Traffic monitoring planning method and system for unmanned aerial vehicle cooperating with mobile vehicle in waterlogging scenario

Abstract

The application provides a traffic monitoring planning method and system for unmanned aerial vehicles (UAVs) and mobile vehicles in a waterlogging scene. First, the monitoring task demand in the road network in the waterlogging scene is obtained through weighted analysis. Then, the actual road condition characteristics of the monitoring area are extracted to assign appropriate detection road sections to the UAVs and the mobile vehicles. Then, a traffic monitoring planning model is established for the vehicle group and the UAV group considering the endurance of the UAVs. The optimal monitoring planning scheme is obtained by solving the model. The beneficial effects of the application are as follows: the endurance demand of the UAV group is added to the path planning problem with emergency time constraints, which is beneficial to fully utilizing the respective advantages of the mobile vehicles and the UAVs in the waterlogging emergency scene, optimizing the efficient cooperative patrol problem of multiple monitoring tools in the urban waterlogging, and improving the monitoring efficiency in the urban waterlogging.

Description

Technical Field

[0001] This invention relates to the field of smart city geographic information service technology, and in particular to a traffic monitoring and planning method and system for drones and mobile vehicles in the context of urban flooding. Background Technology

[0002] Due to the influence of the monsoon climate in most parts of my country, the uneven seasonal and spatial distribution of precipitation makes some cities prone to urban flooding. Urban flooding refers to the phenomenon of water accumulation in cities caused by heavy rainfall exceeding their drainage capacity, endangering the lives and property of urban residents and affecting the safe operation and sustainable development of cities. Urban flooding seriously disrupts traffic order. The national action plan for the construction of urban drainage and flood control systems emphasizes the need to strengthen emergency response capabilities for urban flooding, thus requiring timely, efficient, and reasonable traffic monitoring to ensure urban traffic stability and the safety of people.

[0003] Traditional ground-based police vehicle patrols and surveillance suffer from problems such as poor targeting, lack of flexibility, and untimely monitoring. However, the rapid development of civilian drones in recent years has effectively compensated for the shortcomings of ground-based surveillance vehicles. Their flexibility, high mobility, and timeliness can further improve the efficiency of urban traffic patrols. Therefore, the collaborative operation of mobile vehicles and drones can better leverage the advantages of each. Existing research shows that solutions for mobile vehicles collaborating with drones to perform tasks are mostly used in fields such as power grid inspection and environmental monitoring, with mobile vehicles primarily serving as mobile warehouses to save energy consumption for drones.

[0004] However, in scenarios involving urban flooding, the movement of both mobile vehicles and drones will be subject to certain limitations because:

[0005] (1) Road sections with deep water accumulation and severe congestion are not suitable for moving vehicles to perform monitoring, while culverts and tree-covered areas are not suitable for drones to perform patrol missions. The existing model does not take into account the adaptability of monitoring tools to the road sections to be monitored.

[0006] (2) Most related studies focus on minimizing the total time of collaborative monitoring between a single vehicle and a single UAV, and between a single vehicle and multiple UAVs. However, in the emergency response to urban flooding, the emphasis should be on efficient handling within the emergency time limit. Existing studies have not considered the emergency time limit constraints in collaborative tasks.

[0007] Previous research has primarily focused on using mobile vehicles as carriers to compensate for the limited flight time of drones, playing only a supplementary role and failing to fully leverage the maximum synergy between the two. Therefore, optimizing the collaborative monitoring paths of mobile vehicles and drones in urban flooding emergency scenarios to improve monitoring efficiency is crucial. Efficient drone-mobile vehicle collaborative monitoring paths can acquire more and more important flooding information within limited patrol time, thus providing more reliable support for emergency decision-making and improving the efficiency of emergency response to urban flooding incidents.

