A path planning method based on information grid division

Abstract

The present invention discloses a path planning method based on information grid division, which includes constructing a grid-based search environment and initializing the starting point, ending point, and navigation costs of nodes in the grid; defining a cost function from a node to the ending point, and starting from the ending point, calculating the cost and path according to a reverse search strategy; detecting environmental changes and updating the navigation costs of nodes affected by the environmental changes; recursively updating the navigation costs of adjacent nodes of the affected nodes and their costs to the ending point; updating the globally optimal path, and further optimizing the path in combination with the navigation characteristics of the ship to generate executable navigation instructions. By introducing an incremental update strategy and a dynamic cost function model, the present invention effectively improves the path planning efficiency of the ship in a dynamic environment, can quickly respond to changes in obstacles, provides an efficient and safe navigation path for the ship, significantly improves the execution efficiency of related tasks, and realizes intelligent ship navigation and sea area management applications.

Description

Technical Field

[0001] The present invention relates to the field of software technology, and in particular to a path planning method based on information grid division. Background Art

[0002] With the rapid development of the global shipping industry and the continuous increase in maritime traffic volume, the importance of vessel path planning in the maritime field has become increasingly prominent. Vessel path planning is not only related to transportation efficiency but also involves multiple key issues such as navigation safety, environmental protection, and energy consumption. Effective path planning can help vessels select the optimal route, reduce fuel consumption, reduce carbon emissions, and avoid dangerous areas to ensure navigation safety. However, in practical applications, the complex and changeable marine environment poses great challenges to path planning. These challenges mainly come from the distribution of marine obstacles, the dynamic changes of weather and tides, and the influence of ocean currents and waves, which will significantly increase the uncertainty and risk during navigation.

[0003] Existing path planning technologies are mainly based on graph theory (such as A* algorithm, Dijkstra algorithm) or geometric algorithms, and these methods have good applicability in static or idealized environments. However, when facing a complex dynamic marine environment, their limitations gradually become apparent. For example, the real-time changes of marine obstacles (such as other vessels, buoys, rocks, and channel restrictions), as well as the dynamic characteristics of weather and tides, often make it difficult for traditional methods to quickly update the path planning results. In addition, these methods usually ignore the dynamic attributes of the marine environment such as ocean currents, wind and waves, and the dynamic characteristics of vessels in different navigation states when modeling, resulting in insufficient accuracy and practical feasibility of the planned path. In practical applications, this deficiency may lead to the inability of path planning to respond to environmental changes in a timely manner, thus increasing the risk of vessel collision or reducing navigation efficiency.

[0004] In addition, current research on path planning mostly focuses on specific application scenarios and fails to fully consider the global dynamic characteristics of the marine environment (such as ocean currents, weather changes, etc.) and the dynamic characteristics of vessels in maritime path planning, resulting in inaccurate path calculation results and unable to ensure high navigation efficiency and safety of vessels in a dynamic environment. For example, when dealing with tidal changes or sudden bad weather, traditional path planning technologies may take a long time to recalculate the path, making it difficult to meet the needs of vessels for dynamic route adjustment, thus affecting the overall transportation efficiency and safety. Therefore, how to perform efficient, accurate, and real-time path planning in a complex marine environment remains an urgent technical problem to be solved. Summary of the Invention

[0005] Object of the Invention: The object of the present invention is to provide a path planning method based on information grid division.

[0006] Technical solution: The path planning method based on information grid division according to the present invention includes the following steps:

[0007] (1) Grid division and node cost initialization: Construct a grid-based search environment, and initialize the starting point, ending point, and the navigation cost of nodes in the grid;

[0008] (2) Cost function definition and path search: Define the cost function from a node to the ending point, and starting from the ending point, calculate the cost and path according to the reverse search strategy;

[0009] (3) Dynamic environment detection and cost update: Detect changes in the environment, and update the node costs affected by the environmental changes;

[0010] (4) Incremental cost update: Recursively update the navigation cost of adjacent nodes of the affected nodes and their costs to the ending point;

[0011] (5) Path output and navigation optimization: Update the globally optimal path, and further optimize the path in combination with the ship navigation characteristics to generate executable navigation instructions.

[0012] Further, the step (1) includes dividing the target navigation area into equilateral square grid nodes, and each grid node represents a small area of the actual sea area; marking whether each grid cell is impassable, and if so, setting its navigation cost to Otherwise, set the navigation cost of the grid according to the environmental factors and safety factors of the grid.

[0013] Further, the step (2) includes defining the cost function and initializing the node costs, starting from the ending point, sequentially updating the costs of adjacent nodes, and then starting from the ending point, recursively backtracking the path with the minimum cost until the starting point.

