Method, system, equipment and medium for three-dimensional route planning in restricted waters

Abstract

The present invention relates to the field of underwater route planning and provides a method, system, device, and medium for three-dimensional route planning in restricted waters. The method comprises obtaining an underwater topographic map of a target water area and determining path endpoints; determining the size of the water area, obtaining an elliptical transformation matrix based on the water area size, and determining a conversion matrix; determining a stretching coefficient, calculating the stretching height using the stretching coefficient, thereby determining a random point; and performing an elliptical transformation on the random point using the elliptical transformation matrix and the conversion matrix to obtain a transformed random point; generating an offset optimized cylinder based on the cylinder radius; changing the cylinder radius and updating the offset optimized cylinder when an obstacle exists; determining a growth direction in the offset optimized cylinder based on the path endpoints, and generating an initial path using a path generation algorithm; and constraining the initial path based on a top safety limit constraint, an obstacle safety constraint, and a vehicle angle constraint to obtain a target path for the underwater vehicle. The method can quickly obtain a relatively smooth target path.

Description

Technical Field

[0001] The present invention relates to the technical field of underwater route planning, and in particular to a method, system, equipment and medium for three-dimensional route planning in confined waters. Background Art

[0002] Polar scientific expeditions are of great significance for global climate change research, maintaining polar ecological integrity, and exploring the origins of life. Underwater platforms have played an increasingly important role in polar expeditions in recent years, particularly in subglacial topography surveys, ice sheet monitoring, ecosystem investigations, and climate change research. However, recent incidents of underwater platforms being lost, trapped, or damaged by collisions during polar expeditions have occurred frequently, resulting in significant losses. One contributing factor to these incidents is the lack of real-time performance of underwater 3D path planning algorithms for underwater platforms. Unlike in open waters, underwater platforms operating in top-constrained waters are subject to strong nonlinear hydrodynamic forces and environmental uncertainty, resulting in relatively short obstacle avoidance response times. This places higher demands on the real-time performance of underwater platform path planning. Furthermore, the significantly non-uniform 3D spatial distribution of top-constrained environments reduces the computational efficiency and path quality of path planning algorithms, placing higher demands on the design of the path planning space for underwater platforms in top-constrained environments. Publicly available research on 3D path planning in top-constrained waters is relatively limited, and research on real-time 3D path planning for underwater platforms in top-constrained waters is urgently needed. Summary of the Invention

[0003] The present invention aims to solve at least one of the technical problems existing in the related art. To this end, the present invention provides a method, system, device and medium for three-dimensional route planning in restricted waters, which can achieve more reasonable planning of underwater routes under the condition of restricted top height.

[0004] The present invention provides a three-dimensional route planning method in confined waters, comprising:

[0005] S1: Determine the target water area, obtain the underwater topographic map of the target water area, and determine the path endpoint in the target water area;

[0006] S2: Determine the water area size in the underwater topographic map, obtain the ellipse transformation matrix based on the water area size, and determine the conversion matrix;

[0007] S3: Determine the stretching coefficient, calculate the stretching height by the stretching coefficient and the path endpoint, determine the random point according to the stretching height, and perform elliptical transformation on the random point by using the elliptical transformation matrix and the conversion matrix to obtain the transformed random point;

[0008] S4: Selecting a path generation algorithm and a cylinder radius, generating a biased optimization cylinder based on the cylinder radius, and determining whether there is an obstacle in the biased optimization cylinder. If there is an obstacle, changing the cylinder radius and updating the biased optimization cylinder until there is no obstacle in the biased optimization cylinder. Determining a growth direction based on the path endpoints in the biased optimization cylinder allows the path generation algorithm to obtain an initial path based on the transformed random points and the growth direction.

[0009] S5: Obtain the top environment model through machine learning and perform top safety limit constraints, obtain obstacle safety constraints through the underwater terrain map, obtain random tree node coordinates, obtain the vehicle angle constraints through the random tree node coordinates, constrain the initial path according to the top safety limit constraints, obstacle safety constraints and vehicle angle constraints, and obtain the target path for the underwater vehicle.

[0010] According to the method for three-dimensional route planning in restricted waters provided by the present invention, step S1 specifically includes:

[0011] S11: Determine a target water area, perform a topographic survey on the target water area, and obtain an underwater topographic map of the target water area;

[0012] S12: Determine the end point and the starting point of the path of the underwater vehicle in the underwater topographic map, and use the end point and the starting point of the path as the path endpoints.