[0008] Current research on collaborative surveillance planning between vehicles and drones largely addresses the problem of minimizing the total collaborative surveillance time between a single vehicle and a single drone, or between a single vehicle and multiple drones. However, emergency response to urban flooding should prioritize efficient handling within the emergency timeframe, and existing research has not considered the time constraints in collaborative tasks. Furthermore, existing models do not consider the adaptability of surveillance tools to the monitored road sections in flooding scenarios. Therefore, it is necessary to design a collaborative surveillance path planning method for vehicle and drone swarms in urban flooding scenarios that takes into account drone endurance, in order to efficiently complete emergency flooding surveillance tasks. Summary of the Invention

[0009] To address the aforementioned problems, this invention provides a traffic monitoring and planning method and system for drones and collaborative mobile vehicles in flood-prone scenarios. The traffic monitoring and planning method for drones and collaborative mobile vehicles in flood-prone scenarios mainly includes the following steps:

[0010] S1: Based on rainfall data, traffic flow data, and predicted water accumulation, obtain the monitoring task requirements under the scenario of urban flooding;

[0011] S2: Based on the monitoring task requirements, extract the road condition features of the monitoring area from the actual road conditions, and assign suitable monitoring sections to the drones and mobile vehicles respectively.

[0012] S3: Based on the monitored road section, establish a traffic monitoring planning model for UAV-assisted mobile vehicle in the scenario of urban flooding, and determine the objective function of the model as maximizing the coverage of the collaborative monitoring task within the time limit;

[0013] S4: Solve the traffic monitoring planning model to determine the optimal monitoring path for the UAV and mobile vehicle, and obtain the optimal collaborative monitoring path scheme.

[0014] Furthermore, the specific implementation process of step S1 is as follows:

[0015] S1-1: Obtain near-real-time rainfall values ​​before executing the monitoring task;

[0016] S1-2: Obtain statistical data on past traffic flow on the road to determine the congestion risk of each road;

[0017] S1-3: Extract the predicted water accumulation values ​​of road sections obtained from the water accumulation simulation, and determine the water accumulation risk value of each road section;

[0018] S1-4: Use weighted analysis to process near-real-time rainfall values, past traffic flow data, and predicted water accumulation values, and select a set of road segments that need to be monitored from the task area.

[0019] Furthermore, the specific implementation process of step S2 is as follows:

[0020] S2-1: Obtain the actual road condition characteristics within the monitoring area and mark the road segment characteristics that have a direct impact on the monitoring methods;

[0021] S2-2: Assign vehicle-restricted task sections to sections that can only be monitored by drones;

[0022] S2-3: Mark road sections where drones are restricted as road sections that can only be monitored by vehicles;

[0023] S2-4: The remaining task segments consist of task segments that can be monitored by vehicles and drones working together.

[0024] Furthermore, the specific implementation process of step S3 is as follows:

[0025] S3-1: Construct a traffic monitoring planning model for UAVs and mobile vehicles in the scenario of urban flooding, and determine the objective function of the model as maximizing the coverage of collaborative monitoring task requirements within the time limit;

[0026] S3-2: Determine the upper limit of the emergency monitoring task in the case of urban flooding, set the starting point constraints and access order constraints for mobile vehicles and drone swarms, and avoid sub-loops;

[0027] S3-3: Set the collaborative association constraints and endurance constraints between the drone and the mobile workshop, and construct the access number constraints for the required road segments to ensure that the monitoring and patrol of all task road segments are completed collaboratively.

[0028] S3-4: Establish a traffic monitoring planning model for UAV-assisted mobile vehicles in urban flooding scenarios to maximize the coverage of road segment monitoring tasks within the emergency mission time limit; the traffic monitoring planning model is as follows:

[0029]

[0030] satisfy:

[0031]

[0032]

[0033]

[0034]

[0035]

[0036]

[0037]

[0038]

[0039]

[0040]

[0041]

[0042]

[0043]

[0044]

[0045] Where w represents the objective function for maximizing the coverage required by the road segment monitoring task; K represents the set of UAV sequences and the corresponding set of mobile vehicle sequences, and k represents the kth UAV or mobile vehicle; S ij This represents the demand profit value of road segment (i,j); Used to indicate whether road segment (i,j) is visited by drone k; Indicates whether road segment (i,j) has been visited by moving vehicle k; Used to record whether the kth drone was extended before visiting the (i,j) road segment; A p Indicates road sections that require joint monitoring by drones and vehicles; A d Indicates road sections that require monitoring only by drones; A c This indicates road sections that require monitoring only by vehicles;

[0046] (s,s) represents the starting point of the moving vehicle and the drone. This indicates whether road segment (i,j) is visited by drone k after road segment (s,s). This indicates whether road segment (s,s) is visited by drone k after road segment (i,j). This indicates whether road segment (s,s) is visited by moving car k after road segment (i,j). Indicates whether segment (i,j) is visited by moving car k after segment (s,s);

