Localized ship path planning method based on graph theory

Abstract

The invention discloses a local ship route planning method based on a graph theory, and relates to automatic route planning. Collecting historical AIS data of a ship, and constructing a historical track data set of the ship after preprocessing; clustering track points and tracks in the data set, identifying key waypoints and channels, and constructing an offshore channel directed graph network by taking the key points as nodes and the key channels as directed edges; according to historical trajectory data, similar legs of each directed edge in the channel network are identified, the average speed is used as the estimated passing speed of the edge, and the passing time, the passing distance and the passing probability are calculated to serve as the path cost. Calculating an optimal path from the current point of the ship to the destination under different path costs by a path search algorithm; when the vehicle passes through the non-navigation area, an automatic path avoiding algorithm is adopted for avoiding; and the overall path is smoothed to obtain a planned path, graphic representation of the ship trajectory and construction of a sea channel network are completed, autonomous planning of the localized ship path is realized, and the intelligence and efficiency of path planning are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of automatic route planning, and in particular to a localized ship path planning method based on graph theory. Background Art

[0002] Shipping is an important part of global trade and transportation, and ship path planning is the key to ensuring the efficiency, safety and economy of maritime navigation. Reliable planning relies on massive amounts of data. However, factors such as the complexity of the marine environment and the complexity of ship navigation behavior will increase the uncertainty of the data. It is a challenge to efficiently process and analyze large amounts of dynamic data. In addition, complex marine terrain and obstacles have put forward higher requirements for ship path planning. Some existing path planning methods have certain limitations in accuracy and computational complexity. They are difficult to operate efficiently in large-scale data and real-time applications. The planned paths obtained are often not applicable to actual operations. In reality, they still rely on the driver's experience to correct the planned paths.

[0003] In recent years, automated ship path planning methods based on satellite data and numerical simulation have been widely used. How to efficiently integrate and utilize data has become the key to ship path planning. Summary of the invention

[0004] In view of the above-mentioned problems of path planning efficiency and reliability, the present invention provides a localized ship path planning method based on graph theory. By improving data processing technology and path planning algorithms through graph theory, the real-time response capability of the system is enhanced, and the efficiency and reliability of path planning can be significantly improved. Combined with path localization measures, a planned path that is more in line with actual operations can be finally obtained.

[0005] To achieve the above object, the present invention adopts the following technical solutions:

[0006] A localized ship path planning method based on graph theory includes the following steps:

[0007] S1: Collect historical AIS data of ships, pre-process the historical AIS data of ships, extract ship tracks and obtain historical track data, and construct a ship historical track data set;

[0008] S2: using the ship historical trajectory data set constructed in step S1, clustering the trajectory points and trajectories in the data set through a clustering algorithm to obtain key waypoints and key waterways, and analyzing the historical trajectories to determine the connection relationship between the key waypoints, using the key waypoints as nodes and the key waterways as directed edges to connect the nodes, and establishing a directed graph network of sea waterways; using the historical trajectory data to calculate the key waypoints and directed edge weight information, calculate the directed edge travel distance and estimated travel speed, and thus calculate the travel time;

[0009] S3: Using the directed graph network information of the sea route established in step S2, the optimal path from the current point to the destination under different path costs is searched and calculated by a path search algorithm based on graph theory;

[0010] S4: Use the information of the optimal path obtained in step S3 to localize the path, avoid the obstacles through the path automatic avoidance algorithm, and smooth the overall path through B-spline interpolation to obtain a final path planning result that is passable.

[0011] Furthermore, the preprocessing in step S1 includes abnormal data elimination, condition screening, trajectory extraction, and downsampling operations.

[0012] First, delete the data with null values ​​and data that do not conform to the logical value range and determine the longitude and latitude range of the data;

[0013] Then, multiple ship type trajectory data are divided according to the ship type entries in the AIS data, and the data of a specific ship type is selected for trajectory extraction;

[0014] Finally, linear interpolation is used to downsample the trajectories.

[0015] Furthermore, the step S2 comprises the following steps:

[0016] First, the key point extraction parameters are initialized, including the minimum steering angle and the minimum parking time. When the trajectory angle is less than the minimum steering angle or the duration of a small change in the trajectory point position exceeds the minimum parking time, these trajectory points are judged as key points.

