Ship route and speed combined planning method

Abstract

The invention discloses a ship route and speed combined planning method, and relates to the field of intelligent ships, and the method comprises the steps: obtaining an improved dynamic Theta * algorithm through real-time detection of meteorological data on the basis of a standard Theta * algorithm; an improved dynamic Theta * algorithm is used for determining an initial route which reaches the target point from the starting point and does not pass through the obstacle grid, and the real-time meteorological data at all the positions meet the ship passing condition. And optimizing the initial route by using a route and speed joint optimization method to obtain an optimized route and speed. The initial route is planned by detecting the obstacles on the navigation path and the dynamic meteorological data in real time, the obstacles and severe weather such as typhoons can be accurately avoided, the navigation safety is greatly improved, and a solid foundation is laid for subsequent optimization steps.

Description

Technical Field

[0001] The present application relates to the field of intelligent ships, and in particular to a method for joint planning of ship routes and speeds. Background Art

[0002] With the continuous development of economic globalization, the shipping industry, as the core of supply chain and international trade transportation, has a vital impact on the world economy. Due to long-term sailing at sea, the marine environmental factors are complex and changeable, and the energy consumption required for ship navigation is quite huge. Ensuring safety during the entire voyage and reducing ship energy consumption have always been the key factors to be considered in the formulation of navigation plans. The joint planning of ship routes and speeds can effectively ensure the safety of ship navigation, reduce ship energy consumption, reduce sailing time, and improve navigation efficiency. It is of great significance to promote the development of intelligent ships and improve the energy efficiency of ships.

[0003] The traditional route speed joint planning method takes the route recommended by the ocean route as the initial route, and then uses the route speed joint optimization method to jointly optimize the initial route and initial speed to obtain the target route speed of the ship to achieve better navigation efficiency. The current common route speed joint optimization method mainly establishes a multi-objective optimization model and iteratively solves the optimization results through existing technologies such as genetic algorithms. The subsequent optimization process is mainly to further fine-tune the initial route, so the initial route largely determines the final target route. The initial route determined by this method requires sufficient prior knowledge, but due to the complex and changeable marine environment, the initial route recommended by the ocean route is actually difficult to ensure navigation safety. This will result in that even after the route speed joint optimization, the final target route speed is difficult to ensure navigation safety. Summary of the invention

[0004] In view of the above problems and technical requirements, this application proposes a method for joint planning of ship routes and speeds. The technical solution of this application is as follows:

[0005] A method for joint planning of ship routes and speeds comprises the following steps:

[0006] Obtain geographical information of the sea area that the ship passes through from the starting point to the destination, and construct a grid map of the sea area based on the geographical information;

[0007] Initialize parameter i=1 and use the grid node where the navigation starting point is as the first node;

[0008] At the i-th iteration, based on the grid map and real-time meteorological data, the path planning algorithm is used to determine the i+1th node according to the cost function of the neighboring nodes of the i-th node, and the i-th iteration candidate path from the navigation starting point to the i+1th node is determined. The i-th iteration candidate path does not pass through the obstacle grid in the grid map, and the real-time meteorological data of the estimated arrival time of the ship at each position of the i-th iteration candidate path meets the ship's passage conditions;

[0009] Entering the i+1th iteration, when the i+1th node is the target point, the initial route of the ship from the sailing starting point to the target point is obtained based on all the determined nodes;

[0010] The route and speed joint optimization method is used to optimize the initial route, and the optimized route and optimized speed of the ship from the starting point to the target point are obtained.

[0011] Its further technical solution is that when the real-time wave height data of the estimated arrival time of the ship at each position of the i-th iteration candidate path is less than the wave height threshold, it is determined that the real-time meteorological data of the estimated arrival time of the ship at the current position meets the ship's passage conditions.

