point as the starting node and the two-dimensional starting point as the target node. The A* search process uses the node cost function shown in the following formula to search for the optimal node: ； in, For grid points The node cost, and These are the weighting coefficients. The three-dimensional normalized matrix is ​​projected onto the two-dimensional plane along the Z-axis and then placed at the grid points. Comprehensive risks at the location Let s be the distance between grid point s and the target node. During the search process, any A* search process will determine in real time whether the current node has appeared in the searched node set of another A* search process. If the current node has appeared in the searched node set of another A* search process, the search of the two A* search processes will be stopped. The current node will be taken as the intersection node. Based on the intersection node, the process will backtrack to the two-dimensional starting point and the two-dimensional ending point in the forward and reverse directions respectively. The path points obtained by backtracking will be spliced ​​to obtain the complete path point information on the optimal two-dimensional path in the X and Y directions.

7. The DTRBA* risk trajectory planning method for underwater vehicles according to claim 1, characterized in that, When searching for the optimal height of all path points on the two-dimensional paths in the X and Y directions in the Z direction to generate a three-dimensional path, the method includes, for each path point on the two-dimensional paths in the X and Y directions, obtaining the three-dimensional comprehensive risk value of each path point at different depths in the Z direction in the three-dimensional spatial comprehensive risk assessment results of the target planning area composed of a three-dimensional comprehensive risk matrix, and selecting the depth with the smallest three-dimensional comprehensive risk value as the optimal height of the path point on the two-dimensional paths in the X and Y directions in the Z direction.

8. A DTRBA* risk trajectory planning system for underwater vehicles, comprising interconnected microprocessors and memory, characterized in that, The microprocessor is programmed or configured to execute the DTRBA* risk trajectory planning method for underwater vehicles as described in any one of claims 1 to 7.

9. A computer-readable storage medium storing a computer program or instructions, characterized in that, The computer program or instructions are programmed or configured to execute the DTRBA* risk trajectory planning method for underwater vehicles as described in any one of claims 1 to 7 via a processor.

10. A computer program product, comprising a computer program or instructions, characterized in that, The computer program or instructions are programmed or configured to execute the DTRBA* risk trajectory planning method for underwater vehicles as described in any one of claims 1 to 7 via a processor.

Images