[0017] Secondly, the clustering parameters, including the maximum distance threshold and the minimum distance threshold, are initialized as the distance constraints between key points, and the obtained cluster centers are used as key waypoints.

[0018] Then, the historical trajectory is analyzed based on the key waypoints, the connection relationship between the key waypoints is determined, and the key waterways are obtained. With the key waypoints as nodes and the key waterways as directed edges connecting the nodes, a directed graph network of sea waterways is established.

[0019] After that, the geographical distance of the directed edge is calculated, and similar segments with the same direction and within the preset range of each directed edge are identified based on the historical trajectory data. The average speed of these similar segments is calculated as the estimated speed of the directed edge, thereby calculating the travel time. The number of historical trajectories of the key waypoints is used as the node weight, and the proportion of the number of trajectories of each outgoing edge in the node to the total number of outgoing trajectories is used as the directed edge weight.

[0020] Furthermore, step S3 includes the following steps:

[0021] First, the path costs of all directed edges in the route map network are calculated. The path costs include the travel probability, travel time or travel distance of the path, where the travel probability is calculated by the directed edge weights.

[0022] Secondly, according to the current point and destination of the ship, the path search algorithm is used to search for the optimal path under different path costs.

[0023] Furthermore, the step S4 comprises the following steps:

[0024] First, when passing through a non-navigation area, an automatic avoidance algorithm for the non-navigation area is used to avoid the path; if the path passes through a non-navigation area, the perpendicular bisector of the intersection of the path and the area is obtained, and the intermediate nodes are searched on the perpendicular bisector in a direction closer to the edge of the area with a preset step size, and the intermediate nodes are connected to the two end points to create a new path. The above search operation is repeated until the new path no longer passes through the non-navigation area.

[0025] Secondly, the intermediate nodes within the preset range that do not have non-navigable areas and whose weights are lower than the preset threshold are deleted one by one according to the path direction. If deleting a node causes the path to pass through the non-navigable area again, the path is restored to the state before deletion. Linear interpolation is used to add control points between nodes whose distance exceeds the preset value, and then B-spline interpolation is used to smooth the path.

[0026] After that, a buffer of a certain width is established according to the path before smoothing, and the non-navigation area in the buffer is removed. The buffer is used to limit the offset of the path node after smoothing and avoid repeated operations after smoothing.

[0027] Finally, the path planning results are obtained and the travel distance and time of the planned path are recalculated.

[0028] Compared with the prior art, the present invention has the following beneficial effects:

[0029] The graph-theory-based localized ship path planning scheme provided by the present invention applies probabilistic graph theory to AIS data, uses graph theory to construct a directed graph network of sea routes, uses nodes and directed edges to represent shipping key points and directional channels respectively, and uses weight information to represent their busyness, abstractly represents the historical trajectory data of ships, and can accurately reflect the navigation laws of ships; combined with the path localization method, it can achieve feasible path planning that is more in line with actual navigation laws. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] Figure 1 It is a general flow chart of the localized ship path planning method based on graph theory of the present invention;

[0031] Figure 2 A schematic diagram of a directed graph network of a sea route established based on ship AIS data in an embodiment of the present invention;

[0032] Figure 3 A schematic diagram of an automatic avoidance algorithm for non-navigation areas in localization of the present invention;

[0033] Figure 4 It is a schematic diagram of path smoothing in the localization of the present invention;

[0034] Figure 5 It is a partial schematic diagram of the planning path of the localized ship path planning method based on graph theory in an embodiment of the present invention;

[0035] Figure 6 Schematic diagram of planning paths under three path costs of a localized ship path planning method based on graph theory in an embodiment of the present invention. DETAILED DESCRIPTION

[0036] The present invention will be further described in detail below with reference to the accompanying drawings and specific implementation examples.

[0037] See also Figure 1 The present invention provides a localized ship path planning method based on graph theory, comprising the following steps:

[0038] S1: AIS data cleaning and track extraction: pre-process the historical AIS data of the ship, extract the ship track and obtain the historical track data; the pre-processing includes abnormal data removal, condition screening, track extraction, downsampling, etc.