[0013] According to the method for three-dimensional route planning in restricted waters provided by the present invention, step S2 specifically includes:

[0014] S21: determining the size of a water area including the length and width of the water area in the underwater topographic map, calculating the ellipse focus and the ellipse major axis length according to the water area size, and obtaining the ellipse transformation matrix through the ellipse focus and the ellipse major axis length;

[0015] S22: Determine the path endpoint vector according to the path endpoint, determine the endpoint vector angle through the path endpoint vector, and construct the transformation matrix using the endpoint vector angle.

[0016] According to the method for three-dimensional route planning in restricted waters provided by the present invention, step S3 specifically includes:

[0017] S31: determining a stretching coefficient, wherein the stretching coefficient is 1.2 to 1.5, calculating an endpoint height difference between the path endpoints, and calculating an initial stretching height using the stretching coefficient and the endpoint height difference;

[0018] S32: obtaining a safety distance from the initial stretching height, adjusting the initial stretching height according to the safety distance to obtain a stretching height, and determining a stretching ellipse according to the stretching height;

[0019] S33: Select a random point according to the stretching height, and determine the random point plane coordinates of the random point, perform elliptical transformation on the random point plane coordinates through the elliptical transformation matrix and the conversion matrix to obtain the random point transformation coordinates, and obtain the transformed random point located in the stretched ellipse according to the random point transformation coordinates.

[0020] According to the three-dimensional route planning method for confined waters provided by the present invention, in step S4, when an obstacle exists, the cylinder radius is reduced and a new biased optimization cylinder is generated based on the reduced cylinder radius until no obstacle exists in the biased optimization cylinder, and the update of the biased optimization cylinder is completed. The direction from the path starting point to the path end point in the biased optimization cylinder is used as the growth direction. The path generation algorithm obtains the initial path by transforming the random points and performing random tree growth according to the growth direction.

[0021] According to the three-dimensional route planning method for confined waters provided by the present invention, in step S5, top environment data is obtained and the top environment data is cleaned, preprocessed and interpolated to obtain top environment input data, machine learning is performed on the top environment input data to obtain the top environment model, and the top safety limit constraint is performed through the top environment model.

[0022] According to the three-dimensional route planning method for confined waters provided by the present invention, in step S5, random tree node coordinates including the three-dimensional coordinates of the node and the three-dimensional coordinates of the adjacent nodes are obtained, and the vehicle angle constraints including the pitch angle constraint and the turning angle constraint are obtained through the random tree node coordinates.

[0023] The present invention also provides a three-dimensional route planning system for confined waters, comprising:

[0024] Underwater topographic map module: used to determine the target water area, obtain the underwater topographic map of the target water area, and determine the path endpoint in the target water area;

[0025] Conversion matrix module: used to determine the water area size in the underwater topographic map, obtain the ellipse transformation matrix based on the water area size, and determine the conversion matrix;

[0026] Ellipse transformation module: used to determine the stretching coefficient, calculate the stretching height through the stretching coefficient and the path endpoint, determine the random point according to the stretching height, and perform ellipse transformation on the random point through the ellipse transformation matrix and the conversion matrix to obtain the transformed random point;

[0027] Initial path module: used to select the path generation algorithm and cylinder radius, generate the biased optimization cylinder according to the cylinder radius, and determine whether there are obstacles in the biased optimization cylinder. If there are obstacles, the cylinder radius is changed and the biased optimization cylinder is updated until there are no obstacles in the biased optimization cylinder. The growth direction is determined according to the path endpoint in the biased optimization cylinder, so that the path generation algorithm obtains the initial path according to the transformed random points and growth direction.

[0028] Target path module: used to obtain the top environment model through machine learning and perform top safety limit constraints, obtain obstacle safety constraints through underwater terrain maps, obtain random tree node coordinates, obtain vehicle angle constraints through random tree node coordinates, constrain the initial path according to the top safety limit constraints, obstacle safety constraints and vehicle angle constraints, and obtain the target path for underwater vehicle navigation.

[0029] The present invention also provides an electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, the steps of any of the above-described methods for three-dimensional route planning in restricted waters are implemented.

[0030] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of any of the above-mentioned methods for three-dimensional route planning in restricted waters.

[0031] The above one or more technical solutions in the embodiments of the present invention have at least one of the following technical effects:

[0032] The present invention provides a three-dimensional route planning method, system, device and medium for confined waters. By calculating the stretching height and performing an elliptical transformation, the distribution of random points in a top-constrained underwater environment is made more consistent with the direction of the line connecting the path endpoints, thereby improving the efficiency of subsequent path planning. The use of a biased optimization cylinder makes the growth direction of the path generation algorithm more consistent with the direction of the line connecting the path endpoints, and further obtains a top environment model to constrain the initial path, so that the method can adapt to the underwater vehicle route planning task in a top-constrained underwater environment and generate a suitable target path for it more efficiently.