[0012] A further technical solution is that the ship route speed joint planning method also includes:

[0013] Determine the starting time T0 of the ship's departure from the voyage starting point;

[0014] Interpolate to determine the length D of the navigation route between any position on the i-th iteration candidate path and the navigation starting point, and determine the estimated time △T = D / V for the ship to reach the current position from the navigation starting point along the i-th iteration candidate path, where V is the speed of the ship;

[0015] The estimated arrival time of the ship at the current position of the i-th iteration candidate path is determined to be T0+△T.

[0016] A further technical solution is that the path planning algorithm used is the Theta* algorithm, and the path planning algorithm is used to determine the i+1th node according to the cost function of the neighboring nodes of the i-th node, and the i-th iteration candidate path from the navigation starting point to the i+1th node includes:

[0017] The pth neighboring node with the highest cost function among the neighboring nodes of the i-th node is taken as the p-th candidate node, and the starting value of the integer parameter p is 1;

[0018] Detect whether the parent node of the p-th candidate node and the i-th node are visible; when the straight line connecting the two grid nodes does not pass through the obstacle grid, and the real-time meteorological data of the estimated arrival time of the ship at each position of the straight line connecting the two grid nodes meets the passage conditions of the ship, the two grid nodes are determined to be visible, otherwise the two grid nodes are determined to be invisible; wherein the parent node of the first node is the first node itself;

[0019] When the p-th candidate node and the parent node of the i-th node are not visible, detect whether the p-th candidate node and the i-th node are visible; when the p-th candidate node and the i-th node are visible, take the p-th candidate node as the i+1-th node, and take the i-th node as the parent node of the i+1-th node, and determine that the i-th iteration candidate path includes the path from the navigation starting point to the i-th node and the path from the i-th node to the i+1-th node; when the p-th candidate node and the i-th node are not visible, set p=p+1 and execute again the step of taking the p-th neighboring node of the i-th node from the smallest to the largest cost function as the p-th candidate node;

[0020] When the p-th candidate node and the parent node of the i-th node are visible, the p-th candidate node is taken as the i+1-th node, and the parent node of the i-th node is taken as the parent node of the i+1-th node, and the i-th iteration candidate path is determined to include the path from the navigation starting point to the parent node of the i-th node and the path from the parent node of the i-th node to the i+1-th node.

[0021] Its further technical solution is that constructing a grid map of the sea area includes: dividing the sea area into grids, and marking the grid status of the grids where the physical obstacles in the sea area are located as obstacle grids; determining the water depth data of the sea area, marking the grid status of the grids whose water depth does not meet the conditions for ship passage as obstacle grids, and constructing a grid map of the sea area.

[0022] Its further technical solution is that constructing a grid map of the sea area also includes: performing sparse processing on the constructed grid map, merging grids within a specified row and column range into one grid; and detecting the grid status of grids within the specified row and column range of the grid map, and the grid status of at least one grid within the specified row and column range of the grid map is an obstacle grid, and the merged grid is marked as an obstacle grid.

[0023] A further technical solution is to obtain an initial route from the starting point of the voyage to the target point based on all the determined nodes, including: taking the node where the target point is located as the first turning point, retrieving the parent node of each turning point as each turning point in reverse until the voyage starting point is reached, and obtaining an initial route formed by connecting several turning points in sequence;

[0024] The route and speed joint optimization method is used to optimize the initial route, including:

[0025] Redundant turning points in the initial route are eliminated according to a predetermined elimination method to complete preprocessing of the initial route to obtain the route to be optimized, and the route to be optimized is optimized based on the route to be optimized using a route speed joint optimization method.

[0026] A further technical solution is to eliminate redundant turning points in the initial route according to a predetermined elimination method, including: for two adjacent turning points on the initial route whose straight-line distance does not meet the distance requirement, namely the kth turning point and the k+1th turning point, when the kth turning point and the k+2th turning point are visible, eliminate the k+1th turning point and directly connect the kth turning point and the k+2th turning point; or, when the k-1th turning point and the k+1th turning point are visible, eliminate the kth turning point and directly connect the k-1th turning point and the k+1th turning point.