[0039] The specific implementation of step S1 in this embodiment includes the following sub-steps:

[0040] First, the data with null values ​​and data that do not conform to the logical value range are deleted and the longitude and latitude range of the data are determined. The data of a specific ship type is selected for extracting the trajectory, where the speed value exceeds 30 knots, the longitude value exceeds the range of -180° to 180°, and the latitude value exceeds the range of -90° to 90°. It is considered that it does not conform to the logical value range. In this embodiment, the longitude and latitude (4°, 59°) and longitude and latitude (17°, 53°) are used as the upper left corner and lower right corner of the geographic map to determine the longitude and latitude range of the AIS data, and the data of the ship type Tanker is used to extract the trajectory.

[0041] Secondly, multiple ship type trajectory data are divided according to the ship type entries in the AIS data, the data are grouped according to the ship MMSI, sorted by time, and the trajectory is segmented at the point where the time interval corresponding to the adjacent trajectory coordinate points is greater than the preset time interval threshold, and the trajectory whose duration is less than the preset trajectory duration threshold or the number of trajectory coordinate points is less than the preset trajectory coordinate point threshold is removed. For example, the preset time interval threshold can be set to 2h, the preset trajectory duration threshold can be set to 6h, and the preset trajectory coordinate point threshold is 20.

[0042] Afterwards, the data is downsampled using linear interpolation at a certain time interval. For example, the time interval may be set to 300 seconds.

[0043] Finally, set the latitude and longitude, speed over ground, and heading over ground data with a certain effective resolution. For example, the resolution of the latitude and longitude, speed over ground, and heading over ground data can be set to 0.01°, 1 knot, and 1°, respectively.

[0044] In this process, ship trajectories are extracted from massive data, abnormal data are excluded, and data resolution is reduced to reduce the data volume, providing data support for the construction of a directed graph.

[0045] S2: Key point clustering and route network construction: Using the historical trajectory data set constructed in step S1, obtain key waypoints through clustering, and analyze the historical trajectory to determine the connection relationship between the key waypoints, take the key waypoints as nodes, and use the key waterways as directed edges to connect the nodes, and establish a directed graph network of sea routes; use the historical trajectory data to calculate the key waypoints and directed edge weight information, calculate the directed edge travel distance and estimated travel speed, and thus calculate the travel time;

[0046] The specific implementation of step S2 in this embodiment includes the following sub-steps:

[0047] First, the key point extraction parameters are initialized, including the minimum steering angle and the minimum parking time. When the trajectory angle is less than the minimum steering angle or the duration of the small change in the trajectory point position exceeds the minimum parking time, these trajectory points are determined to be key points. In this embodiment, the minimum steering angle and the minimum parking time can be set to 45° and 5 minutes respectively.

[0048] Secondly, the clustering parameters are initialized, including the maximum distance threshold and the minimum distance threshold, as the distance constraints between the key points, and the obtained cluster centers are used as the key waypoints. In this embodiment, the maximum distance threshold and the minimum distance threshold can be set to 20km and 5km respectively.

[0049] Then, the historical trajectory is analyzed based on the key waypoints, the connection relationship between the key waypoints is determined, and the key waterways are obtained. With the key waypoints as nodes and the key waterways as directed edges connecting the nodes, a directed graph network of sea waterways is established.

[0050] After that, the geographical distance of the directed edge is calculated, and similar segments with the same direction and within the preset range of each directed edge are identified based on the historical trajectory data. The average travel speed of these similar segments is calculated as the estimated travel speed of the directed edge, thereby calculating the travel time. The number of historical trajectories of the key waypoints is used as the node weight, and the proportion of the number of trajectories of each outgoing edge in the key point to the total number of trajectories of the outgoing edges is used as the weight of the directed edge. Exemplarily, the preset range can be set to a circle with a radius of 5 km with the two endpoints of the directed edge as the center, and similar segments are determined by finding trajectory points that fall within the preset range.

[0051] In this process, the historical trajectory dataset is used to mine key waypoints, i.e., busy maritime traffic fortresses, such as turning points or strait mouths, and these waypoints are connected through key waterways to form a route network based on historical data. The obtained directed edge travel time, travel distance and weight information lays the foundation for subsequent path finding cost calculation and path search.