[0033] Additional aspects and advantages of the present invention will be set forth in part in the description which follows and, in part, will be obvious from the description which follows, or may be learned by practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0035] Figure 1 It is a flow chart of the three-dimensional route planning method for restricted waters provided by the present invention.

[0036] Figure 2 It is a schematic diagram of the elliptical area and stretching height of the three-dimensional route planning method for restricted waters provided by the present invention.

[0037] FIG3( a ) is a schematic diagram of the longitudinal inclination angle of the three-dimensional route planning method for confined waters provided by the present invention.

[0038] FIG3( b ) is a schematic diagram of the turning angle of the three-dimensional route planning method for confined waters provided by the present invention.

[0039] Figure 4 It is a schematic diagram of the target path of the three-dimensional route planning method for confined waters provided by the present invention.

[0040] Figure 5 It is a structural schematic diagram of the confined waters three-dimensional route planning system provided by the present invention.

[0041] Figure 6 It is a structural schematic diagram of the three-dimensional route planning device for confined waters provided by the present invention.

[0042] Reference numerals:

[0043] 100, underwater topographic map module; 200, conversion matrix module; 300, ellipse transformation module; 400, initial path module; 500, target path module; 810, processor; 820, communication interface; 830, memory; 840, communication bus. DETAILED DESCRIPTION

[0044] To make the purpose, technical solutions and advantages of the present invention clearer, the technical solutions of the present invention will be described clearly and completely below. Obviously, the embodiments described are part of the embodiments of the present invention, not all of them. 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. The following embodiments are used to illustrate the present invention, but are not used to limit the scope of the present invention.

[0045] In the description of the embodiments of the present invention, it should be noted that the terms “first”, “second” and “third” are used for descriptive purposes only and should not be understood as indicating or implying relative importance.

[0046] In the description of this specification, the reference terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" mean that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the embodiment of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art can combine and combine different embodiments or examples described in this specification and features of different embodiments or examples without contradiction.

[0047] The following combination Figures 1 to 6 Describe the specific embodiment of the present invention:

[0048] Figure 1 It is a flow chart of the three-dimensional route planning method for restricted waters provided by the present invention.

[0049] First, the target water area is determined, the underwater topographic map of the target water area is obtained, and the path endpoints are determined in the target water area; then the water area size is determined in the underwater topographic map, and the elliptical transformation matrix is ​​obtained according to the water area size, and the conversion matrix is ​​determined; then the stretching height is calculated by the stretching coefficient, and the random points are determined according to the stretching height and elliptical transformation is performed to obtain the transformed random points; then the growth direction is determined according to the path endpoints in the paranoid optimization cylinder, and the path generation algorithm obtains the initial path according to the growth direction; finally, the initial path is constrained according to the top safety constraint, obstacle safety constraint and vehicle angle constraint to obtain the target path.

[0050] The present invention provides a three-dimensional route planning method in confined waters, comprising:

[0051] S1: Determine the target water area, obtain the underwater topographic map of the target water area, and determine the path endpoint in the target water area;

[0052] Furthermore, the purpose of this stage is to obtain an underwater topographic map of the target water area, thereby determining the path endpoints therein. Specifically, step S1 includes:

[0053] S11: Determine a target water area, perform a topographic survey on the target water area, and obtain an underwater topographic map of the target water area;

[0054] S12: Determine the end point and the starting point of the path of the underwater vehicle in the underwater topographic map, and use the end point and the starting point of the path as the path endpoints.

[0055] With respect to the above steps, the specific implementation plan in this embodiment is as follows:

[0056] First, the target waters—the area where the underwater vehicle will operate—are identified. Then, sonar is used to survey the ocean topography of the target waters, generating an underwater topographic map that reflects the distribution of the underwater topography and landforms in the target area. Here, the target waters are areas with limited overhead space, such as beneath the ice caps in polar oceans. The end and starting points of the underwater vehicle's path are then determined within the underwater topographic map based on the vehicle's location and the purpose of the survey. These two paths are then used as the path endpoints.

[0057] S2: Determine the water area size in the underwater topographic map, obtain the ellipse transformation matrix based on the water area size, and determine the conversion matrix;

[0058] Furthermore, the purpose of this stage is to determine the size of the water area, thereby obtaining the elliptical transformation matrix and determining the conversion matrix. Specifically, step S2 includes:

[0059] S21: determining the size of a water area including the length and width of the water area in the underwater topographic map, calculating the ellipse focus and the ellipse major axis length according to the water area size, and obtaining the ellipse transformation matrix through the ellipse focus and the ellipse major axis length;

[0060] S22: Determine the path endpoint vector according to the path endpoint, determine the endpoint vector angle through the path endpoint vector, and construct the transformation matrix using the endpoint vector angle.