[0047] This indicates whether road segment (i',j') is visited by drone k after road segment (i,j). This indicates whether road segment (i,j) is visited by drone k after road segment (i',j'). Indicates whether segment (i',j') is visited by moving car k after segment (i,j); Indicates whether segment (i,j) is visited by moving car k after segment (i',j');

[0048] t ij The time cost of the drone flying over road segment (i,j); r ji' This represents the shortest distance the drone travels from j to i'; r ij H1 represents the shortest distance the drone travels from i to j; H2 represents the average speed of the drone; H3 represents the average speed of the moving vehicle; T represents the average speed of the moving vehicle. max Indicates the upper limit of the time for emergency response to urban flooding; This indicates the start time of service for vehicle k on road segment (i,j);

[0049] This represents the start time of drone k's service on road segment (i,j); This represents the start time of drone k's service on road segment (i', j'); M represents a sufficiently large value. This indicates the start time of service for vehicle k on road segment (i', j'); r si T represents the shortest distance from s to i for the drone; d Indicates the longest continuous flight time of the drone;

[0050] Decision variables A value of 0 indicates a negative result, and a value of 1 indicates a positive result.

[0051] S3-5: Solve the traffic monitoring planning model to determine the monitoring paths of the UAV and mobile vehicle, and obtain the optimal collaborative monitoring path scheme.

[0052] A traffic monitoring and planning system for drones and mobile vehicles in flood-prone scenarios includes:

[0053] The task requirement acquisition module is used to obtain monitoring task requirements in urban flooding scenarios based on rainfall values, traffic flow data, and predicted water accumulation values.

[0054] The monitoring segment allocation module is used to extract the road condition features of the monitoring area from the actual road conditions according to the monitoring task requirements, and allocate suitable monitoring segments to the drones and mobile vehicles respectively.

[0055] The traffic monitoring planning model building module is used to build a traffic monitoring planning model for UAVs and mobile vehicles in the context of urban flooding based on the monitored road segment, and to determine the objective function of the model as maximizing the coverage of collaborative monitoring task requirements within the time limit.

[0056] The optimal surveillance path determination module is used to determine the optimal surveillance path for the UAV and mobile vehicle by solving the traffic surveillance planning model, thereby obtaining the optimal collaborative surveillance path scheme.

[0057] Furthermore, the specific implementation process of the task requirement acquisition module is as follows:

[0058] S1-1: Obtain near-real-time rainfall values ​​before executing the monitoring task, and obtain the near-real-time rainfall grid cumulative values ​​for each road within the task range through spatial interpolation;

[0059] S1-2: Obtain statistical data on past traffic flow on the road to determine the congestion risk of each road;

[0060] S1-3: Extract the predicted water accumulation values ​​of road sections obtained from the water accumulation simulation, and determine the water accumulation risk value of each road section;

[0061] S1-4: Use weighted analysis to process near-real-time rainfall values, past traffic flow data, and predicted water accumulation values, and select a set of road segments that need to be monitored from the task area.

[0062] Furthermore, the specific implementation process of the monitored road segment allocation module is as follows:

[0063] S2-1: Obtain the actual road condition characteristics within the monitoring area and mark the road segment characteristics that have a direct impact on the monitoring methods;

[0064] S2-2: Assign vehicle-restricted task sections to sections that can only be monitored by drones;

[0065] S2-3: Mark road sections where drones are restricted as road sections that can only be monitored by vehicles;

[0066] S2-4: The remaining task segments consist of task segments that can be monitored by vehicles and drones working together.

[0067] Furthermore, the specific implementation process of the traffic monitoring planning model establishment module is as follows:

[0068] S3-1: Construct a traffic monitoring planning model for UAVs and mobile vehicles in the scenario of urban flooding, and determine the objective function of the model as maximizing the coverage of collaborative monitoring task requirements within the time limit;

[0069] S3-2: Determine the upper limit of the emergency monitoring task in the case of urban flooding, set the starting point constraints and access order constraints for mobile vehicles and drone swarms, and avoid sub-loops;

[0070] S3-3: Set the collaborative association constraints and endurance constraints between the drone and the mobile workshop, and construct the access number constraints for the required road segments to ensure that the monitoring and patrol of all task road segments are completed collaboratively.

