Station integrated path planning method and device, computer equipment and storage medium

Abstract

The invention discloses a station integrated path planning method and device, computer equipment and a storage medium, and the method comprises the following steps: collecting and storing the road network data of a station, and constructing a road network topological structure according to the road network data; different weight models are constructed based on the road network data, the weight models are all constructed for roads in all road networks of the station, and the weight models comprise a driving weight model and a walking weight model; and performing path planning based on the driving weight model and the walking weight model, switching different weight models according to the road type of the road section to calculate the path cost, and finding the path with the minimum cost as the optimal path. According to the method, the two sets of weight models, namely the driving weight model and the walking weight model, covering the whole station road network are constructed, so that global path optimization of a driving and walking mixed travel mode can be completed in a single calculation process, and the problem of local optimization caused by'segmented path calculation + path splicing 'in a traditional scheme is thoroughly avoided.

Description

Technical Field

[0001] The present invention relates to the field of navigation technology, and in particular to a method, device, computer equipment and storage medium for station integrated path planning. Background Art

[0002] Common route planning solutions generally only provide the most optimized route planning solutions for a single mode of travel. Some solutions can also support mixed travel modes, such as AutoNavi's bus route planning, which supports mixed travel route solutions such as bus + walking, bus + cycling, etc. However, its route planning solution for mixed travel modes is essentially a locally optimal route planning solution, not a globally optimized solution. The above situation is closely related to the data organization of current map vendors. The road network data we commonly use includes all vehicle roads and some non-vehicle roads, as well as some pedestrian facility data in other data. Bus data is also a separate set of data, so driving routes, walking and cycling routes, and bus routes are all planned separately.

[0003] For example, a route plan for mixed bus and walking modes first binds the nearest bus stop based on the user's starting and ending points. A bus route is then planned based on the bus stops. Walking routes are then calculated for the starting and ending points and the corresponding stops. Finally, these three routes are combined to form the final mixed travel route plan presented to the user. Driving route planning, on the other hand, filters out non-driving roads during initial data processing, retaining only the topological relationships of driving roads. Therefore, it only supports route planning for driving alone and does not support optimized route planning that combines driving with other modes.

[0004] However, in some vertical scenarios, such as station inspection scenarios, since the roads involved in the inspection include both vehicular roads and non-vehicular pedestrian roads, a globally optimal integrated mixed travel (driving and walking) route planning solution is required to ensure the overall optimization of the route and improve inspection efficiency. Summary of the Invention

[0005] In view of the above-mentioned deficiencies in the prior art, the technical problem to be solved by the present invention is to provide a station-integrated path planning method, device, computer equipment and storage medium that can plan mixed travel routes of driving and walking.

[0006] To solve the above technical problems, the present invention adopts a technical solution: providing a station integrated path planning method, comprising the following steps:

[0007] Collecting and storing road network data of the station, and constructing a road network topology structure based on the road network data;

[0008] Constructing different weight models based on the road network data, wherein the weight models are all constructed for roads in all road networks of the station, and the weight models include a vehicle weight model and a pedestrian weight model;

[0009] Path planning is performed based on the vehicle weight model and the pedestrian weight model. Different weight models are switched according to the road type of the road segment to calculate the path cost, and the path with the minimum cost is found as the optimal path.

[0010] Furthermore, the step of collecting and storing the road network data of the station and constructing the road network topology structure according to the road network data includes the following sub-steps:

[0011] Collect road network data of the station through satellite image vectorization, aerial image vectorization, vehicle trajectory and / or pedestrian trajectory vectorization;

[0012] The collected road network data is processed and stored in units of road segments. A unique identifier is assigned to each road segment. The attribute information of each road segment includes the starting point identifier, end point identifier, road width, paving status, road type and spatial shape.

[0013] The road network topology is constructed based on the starting point and end point identifiers of each road segment.

[0014] Furthermore, the road types include carriageways and pedestrian paths. The step of constructing different weight models based on the road network data specifically includes the following sub-steps:

[0015] Setting the cost of each road segment under different travel modes based on the road network data, wherein the cost refers to the time required to pass the road segment;

[0016] For each driving mode, a weight model for the driving mode is constructed based on the mapping relationship between the road segments for the driving mode and the costs corresponding to the road segments. The weight model for the vehicle driving mode is the vehicle driving weight model, and the weight model for the pedestrian driving mode is the pedestrian weight model.

