An intelligent ship path planning online editing method

Abstract

The application discloses an intelligent ship path planning online editing method and relates to the technical field of path planning, and comprises the following steps: generating an initial planning path from a starting point to an ending point, the path being composed of at least two nodes, and automatically numbering each node of the broken line in the order of from the starting point, through each intermediate point, and finally to the ending point; editing the initial path, the editing method comprising: inserting a node, deleting a node and modifying a node, and reordering the node numbers after the path editing is completed; editing the path for multiple times until the user determines the editing result, automatically using a smoothing optimization processing based on a second-order Bezier curve on the latest generated broken line path, generating a final path, and sailing according to the final path by the intelligent ship; combining a straight line part of the original planning path and the second-order Bezier curve to obtain a smoothing path of the original planning path, and putting the path after the smoothing optimization processing into use.

Description

Technical Field

[0001] The present invention relates to the technical field of path planning, and in particular to an online editing method for intelligent ship path planning. Background Art

[0002] In recent years, with the rise of the marine economy, marine intelligent equipment has also entered a period of rapid development. Intelligent ships have become the development trend of future marine unmanned equipment. Their autonomous navigation in the marine environment requires path planning. A ship navigation path can be generated through various prior information through path planning algorithms or manual planning.

[0003] There are many existing path planning methods, such as artificial potential field method, A* algorithm, D* algorithm, ant colony algorithm, genetic algorithm, etc. These methods are widely used in drones, robots, smart cars, unmanned boats, etc.

[0004] When smart ships are autonomously navigating along a planned path, they often need to change the original planned path in a timely manner due to mission changes, weather factors, route congestion, and other reasons. Although there are many algorithms that can be used for path planning, there is currently a lack of methods for secondary editing of the path. Often, once a path is generated, it cannot be effectively edited.

[0005] In addition, most of the existing path planning algorithms only consider collision avoidance and the shortest path. However, for the complex marine environment, the available paths automatically planned by them often cannot meet the actual scenarios. Although the paths obtained by commonly used automatic path planning algorithms are usually short, they may cause too many turns or lead the unmanned boat into dangerous areas with more obstacles, increasing the possibility of grounding, reef collision and collision. Moreover, they cannot automatically adjust the planned route in time according to weather conditions and traffic congestion at the time, which reduces the safety of navigation and requires manual adjustment or correction of the planned route globally or locally. Summary of the Invention

[0006] The purpose of the present invention is to provide an online editing method for intelligent ship path planning that can meet the path changes and modifications brought about by changes in objective reality needs of intelligent ships in the marine environment, and realize online editing of planned paths and real-time path modification.

[0007] The technical solution of the present invention is to provide an online editing method for intelligent ship path planning, which includes:

[0008] Generate an initial planned path from the starting point to the end point. The path consists of a set of sequential polylines with at least two nodes. Each node of the polyline is automatically numbered in the order from the starting point to the intermediate points and finally to the end point.

[0009] Edit the initial path. Editing methods include: inserting nodes, deleting nodes, and modifying nodes. After the path editing is completed, the node numbers are reordered.

[0010] The path is edited multiple times until the user confirms the editing result. The system automatically applies smoothing optimization processing based on the second-order Bezier curve to the newly generated polyline path to generate the final path. The intelligent ship navigates according to the final path.

[0011] The smoothing optimization processing steps based on the second-order Bezier curve include:

[0012] For a polyline, starting from the starting point, for the lines between any three adjacent nodes, apply the Bezier curve for smoothing. The second-order Bezier curve can be determined by the following formula:

[0013] B(t)=(1-t) 2 P0+2t(1-t)P1+t 2 P2,t∈[0,1],

[0014] Among them, P0, P1, and P2 are three points in a given two-dimensional plane, P0 is the starting point of the curve, P2 is the end point of the curve, and P1 is the control point;

[0015] For other path points that do not include the starting point and the end point, a node is inserted on each side based on the following conditions: the node setting must meet the turning angle less than 35°, that is, it must meet:

[0016]

[0017] Point B' is any node that is not the starting point or the end point, and is used as the control point of the second-order Bezier curve. A' is the previous node of B', and C' is the next node of B'. Points B'0 and B'1 are inserted on both sides of B', where B'0 is the starting point of the second-order Bezier curve and B'1 is the end point of the second-order Bezier curve. Then, the second-order Bezier curve is processed on the inflection point of the broken line. After all the inflection points of the broken line path are processed by the second-order Bezier curve, the straight part of the original planned path and the second-order Bezier curve are combined to obtain a smooth path of the original planned path, and the smoothed and optimized path is put into use.