[0027] A further technical solution is to optimize the route to be optimized by using a route speed joint optimization method, including: connecting m turning points of the route to be optimized on the same great circle route, the great circle route is a great circle navigation curve of a ship from a sailing starting point to a target point, dividing the great circle route between two adjacent turning points into n reference points at equal distances, and obtaining n turning points to be optimized based on the positions of the reference points;

[0028] When optimizing the route to be optimized using the route and speed joint optimization method, m turning points and n turning points to be optimized are adjusted to optimize the route to be optimized to obtain an optimized route.

[0029] Its further technical solution is to obtain n turning points to be optimized based on the position of the reference point, including: according to the angle bisector principle, with the reference point as the foot of the perpendicular, the reference point is moved a predetermined distance in a direction perpendicular to the great circle route to obtain n turning points to be optimized.

[0030] The beneficial technical effects of this application are:

[0031] This application proposes a method for joint planning of ship routes and speeds. During the initial route planning process, obstacles and real-time weather data of each location on the ship's navigation path are detected simultaneously. This ensures that the shortest initial route from the starting point to the target point can accurately avoid obstacles and severe weather such as typhoons, greatly improving the safety of navigation and laying a solid foundation for the subsequent joint optimization of route speeds.

[0032] A detailed grid map is constructed based on ship data information, and the water depth data of the actual environment is modeled as an obstacle grid, which accurately screens out shallow water areas to ensure that dangerous areas with shallow waters can be effectively avoided when planning navigation routes.

[0033] By discretizing the continuous space of the actual environment map into a grid map, the computational complexity is simplified. The grid map is sparsely processed to reduce the grid density, which can effectively reduce the amount of algorithm calculation and achieve efficient route and speed joint optimization calculation.

[0034] The route to be optimized is obtained by eliminating redundant turning points in the initial route through a predetermined elimination method, which reduces the complexity of the route and ensures that the distance between adjacent turning points in the route is not too close, which is of great significance to the safety and accuracy of navigation. On this basis, the route and speed joint optimization algorithm is used to adjust the turning points of the route to be optimized, accurately calculate the moving direction and range of each turning point, and ensure the accuracy, smoothness and safety of route steering. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Figure 1 It is a flow chart of the joint optimization method for ship routes and speeds.

[0036] Figure 2 These are two example graphs of paths for the Theta* algorithm.

[0037] Figure 3 This is an example diagram of the Theta* algorithm searching for the initial route.

[0038] Figure 4 is the initial route with redundant nodes.

[0039] Figure 5 It is a schematic diagram of adjusting the turning point of the route to be optimized. DETAILED DESCRIPTION

[0040] The specific implementation of the present application is further described below in conjunction with the accompanying drawings.

[0041] This application discloses a method for joint planning of ship routes and speeds. Please refer to Figure 1 As shown in the flowchart, the ship route speed joint optimization method includes:

[0042] Step 1: Obtain geographical information of the sea area that the ship passes through from the starting point to the destination point through the world ocean route data, including water depth data and physical obstacles, and construct a grid map of the sea area based on the geographical information.

[0043] The geographical condition information at least includes the coverage of physical obstacles in the sea area. Physical obstacles include islands and reefs in the sea area and inaccessible areas such as the location of military restricted areas. The sea area through which the ship sails is divided into grids by using the grid map method, and the grid status of the grids where physical obstacles such as islands and reefs, military restricted areas, etc. in the sea area are located is marked as an obstacle grid, and the grid status of other grids is marked as a navigable grid.

[0044] In another embodiment, the geographical condition information also includes water depth data at different locations in the sea area. According to the water depth data, the grid status of the grid whose water depth does not meet the ship's passage conditions is marked as an obstacle grid. When the water depth of a grid is less than the ship's draft depth requirement, it is determined that the water depth of the grid does not meet the ship's passage conditions. By consulting the ship's navigation report, the relevant information of the ship can be determined, including the ship type, the ship's cargo situation, the ship's displacement, the ship's draft depth, etc., and then the ship's draft depth requirement can be determined. Through this step, the physical obstacles and shallow water areas in the navigation area are accurately screened out and modeled as obstacles to ensure that these dangerous areas can be effectively avoided when planning routes.