[0017] Furthermore, in the step of performing path planning based on the vehicle weight model and the pedestrian weight model, switching different weight models according to the road type of the road segment to calculate the path cost, and finding the path with the minimum cost as the optimal path, the following sub-steps are included:

[0018] Determine the initial road, determine the road segment bound to the starting point through spatial binding, and put this road segment into the queue as the initial road;

[0019] Cost initialization: obtaining the cost of the initial road and using the cost of the initial road as the initial value of the path cost and performing subsequent calculations based on the initial value;

[0020] Road search: using the initial road as the current road segment and searching for a set of reachable road segments at the next level based on the road network topology, switching to a corresponding weight model based on the road type of the current road segment and obtaining the cost of each road segment at the next level under the weight model;

[0021] Cost calculation and comparison: calculating the path cost from the initial road to each road segment of the next level based on the initial value, comparing the costs of all current paths and selecting the path with the minimum cost as the current optimal path;

[0022] Iterative planning updates the end road segment of the current optimal path to the current road segment, repeats the road search, cost calculation and comparison steps until the planned path reaches the road segment bound to the end point, and outputs the path with the minimum cost as the final optimal path.

[0023] Furthermore, the step of performing spatial binding includes the following sub-steps:

[0024] Starting point binding: perform spatial query based on the starting point coordinates, and select the road segment with the smallest projection distance from the queried road segments as the starting point binding road segment according to the projection distance;

[0025] Destination binding: perform spatial query based on the coordinates of the destination, and select the road segment with the smallest projection distance from the queried road segments as the destination binding road segment according to the projection distance.

[0026] Furthermore, the method for obtaining the cost of the initial road specifically includes: selecting an initial weight model according to the road type of the initial road, and obtaining the cost of the initial road by mapping the initial road and the cost under the initial weight model.

[0027] Furthermore, the method of switching to a corresponding weight model based on the road type of the current road segment specifically includes:

[0028] When the previous level road segment is a carriageway, if the current road segment is a carriageway, there is no need to switch the weight model. If the current road segment is a pedestrian path, it is necessary to switch to the pedestrian weight model.

[0029] When the previous level road segment is a pedestrian path, no matter whether the current road segment is a driveway or a pedestrian path, the weight model will not be switched and the pedestrian weight model will continue to be used.

[0030] In order to solve the above technical problems, another technical solution adopted by the present invention is to provide a station integrated path planning device, comprising:

[0031] A topology structure building module is used to collect and store the road network data of the station and build a road network topology structure based on the road network data;

[0032] A weight model construction module is used to construct different weight models based on the road network data. The weight models are all constructed for roads in the entire road network of the station. The weight models include a vehicle weight model and a pedestrian weight model.

[0033] The path planning module is used to perform path planning based on the vehicle weight model and the pedestrian weight model, switch different weight models according to the road type of the road segment to calculate the path cost, and find the path with the minimum cost as the optimal path.

[0034] In order to solve the above technical problems, another technical solution adopted by the present invention is: providing a computer device, including a memory and a processor, the memory storing a computer program, and the processor implementing the steps of the integrated station path planning method when executing the computer program.

[0035] In order to solve the above technical problems, another technical solution adopted by the present invention is: providing a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the integrated station path planning method are implemented.

[0036] The station integrated path planning method, device, computer equipment and storage medium of the present invention have at least the following beneficial effects: the present invention constructs two sets of weight models, namely the vehicle weight model and the pedestrian weight model, which cover the entire station road network. In a single calculation process, the global path optimization of the mixed driving and walking travel mode can be completed, which completely avoids the local optimal problem caused by the "segmented route calculation + route splicing" in the traditional solution; it realizes the global optimal path planning of the mixed driving and walking travel mode, and significantly improves the path planning efficiency of vertical scenes such as station inspection; based on the real-time collected vehicle and pedestrian trajectory data, the large model is dynamically adjusted The cost of road segments makes the path planning results more in line with the actual road conditions and effectively copes with the fluctuations in traffic efficiency caused by changes in the frequency of road use within the station; integrating satellite images, aerial images and trajectory data to build a unified road network topology structure, realizes the spatial association between vehicle roads and pedestrian facilities, and provides complete data support for mixed travel path planning; through intelligent weight model switching, dynamic cost calculation mechanism and iterative planning mechanism, the path selection is continuously optimized, and a significant improvement in path search efficiency is achieved under complex road network structures. While ensuring the accuracy of the results, the road calculation performance is optimized, providing an efficient and accurate mixed travel path planning solution. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0038] Figure 1 This is a flow chart of an implementation method of the station integrated path planning method of the present invention.