[0018] In any of the above technical solutions, further, the step of generating an initial planned path from the starting point to the end point includes:

[0019] The Lazy Theta* algorithm uses a cost function to achieve optimal path planning. The map is rasterized and expanded from the grid where the starting point is located to the neighboring grids. The cost value of the neighboring grid is calculated, and the grid node with the smallest cost value is determined as the next node. The calculation is iteratively calculated, and the line of sight method is tested between each node and the previous node. This process is repeated until the end point is reached and a planned path is generated. The line of sight method test includes: if there is a node that can form a line of sight with the current node, all intermediate nodes between the two nodes are deleted.

[0020] The cost function of the Lazy Theta* algorithm is:

[0021] F(s)=G(s)+H(s),

[0022] Where F(s) is the total cost of node s, G(s) is the path movement cost from the starting point to node s, and H(s) is the estimated path movement cost between node s and the end point. The estimated path movement cost H(s) between node s and the end point is calculated using Chebyshev distance. The cost of moving up, down, left, and right is 1, and the cost of moving up, down, left, and right is 1. but:

[0023]

[0024] where s x , s y is the plane coordinate of node s, d x , d y is the plane coordinate of the end point d.

[0025] In any of the above technical solutions, further, the Lazy Theta* algorithm steps include:

[0026] S1. Set up two data sets, open_list and closed_list, and initialize them. Store the starting point m data into open_list.

[0027] S2. Select the starting point m as the current node for processing, calculate the cost of all neighboring nodes of the current node, and select the node s with the smallest total cost as the current point to be expanded. m is the parent node of node s.

[0028] S3. Treat s as the current node, expand node s, find the neighboring node p with the minimum total cost, and optimistically determine that node p is visible to the parent node m of node s;

[0029] S4. Add node s to the data set closed_list and delete it from the data set open_list. Determine whether the data set open_list is empty. If it is empty, the search fails and the algorithm ends. If it is not empty, proceed to the next step.

[0030] S5. Process node p as the current node and check whether node p is visible to the parent node m of node s. If not, search for a visible parent node again and update the cost with the new parent node. If visible, expand node p and find the next neighboring node with the minimum total cost. Optimistically determine that the neighboring node is visible to the parent node of node p by default, and repeat steps S4-S5.

[0031] S6. Iterate the above steps until the current node is the end point and the path search is successful. Extract node data from the data set closed_list to generate the planned initial path.

[0032] In any of the above technical solutions, further, during the process of the intelligent ship navigating along the path, in order to ensure the navigation safety of the ship, the executed path points and the next path point to be reached are locked and editing is prohibited. Only the path after the next path point to be reached can be inserted, deleted, modified and edited. During the path editing process, the intelligent ship navigates according to the original planned path.

[0033] In any of the above technical solutions, further, inserting a node includes:

[0034] When the starting point and end point do not need to be changed, and the user only specifies the insertion point coordinates, the point to be inserted is placed at the corresponding position, and the positions of other points remain unchanged. When an intermediate point is inserted, the Euclidean distance to other intermediate points, the starting point, and the end point is automatically calculated, and the two closest adjacent points are automatically connected. When the user specifies the insertion point coordinates and the node number, the point to be inserted is placed at the corresponding position, and the positions of other points remain unchanged. The insertion point is connected to the point before the specified number, and then to the point with the same number as the specified number. After the new path is formed, the numbers are reordered.

[0035] The starting point is changed without changing the original route. The user specifies the coordinates of the insertion point and places the point to be inserted at the corresponding position. The positions of other points remain unchanged. The insertion point is connected to the original starting point to form a new path and the numbers are reordered.

[0036] The end point is changed without changing the original route. The user specifies the coordinates of the insertion point and places the point to be inserted at the corresponding position. The positions of other points remain unchanged. The insertion point is connected to the original end point to form a new path and the numbers are reordered.

[0037] In any of the above technical solutions, further, deleting the node includes:

[0038] The user specifies the number of the node to be deleted. After deleting the node with the number, the path points before and after the point will be automatically connected. If the specified point is the starting point or the end point, only the deletion operation will be performed without connecting. After the new path is formed, the numbers will be reordered.