[0045] Considering the influence of data density on computational efficiency in environmental modeling, and the distance between adjacent grid nodes in the existing grid map is only 1.4221 nautical miles, the density of the grid in the existing grid map is too high, which will cause the path planning algorithm to consume a lot of computing time when calculating the initial route. In order to improve the computational efficiency of the path planning algorithm while ensuring the safety of route planning, in one embodiment, the constructed grid map is further sparsely processed, the grids of the grids within the specified row and column range are merged into one grid, and the grid state of the grids within the specified row and column range of the grid map is detected. When the grid state of at least one grid in the specified row and column range of the grid map is an obstacle grid, the merged grid is marked as an obstacle grid, otherwise the merged grid is marked as a navigable grid. For example, the obstacle grid in the grid map is marked as 1, the navigable grid is marked as 0, and 9 grids in every 3 rows and 3 columns are merged into 1 grid. The mark value of the 9 grids in every 3 rows and 3 columns is detected, and as long as one of the 9 grids is marked as 1, the merged grid is marked as 1. This method ensures that all obstacle areas are not ignored, reduces the amount of calculation while maintaining accurate identification of obstacles, and improves the efficiency and safety of route planning. The number of grid rows and columns included in the specified row and column range can be adjusted according to actual needs.

[0046] Step 2, initialize parameter i=1 and use the grid node where the navigation starting point is located as the first node.

[0047] Step 3, in the i-th iteration, based on the grid map and real-time meteorological data, the path planning algorithm is used to determine the i+1th node according to the cost function of the neighboring nodes of the i-th node, and the i-th iteration candidate path from the navigation starting point to the i+1th node is determined. The path planning algorithm here can select any path planning algorithm in the prior art. When the path planning algorithm searches for the i+1th node, the i-th iteration candidate path selected does not pass through the obstacle grid in the grid map, and the real-time meteorological data of the estimated arrival time of the ship at each position of the i-th iteration candidate path meets the ship's passage conditions.

[0048] When searching for the i-th iteration candidate path, it is necessary to estimate the arrival time of the ship at each position of the i-th iteration candidate path. In one embodiment, the method for estimating the arrival time is:

[0049] Determine the starting time T0 of the ship from the sailing starting point. Interpolate the i-th iteration candidate path, where the interpolation can use the linear interpolation method. Determine the length D of the navigation route between any position on the i-th iteration candidate path and the navigation starting point, and determine the estimated time △T=D / V from the navigation starting point to the current position along the i-th iteration candidate path, where V is the speed of the ship, and determine the estimated arrival time of the ship at the current position of the i-th iteration candidate path as T0+△T.

[0050] In one embodiment, the real-time wave height data of the estimated arrival time at the current position is read. When the wave height data is less than the wave height threshold, it is determined that the real-time meteorological data of the estimated arrival time of the ship at the current position meets the passage conditions of the ship. The wave height threshold here is set according to the safety requirements of the actual navigation of the ship.

[0051] Step 4, enter the i+1th iteration, repeat the iterative steps of searching for candidate paths in step 3, until the i+1th node is the target point, and obtain the initial route of the ship from the starting point to the target point based on all nodes determined by the iterative process.

[0052] Step 5, using the route and speed joint optimization method to optimize based on the initial route, to obtain the optimized route and optimized speed of the ship from the sailing starting point to the target point.

[0053] The route speed joint optimization method can construct a multi-objective optimization model including the total route length, the total sailing time, the total sailing fuel consumption, the total sailing cost, etc., and then input the nodes of the initial route and the ship speed of each segment in the initial route into the multi-objective optimization model and use particle swarm, genetic and other optimization solving algorithms to solve the problem, and the optimized route and optimized speed can be obtained. This part can adopt the existing route speed joint optimization solving method, which will not be described in detail in this embodiment.