[0039] Figure 2 for Figure 1 Flowchart of step S100 in FIG.

[0040] Figure 3 for Figure 1 Flowchart of step S200 in FIG.

[0041] Figure 4 for Figure 1 Flowchart of step S300 in FIG.

[0042] Figure 5 This is a structural block diagram of an embodiment of the station integrated path planning device of the present invention. DETAILED DESCRIPTION

[0043] The present invention will be further described below with reference to the accompanying drawings.

[0044] The station mentioned in the present invention refers to a specific area or place with a certain scale, which concentrates a variety of facilities and equipment and requires regular inspection and maintenance, including transportation stations, energy stations, industrial stations, etc.

[0045] See also Figure 1 , a flow chart of an embodiment of the method for integrated station path planning of the present invention. This embodiment specifically includes the following steps:

[0046] S100: Collect data and construct a road network topology.

[0047] Specifically, the road network data of the station is collected and stored, and the road network topology is constructed based on the road network data. Figure 2 , this step S100 includes the following sub-steps:

[0048] S110: Collect road network data.

[0049] Specifically, the road network data of the station is collected through satellite image vectorization, aerial image vectorization, vehicle trajectory and / or pedestrian trajectory vectorization.

[0050] S120: Data processing and storage.

[0051] Specifically, the collected road network data is processed and stored in units of road segments. Each road segment is assigned a unique identifier. Attribute information for each road segment includes its starting and ending points, road width, paving status, road type, and spatial shape. It's understandable that the aforementioned attributes only cover some of the characteristics of a road segment. In actual road network data, road segment attributes may also include road length, number of lanes, and real-time congestion status, all of which influence the cost of the road segment.

[0052] S130. Construct a road network topology structure.

[0053] Specifically, a road network topology is constructed based on the start and end identifiers of each road segment. The road network topology is a model used to describe the connection relationship between each road segment in the road network. The method of constructing the road network topology is an existing technology and will not be described in detail here.

[0054] S200: Build a weight model.

[0055] Specifically, different weight models are constructed based on the road network data. These weight models are all constructed for roads in the entire road network of the station, including a vehicle weight model and a pedestrian weight model. The entire road network refers to all actual roads within the station. The weight models are used to quantify the cost of a road, which refers to the time required to travel a road segment.

[0056] See also Figure 3 , this step 200 includes the following sub-steps:

[0057] S210: Set the price.

[0058] Specifically, the corresponding costs for each road segment under different travel modes are set based on road network data. For roadways, the driving cost in vehicle mode and the pedestrian cost in pedestrian mode are set. For pedestrian paths, the pedestrian cost in vehicle mode and the pedestrian cost in pedestrian mode are set. Before vehicles and pedestrians travel on the road, initial costs are manually set for each road segment under different travel modes (vehicle mode, pedestrian mode) based on the road segment's attribute information and past experience. These initial costs will serve as the basis for subsequent dynamic adjustments. To improve accuracy, a preset time period (e.g., one week, one month, etc.) can be set after vehicles and pedestrians begin to travel on the road. At the end of the preset time period, the pedestrian and vehicle trajectory data collected during this period is used to conduct learning and analysis using a large model (such as a deep learning model). The large model will adjust the costs of each road segment under different travel modes based on the learned traffic patterns and traffic patterns. This dynamic adjustment can more accurately reflect the actual traffic conditions of the road and improve the accuracy and efficiency of path planning. The specific cost setting method is an existing technology and will not be described in detail here.

[0059] S220: Construct a vehicle weight model and a walking weight model.

[0060] Specifically, for each driving mode, a weight model for the driving mode is constructed based on the mapping relationship between the road segments for the driving mode and the costs corresponding to the road segments. The weight model for the vehicle driving mode is the vehicle driving weight model, and the weight model for the walking driving mode is the walking weight model.