[0039] In any of the above technical solutions, further, during the node deletion process, when the entire path has only two nodes, node deletion is not supported; when the entire path has only three nodes, only one of the starting point or the end point is supported to be deleted.

[0040] In any of the above technical solutions, further, modifying the node includes:

[0041] The user specifies the number of the node to be modified and then enters the new coordinates to complete the modification.

[0042] In any of the above technical solutions, further, the modified node can be modified by directly dragging the node of the path image in the visualization client.

[0043] The beneficial effects of the present invention are:

[0044] The technical solution of the present invention can realize online editing and real-time path modification of the planned path by adding, deleting, and modifying the editing methods of path points on the basis of the automatically planned or manually planned path. It can meet the path changes and modifications brought about by the objective reality changes of intelligent ships in the marine environment. The intelligent ship can execute the path editing results online in real time, which not only ensures the navigation and operation safety of the intelligent ship after the editing is executed, but also avoids unnecessary time loss. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] The advantages of the above and additional aspects of the present invention will become apparent and readily understood from the following description of the embodiments with reference to the accompanying drawings, in which:

[0046] Figure 1 is a schematic diagram of an online editing method for intelligent ship path planning according to an embodiment of the present invention;

[0047] Figure 2 is a flowchart of an initial path planning method for online editing of intelligent ship path planning according to an embodiment of the present invention;

[0048] Figure 3 2. Schematic diagram of an automatic path planning algorithm of an online editing method for intelligent ship path planning according to an embodiment of the present invention;

[0049] Figure 4 This is a schematic diagram of achieving path smoothing based on a second-order Bezier curve in an online editing method for intelligent ship path planning according to an embodiment of the present invention;

[0050] Figure 5 This is a schematic diagram of automatically inserting intermediate points according to an online editing method for intelligent ship path planning according to an embodiment of the present invention;

[0051] Figure 6 1. A schematic diagram of inserting a given number into an intermediate point according to an online editing method for intelligent ship path planning according to an embodiment of the present invention;

[0052] Figure 7 1 is a schematic diagram of an insertion starting point according to an online editing method for intelligent ship path planning according to an embodiment of the present invention;

[0053] Figure 8 1. A schematic diagram of inserting a destination point according to an online editing method for intelligent ship path planning according to an embodiment of the present invention;

[0054] Figure 9 1. A schematic diagram of deleting intermediate points in an online editing method for intelligent ship path planning according to an embodiment of the present invention;

[0055] Figure 10 1. A schematic diagram of deleting a starting point and an end point according to an online editing method for intelligent ship path planning according to an embodiment of the present invention;

[0056] Figure 11 1 is a schematic diagram of path execution restrictions of an online editing method for intelligent ship path planning according to an embodiment of the present invention. DETAILED DESCRIPTION

[0057] In order to more clearly understand the above-mentioned objects, features and advantages of the present invention, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments. It should be noted that the embodiments of the present invention and the features therein can be combined with each other without conflict.

[0058] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Therefore, the scope of protection of the present invention is not limited to the specific embodiments disclosed below.

[0059] like Figure 1 As shown, this embodiment provides an online editing method for intelligent ship path planning, which includes:

[0060] Planning the initial path. In this embodiment, the Lazy Theta* algorithm is used to automatically generate the initial path of the intelligent ship. The Lazy Theta* algorithm implements optimal path planning through a cost function. First, the map is rasterized and expanded from the grid where the starting point is located to the neighboring grids. By calculating the cost value of the neighboring grids, the grid node with the smallest cost value is determined as the next node. Iterative calculation is performed, and the line of sight (LOS) method is performed on each node and the previous node respectively. This process is repeated until the end point is reached, and a planned path is generated.

[0061] Line of sight (LOS) detection includes: if there is a line of sight between the current node and a previous node, all intermediate nodes between the two nodes are deleted.

[0062] The cost function of the Lazy Theta* algorithm is:

[0063] F(s)=G(s)+H(s),

[0064] Where F(s) is the total cost of node s, G(s) is the path movement cost from the starting point to node s, and H(s) is the estimated path movement cost between node s and the end point. The estimated path movement cost H(s) between node s and the end point is calculated using Chebyshev distance. The cost of moving up, down, left, and right is 1, and the cost of moving up, down, right, down, and down is but:

[0065]

[0066] where s x , s y is the plane coordinate of node s, d x , d y is the plane coordinate of the end point d.