[0071] S3-4: Establish a traffic monitoring planning model for UAV-assisted mobile vehicles in urban flooding scenarios to maximize the coverage of road segment monitoring tasks within the emergency mission time limit; the traffic monitoring planning model is as follows:

[0072]

[0073] satisfy:

[0074]

[0075]

[0076]

[0077]

[0078]

[0079]

[0080]

[0081]

[0082]

[0083]

[0084]

[0085]

[0086]

[0087]

[0088] Where w represents the objective function for maximizing the coverage required by the road segment monitoring task; K represents the set of UAV sequences and the corresponding set of mobile vehicle sequences, and k represents the kth UAV or mobile vehicle; S ij This represents the demand profit value of road segment (i,j); Used to indicate whether road segment (i,j) is visited by drone k; Indicates whether road segment (i,j) has been visited by moving vehicle k; Used to record whether the kth drone was extended before visiting the (i,j) road segment; A p Indicates road sections that require joint monitoring by drones and vehicles; A d Indicates road sections that require monitoring only by drones; A cThis indicates road sections that require monitoring only by vehicles;

[0089] (s,s) represents the starting point of the moving vehicle and the drone. This indicates whether road segment (i,j) is visited by drone k after road segment (s,s). This indicates whether road segment (s,s) is visited by drone k after road segment (i,j). This indicates whether road segment (s,s) is visited by moving car k after road segment (i,j). Indicates whether segment (i,j) is visited by moving car k after segment (s,s); e.g., Z 1 (11,14)(2,7) This indicates that after visiting the required road segment (11, 14), UAV 1 visited the road segment (2, 7). This only considers the road segment required for the mission, not all road segments in the road network.

[0090] This indicates whether road segment (i',j') is visited by drone k after road segment (i,j). This indicates whether road segment (i,j) is visited by drone k after road segment (i',j'). Indicates whether segment (i',j') is visited by moving car k after segment (i,j); Indicates whether segment (i,j) is visited by moving car k after segment (i',j');

[0091] t ij The time cost of the drone flying over road segment (i,j); r ji' This indicates that the shortest distance between road segments (i,j) and (i',j') is from point j to point i'; r ij H1 represents the shortest distance the drone travels from i to j; H2 represents the average speed of the drone; H3 represents the average speed of the moving vehicle; T represents the average speed of the moving vehicle. max Indicates the upper limit of the time for emergency response to urban flooding; This indicates the start time of service for vehicle k on road segment (i,j);

[0092] This represents the start time of drone k's service on road segment (i,j); This represents the start time of drone k's service on road segment (i', j'); M represents a sufficiently large value. This indicates the start time of service for vehicle k on road segment (i', j'); r si T represents the shortest distance from s to i for the drone; d Indicates the longest continuous flight time of the drone;

[0093] Decision variables A value of 0 indicates a negative result, and a value of 1 indicates a positive result.

[0094] S3-5: Solve the traffic monitoring planning model to determine the monitoring paths of the UAV and mobile vehicle, and obtain the optimal collaborative monitoring path scheme.

[0095] The beneficial effects of the technical solution provided by this invention are:

[0096] (1) This invention takes into account the real road conditions in the flooding scenario and is more suitable for the monitoring planning needs in the actual flooding scenario. It allocates suitable monitoring road sections to mobile vehicles and drones respectively, and introduces the constraint of vehicle group for drone group endurance, etc., to make full use of the respective advantages of drones and ground vehicles to monitor their respective suitable monitoring road sections, avoid the monitoring task being unable to be carried out due to the actual road conditions, give full play to the collaborative advantages, and make up for the limitation of short drone endurance.

[0097] (2) Most traditional inventions focus on minimizing the total time of all patrol tasks, ignoring the time limit of emergency response. This invention establishes an emergency planning model for UAVs and mobile vehicles in the context of urban flooding, which maximizes the coverage of road task requirements within the limited time of emergency tasks. It is more suitable for urban flooding emergency patrol scenarios, thereby improving the efficiency of collaborative monitoring and increasing the response speed of key road sections. Attached Figure Description

[0098] The present invention will be further described below with reference to the accompanying drawings and embodiments. In the accompanying drawings:

[0099] Figure 1 This is a flowchart of a traffic monitoring and planning method for unmanned aerial vehicles (UAVs) in conjunction with mobile vehicles in an urban flooding scenario, as described in an embodiment of the present invention.