[0061] S300: Plan an optimal path.

[0062] Specifically, based on the vehicle weight model and the pedestrian weight model, path planning is performed, and different weight models are switched according to the road type of the road segment to calculate the path cost, and the path with the minimum cost is found as the optimal path. Figure 4 , this step S300 includes the following sub-steps:

[0063] S310: Determine an initial road.

[0064] Specifically, a spatial binding method is used to determine a road segment bound to the starting point, and this road segment is placed in the queue as the initial road. The spatial binding method specifically includes: starting point binding, which performs a spatial query based on the starting point coordinates, and selects the road segment with the smallest projection distance from the queried road segments as the starting point binding road segment; and end point binding, which performs a spatial query based on the end point coordinates, and selects the road segment with the smallest projection distance from the queried road segments as the end point binding road segment.

[0065] S320: Cost initialization.

[0066] Specifically, the cost of the initial road is obtained and used as the initial value of the path cost, and subsequent calculations are performed based on the initial value. The method for obtaining the cost of the initial road specifically includes: selecting an initial weight model based on the road type of the initial road, and obtaining the cost of the initial road by mapping the initial road to the cost under the initial weight model.

[0067] S330: Road search.

[0068] Specifically, the initial road is used as the current road segment, and based on the road network topology, a search is performed for a set of accessible road segments at the next level. Based on the road type of the current road segment, a switch is made to a corresponding weight model, and the cost of each road segment at the next level is obtained under the weight model. The method of switching to a corresponding weight model based on the road type of the current road segment specifically includes: when the previous level road segment is a roadway, if the current road segment is a roadway, the weight model does not need to be switched; if the current road segment is a pedestrian path, the pedestrian weight model is switched; and when the previous level road segment is a pedestrian path, regardless of whether the current road segment is a roadway or a pedestrian path, the weight model is not switched, and the pedestrian weight model continues to be used. In this embodiment, during station inspections, there are no shared cars. If the vehicle is switched from driving to walking, it is no longer possible to switch back from walking to driving. The vehicle has been abandoned, and subsequent roadways can only be traversed by foot.

[0069] S340. Cost calculation and comparison.

[0070] Specifically, the path costs from the initial road to each road segment of the next level are calculated based on the initial value, the costs of all current paths are compared, and the path with the minimum cost is selected as the current optimal path.

[0071] S350, iterative planning.

[0072] Specifically, the end road segment of the current optimal path is updated to the current road segment, and the steps of road search, cost calculation and comparison are repeated until the planned path reaches the road segment bound to the end point, and the path with the minimum cost is output as the final optimal path.

[0073] For example, when the road segment bound to the starting point is lane A, the driving weight model is used to obtain the cost of lane A as 10; continue to search for the next level of accessible road segments including pedestrian lane B and lane C. At this time, the cost of pedestrian lane B obtained based on the driving weight model is 100, and the cost of lane C is 10. Then the cost of path AB is 110, and the cost of path AC is 20; select path AC with a smaller cost to continue pathfinding, and explore the next level of accessible roads including pedestrian lane D and pedestrian lane F. At this time, the cost of pedestrian lane D obtained based on the driving weight model is 100, and the cost of pedestrian lane F is 200. At this time, the cost of path ACD is 120, the cost of path ACF is 220, and the cost of path AB is 110; at this time, choose the cost The minimum path AB continues to search for the path, and it is discovered that path AB can reach the road segment bound to the destination through road E, and the weight model is switched to the walking weight model. Based on the walking weight model, the cost of road E is 90. At this time, the cost of path ABE is 200, the cost of path ACD is 120, and the cost of path ACF is 220. The path ACD with the minimum cost is selected to continue searching for the path, and it is discovered that path ACD can reach the road segment bound to the destination through road F. Because road segment D is a pedestrian path, the walking weight model is switched to. Under the walking weight model, the cost of road F is 90, and the cost of path ACDF is 210. The path ABE with the minimum cost between paths ABE and ACDF is selected as the optimal path.