[0067] like Figure 2 As shown in the figure, the Lazy Theta* algorithm first sets two data sets, open_list and closed_list, during the search for path nodes. The steps of the algorithm are as follows:

[0068] S1. Initialize two data sets open_list and closed_list, and store the starting point m data into open_list.

[0069] S2. Select the starting point m as the current node for processing, calculate the cost of all neighboring nodes of the current node, and select the node s with the smallest total cost as the current point to be expanded. m is the parent node of node s.

[0070] S3. Treat s as the current node, expand node s, find the neighboring node p with the minimum total cost, and optimistically determine that node p is visible to the parent node m of node s.

[0071] S4. Add node s to the data set closed_list and delete it from the data set open_list. Determine whether the data set open_list is empty. If it is empty, the search fails and the algorithm ends. If it is not empty, proceed to the next step.

[0072] S5. Process node p as the current node and check whether node p and node s's parent node m are visible. If not, re-search for a visible parent node and update the cost with the new parent node. If visible, expand node p and find the next neighboring node with the smallest total cost. Optimistically, by default, determine that the neighboring node and node p's parent node are visible, and loop through steps S4-S5.

[0073] S6. Iterate the above steps until the current node is the end point and the path search is successful. Extract node data from the data set closed_list to generate the planned initial path.

[0074] like Figure 3 As shown in Figure 1, in Step 1, the starting point E4 is processed as the current node, E4 is expanded, and the node D3 with the smallest total cost is selected as the current point to be expanded. E4 is the parent node of node D3. In Step 2, D3 is processed as the current node and D3 is expanded. C3 is the extension point with the smallest total cost of D3, pointing to the starting point E4 instead of D3, because B2 has not been opened yet and has not been used as the current processing node. The algorithm optimistically assumes that C3 and the parent node E4 of the current processing node D3 are visible. This assumption is corrected in Step 3 when C3 is the node being processed. In ep3, C3 is taken as the node being processed. The visibility of C3 and its parent node E4 in Step 2 is first checked. If it is not visible, the algorithm searches again and takes D3 as the parent node of C3. Then, C3 is extended and the end point B2 is found to be the extension point of C3. The algorithm optimistically assumes that the end point B2 and the parent node D3 of the currently processed node C3 are visible. In Step 4, the end point B2 is taken as the node being processed. The visibility of C3 and its parent node D3 in Step 3 is first checked. If it is visible, the path search is successful. The parent node and the end point are connected in sequence to form an initial planned path from the starting point to the end point.

[0075] After obtaining the initial planned path of the polyline, each node of the polyline is automatically numbered in the order from the starting point through the intermediate points to the end point for subsequent editing and use.

[0076] If there is no problem with the initial planned path and no editing is required, the initial path will be smoothed and optimized. Commonly used trajectory smoothing methods include cubic spline interpolation and cubic B-spline interpolation. However, such interpolation methods will change the straight line portion of the planned path, causing the curvature of the straight line portion to change, which reduces the accuracy of the ship's trajectory tracking. In addition, the curvature change of the straight line portion may cause the planned path to intersect with obstacles, reducing the safety of the planned path.

[0077] This embodiment uses a second-order Bezier curve to perform smooth optimization processing only on the inflection point part of the broken line, which not only ensures the trajectory tracking accuracy of the straight line part, but also smoothes the inflection point so that the planned path is suitable for ship tracking and navigation, and complies with the kinematic laws of the ship.

[0078] For a polyline, starting from the starting point, the angle formed by two lines between any three adjacent nodes is smoothed using a Bezier curve. The second-order Bezier curve can be determined using the following formula:

[0079] B(t)=(1-t) 2 P0+2t(1-t)P1+t 2 P2,t∈[0,1],

[0080] Among them, P0, P1, and P2 are three points in a given two-dimensional plane, P0 is the starting point of the curve, P2 is the end point of the curve, and P1 is the control point.