[0014] Further, the cost function definition and path search in the step (2) include:

[0015] Define the starting point and the ending point ;

[0016] Define the cost function : The cost spent by the node to the ending point is calculated as follows:

[0017]

[0018] Among them, represents the minimum cost from the node to the ending point and is equal to ; Indicates the estimated value of the minimum cost from the node to the end point is calculated as follows:

[0019]

[0020] Wherein, is the adjacent node of the node and is the set of adjacent nodes. is the navigation cost from the node to the node When is updated, will be updated together. Initialize , initialize the remaining nodes , and add the node to the priority queue;

[0021] Select the node with the minimum cost from the priority queue for processing. If , then update to , and then traverse all adjacent nodes , and update their according to the following formula:

[0022]

[0023] And add all adjacent nodes to the priority queue. If , then mark the node as consistent and remove it from the priority queue;

[0024] Repeat the above update process until the priority queue is empty and all nodes reach a consistent state, and generate a globally optimal path by backtracking from the starting point.

[0025] Furthermore, step (3) includes using a real-time sensor or a maritime dynamic data monitoring system to continuously detect environmental changes affecting ship navigation in the sea area. If the environment of some nodes in the grid changes, then mark these nodes as inconsistent states, recalculate the navigation costs of these nodes, and then recalculate the of these nodes according to formula (2), and finally add them to the priority queue.

[0026] Furthermore, the inconsistent state means that the current cost value of the node needs to be re-evaluated due to environmental changes, that is .

[0027] Furthermore, step (4) includes selecting the node with the minimum cost from the priority queue​​​​​​​​​​​​​​​​​​ Update the cost value step by step. First, check the consistency; then propagate the update. If a change occurs, propagate its influence to all adjacent nodes and update according to formula (3) , and add all adjacent nodes to the priority queue; finally, repeat selecting the node with the minimum cost from the priority queue and updating until all nodes reach a consistent state, that is, until the priority queue is empty.

[0028] Furthermore, the checking of consistency refers to checking whether the and of the grid nodes are equal. If not, update to .

[0029] Furthermore, step (5) includes generating a path with the minimum cost according to the calculated cost value; then further optimizing the generated path according to the actual situation of the ship; finally, converting the optimized path into navigation coordinates in the actual sea area to generate an executable navigation instruction.

[0030] Furthermore, the path with the minimum cost refers to starting from the starting point according to the final cost value map and tracing back to the end point in reverse to generate a globally optimal path.

[0031] Beneficial effects: Compared with the prior art, the present invention has the following remarkable advantages: By introducing an incremental update strategy and a dynamic cost function model, the present invention effectively improves the path planning efficiency of ships in a dynamic environment. Especially in a complex sea area environment, it can quickly respond to changes in obstacles, provide an efficient and safe navigation path for ships, significantly improve the execution efficiency of related tasks, and realize intelligent ship navigation and sea area management applications. Brief Description of the Drawings

[0032] Figure 1 is a flowchart of the present invention. Detailed Embodiment

[0033] The technical solution of the present invention will be further described below with reference to the drawings.

[0034] The present invention first divides the map into a grid structure, initializes the starting point and the end point, and defines the cost of each node in the grid according to the attributes of each node such as environmental factors and safety factors. Then, a cost function is defined, and the cost required for each node to reach the end point is calculated according to the cost function, and the minimum cost path from the starting point to the end point is recorded. Then, the environmental change is detected. When the environment changes, update the cost of the affected nodes and recursively recalculate the cost of the affected nodes to reach the end point. Finally, update the globally optimal path and optimize the navigation path according to the actual situation of the ship.

[0035] To better illustrate the technical content of the present invention, the following description is made in conjunction with the accompanying drawings.

[0036] As Figure 1 shown in the overall flowchart of the present invention, the path planning method based on information grid division of the present invention includes the following 5 steps:

[0037] (1) Environmental grid division and grid navigation cost initialization. Divide the target navigation area into equilateral square grids, and each grid unit represents a small area of the actual sea area. The grid size is determined by the specific application scenario, generally from 100m×100m to 1km×1km. Mark whether each grid unit is impassable. If so, set its navigation cost to , otherwise set the navigation cost of the grid according to the environmental factors of the grid (such as wind direction and speed, water flow direction and speed, etc.) and safety factors (such as water depth information and obstacle density of the area), and define the starting point and the end point .