[0074] See also Figure 5 , is a structural block diagram of an embodiment of a station-integrated path planning device of the present invention. The station-integrated path planning device of this embodiment is used to implement the station-integrated path planning method described in the above embodiment. Specifically, the station-integrated path planning device of this embodiment includes a topology structure construction module 100, a weight model construction module 200, and a path planning module 300. Among them:

[0075] The topology structure construction module 100 is used to collect and store the road network data of the station and construct a road network topology structure based on the road network data. Specifically, the topology structure construction module 100 is used to collect the road network data of the station through satellite image vectorization, aerial image vectorization, vehicle trajectory and / or pedestrian trajectory vectorization; process the collected road network data and store it in units of road segments, assign a unique identifier to each road segment, and the attribute information of each road segment includes a starting point identifier, an end point identifier, road width, paving status, road type, and spatial shape; and construct a road network topology structure based on the starting point identifier and end point identifier of each road segment.

[0076] The weight model construction module 200 is used to construct different weight models based on the road network data. The weight models are all constructed for the roads in the entire road network of the station, and the weight models include a vehicle weight model and a pedestrian weight model. Specifically, the weight model construction module 200 sets the corresponding cost for each road segment under different travel modes based on the road network data. The cost refers to the time required to pass the road segment. For each travel mode, the weight model for that travel mode is constructed based on the mapping relationship between the road segment for the travel mode and the corresponding cost of the road segment. The weight model for the vehicle travel mode is the vehicle weight model, and the weight model for the pedestrian travel mode is the pedestrian weight model.

[0077] The path planning module 300 is configured to perform path planning based on the vehicle weight model and the pedestrian weight model, switching between different weight models based on the road type of the road segment to calculate the path cost, and finding the path with the minimum cost as the optimal path. Specifically, the path planning module 300 is configured to determine the road segment bound to the starting point through spatial binding, place the road segment as the initial road in a queue, obtain the cost of the initial road and use the initial road cost as the initial value of the path cost, and perform subsequent calculations based on the initial value; use the initial road as the current road segment and search for a set of reachable road segments at the next level based on the road network topology; switch to a corresponding weight model based on the road type of the current road segment and obtain the cost of each road segment at the next level under the weight model; calculate the path cost from the initial road to each road segment at the next level based on the initial value, compare the costs of all current paths, and select the path with the minimum cost as the current optimal path; update the end road segment of the current optimal path to the current road segment, and repeat the road search, cost calculation, and comparison steps until the planned path reaches the road segment bound to the end point, and output the path with the minimum cost as the final optimal path.

[0078] The present invention also discloses a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the station integrated path planning method when executing the computer program.

[0079] The present invention also discloses a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps of the station integrated path planning method are implemented.

[0080] By constructing two sets of weight models, a vehicle weight model and a pedestrian weight model, covering the entire station road network, the present invention can complete the global path optimization of mixed driving and walking travel modes in a single calculation process, completely avoiding the local optimal problem caused by the "segmented route calculation + route splicing" method in traditional solutions; it realizes the global optimal path planning for mixed driving and walking travel modes, significantly improving the path planning efficiency in vertical scenarios such as station inspections; based on real-time collected vehicle and pedestrian trajectory data, the traffic costs of road segments are dynamically adjusted through a large model, making the path planning results more in line with actual road conditions and effectively addressing the traffic efficiency fluctuations caused by changes in the frequency of road use within the station; integrating satellite imagery, aerial imagery, and trajectory data to construct a unified road network topology, realizing the spatial correlation between vehicle roads and pedestrian facilities, and providing complete data support for mixed travel path planning; through intelligent weight model switching, dynamic cost calculation mechanism, and iterative planning mechanism, path selection is continuously optimized, significantly improving path search efficiency in complex road network structures, optimizing route calculation performance while ensuring the accuracy of the results, and providing an efficient and accurate mixed travel path planning solution.

[0081] The above description merely expresses the preferred embodiments of the present invention, and its description is relatively specific and detailed, but it should not be construed as limiting the scope of the patent. It should be noted that a person skilled in the art may make a number of variations and improvements without departing from the concept of the present invention, and these variations and improvements fall within the scope of protection of the present invention. Therefore, the scope of protection of the patent of the present invention shall be based on the appended claims.

Claims

1. A station integrated path planning method, characterized in that: The following steps are involved: Collecting and storing road network data of the station, and constructing a road network topology structure based on the road network data; Constructing different weight models based on the road network data, wherein the weight models are all constructed for roads in all road networks of the station, and the weight models include a vehicle weight model and a pedestrian weight model; Path planning is performed based on the vehicle weight model and the pedestrian weight model. Different weight models are switched according to the road type of the road segment to calculate the path cost, and the path with the minimum cost is found as the optimal path.