[0081] like Figure 4 As shown in the figure, the planned path obtained by the Lazy Theta* algorithm is an ABCDEF polyline, where A is the starting point and F is the end point. A node is inserted on both sides of other path points that do not include the starting point and the end point. Since the maximum left and right turning angle of the ship is 35°, the node setting must also meet the steering angle less than 35°. Taking point B as an example, the node insertion rule must meet the following requirements:

[0082]

[0083] Insert points B0 and B1 on both sides of B, where point B is any node other than the starting point and the end point, as the control point of the second-order Bezier curve, B0 as the starting point of the second-order Bezier curve, and B1 as the end point of the second-order Bezier curve. Then, perform second-order Bezier curve processing on the inflection points of the broken line. After all inflection points of the broken line path are processed by the second-order Bezier curve, combine the straight line part of the original planned path and the second-order Bezier curve to obtain a smooth path A-B0-B1-C0-C1-D0-D1-E0-E1-F of the original planned path. The smoothed and optimized path is put into use.

[0084] If you need to edit the initial path, there are several editing methods available depending on your needs:

[0085] 1) Insert node:

[0086] like Figure 5 As shown in the figure, if the starting point and the end point do not need to be changed and the user only specifies the coordinates of the insertion point, the point to be inserted will be placed at the corresponding position, and the positions of other points will remain unchanged. When an intermediate point is inserted, the Euclidean distance to other intermediate points, the starting point, and the end point will be automatically calculated, and the two adjacent points with the closest distance will be automatically connected to form a new path and the numbers will be reordered.

[0087] like Figure 6 As shown, if the starting point and the end point do not need to be changed, and the user specifies the insertion point coordinates and number at the same time, the point to be inserted will be placed at the corresponding position, and the positions of other points will remain unchanged. The insertion point will be connected to the point before the specified number, and then the insertion point will be connected to the point with the same number as the specified number. After forming a new path, the numbers will be reordered.

[0088] like Figure 7 As shown, if the starting point needs to be changed while the original route remains unchanged, the user specifies the coordinates of the insertion point, places the point to be inserted at the corresponding position, and keeps the positions of other points unchanged. The insertion point is connected to the original starting point to form a new path and the numbers are reordered.

[0089] like Figure 8 As shown, if the end point needs to be changed while the original route remains unchanged, the user specifies the coordinates of the insertion point, places the point to be inserted at the corresponding position, and keeps the positions of other points unchanged. The insertion point is connected to the original end point to form a new path and then the numbers are reordered.

[0090] 2) Delete node:

[0091] like Figure 9 As shown, if you need to remove a single point in the middle of a planned path, delete the middle point with the user-specified number, and automatically connect the path points before and after this middle point to form a new path and reorder the numbers.

[0092] like Figure 10 As shown in the figure, if you need to remove the starting point or end point of a planned path, simply delete the user-specified starting point or end point, and reorder the numbers after forming a new path. When the entire path has only two nodes, node deletion is not supported. When the entire path has only three nodes, only one of the starting point or end point can be deleted.

[0093] 3) Modify the node:

[0094] The planned path can be adjusted by modifying the path points. The modification of the path points includes two aspects: one is to modify the position of the path points, and the other is to modify the number of the points. Considering that the path adjustment results produced by modifying the number of the path points in the actual engineering application of intelligent ships are not easy to understand and intuitively express, and are not very practical, only the position of the path points can be modified in this patent.

[0095] like Figure 1 As shown, the user specifies the number of the node to be modified and enters the new coordinates to complete the modification. In the visual client, the node of the path image can be modified by directly dragging it.

[0096] The above-mentioned multiple editing methods can be used to edit the same path multiple times. After the user confirms the editing results, the system automatically applies the above-mentioned smoothing optimization processing to the newly generated broken line path, and the intelligent ship navigates according to the final path.

[0097] Specifically, in the process of smart ships sailing along the path, in order to ensure the safety of the ship's navigation, the executed path points and the next path point to be reached are locked and cannot be edited. Only the path after the next path point to be reached can be inserted, deleted, modified and edited. During the path editing process, the smart ship sails according to the original planned path; Figure 11 As shown, path points 1, 2, 3, and 4 are the path points that the smart ship has already executed, and 5 is the next path point that the smart ship is about to reach. The path between 5, 6, and 7 and path points 6 and 7 can be inserted, deleted, modified, and edited. Other path points are locked and editing is prohibited.

[0098] In summary, the present invention proposes an online editing method for intelligent ship path planning, comprising:

[0099] Generate an initial planned path from the starting point to the end point. The path consists of a set of sequential polylines with at least two nodes. Each node of the polyline is automatically numbered in the order from the starting point through the intermediate points to the end point.