[0061] Regarding the above steps, the specific implementation methods in this embodiment are as follows:

[0062] First, you need to determine the length of the water area in the underwater topography map a The water area size and water area width b, then the ellipse focus can be calculated based on the water area size and the length of the major axis of the ellipse :

[0063]

[0064]

[0065] in, is the first adjustment coefficient determined based on experience, is the second adjustment coefficient determined based on experience. Then the ellipse transformation matrix L can be obtained through the ellipse focus and the ellipse major axis length:

[0066]

[0067] Wherein, diag{} represents the diagonal matrix of the contents within the brackets.

[0068] Then, the path endpoint vector is determined based on the path endpoint. Here, the endpoint vector is the vector pointing from the path starting point to the path end point. The endpoint vector angle θ is determined by the path endpoint vector. Here, the endpoint vector angle is the angle between the endpoint vector and the length of the water area in the horizontal direction. Then, the transformation matrix C can be constructed:

[0069]

[0070] S3: Determine the stretching coefficient, calculate the stretching height by the stretching coefficient and the path endpoint, determine the random point according to the stretching height, and perform elliptical transformation on the random point by using the elliptical transformation matrix and the conversion matrix to obtain the transformed random point;

[0071] Furthermore, the purpose of this stage is to determine the stretching coefficient and calculate the stretching height, thereby determining the random point and performing elliptical transformation on the random point through the elliptical transformation matrix and the conversion matrix to obtain the transformed random point. Specifically, step S3 specifically includes:

[0072] S31: determining a stretching coefficient, wherein the stretching coefficient is 1.2 to 1.5, calculating an endpoint height difference between the path endpoints, and calculating an initial stretching height using the stretching coefficient and the endpoint height difference;

[0073] S32: obtaining a safety distance from the initial stretching height, adjusting the initial stretching height according to the safety distance to obtain a stretching height, and determining a stretching ellipse according to the stretching height;

[0074] S33: Select a random point according to the stretching height, and determine the random point plane coordinates of the random point, perform elliptical transformation on the random point plane coordinates through the elliptical transformation matrix and the conversion matrix to obtain the random point transformation coordinates, and obtain the transformed random point located in the stretched ellipse according to the random point transformation coordinates.

[0075] Regarding the above steps, the specific implementation methods in this embodiment are as follows:

[0076] First, the stretch factor needs to be determined based on experience , which ranges from 1.2 to 1.5, and then calculates the endpoint height difference between the height of the path starting point and the height of the path end point to calculate the initial stretch height :

[0077]

[0078] in, is the height of the starting point of the path, is the height of the end point of the path. Then let half of the initial stretch height be located at the center of the line between the start point and the end point of the path, and the height of the top of the initial stretch height can be used as the top height and obtain the lowest height of the obstacle at the top of the water area from the underwater terrain map as the obstacle height , calculate the difference between the two to get the safe distance :

[0079]

[0080] Then adjust the initial stretch height according to the safety distance. That is, when the safety distance is greater than 0, the safety distance needs to be subtracted from the initial stretch height to obtain the stretch height. , this can avoid the stretching height being above the obstacle at the top of the water area, otherwise the initial stretching height will be used directly as the stretching height. Then the stretching ellipse is determined based on the stretching height. The projection of the stretching ellipse on the horizontal plane is an ellipse, and the center of the ellipse is located at the center of the line between the starting point and the end point of the path. Its focus and major axis length are the previously calculated ellipse focus and major axis length respectively, and the height is the ellipse area of ​​the stretching height. The ellipse area also needs to ensure that the height of half the stretching height is the same as the height of the center of the line between the starting point and the end point of the path. The ellipse area and the stretching height are as follows: Figure 2 shown.

[0081] In general In the algorithm, the range of random points is generally a circular area with the center of the line between the path start point and the path end point as the center and a diameter larger than the line between the path start point and the path end point. Therefore, random points are first taken in the circular area, and the height of the random points is within the stretching height. Then, the coordinates of the projections of these random points on the plane are used as the plane coordinates of the random points. , and perform elliptical transformation on the plane coordinates of the random point through the elliptical transformation matrix and the conversion matrix, so that the plane coordinates of the random point are within the horizontal projection of the elliptical area:

[0082]

[0083]

[0084] in, is the horizontal projection coordinate of the starting point of the path, is the horizontal projection coordinate of the end point of the path, is the horizontal projection coordinate of the transformed random point, The ellipse center coordinates are kept constant during ellipse transformation. Combining the height coordinates with the horizontal projection coordinates of the transformed random point yields the transformed coordinates. The transformed random point is then located within the stretched ellipse, ensuring that the random point's growth direction is more focused when the algorithm obtains the initial path. This allows for faster initial path generation and reduces computational latency.