[0052] A schematic diagram of a directed graph network of a sea route established based on ship AIS data in an embodiment of the present invention is shown in FIG. Figure 2 ,The black nodes are the key waypoints obtained by clustering, and the blue lines are the key channels after trajectory clustering. The waypoints are connected by these directed channels to form a maritime route network.

[0053] S3: Optimal path search algorithm: Using the directed graph network information of the sea route established in step S2, a path search algorithm is used to search for the optimal path from the current point to the destination.

[0054] The specific implementation of step S3 in this embodiment includes the following sub-steps:

[0055] First, calculate the path cost of all directed edges in the route map network. The cost can be the travel probability, travel time or travel distance. The probability cost is obtained by converting the directed edge weight information. The formula is as follows:

[0056] w′(u,v)=-log(w(v,v))

[0057] Where w′(u, v) is the cost from node u to node v, and w(u, v) is the weight of the directed edge between node u and node v, which is determined by the travel probability of each trajectory diversion.

[0058] Secondly, find the nodes closest to the starting point and the expected end point respectively, and calculate the total probability cost of all possible paths between the two nodes. The formula is as follows:

[0059] s(v1,v n )=w′(v1, v2)+w′(v2, v3)+w′(v3, v4)+…+w′(v n-1 , vn )

[0060] In the formula, s(v1,v n ) is nodes v1 to v n The total probability cost of the path.

[0061] Then, calculate the total distance cost and total time cost of all possible paths, the formula is as follows:

[0062] d(v1,v n )=d(v1, v2)+d(v2, v3)+d(v3, v4)+…+d(v n-1 , v n )

[0063] t(v1,v n )=t(v1, v2)+t(v2, v3)+t(v3, v4)+…+t(v n-1 , v n )

[0064] In the formula, d(v1,v n ) is nodes v1 to v n The total path distance cost, t(v1,v n ) is nodes v1 to v n The total distance cost of the path.

[0065] Afterwards, the Dijkstra path search algorithm based on graph theory is used to search for the optimal path under different path costs.

[0066] In this process, the path search algorithm can find the shortest time path, shortest distance path and maximum probability path from the current point to the destination, which correspond to the path finding results with the minimum cost. The route map only needs to be constructed once, and subsequent operations are all performed on this map, which greatly improves the efficiency of path planning.

[0067] S4: Ship path localization: Using the information of the optimal path obtained in step S3, the final path planning result is obtained through the localization method of the path automatic avoidance algorithm and the B-spline interpolation path smoothing.

[0068] In this embodiment, the schematic diagram of the automatic avoidance algorithm for non-navigation areas in localization is as follows: Figure 3 As shown, the blue polygon O is the non-navigation area.<U,V> The original path from node U to node V is searched for intermediate nodes on the vertical line according to a certain step length to avoid the non-navigation area, and P1 and P2 are obtained, where P2 is the first intermediate node that meets the avoidance condition. The connection between nodes U and V and the intermediate nodes is created to obtain a new path<U,P2> and <P2,V>; the schematic diagram of path smoothing is as follows Figure 4 As shown, Figure 4The narrow area formed by the two non-navigation areas O1 and O2 represents the narrow sea area that may appear in the actual navigation environment. The local path passing through the area is generated by connecting V1, V2 and V3 in sequence. The B-spline interpolation result is represented by a curve passing through each point. The buffer zone used to limit the range of the smoothed curve is represented by a gray dotted line range. The specific implementation of step S4 includes the following sub-steps:

[0069] First, when passing through a non-navigation area, the non-navigation area automatic avoidance algorithm is used for avoidance; if the path passes through a non-navigation area, the perpendicular bisector of the intersection of the path and the area is obtained, and the middle node is searched on the perpendicular bisector in the direction closer to the edge of the area with a preset step length, and the middle node is connected to the two end points to create a new path, and the above search operation is repeated until the new path no longer passes through the non-navigation area. For example, the preset step length can be set to 200m.