[0100] The initial path is edited. Editing methods include: inserting nodes, deleting nodes, and modifying nodes. After the path editing is completed, the node numbers are reordered.

[0101] The path is edited multiple times until the user confirms the editing result. The system automatically uses smoothing optimization processing based on the second-order Bezier curve to the newly generated broken line path to generate the final path. The intelligent ship navigates according to the final path.

[0102] The smoothing optimization processing steps based on the second-order Bezier curve include:

[0103] For a polyline, starting from the starting point, the angle formed by two lines between any three adjacent nodes is smoothed using a Bezier curve. The second-order Bezier curve can be determined using the following formula:

[0104] B(t)=(1-t) 2 P0+2t(1-t)P1+t 2 P2,t∈[0,1],

[0105] Among them, P0, P1, and P2 are three points in a given two-dimensional plane, P0 is the starting point of the curve, P2 is the end point of the curve, and P1 is the control point.

[0106] Insert a node on each side of other path points that do not include the starting point and the end point. Since the maximum left and right turning angle of the ship is 35°, the node setting must ensure that the turning angle is less than 35°, that is, it must meet the following requirements:

[0107]

[0108] Point B is the control point of the second-order Bezier curve, A is the previous node of B, C is the next node of B, and points B0 and B1 are inserted on both sides of B, where B0 is the starting point of the second-order Bezier curve and B1 is the end point of the second-order Bezier curve. Then, the second-order Bezier curve is processed on the inflection point of the broken line. After all the inflection points of the broken line path are processed by the second-order Bezier curve, the straight line part of the original planned path and the second-order Bezier curve are combined to obtain a smooth path of the original planned path, and the smoothed and optimized path is put into use.

[0109] The steps in the present invention can be adjusted in sequence, combined, or deleted according to actual needs.

[0110] Although the present invention has been disclosed in detail with reference to the accompanying drawings, it should be understood that these descriptions are merely illustrative and are not intended to limit the application of the present invention. The scope of the present invention is defined by the appended claims and includes various modifications, variations, and equivalents made to the invention without departing from the scope and spirit of the present invention.

Claims

1. An online editing method for intelligent ship path planning, characterized in that: The method comprises: Generate an initial planned path from the starting point to the end point. The path consists of a set of sequential polylines with at least two nodes. Each node of the polyline is automatically numbered in the order from the starting point to the intermediate points and finally to the end point. Edit the initial path. Editing methods include: inserting nodes, deleting nodes, and modifying nodes. After the path editing is completed, the node numbers are reordered. The path is edited multiple times until the user confirms the editing result. The system automatically applies smoothing optimization processing based on the second-order Bezier curve to the newly generated polyline path to generate the final path. The intelligent ship navigates according to the final path. The smoothing optimization processing step based on the second-order Bezier curve includes: For a polyline, starting from the starting point, the angle formed by two lines between any three adjacent nodes is smoothed using a Bezier curve. The second-order Bezier curve can be determined using the following formula: B(t)=(1-t) 2 P0+2t(1-t)P1+t 2 P2,t∈[0,1], Among them, P0, P1, and P2 are three points in a given two-dimensional plane, P0 is the starting point of the curve, P2 is the end point of the curve, and P1 is the control point; For other path points that do not include the starting point and the end point, a node is inserted on both sides based on the following conditions: the node setting must meet the turning angle less than 35°, that is, it must meet: Point B' is any node that is not the starting point or the end point, and is used as the control point of the second-order Bezier curve. A' is the previous node of B', and C' is the next node of B'. Points B'0 and B'1 are inserted on both sides of B', where B'0 is the starting point of the second-order Bezier curve and B'1 is the end point of the second-order Bezier curve. Then, the second-order Bezier curve is processed on the inflection point of the broken line. After all the inflection points of the broken line path are processed by the second-order Bezier curve, the straight part of the original planned path and the second-order Bezier curve are combined to obtain a smooth path of the original planned path, and the smoothed and optimized path is put into use.