[0054] In another embodiment, the path planning algorithm used in step 3 is the Theta* algorithm. The present application obtains an improved dynamic Theta* algorithm by real-time detection of meteorological data based on the standard Theta* algorithm. The specific steps of using the improved dynamic Theta* algorithm to determine the i+1th node according to the cost function of the neighboring nodes of the i-th node, and determining the i-th iteration candidate path from the navigation starting point to the i+1th node include:

[0055] The pth neighboring node with the highest cost function among the neighboring nodes of the i-th node is taken as the p-th candidate node, and the starting value of the integer parameter p is 1.

[0056] Check whether the p-th candidate node and the parent node of the i-th node are visible; when the straight line connecting the two grid nodes does not pass through the obstacle grid, and the real-time meteorological data of the estimated arrival time of the ship at each position of the straight line connecting the two grid nodes meet the passage conditions of the ship, the two grid nodes are determined to be visible, otherwise the two grid nodes are determined to be invisible; wherein, the parent node of the first node is the first node itself.

[0057] When the p-th candidate node and the parent node of the i-th node are not visible, check whether the p-th candidate node and the i-th node are visible; when the p-th candidate node and the i-th node are visible, take the p-th candidate node as the i+1-th node, and take the i-th node as the parent node of the i+1-th node, and determine that the i-th iteration candidate path includes the path from the navigation starting point to the i-th node and the path from the i-th node to the i+1-th node; when the p-th candidate node and the i-th node are not visible, set p=p+1 and execute again the step of taking the p-th neighboring node with the cost function from the smallest to the largest among the neighboring nodes of the i-th node as the p-th candidate node.

[0058] When the p-th candidate node and the parent node of the i-th node are visible, the p-th candidate node is taken as the i+1-th node, and the parent node of the i-th node is taken as the parent node of the i+1-th node, and the i-th iteration candidate path is determined to include the path from the navigation starting point to the parent node of the i-th node and the path from the parent node of the i-th node to the i+1-th node.

[0059] When the present application detects whether the straight connection route from the voyage starting point to the i+1th node s' is the i-th iteration candidate path, since the visual connection route from the voyage starting point to the parent node of the i-th node has been obtained when detecting the i-1th iteration candidate path, when detecting the i-th iteration candidate path, it is only necessary to accumulate the visual connection route from the parent node of the i-th node to the i+1th node to the i-1th iteration candidate path to obtain the i-th iteration candidate path. When detecting the visual connection route from the parent node of the i-th node to the i+1th node, the Theta* algorithm compares the cost functions of the two different paths from the parent node of the i-th node to the i+1th node. Figure 2 As shown, calculate the parent node s from the i-th node s start The distance cost g(s) to the i-th node s and the straight line length c(s,s') between the i-th node s and the i+1-th node s', thus obtaining the cost function f(s) = g(s) + c(s,s') of Path1, corresponding to Figure 2 (a) and Figure 2 The dotted line in (b) shows the path Path1. From the parent node s of the i-th node s start The length of the straight line to the i+1th node s' is c(s start ,s'), thus obtaining the cost function of Path2 f(s) = g(s start )+c(s start ,s'), corresponding to Figure 2 (a) and Figure 2 (b) is the path Path2 shown by the solid line.

[0060] According to the triangle inequality principle, the length of Path2 is less than or equal to the length of Path1, but Path1 is a visible path, and Path2 needs to detect the parent node s of the i-th node s start Is the i+1th node s' visible? Figure 2 As shown in (a), if the parent node s of the i-th node s start It is visible to the i+1th node s', indicating that Path2 is a visible path. The Theta* algorithm will give priority to selecting Path2 as the i-th iteration candidate path from the starting point of the voyage to the i+1th node s'. Figure 2 As shown in (b), if the parent node s of the i-th node s start If the i+1th node s' is not visible, the Theta* algorithm will select Path1 as the candidate path for the i-th iteration.