2. The method for integrated station path planning according to claim 1, wherein: The steps of collecting and storing the road network data of the station and constructing the road network topology structure according to the road network data include the following sub-steps: Collect road network data of the station through satellite image vectorization, aerial image vectorization, vehicle trajectory and / or pedestrian trajectory vectorization; The collected road network data is processed and stored in units of road segments. A unique identifier is assigned to each road segment. The attribute information of each road segment includes the starting point identifier, end point identifier, road width, paving status, road type and spatial shape. The road network topology is constructed based on the starting point and end point identifiers of each road segment.

3. The method for integrated station path planning according to claim 2, wherein: The road types include carriageways and pedestrian paths. The step of constructing different weight models based on the road network data specifically includes the following sub-steps: Setting the cost of each road segment under different travel modes based on the road network data, wherein the cost refers to the time required to pass the road segment; For each driving mode, a weight model for the driving mode is constructed based on the mapping relationship between the road segments for the driving mode and the costs corresponding to the road segments. The weight model for the vehicle driving mode is the vehicle driving weight model, and the weight model for the pedestrian driving mode is the pedestrian weight model.

4. The method for integrated station path planning according to claim 1, wherein: The step of performing path planning based on the vehicle weight model and the pedestrian weight model, switching different weight models according to the road type of the road segment to calculate the path cost, and finding the path with the minimum cost as the optimal path includes the following sub-steps: Determine the initial road, determine the road segment bound to the starting point through spatial binding, and put this road segment into the queue as the initial road; Cost initialization: obtaining the cost of the initial road and using the cost of the initial road as the initial value of the path cost and performing subsequent calculations based on the initial value; Road search: using the initial road as the current road segment and searching for a set of reachable road segments at the next level based on the road network topology, switching to a corresponding weight model based on the road type of the current road segment and obtaining the cost of each road segment at the next level under the weight model; Cost calculation and comparison: calculating the path cost from the initial road to each road segment of the next level based on the initial value, comparing the costs of all current paths and selecting the path with the minimum cost as the current optimal path; Iterative planning updates the end road segment of the current optimal path to the current road segment, repeats the road search, cost calculation and comparison steps until the planned path reaches the road segment bound to the end point, and outputs the path with the minimum cost as the final optimal path.

5. The method for integrated station path planning according to claim 4, characterized in that: The steps for performing spatial binding include the following sub-steps: Starting point binding: perform spatial query based on the starting point coordinates, and select the road segment with the smallest projection distance from the queried road segments as the starting point binding road segment according to the projection distance; Destination binding: perform spatial query based on the coordinates of the destination, and select the road segment with the smallest projection distance from the queried road segments as the destination binding road segment according to the projection distance.

6. The method for integrated station path planning according to claim 4, characterized in that: The method for obtaining the cost of the initial road specifically includes: selecting an initial weight model according to the road type of the initial road, and obtaining the cost of the initial road by mapping the initial road and the cost under the initial weight model.

7. The method for integrated station path planning according to claim 4, characterized in that: The method of switching to a corresponding weight model based on the road type of the current road segment specifically includes: When the previous level road segment is a carriageway, if the current road segment is a carriageway, there is no need to switch the weight model. If the current road segment is a pedestrian path, it is necessary to switch to the pedestrian weight model. When the previous level road segment is a pedestrian path, no matter whether the current road segment is a driveway or a pedestrian path, the weight model will not be switched and the pedestrian weight model will continue to be used.

8. A station-integrated path planning device, characterized in that: include: A topology structure building module is used to collect and store the road network data of the station and build a road network topology structure based on the road network data; A weight model construction module is used to construct different weight models based on the road network data. The weight models are all constructed for roads in the entire road network of the station. The weight models include a vehicle weight model and a pedestrian weight model. The path planning module is used to perform path planning based on the vehicle weight model and the pedestrian weight model, switch different weight models according to the road type of the road segment to calculate the path cost, and find the path with the minimum cost as the optimal path.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the station integrated path planning method described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the station integrated path planning method described in any one of claims 1 to 7 are implemented.

Images