2. The online editing method for intelligent ship path planning according to claim 1, characterized in that: The step of generating an initial planned path from the starting point to the end point includes: The Lazy Theta* algorithm uses a cost function to achieve optimal path planning. The map is rasterized and expanded from the grid where the starting point is located to the neighboring grids. The cost value of the neighboring grid is calculated, and the grid node with the smallest cost value is determined as the next node. The calculation is iteratively calculated, and the line of sight method is tested between each node and the previous node. This process is repeated until the end point is reached and a planned path is generated. The line of sight method test includes: if there is a node that can form a line of sight with the current node, all intermediate nodes between the two nodes are deleted. The cost function of the Lazy Theta* algorithm is: F(s)=G(s)+H(s), Where F(s) is the total cost of node s, G(s) is the path movement cost from the starting point to node s, and H(s) is the estimated path movement cost between node s and the end point. The estimated path movement cost H(s) between node s and the end point is calculated using Chebyshev distance. The cost of moving up, down, left, and right is 1, and the cost of moving up, down, left, and right is 1. but: where s x , s y is the plane coordinate of node s, d x , d y is the plane coordinate of the end point d.

3. The online editing method for intelligent ship path planning according to claim 2, characterized in that: The LazyTheta* algorithm steps include: S1. Set up two data sets, open_list and closed_list, and initialize them. Store the starting point m data into open_list. S2. Select the starting point m as the current node for processing, calculate the cost of all neighboring nodes of the current node, and select the node s with the smallest total cost as the current point to be expanded. m is the parent node of node s. S3. Treat s as the current node, expand node s, find the neighboring node p with the minimum total cost, and optimistically determine that node p is visible to the parent node m of node s; S4. Add node s to the data set closed_list and delete it from the data set open_list. Determine whether the data set open_list is empty. If it is empty, the search fails and the algorithm ends. If it is not empty, proceed to the next step. S5. Process node p as the current node and check whether node p is visible to the parent node m of node s. If not, search for a visible parent node again and update the cost with the new parent node. If visible, expand node p and find the next neighboring node with the minimum total cost. Optimistically determine that the neighboring node is visible to the parent node of node p by default, and repeat steps S4-S5. S6. Iterate the above steps until the current node is the end point and the path search is successful. Extract node data from the data set closed_list to generate the planned initial path.

4. The online editing method for intelligent ship path planning according to claim 1, characterized in that: During the process of smart ships navigating along a route, to ensure navigation safety, the executed route points and the next route point to be reached are locked and editing is prohibited. Only insertion, deletion, and modification of the path after the next route point to be reached can be performed. During the path editing process, the smart ship navigates along the originally planned route.

5. The online editing method for intelligent ship path planning according to claim 1, characterized in that: The insertion node includes: When the starting point and end point do not need to be changed, and the user only specifies the insertion point coordinates, the point to be inserted is placed at the corresponding position, and the positions of other points remain unchanged. When an intermediate point is inserted, the Euclidean distance to other intermediate points, the starting point, and the end point is automatically calculated, and the two closest adjacent points are automatically connected. When the user specifies the insertion point coordinates and the node number, the point to be inserted is placed at the corresponding position, and the positions of other points remain unchanged. The insertion point is connected to the point before the specified number, and then to the point with the same number as the specified number. After the new path is formed, the numbers are reordered. The starting point is changed without changing the original route. The user specifies the coordinates of the insertion point and places the point to be inserted at the corresponding position. The positions of other points remain unchanged. The insertion point is connected to the original starting point to form a new path and the numbers are reordered. The end point is changed without changing the original route. The user specifies the coordinates of the insertion point and places the point to be inserted at the corresponding position. The positions of other points remain unchanged. The insertion point is connected to the original end point to form a new path and the numbers are reordered.

6. The online editing method for intelligent ship path planning according to claim 1, characterized in that: The deleting node includes: The user specifies the number of the node to be deleted. After deleting the node with the number, the path points before and after the point will be automatically connected. If the specified point is the starting point or the end point, only the deletion operation will be performed without connecting. After the new path is formed, the numbers will be reordered.

7. The online editing method for intelligent ship path planning according to claim 6, characterized in that: During the node deletion process, when the entire path has only two nodes, node deletion is not supported; when the entire path has only three nodes, only one of the starting point or the end point can be deleted.

8. The online editing method for intelligent ship path planning according to claim 1, characterized in that: The modification node includes: The user specifies the number of the node to be modified and then enters the new coordinates to complete the modification.

9. The online editing method for intelligent ship path planning according to claim 8, characterized in that: The modified node can be modified by directly dragging the node of the path image in the visualization client.

Images