[0085] S4: Selecting a path generation algorithm and a cylinder radius, generating a biased optimization cylinder based on the cylinder radius, and determining whether there is an obstacle in the biased optimization cylinder. If there is an obstacle, changing the cylinder radius and updating the biased optimization cylinder until there is no obstacle in the biased optimization cylinder. Determining a growth direction based on the path endpoints in the biased optimization cylinder allows the path generation algorithm to obtain an initial path based on the transformed random points and the growth direction.

[0086] Furthermore, the purpose of this stage is to generate an offset optimization cylinder based on the cylinder radius and update the offset optimization cylinder, thereby determining the growth direction based on the path endpoint and obtaining the initial path. Specifically, in step S4, when an obstacle exists, the cylinder radius is reduced and a new offset optimization cylinder is generated based on the reduced cylinder radius. This is done until the offset optimization cylinder is free of obstacles. The offset optimization cylinder is then updated and the direction from the path starting point to the path endpoint in the offset optimization cylinder is used as the growth direction. The path generation algorithm transforms the random points and performs random tree growth based on the growth direction to obtain the initial path.

[0087] Regarding the above steps, the specific implementation methods in this embodiment are as follows:

[0088] First, select the path generation algorithm. Here, the path generation algorithm is selected In addition, the cylinder radius R is selected based on experience. With the path starting point as the center, the cylinder radius as the radius, and the height as the stretch height, an offset optimization cylinder is generated and a check is performed to determine whether there is an obstacle within the offset optimization cylinder. If an obstacle is present, the cylinder radius is reduced and a new offset optimization cylinder is generated based on the reduced cylinder radius, keeping other parameters unchanged. This process is repeated until no obstacle is found within the offset optimization cylinder, completing the update of the offset optimization cylinder.

[0089] In the bias optimization cylinder, the direction from the path starting point to the path end point is used as the growth direction, and the path generation algorithm uses the transformed random points to perform random tree growth along the growth direction until the path end point is reached, thereby obtaining the initial path.

[0090] S5: Obtain the top environment model through machine learning and perform top safety limit constraints, obtain obstacle safety constraints through the underwater terrain map, obtain random tree node coordinates, obtain the vehicle angle constraints through the random tree node coordinates, constrain the initial path according to the top safety limit constraints, obstacle safety constraints and vehicle angle constraints, and obtain the target path for the underwater vehicle.

[0091] Furthermore, the purpose of this stage is to obtain top safety limit constraints, obstacle safety constraints, and aircraft angle constraints, thereby constraining the initial path and obtaining the target path. Specifically, in step S5, top environment data is acquired and cleaned, preprocessed, and interpolated to obtain top environment input data. Machine learning is performed on this top environment input data to obtain the top environment model, and the top safety limit constraints are applied using the top environment model.

[0092] In step S5, random tree node coordinates including the node three-dimensional coordinates and the adjacent node three-dimensional coordinates are obtained, and the aircraft angle constraints including the pitch angle constraint and the roll angle constraint are obtained through the random tree node coordinates.

[0093] Regarding the above steps, the specific implementation methods in this embodiment are as follows:

[0094] First, it is necessary to obtain the top environment data of the top obstacles from the underwater topographic map, that is, various data related to the top obstacles, and clean, preprocess and interpolate the top environment data to remove unreasonable and incomplete data and complete the data to obtain the top environment input data. Then, the top environment input data is used for machine learning to obtain a more complete top environment model. Then, the safe distance is determined based on experience. ， The top safety limit constraint is performed through the top environment model, that is, it is necessary to ensure that the distance between any point on the target path and any point in the top environment model is greater than the safety distance.

[0095] Next, obstacle safety constraints are formulated. That is, the size of all obstacles except the top obstacle is expanded by 1.5 to 2 times, and the target path is guaranteed not to contact the expanded obstacles. This completes the formulation of obstacle safety constraints.