[0100] Figure 2 This is a flowchart illustrating the monitoring task requirements in an embodiment of the present invention.

[0101] Figure 3 This is a schematic diagram of road network nodes and road segments in an embodiment of the present invention.

[0102] Figure 4 This is a schematic diagram illustrating the monitoring task requirements in the road network in an embodiment of the present invention.

[0103] Figure 5 This is a schematic diagram illustrating the allocation of suitable monitoring road sections in an embodiment of the present invention.

[0104] Figure 6 This is a schematic diagram illustrating the allocation of monitoring tasks based on road condition characteristics in an embodiment of the present invention.

[0105] Figure 7 This is a flowchart of establishing a traffic monitoring planning model in an embodiment of the present invention.

[0106] Figure 8This is a rendering of the collaborative traffic monitoring scheme in an urban flooding scenario, as described in this embodiment of the invention. Detailed Implementation

[0107] To provide a clearer understanding of the technical features, objectives, and effects of the present invention, specific embodiments of the present invention will now be described in detail with reference to the accompanying drawings.

[0108] This invention provides a traffic monitoring planning method and system for drones and mobile vehicles in urban flooding scenarios. First, based on near-real-time rainfall, past traffic flow data, and predicted water accumulation, the monitoring task requirements for urban flooding scenarios are obtained. Then, by extracting road condition characteristics of the monitoring area, suitable monitoring sections are assigned to both drones and mobile vehicles. Next, a collaborative traffic monitoring planning model for vehicle and drone swarms is established to maximize the coverage of road sections within the time limit of the urban flooding emergency task. Finally, the model is solved to obtain the optimal collaborative monitoring path scheme for urban flooding emergency scenarios.

[0109] Please refer to Figure 1 , Figure 1 This is a flowchart of a traffic monitoring and planning method for unmanned aerial vehicles (UAVs) in conjunction with mobile vehicles in a flood-prone scenario, as described in an embodiment of the present invention. The method specifically includes:

[0110] S1: Based on near-real-time rainfall data, past traffic flow data, and predicted water accumulation, obtain the monitoring task requirements for urban flooding scenarios. The specific process is as follows: Figure 2 As shown, the implementation process is as follows:

[0111] S1-1: The experimental road network is a Sioux Falls network, consisting of 24 nodes and 38 line segments, such as... Figure 3 The diagram shows the network, and Table 1 shows the network data. The near-real-time rainfall values ​​were obtained before the monitoring task was performed. The process was as follows: raster layers were obtained through ArcGIS spatial interpolation, and the sum of the raster values ​​in the road buffer was extracted as the near-real-time rainfall values ​​for each road within the task range.

[0112] Table 1. Sioux Falls Network Data Values

[0113]

[0114] S1-2: Use Baidu Maps API to obtain traffic flow statistics for past roads and identify the congestion risk of each road;

[0115] S1-3: Extract the predicted water accumulation values ​​of road sections obtained from the water accumulation simulation, and determine the water accumulation risk value of each road section;

[0116] S1-4: A weighted analysis method is used to process near-real-time rainfall values, past traffic flow data, and predicted water accumulation values. A set of road segments that need to be monitored is selected from the task area, such as... Figure 4As shown, a total of 19 road sections were selected for monitoring in this example.

[0117] S2: Extract road condition features of the monitored area and assign suitable monitoring sections to the drones and mobile vehicles. The specific process is as follows: Figure 5 As shown, the implementation process is as follows:

[0118] S2-1: Obtain actual road condition characteristics within the monitored area, marking features that directly affect monitoring methods, such as severe congestion, culverts, tree obstructions, and deep water accumulation. Figure 6 As shown, road segment features that directly affect monitoring methods are marked; in this embodiment, two road segments that can only be monitored by mobile vehicles and two road segments that can only be monitored by drones are marked.

[0119] S2-2: Assign task sections that are inaccessible by vehicles or restricted by congestion to sections that can only be monitored by drones;

[0120] S2-3: Mark road sections with culverts or tree cover as road sections that can only be monitored by vehicles;

[0121] S2-4: The remaining task segments consist of task segments that can be monitored by vehicles and drones working together.