[0038] The specific steps are as follows:

[0039] (1.1) Grid division: Divide the target sea area into regular two-dimensional or three-dimensional grids, and record the geographical coordinates, depth information and navigation conditions of each grid node;

[0040] (1.2) Node cost initialization: Calculate the navigation cost of the grid node according to the previously recorded grid information. The navigation cost includes the following factors:

[0041] Distance cost: The navigation distance between nodes;

[0042] Environmental cost: Consider the influence of environmental factors such as wind and water flow on the path;

[0043] Safety cost: Set the navigation risk cost according to the navigation depth and obstacle distribution;

[0044] (1.3) Definition of starting point and end point: Designate the current position of the ship as the starting point and the target position as the end point.

[0045] (2) Define the cost function and initialize the node cost. Starting from the end point, update the cost of adjacent nodes in turn, and then starting from the end point, recursively backtrack the path with the minimum cost until the starting point.

[0046] The specific steps are as follows:

[0047] (2.1) Define the cost function: Define the cost function f(n) as the cost spent from node n to the end point G;

[0048] (2.2)Initialize the nodes and define the initial state: Set the cost value of the end point to zero, indicating that the cost of reaching the end point is zero; Set the initial cost of other nodes to infinity, indicating that the cost of reaching the end point has not been calculated yet. Establish a priority queue to store the nodes to be processed, and give priority to processing the node with the minimum cost;

[0049] (2.3)Update the node cost: Starting from the end point, update the costs of adjacent nodes in turn and determine their predecessor nodes;

[0050] (2.4)Path tracing: Starting from the starting point, generate the optimal path according to its predecessor nodes.

[0051] Define the cost function for the node to the end point The cost is calculated as follows:

[0052]

[0053] where represents the minimum cost from node to the end point and is equal to . represents the estimated value of the minimum cost from node to the end point and is calculated as follows:

[0054]

[0055] where is the adjacent node of node , is the set of adjacent nodes, is the navigation cost from node to node . When is updated, will be updated together. Initialize , initialize the remaining nodes , and add node to the priority queue.

[0056] Then calculate the cost. Select the node with the minimum cost from the priority queue for processing. If , then update the value of to , and then traverse all adjacent nodes and update their according to the following formula:

[0057]

[0058] And add all adjacent nodes to the priority queue. If , then mark the node as "consistent" and remove it from the priority queue.

[0059] Repeat the above update process until the priority queue is empty and all nodes reach a consistent state, and then generate the global optimal path by backtracking from the starting point.

[0060] (3)Detect environmental changes. Use real-time sensors or a maritime dynamic data monitoring system to continuously detect environmental changes in the sea area that may affect ship navigation, such as dynamic obstacles (such as the movement of other ships, the appearance of floating objects, etc.) and changes in environmental conditions (such as changes in wind speed, wind direction, water flow intensity and direction, or tidal effects). If the environment of some nodes in the grid changes, then mark these nodes as "inconsistent state", and the inconsistent state means that the current cost value of this node needs to be re-evaluated due to environmental changes. Subsequently, redefine the navigation cost of these nodes in the manner of step (1), then recalculate these nodes according to formula (2), and finally add them to the priority queue.

[0061] The specific steps are as follows:

[0062] (3.1)Dynamic environment detection: Detect dynamic environmental changes in the sea area through real-time sensors or maritime data;

[0063] (3.2)Update the cost of affected nodes: Determine the navigation cost of the node and the cost from this node to the end point again according to the changed environment;

[0064] (3.3)Add to the priority queue: Add the affected nodes to the priority queue.

[0065] (4)Incrementally update the cost. Select the node with the minimum cost from the priority queue and gradually update the cost value. The specific process is as follows: First, check the consistency. For the selected node , detect and whether they are consistent. If not, then update to . Then propagate the update. If changes, then propagate its influence to all adjacent nodes , update according to formula (3), and add all adjacent nodes to the priority queue. Finally, repeat selecting the node with the minimum cost from the priority queue and updating until all nodes reach a consistent state, that is, until the priority queue is empty.

[0066] The specific steps are as follows:

[0067] (4.1) Priority queue management: Process and take out the node with the minimum cost in sequence. After the processing is completed, add its adjacent nodes to the priority queue;

[0068] (4.2) Recursive update of adjacent node costs: Recursively update the cost from the node to the end point according to the adjacent nodes of the affected nodes.

[0069] (5) Path optimization and output. After the cost update is completed, starting from the starting point, trace back in the reverse direction to the target node according to the final cost value graph to generate a globally optimal path. Combine the actual navigation parameters of the ship to further optimize the generated path. For example, smooth the path according to the minimum turning radius of the ship to avoid safety problems caused by sharp turns. Convert the optimized path into navigation coordinates in the actual sea area to generate executable navigation instructions, including specific parameters such as heading, speed, and turning points, and combine with the real-time navigation system to provide continuous guidance for the ship to ensure that the ship sails along the optimal path and dynamically adjust the path when necessary.