[0096] Finally, the three-dimensional coordinates of the nodes including the path points on the initial path are obtained and the three-dimensional coordinates of adjacent nodes The random tree node coordinates can be used to formulate the pitch angle constraint:

[0097]

[0098] in, is the pitch angle of the underwater vehicle, is the x-axis coordinate of the path point in the left-handed space rectangular coordinate system, is the y-axis coordinate of the path point in the left-handed space rectangular coordinate system, is the z-axis coordinate of the path point in the left-handed rectangular coordinate system, is the x-axis coordinate of the adjacent node of the path point in the left-handed space rectangular coordinate system, is the y-axis coordinate of the adjacent node of the path point in the left-hand space rectangular coordinate system, is the z-axis coordinate of the neighboring node of the path point in the left-handed rectangular coordinate system. Here, the neighboring node is the other path point closest to the path point. is the limit value of the pitch angle of the underwater vehicle, is the inverse of the tangent function. The pitch angle is shown in Figure 3(a), where the coordinate system is the left-handed space coordinate system.

[0099] It is also necessary to use the node plane coordinates obtained from the node three-dimensional coordinates , the plane coordinates of the adjacent nodes obtained from the three-dimensional coordinates of the adjacent nodes And the plane coordinates of the parent node of the adjacent node of the path point obtained from the initial path To create a rotation angle constraint:

[0100]

[0101]

[0102]

[0103] in, is the first intermediate vector, is the second intermediate vector, is the x-axis coordinate of the parent node of the adjacent node of the path point in the left-handed space rectangular coordinate system, is the y-axis coordinate of the parent node of the adjacent node of the path point in the left-handed space rectangular coordinate system, β is the rotation angle of the underwater vehicle, is the maximum turning angle of the underwater vehicle, is the arc cosine function. The rotation angle is shown in Figure 3 (b). The initial path is adjusted to meet the top safety limit constraint, obstacle safety constraint and vehicle angle constraint, and the target path of the underwater vehicle can be obtained, and the underwater vehicle can navigate according to the target path. The target path is as follows: Figure 4 As shown, the distance unit is meter. The time of obtaining the target path by the method provided by the present invention is shorter than that of the original The algorithm reduces the time by about 92%. For a navigation simulation environment with a limited underwater top of 4000m*4000m*100m in size, the time for the present invention to obtain the target path does not exceed 2s.

[0104] The present invention provides a three-dimensional route planning method for an underwater vehicle in confined waters, which enables the underwater vehicle to quickly generate a relatively smooth target path with less fluctuation and navigate according to the target path.

[0105] The following describes the confined waters three-dimensional route planning device provided by the present invention. The confined waters three-dimensional route planning device described below and the confined waters three-dimensional route planning method described above can be referenced to each other.

[0106] Figure 5 The structural diagram of the restricted water three-dimensional route planning system is shown as an example. Figure 5 As shown, the method for executing the above-mentioned three-dimensional route planning in restricted waters includes:

[0107] Underwater topographic map module 100: used to determine the target water area, obtain the underwater topographic map of the target water area, and determine the path endpoint in the target water area;

[0108] Conversion matrix module 200: used to determine the water area size in the underwater topographic map, obtain the ellipse transformation matrix according to the water area size, and determine the conversion matrix;

[0109] Ellipse transformation module 300: used to determine the stretching coefficient, calculate the stretching height by the stretching coefficient and the path endpoint, determine the random point according to the stretching height, and perform ellipse transformation on the random point by using the ellipse transformation matrix and the conversion matrix to obtain the transformed random point;

[0110] Initial path module 400: used to select a path generation algorithm and a cylinder radius, generate an offset optimization cylinder based on the cylinder radius, and determine whether there is an obstacle in the offset optimization cylinder. If an obstacle exists, the cylinder radius is changed and the offset optimization cylinder is updated until there is no obstacle in the offset optimization cylinder. The growth direction is determined in the offset optimization cylinder based on the path endpoints, so that the path generation algorithm obtains the initial path based on the transformed random points and the growth direction.

[0111] Target path module 500: used to obtain a top environment model through machine learning and perform top safety limit constraints, obtain obstacle safety constraints through underwater terrain maps, obtain random tree node coordinates, obtain vehicle angle constraints through random tree node coordinates, constrain the initial path according to the top safety limit constraints, obstacle safety constraints and vehicle angle constraints, and obtain the target path for underwater vehicle navigation.