[0061] Figure 3The example of the Theta* algorithm searching for the initial route is shown. The g(s) value of each node and the parent node are marked at the grid node in the figure. In the example, the horizontal axis (1,2,3,4,5) can be understood as the longitude divided equally, and the vertical axis (A,B,C) is different dimensions. The hollow circle represents the current node, and the dotted arrow represents the node generated by the expansion process. The Theta* algorithm first expands outward from the starting point A4 as the current node, and sets the parent node of its visible neighbor node to A4 itself, such as Figure 3 (a) is shown. The requirement for visibility is that the line connecting the neighbor node and its parent node A4 does not pass through obstacles or wave height areas that exceed the set threshold. If the f(s) value of the visible neighbor node is smaller than the original value, it is added to the open list (A3, A5, B3, B4, B5), and the current node A4 is added to the closed list. In the next iteration, the node B3 with the smallest f(s) value is selected from the open list as the current node to expand its neighbor nodes, as shown in Figure 3 (b) shows that node B2 is a visible neighbor of the current node B3, and it is not visible to the parent node A4 of B3, so Theta* is calculated according to Figure 2 Path 1 in (b) updates it and sets its parent node to B3. On the other hand, nodes C2, C3, and C4 are also visible neighbors of the current node B3, but they are visible to B3’s parent node A4. Then Theta* is calculated according to Figure 2 Path 2 in (a) updates them and sets their parent node to A4. Because A4 is in the closed list, and the f(s) values ​​of A3 and B4 are greater than or equal to the corresponding values ​​of the previous iteration, the other visible neighbor nodes A4, A3 and B4 of the current node B3 are not updated. Similar to the previous step, the updated B2, C2, C3 and C4 are added to the open list, and the current node B3 is added to the closed list. Afterwards, B2 is used as the current node to expand its visible neighbor nodes, as shown in Figure 3 (c) As shown in Figure 2, A1 and A2 are visible neighbors of B2 and are not visible to B2’s parent node B3, so Theta* follows Figure 2 Path 1 in (b) updates them. If B1, C1 and B3 are visible, then Theta* follows Figure 2 Finally, C1 is selected as the node with the smallest f(s) value in the open list as the current node, and the Theta* algorithm finds a feasible path, such as Figure 3 (d) as shown.

[0062] In one embodiment, each node and its parent node on the initial path are obtained based on an improved dynamic Theta* algorithm, and the initial route of the ship from the sailing starting point to the target point is obtained based on all the determined nodes, including: taking the node where the target point is located as the first turning point, reversely retrieving the parent node of each turning point as each turning point until reaching the sailing starting point, and obtaining an initial route formed by connecting several turning points in sequence.

[0063] The initial route obtained based on the improved dynamic Theta* algorithm often has redundant turning points that are too close, such as Figure 4 Medium k and P k+1 , these redundant turning points not only increase the complexity of the navigation route but also reduce the computational efficiency. Therefore, in one embodiment, firstly, redundant turning points in the initial route are eliminated according to a predetermined elimination method to complete the preprocessing of the initial route to obtain the route to be optimized, and then the route speed joint optimization method is used to optimize the route to be optimized, which can improve the efficiency of route speed optimization. In one embodiment, the redundant turning points in the initial route are eliminated according to a predetermined elimination method, including: for two adjacent turning points whose straight-line distance on the initial route does not meet the distance requirement, the kth turning point P k and the k+1th turning point P k+1 , where the distance requirement is set according to the actual navigation requirements. k and the k+2th turning point P k+2 When the k+1th turning point P is visible, remove k+1 And directly connect the kth turning point P k and the k+2th turning point P k+2 Or, when the k-1th turning point P k-1 and the k+1th turning point P k+1 When the kth turning point P is visible, remove k And directly connect the k-1th turning point P k-1 and the k+1th turning point P k+1 Among them, the turning point P k+1 It is the direction from the starting point to the target point and the turning point P k The next turning point directly connected, turning point P k-1 It is the direction from the starting point to the target point and the turning point P k The last turning point for a direct connection.