[0070] Secondly, delete the intermediate nodes within the preset range that do not have non-navigation areas and whose weights are lower than the preset threshold one by one according to the path direction. If deleting a node causes the path to pass through the non-navigation area again, the path is restored to the previous state after deletion. Linear interpolation is used to add control points between nodes whose distance exceeds the preset value, and then B-spline interpolation is used to smooth the path. For example, the node preset range can be set to a circle with a radius of 5km with the node coordinates as the center, the weight preset threshold can be set to 2000, and the linear interpolation distance preset threshold can be set to 40km.

[0071] Afterwards, a buffer of a certain width is established according to the path before smoothing, and the non-navigation area in the buffer is removed. The buffer is used to limit the offset of the path node after smoothing and avoid repeated operations after smoothing. For example, the buffer width can be set to 1 km.

[0072] Finally, the path planning results are obtained and the travel distance and time of the planned path are recalculated.

[0073] In this process, the automatic avoidance algorithm for non-navigational areas is used to avoid non-navigational areas that may be encountered by the path in step S3, ensuring the passability of the planned path. The purpose of deleting intermediate nodes is to reduce the possibility of passing through turning points with low importance, while reducing the travel time and distance, and not affecting the original path too much. Smoothing the path can avoid excessive corners, making the planning results more in line with ship dynamics and more in line with actual operations. The localization method in this step adjusts the results of the path search algorithm to ensure that the planned path can be efficiently generated in a complex marine environment.

[0074] Figure 5A partial schematic diagram of the planned path of the localized ship path planning method based on graph theory in an embodiment of the present invention is given. The red broken line represents the local result of the path planning from the starting point to the end point in step S3, and the green curve is the local path after the result is localized in step S4. As can be seen from the figure, the path planned by the red broken line will pass through non-navigation areas such as islands, and cannot maintain a safe distance from the land, posing a high safety risk. The localized green path effectively avoids the non-navigation area and maintains a safe distance from the land. At the same time, it is smoother at the turn, which is in line with the dynamic characteristics of the ship.

[0075] Figure 6 A schematic diagram of the planned paths under three path costs of the localized ship path planning method based on graph theory in an embodiment of the present invention is given, and the red nodes represent the starting point and the end point of the ship. In this embodiment, the ship sails from the south to the north, and the optimal paths under three path costs are obtained based on the maritime route network, which are the shortest time, shortest distance and maximum probability paths. Finally, after the path is localized in step S4, the purple, green and orange curves represent the final path results of the shortest time, shortest distance and maximum probability, respectively.

[0076] The present invention provides a localized ship path planning method based on graph theory, which systematically processes the historical AIS data of the ship to construct an accurate directed graph network of sea routes, and uses the network to achieve efficient and accurate path planning. Specifically, the method includes four main steps: data preprocessing, key waypoint extraction and directed graph construction, path search, and path optimization and smoothing. In the data preprocessing stage, by cleaning, screening and downsampling the massive AIS data, abnormal data is removed and the data resolution is reduced, thereby effectively reducing the amount of data and providing high-quality data support for subsequent steps. In the key waypoint extraction and directed graph construction stage, the key waypoints with heavy traffic are mined by a clustering algorithm, and a directed graph network is established based on historical trajectory data. At the same time, the weight information, travel distance and estimated travel speed of the key waypoints and directed edges are calculated, providing a rich information basis for path search. In the path search stage, by calculating the path cost and adopting a suitable path search algorithm, the optimal path from the current point to the destination can be quickly found, including the shortest time path, the shortest distance path and the maximum probability path, etc., greatly improving the efficiency of path planning. During the path optimization and smoothing stage, the path is optimized and smoothed in one step through the automatic avoidance algorithm for non-navigation areas and the B-spline interpolation path smoothing technology to ensure the feasibility and practicality of the planned path, while making the path more in line with the ship's dynamic characteristics and in line with actual operational needs.

[0077] In summary, the graph-theory-based localized ship path planning method proposed in the present invention has the advantages of high efficiency, accuracy, and strong practicality, and has broad application prospects in the fields of marine transportation, ship navigation, etc.

[0078] The above embodiments are only preferred embodiments of the present invention and cannot be considered to limit the scope of the present invention. All equivalent changes and improvements made within the scope of the present invention should still fall within the scope of the present invention.