[0112] on the other hand, Figure 6An example of a physical structure diagram of an electronic device is shown below. Figure 6 As shown, the electronic device may include: a processor 810, a communication interface 820, a memory 830, and a communication bus 840, wherein the processor 810, the communication interface 820, and the memory 830 communicate with each other via the communication bus 840. The processor 810 may call the logic instructions in the memory 830 to execute the method for three-dimensional route planning in restricted waters, which includes:

[0113] S1: Determine the target water area, obtain the underwater topographic map of the target water area, and determine the path endpoint in the target water area;

[0114] S2: Determine the water area size in the underwater topographic map, obtain the ellipse transformation matrix based on the water area size, and determine the conversion matrix;

[0115] S3: Determine the stretching coefficient, calculate the stretching height by the stretching coefficient and the path endpoint, determine the random point according to the stretching height, and perform elliptical transformation on the random point by using the elliptical transformation matrix and the conversion matrix to obtain the transformed random point;

[0116] S4: Selecting a path generation algorithm and a cylinder radius, generating a biased optimization cylinder based on the cylinder radius, and determining whether there is an obstacle in the biased optimization cylinder. If there is an obstacle, changing the cylinder radius and updating the biased optimization cylinder until there is no obstacle in the biased optimization cylinder. Determining a growth direction based on the path endpoints in the biased optimization cylinder allows the path generation algorithm to obtain an initial path based on the transformed random points and the growth direction.

[0117] S5: Obtain the top environment model through machine learning and perform top safety limit constraints, obtain obstacle safety constraints through the underwater terrain map, obtain random tree node coordinates, obtain the vehicle angle constraints through the random tree node coordinates, constrain the initial path according to the top safety limit constraints, obstacle safety constraints and vehicle angle constraints, and obtain the target path for the underwater vehicle.

[0118] Furthermore, the logic instructions in the aforementioned memory 830 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the portion that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product, stored in a storage medium, includes instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as a USB flash drive, a mobile hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0119] In another aspect, the present invention further provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method for three-dimensional route planning in restricted waters provided by the above methods, the method comprising:

[0120] S1: Determine the target water area, obtain the underwater topographic map of the target water area, and determine the path endpoint in the target water area;

[0121] S2: Determine the water area size in the underwater topographic map, obtain the ellipse transformation matrix based on the water area size, and determine the conversion matrix;

[0122] S3: Determine the stretching coefficient, calculate the stretching height by the stretching coefficient and the path endpoint, determine the random point according to the stretching height, and perform elliptical transformation on the random point by using the elliptical transformation matrix and the conversion matrix to obtain the transformed random point;

[0123] S4: Selecting a path generation algorithm and a cylinder radius, generating a biased optimization cylinder based on the cylinder radius, and determining whether there is an obstacle in the biased optimization cylinder. If there is an obstacle, changing the cylinder radius and updating the biased optimization cylinder until there is no obstacle in the biased optimization cylinder. Determining a growth direction based on the path endpoints in the biased optimization cylinder allows the path generation algorithm to obtain an initial path based on the transformed random points and the growth direction.

[0124] S5: Obtain the top environment model through machine learning and perform top safety limit constraints, obtain obstacle safety constraints through the underwater terrain map, obtain random tree node coordinates, obtain the vehicle angle constraints through the random tree node coordinates, constrain the initial path according to the top safety limit constraints, obstacle safety constraints and vehicle angle constraints, and obtain the target path for the underwater vehicle.

[0125] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, i.e., they may be located in one location or distributed across multiple network units. Some or all of the modules may be selected based on actual needs to achieve the objectives of the present embodiment. Persons of ordinary skill in the art will be able to understand and implement the present invention without inventive effort.

[0126] Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented using software plus a necessary general-purpose hardware platform, or of course, hardware. Based on this understanding, the essence of the above technical solution, or the portion that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a magnetic disk, or an optical disk, and includes a number of instructions for causing a computer device (such as a personal computer, server, or network device) to execute the methods described in each embodiment or certain portions of the embodiments.

[0127] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A three-dimensional route planning method for restricted waters, characterized in that: include: S1: Determine the target water area, obtain the underwater topographic map of the target water area, and determine the path endpoint in the target water area; S2: Determine the water area size in the underwater topographic map, obtain the ellipse transformation matrix based on the water area size, and determine the conversion matrix; S3: Determine the stretching coefficient, calculate the stretching height by the stretching coefficient and the path endpoint, determine the random point according to the stretching height, and perform elliptical transformation on the random point by using the elliptical transformation matrix and the conversion matrix to obtain the transformed random point; S4: Selecting a path generation algorithm and a cylinder radius, generating a biased optimization cylinder based on the cylinder radius, and determining whether there is an obstacle in the biased optimization cylinder. If there is an obstacle, changing the cylinder radius and updating the biased optimization cylinder until there is no obstacle in the biased optimization cylinder. Determining a growth direction based on the path endpoints in the biased optimization cylinder allows the path generation algorithm to obtain an initial path based on the transformed random points and the growth direction. S5: Obtain the top environment model through machine learning and perform top safety limit constraints, obtain obstacle safety constraints through the underwater terrain map, obtain random tree node coordinates, obtain the vehicle angle constraints through the random tree node coordinates, constrain the initial path according to the top safety limit constraints, obstacle safety constraints and vehicle angle constraints, and obtain the target path for the underwater vehicle.