[0064] In addition to the problem that some turning points are too dense in the initial route, there are also some turning points that are too sparse. Although the route to be optimized obtained by the preprocessing method has eliminated redundant points, the remaining nodes may still be too sparse, which will cause the ship to turn at each node position. The steering angle is too large, making it difficult to turn, and too sparse turning points will reduce the accuracy of the subsequent route speed optimization results. Therefore, before optimizing the route to be optimized using the route speed joint optimization, the turning points of the route to be optimized need to be further processed.

[0065] In one embodiment, Figure 5 As shown, the m turning points of the route to be optimized are connected to the same great circle route, and the m turning points are P1, P2, ..., P m The great circle route is a great circle navigation curve from the starting point to the destination point. The great circle route between two adjacent turning points is divided into n reference points B1, B2, ..., B n According to the angle bisector principle, with the reference point as the foot of the perpendicular, the reference point is moved a predetermined distance in a direction perpendicular to the great circle route to obtain n turning points x1, x2, ..., x n When optimizing the route to be optimized by using the route speed joint optimization method, m turning points and n turning points to be optimized are adjusted to optimize the route to be optimized to obtain the optimized route. The speeds of m+n-1 segments are adjusted to optimize the route to be optimized to obtain the optimized speed.

[0066] The above is only a preferred embodiment of the present application, and the present application is not limited to the above embodiments. It is understood that other improvements and changes directly derived or associated by those skilled in the art without departing from the spirit and concept of the present application should be considered to be included in the protection scope of the present application.

Claims

1. A method for joint planning of ship routes and speeds, characterized in that: The ship route speed joint planning method comprises: Obtaining geographical condition information of the sea area that the ship passes through from the sailing starting point to the target point, and constructing a grid map of the sea area according to the geographical condition information; Initialize parameter i=1 and use the grid node where the navigation starting point is located as the first node; In the i-th iteration, based on the grid map and the real-time meteorological data, the path planning algorithm is used to determine the i+1-th node according to the cost function of the neighboring nodes of the i-th node, and the i-th iteration candidate path from the navigation starting point to the i+1-th node is determined, the i-th iteration candidate path does not pass through the obstacle grid in the grid map, and the real-time meteorological data of the estimated arrival time of the ship at each position of the i-th iteration candidate path meets the passage conditions of the ship; Entering the i+1th iteration, until the i+1th node is the target point, an initial route of the ship from the sailing starting point to the target point is obtained based on all the determined nodes; The initial route is optimized by using a route and speed joint optimization method to obtain an optimized route and optimized speed of the ship from a sailing starting point to a target point.

2. The method for joint planning of ship routes and speeds according to claim 1, characterized in that: When the real-time wave height data of the estimated arrival time of the ship at each position of the i-th iteration candidate path is less than the wave height threshold, it is determined that the real-time meteorological data of the estimated arrival time of the ship at the current position meets the passage conditions of the ship.

3. The ship route and speed joint planning method according to claim 2 is characterized in that: The ship route speed joint planning method also includes: Determine the starting time T0 of the ship's departure from the voyage starting point; Determine by interpolation the length D of the navigation route between any position on the i-th iteration candidate path and the navigation starting point, and determine the estimated time △T=D / V for the ship to reach the current position from the navigation starting point along the i-th iteration candidate path, where V is the speed of the ship; The estimated arrival time of the ship at the current position of the i-th iteration candidate path is determined to be T0+ΔT.