[0122] S3: Establish a collaborative traffic monitoring planning model for vehicle and drone swarms, taking into account the need for drone endurance, determine the optimal monitoring paths for drones and mobile vehicles, and obtain the optimal collaborative monitoring path scheme. The specific process is as follows: Figure 7 As shown, the implementation process is as follows:

[0123] S3-1: Construct a traffic monitoring planning model for UAVs and mobile vehicles in the scenario of urban flooding, and determine the objective function of the model as maximizing the coverage of collaborative task requirements within the time limit;

[0124] In this embodiment, a road segment in the road network is replaced by a two-way road segment {(i, j), (j, i)} with two nodes. (s, s) represents the starting point of the moving vehicle and the drone; in this example, (9, 9) is used as the starting point. A p This represents the road segments that can be jointly monitored by drones and vehicles. In this example, it includes 15 shared monitoring arcs, such as (1,3) and (2,6). In the model, (1,3) and (3,1) represent the same road segment; A d This indicates road segments that can only be monitored by drones; in this example, these include (3, 12) and (14, 15). A cThe required road segments can only be monitored by vehicles. In this example, (14, 23) and (16, 17) are included. The objective function w of the model is determined to maximize the task requirement coverage of the UAV-coordinated mobile vehicle in the flood emergency scenario, that is, to maximize the sum of the road segment requirement values ​​collected by the vehicle group and the UAV group within the time limit, while removing the overlapping road segment requirement values ​​at the end of the range.

[0125] S3-2: Determine the upper limit of the emergency monitoring task in the flooding scenario, set the starting point constraints and access order constraints for mobile vehicles and drone swarms, avoid sub-loops, and constraints 2 and 3 ensure that the number of times each monitoring tool enters and leaves a certain road segment is consistent; constraint 4 establishes the relationship between the access order of the road segment to be monitored and whether the road segment is monitored; constraint 5 determines the upper limit T of the emergency monitoring task in the flooding scenario. max In this example, it is set to 60 minutes, meaning that the total monitoring time of the vehicle group and the drone group does not exceed this limit.

[0126] S3-3: Construct access frequency constraints for demand road segments, with constraint 6 ensuring that each monitored road segment is not served repeatedly; set collaborative association constraints and battery life constraints between the drone and the mobile workshop, and construct access frequency constraints for demand road segments to ensure collaborative completion of monitoring and patrol of all task road segments; in this embodiment, set collaborative association constraints between the drone and the mobile workshop, with constraints 7, 8, 9, 10, 11, and 12 limiting the start service time of the mobile vehicle or drone for the monitored road segment to avoid sub-loops; set battery life constraints, in this example the battery limit is set to 40 minutes of continuous flight, with constraints 12, 13, and 14 ensuring that each drone's flight is within the battery limit, and constraint 15 ensuring that at each battery life point, the mobile vehicle arrives in advance to wait for the drone;

[0127] S3-4: Establish a traffic monitoring planning model for UAVs and mobile vehicles in urban flooding scenarios to maximize the coverage of road segment monitoring tasks within the emergency mission time limit. The traffic monitoring planning model is as follows:

[0128]

[0129] satisfy:

[0130]

[0131]

[0132]

[0133]

[0134]

[0135]

[0136]

[0137]

[0138]

[0139]

[0140]

[0141]

[0142]

[0143]

[0144] Where w represents the objective function for maximizing the coverage required by the drone-mobile vehicle collaboration in the urban flooding emergency scenario; K represents the set of drone sequences and the corresponding set of mobile vehicle sequences, in this example K = {1, 2}, which means two drones and two mobile vehicles are conducting collaborative monitoring; S ij Let (i,j) represent the demand profit value of road segment (i,j); (s,s) represent the starting point of the mobile vehicle and the drone; A p Indicates road sections that require joint monitoring by drones and vehicles; A d Indicates road sections that require monitoring only by drones; A c Indicates road sections requiring monitoring only by vehicles; T max Indicates the upper limit of the emergency response time for flooding; T d Indicates the longest continuous flight time of a drone; t ij The time cost of the drone flying over road segment (i,j); r ij r represents the shortest distance from i to j for the drone. ji' The shortest distance between road segments (i,j) and (i',j') is from point j to point i'; M represents a sufficiently large value. Used to indicate whether road segment (i,j) is visited by drone k; Indicates whether road segment (i,j) has been visited by moving vehicle k; Indicates whether road segment (i',j') is visited by drone k after road segment (i,j); Indicates whether segment (i',j') is visited by moving car k after segment (i,j); This represents the start time of drone k's service on road segment (i,j); H1 represents the start time of mobile vehicle k on road segment (i,j); H2 represents the average speed of the drone; H3 represents the average speed of the mobile vehicle. Used to record whether the k-th drone is extended before visiting road segment (i,j). Decision variable. This is a binary decision variable, with a value of 0 indicating a no decision and a value of 1 indicating a yes decision.