2. The method for three-dimensional route planning in restricted waters according to claim 1, characterized in that: Step S1 specifically includes: S11: Determine a target water area, perform a topographic survey on the target water area, and obtain an underwater topographic map of the target water area; S12: Determine the end point and the starting point of the path of the underwater vehicle in the underwater topographic map, and use the end point and the starting point of the path as the path endpoints.

3. The method for three-dimensional route planning in restricted waters according to claim 1, characterized in that: Step S2 specifically includes: S21: determining the size of a water area including the length and width of the water area in the underwater topographic map, calculating the ellipse focus and the ellipse major axis length according to the water area size, and obtaining the ellipse transformation matrix through the ellipse focus and the ellipse major axis length; S22: Determine the path endpoint vector according to the path endpoint, determine the endpoint vector angle through the path endpoint vector, and construct the transformation matrix using the endpoint vector angle.

4. The method for three-dimensional route planning in restricted waters according to claim 1, characterized in that: Step S3 specifically includes: S31: determining a stretching coefficient, wherein the stretching coefficient is 1.2 to 1.5, calculating an endpoint height difference between the path endpoints, and calculating an initial stretching height using the stretching coefficient and the endpoint height difference; S32: obtaining a safety distance from the initial stretching height, adjusting the initial stretching height according to the safety distance to obtain a stretching height, and determining a stretching ellipse according to the stretching height; S33: Select a random point according to the stretching height, and determine the random point plane coordinates of the random point, perform elliptical transformation on the random point plane coordinates through the elliptical transformation matrix and the conversion matrix to obtain the random point transformation coordinates, and obtain the transformed random point located in the stretched ellipse according to the random point transformation coordinates.

5. The method for three-dimensional route planning in restricted waters according to claim 1, characterized in that: In step S4, when there is an obstacle, the cylinder radius is reduced and a new biased optimization cylinder is generated based on the reduced cylinder radius until there is no obstacle in the biased optimization cylinder. The update of the biased optimization cylinder is completed, and the direction from the path starting point to the path end point in the biased optimization cylinder is used as the growth direction. The path generation algorithm obtains the initial path by transforming the random points and performing random tree growth according to the growth direction.

6. The method for three-dimensional route planning in restricted waters according to claim 1, characterized in that: In step S5, top environment data is acquired and cleaned, preprocessed and interpolated to obtain top environment input data, machine learning is performed on the top environment input data to obtain the top environment model, and the top safety limit constraint is performed using the top environment model.

7. The method for three-dimensional route planning in restricted waters according to claim 1, characterized in that: In step S5, the random tree node coordinates including the node three-dimensional coordinates and the adjacent node three-dimensional coordinates are obtained, and the aircraft angle constraints including the pitch angle constraint and the roll angle constraint are obtained through the random tree node coordinates.

8. A three-dimensional route planning system for confined waters, configured to execute the three-dimensional route planning method for confined waters according to any one of claims 1 to 7, characterized in that: include: Underwater topographic map module: used to determine the target water area, obtain the underwater topographic map of the target water area, and determine the path endpoint in the target water area; Conversion matrix module: used to determine the water area size in the underwater topographic map, obtain the ellipse transformation matrix based on the water area size, and determine the conversion matrix; Ellipse transformation module: used to determine the stretching coefficient, calculate the stretching height through the stretching coefficient and the path endpoint, determine the random point according to the stretching height, and perform ellipse transformation on the random point through the ellipse transformation matrix and the conversion matrix to obtain the transformed random point; Initial path module: used to select the path generation algorithm and cylinder radius, generate the biased optimization cylinder according to the cylinder radius, and determine whether there are obstacles in the biased optimization cylinder. If there are obstacles, the cylinder radius is changed and the biased optimization cylinder is updated until there are no obstacles in the biased optimization cylinder. The growth direction is determined according to the path endpoint in the biased optimization cylinder, so that the path generation algorithm obtains the initial path according to the transformed random points and growth direction. Target path module: used to obtain the top environment model through machine learning and perform top safety limit constraints, obtain obstacle safety constraints through underwater terrain maps, obtain random tree node coordinates, obtain vehicle angle constraints through random tree node coordinates, constrain the initial path according to the top safety limit constraints, obstacle safety constraints and vehicle angle constraints, and obtain the target path for underwater vehicle navigation.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the steps of the method for three-dimensional route planning in restricted waters according to any one of claims 1 to 7 are implemented.

10. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method for three-dimensional route planning in restricted waters according to any one of claims 1 to 7 are implemented.

Images