Claims

1. A localized ship path planning method based on graph theory, Features The following steps are involved: S1: Collect historical AIS data of ships, pre-process the historical AIS data of ships, extract ship tracks and obtain historical track data, and construct a ship historical track data set; S2: using the ship historical trajectory data set constructed in step S1, clustering the trajectory points and trajectories in the data set through a clustering algorithm to obtain key waypoints and key waterways, and analyzing the historical trajectories to determine the connection relationship between the key waypoints, using the key waypoints as nodes and the key waterways as directed edges to connect the nodes, and establishing a directed graph network of sea waterways; using the historical trajectory data to calculate the key waypoints and directed edge weight information, calculate the directed edge travel distance and estimated travel speed, and thus calculate the travel time; S3: Using the directed graph network information of the sea route established in step S2, the optimal path from the current point to the destination under different path costs is searched and calculated by a path search algorithm based on graph theory; S4: Use the information of the optimal path obtained in step S3 to localize the path, avoid the obstacles through the path automatic avoidance algorithm, and smooth the overall path through B-spline interpolation to obtain a final path planning result that is passable.

2. According to the graph theory-based localized ship path planning method of claim 1, Features The preprocessing in step S1 includes abnormal data removal, condition screening, trajectory extraction, and downsampling operations; first, the data with null values ​​and data that do not conform to the logical value range are deleted and the longitude and latitude range of the data is determined, and then multiple ship type trajectory data are divided according to the ship type entries in the AIS data, and the data of a specific ship type is selected for trajectory extraction, and then linear interpolation is used to perform trajectory downsampling.

3. According to the graph theory-based localized ship path planning method of claim 1, Features The implementation of step S2 includes the following steps: (1) Initializing the key point extraction parameters, including the minimum steering angle and the minimum parking time. When the trajectory angle is less than the minimum steering angle or the duration of the small change in the trajectory point position exceeds the minimum parking time, these trajectory points are determined to be key points; (2) Initialize clustering parameters, including the maximum distance threshold and the minimum distance threshold, as the distance constraints between key points, and use the obtained cluster centers as key waypoints; (3) Analyze the historical trajectory based on key waypoints, determine the connection relationship between key waypoints, and obtain key waterways; use key waypoints as nodes and key waterways as directed edges to connect nodes to establish a directed graph network of sea waterways; (4) Calculate the geographic distance of the directed edge, identify similar segments that are within the preset range of each directed edge and have the same direction based on the historical trajectory data, calculate the average travel speed of these similar segments, and use it as the estimated travel speed of the directed edge, thereby calculating the travel time; the number of historical trajectories of the key waypoints is used as the node weight, and the ratio of the number of trajectories of each outgoing edge in the node to the total number of outgoing trajectories is used as the directed edge weight.

4. According to the graph theory-based localized ship path planning method of claim 1, Features The implementation of step S3 includes the following steps: (1) Calculate the path cost of all directed edges in the route map network. The path cost includes the path's travel probability, travel time, or travel distance. The travel probability is calculated based on the directed edge weights. (2) Based on the current point and destination of the ship, the path search algorithm is used to search for the optimal path under different path costs.

5. According to claim 1, a localized ship path planning method based on graph theory, Features The implementation of step S4 includes the following steps: (1) When passing through a non-navigation area, the non-navigation area automatic avoidance algorithm is used for avoidance; if the path passes through a non-navigation area, the perpendicular bisector of the intersection of the path and the area is obtained, and the intermediate node is searched on the perpendicular bisector in a direction closer to the edge of the area with a preset step size, and the intermediate node is connected to the two end points to create a new path, and the above search operation is repeated until the new path no longer passes through the non-navigation area; (2) Delete intermediate nodes within a preset range that do not have non-navigable areas and whose weights are lower than a preset threshold one by one according to the path direction; if deleting a node causes the path to pass through a non-navigable area again, restore the path to the state before deletion; between nodes whose distance exceeds a preset value, use linear interpolation to add control points, and then use B-spline interpolation to smooth the path; (3) A buffer of a certain width is established based on the path before smoothing, and the non-navigation area in the buffer is removed; the buffer is used to limit the offset of the path node after smoothing and avoid repeated operations after smoothing; (4) Obtain the path planning results and recalculate the travel distance and time of the planned path.

Images