4. The ship route and speed joint planning method according to claim 1 is characterized in that: The path planning algorithm used is the Theta* algorithm. The path planning algorithm is used to determine the i+1th node according to the cost function of the neighboring nodes of the i-th node, and to determine the i-th iteration candidate path from the navigation starting point to the i+1th node, including: The pth neighboring node with the highest cost function among the neighboring nodes of the i-th node is taken as the p-th candidate node, and the starting value of the integer parameter p is 1; Detect whether the p-th candidate node and the parent node of the i-th node are visible; when the straight line connecting the two grid nodes does not pass through the obstacle grid, and the real-time meteorological data of the estimated arrival time of the ship at each position of the straight line connecting the two grid nodes meets the passage conditions of the ship, the two grid nodes are determined to be visible, otherwise, the two grid nodes are determined to be invisible; wherein the parent node of the first node is the first node itself; When the p-th candidate node and the parent node of the i-th node are not visible, detect whether the p-th candidate node and the i-th node are visible; when the p-th candidate node and the i-th node are visible, use the p-th candidate node as the i+1-th node, and use the i-th node as the parent node of the i+1-th node, and determine that the i-th iteration candidate path includes a path from the navigation starting point to the i-th node and a path from the i-th node to the i+1-th node; when the p-th candidate node and the i-th node are not visible, set p=p+1 and execute again the step of using the p-th neighboring node of the i-th node from the smallest to the largest cost function as the p-th candidate node; When the p-th candidate node and the parent node of the i-th node are visible, the p-th candidate node is used as the i+1-th node, and the parent node of the i-th node is used as the parent node of the i+1-th node, and the i-th iteration candidate path is determined to include the path from the navigation starting point to the parent node of the i-th node and the path from the parent node of the i-th node to the i+1-th node.

5. The ship route speed joint optimization method according to claim 1 is characterized in that: The step of constructing the grid map of the sea area comprises: Dividing the sea area into grids, and marking the grid status of the grid where the physical obstacle in the sea area is located as an obstacle grid; The water depth data of the sea area is determined, and the grid status of the grids whose water depth does not meet the ship passage condition is marked as obstacle grids, so as to construct a grid map of the sea area.

6. The method for joint planning of ship routes and speeds according to claim 5 is characterized in that: The step of constructing the grid map of the sea area further comprises: The constructed grid map is subjected to sparse processing, and grids within a specified range of rows and columns are merged into one grid; and the grid states of the grids within the specified range of rows and columns of the grid map are detected, and the grid state of at least one grid within the specified range of rows and columns of the grid map is an obstacle grid, and the merged grid is marked as an obstacle grid.

7. The method for joint planning of ship routes and speeds according to claim 4, characterized in that: Based on all the determined nodes, an initial route of the ship from the sailing starting point to the target point is obtained, including: taking the node where the target point is located as the first turning point, retrieving the parent node of each turning point as each turning point in reverse order until the sailing starting point is reached, and obtaining the initial route formed by connecting several turning points in sequence; The optimization based on the initial route using the route and speed joint optimization method includes: Redundant turning points in the initial route are eliminated according to a predetermined elimination method to complete preprocessing of the initial route to obtain a route to be optimized, and the route to be optimized is optimized based on the route to be optimized using a route and speed joint optimization method.

8. The method for joint planning of ship routes and speeds according to claim 7, characterized in that: Eliminating redundant turning points in the initial route according to a predetermined elimination method, including: For the two adjacent turning points, the kth turning point and the k+1th turning point, whose straight-line distance on the initial route does not meet the distance requirement, when the kth turning point and the k+2th turning point are visible, the k+1th turning point is eliminated and the kth turning point and the k+2th turning point are directly connected; or, when the k-1th turning point and the k+1th turning point are visible, the kth turning point is eliminated and the k-1th turning point and the k+1th turning point are directly connected.

9. The ship route and speed joint planning method according to claim 7 is characterized in that: The optimization based on the route to be optimized by using the route speed joint optimization method includes: Connecting the m turning points of the route to be optimized on the same great circle route, the great circle route is a great circle navigation curve of the ship from the navigation starting point to the target point, dividing the great circle route between two adjacent turning points into n reference points with equal distance, and obtaining n turning points to be optimized based on the positions of the reference points; When optimizing the route to be optimized using the route and speed joint optimization method, the m turning points and the n turning points to be optimized are adjusted to optimize the route to be optimized to obtain the optimized route.

10. The method for joint planning of ship routes and speeds according to claim 9, characterized in that: The obtaining of n turning points to be optimized based on the position of the reference point comprises: According to the angle bisector principle, with the reference point as the foot of the perpendicular, the reference point is moved a predetermined distance in a direction perpendicular to the great circle route to obtain n turning points to be optimized.

Images