[0070] The specific steps are as follows:

[0071] (5.1) Path output: According to the updated cost value, trace back from the starting point in the reverse direction to the end point and output the globally optimal path;

[0072] (5.2) Navigation characteristic optimization: Further optimize the path by combining parameters such as the speed and turning radius of the ship;

[0073] (5.3) Generate navigation instructions: Convert the optimized path into executable navigation instructions for the ship, including specific parameters such as heading, speed, and turning points.

Claims

1. A path planning method based on information grid division, characterized in that It includes the following steps: (1) Grid division and node cost initialization: Construct a grid-based search environment, and initialize the starting point, ending point, and the navigation cost of nodes in the grid; (2) Cost function definition and path search: Define the cost function from a node to the ending point, and starting from the ending point, calculate the cost and path according to the reverse search strategy; (3) Dynamic environment detection and cost update: Detect environmental changes, and update the node costs affected by the environmental changes; (4) Incremental cost update: Recursively update the navigation cost of the adjacent nodes of the affected nodes and their costs to the ending point; (5) Path output and navigation optimization: Update the globally optimal path, and further optimize the path in combination with the ship navigation characteristics to generate executable navigation instructions; The step (2) cost function definition and path search includes: Define the starting point and the ending point ; Define the cost function : Node to the end point The cost incurred is calculated as follows: ， Among them, represents the minimum cost from the node to the end point, which is equal to ; represents the estimated value of the minimum cost from the node to the end point , and the calculation method is as follows: ， Among them, is the adjacent node of the node is the set of adjacent nodes, is the node to the node of the sailing cost. When is updated, will be updated together. Initialize , initialize the remaining nodes , and add the node to the priority queue; Select the node with the smallest cost from the priority queue for processing. If , then update to be , and then traverse all adjacent nodes , and update their according to the following formula: ， And add all adjacent nodes to the priority queue. If , then mark the node as consistent and remove it from the priority queue; Repeat the above update process until the priority queue is empty and all nodes reach a consistent state, and generate the globally optimal path by backtracking from the starting point in reverse; 2. The path planning method based on information grid division according to claim 1, wherein The step (1) includes dividing the target navigation area into equilateral square grid nodes, where each grid node represents a small area of the actual sea area; marking whether each grid cell is impassable, and if so, setting its navigation cost to , otherwise, setting the navigation cost of the grid according to the environmental factors and safety factors of the grid.

3. The path planning method based on information grid division according to claim 1, characterized in that The step (2) includes defining the cost function and initializing the node costs, starting from the ending point, updating the costs of the adjacent nodes in sequence, and then starting from the ending point, backtracking the path with the minimum cost recursively until the starting point; 4. The path planning method based on information grid division according to claim 1, wherein, The said step (3) includes using a real-time sensor or a maritime dynamic data monitoring system to continuously detect environmental changes in the sea area that affect ship navigation. If the environment of some nodes in the grid changes, these nodes are marked as inconsistent states, and the navigation costs of these nodes are recalculated. Then, according to formula (2), the , and finally they are added to the priority queue.

5. The path planning method based on information grid division according to claim 4, wherein The inconsistent state means that the current cost value of the node needs to be re-evaluated due to environmental changes, that is .

6. The path planning method based on information grid division according to claim 1, characterized in that The step (4) includes selecting the node with the minimum cost from the priority queue Gradually update the cost value. First, check the consistency; then propagate the update. If it changes, then propagate its influence to all adjacent nodes and update according to formula (3) , and add all adjacent nodes to the priority queue; finally, repeat selecting the node with the minimum cost from the priority queue and updating until all nodes reach a consistent state, that is, until the priority queue is empty.

7. The path planning method based on information grid division according to claim 6, wherein The consistency check refers to checking whether the and of the grid nodes are equal. If they are not equal, then update to .

8. The path planning method based on information grid division according to claim 1, characterized in that The step (5) includes generating a path with the minimum cost according to the calculated cost values; then further optimizing the generated path according to the actual situation of the ship; finally, converting the optimized path into navigation coordinates in the actual sea area to generate executable navigation instructions; 9. The path planning method based on information grid division according to claim 8, characterized in that, The path with the minimum cost refers to generating a globally optimal path by backtracking from the starting point to the ending point according to the final cost value map;

Images