[0145] S3-5: As Figure 8 As shown in Table 2, the monitoring paths of the drone and the mobile vehicle are confirmed, and the monitoring planning scheme of the drone and the mobile vehicle is obtained:

[0146] Table 2 Collaborative Monitoring Scheme under Urban Flooding Scenarios

[0147]

[0148] A traffic monitoring and planning system for drones and mobile vehicles in flood-prone scenarios includes:

[0149] The task requirement acquisition module is used to obtain monitoring task requirements in urban flooding scenarios based on rainfall values, traffic flow data, and predicted water accumulation values.

[0150] The monitoring segment allocation module is used to extract the road condition features of the monitoring area from the actual road conditions according to the monitoring task requirements, and allocate suitable monitoring segments to the drones and mobile vehicles respectively.

[0151] The traffic monitoring planning model building module is used to build a traffic monitoring planning model for UAVs and mobile vehicles in the context of urban flooding based on the monitored road segment, and to determine the objective function of the model as maximizing the coverage of collaborative monitoring task requirements within the time limit.

[0152] The optimal surveillance path determination module is used to determine the optimal surveillance path for the UAV and mobile vehicle by solving the traffic surveillance planning model, thereby obtaining the optimal collaborative surveillance path scheme.

[0153] The specific implementation process of the task requirement acquisition module is as follows:

[0154] S1-1: Obtain near-real-time rainfall values ​​before executing the monitoring task, and obtain the near-real-time rainfall grid cumulative values ​​for each road within the task range through spatial interpolation;

[0155] S1-2: Obtain statistical data on past traffic flow on the road to determine the congestion risk of each road;

[0156] S1-3: Extract the predicted water accumulation values ​​of road sections obtained from the water accumulation simulation, and determine the water accumulation risk value of each road section;

[0157] S1-4: Use weighted analysis to process near-real-time rainfall values, past traffic flow data, and predicted water accumulation values, and select a set of road segments that need to be monitored from the task area.

[0158] The specific implementation process of the monitored road segment allocation module is as follows:

[0159] S2-1: Obtain the actual road condition characteristics within the monitoring area and mark the road segment characteristics that have a direct impact on the monitoring methods;

[0160] S2-2: Assign vehicle-restricted task sections to sections that can only be monitored by drones;

[0161] S2-3: Mark road sections where drones are restricted as road sections that can only be monitored by vehicles;

[0162] S2-4: The remaining task segments consist of task segments that can be monitored by vehicles and drones working together.

[0163] The specific implementation process of the traffic monitoring planning model establishment module is as follows:

[0164] S3-1: Construct a traffic monitoring planning model for UAVs and mobile vehicles in the scenario of urban flooding, and determine the objective function of the model as maximizing the coverage of collaborative monitoring task requirements within the time limit;

[0165] S3-2: Determine the upper limit of the emergency monitoring task in the case of urban flooding, set the starting point constraints and access order constraints for mobile vehicles and drone swarms, and avoid sub-loops;

[0166] S3-3: Set the collaborative association constraints and endurance constraints between the drone and the mobile workshop, and construct the access number constraints for the required road segments to ensure that the monitoring and patrol of all task road segments are completed collaboratively.

[0167] S3-4: Establish a traffic monitoring planning model for UAV-assisted mobile vehicles in urban flooding scenarios to maximize the coverage of road segment monitoring tasks within the emergency mission time limit; the traffic monitoring planning model is as follows:

[0168]

[0169] satisfy:

[0170]

[0171]

[0172]

[0173]

[0174]

[0175]

[0176]

[0177]

[0178]

[0179]

[0180]

[0181]

[0182]

[0183]

[0184] Where w represents the objective function for maximizing the coverage required by the road segment monitoring task; K represents the set of UAV sequences and the corresponding set of mobile vehicle sequences, and k represents the kth UAV or mobile vehicle; S ij This represents the demand profit value of road segment (i,j); Used to indicate whether road segment (i,j) is visited by drone k; Indicates whether road segment (i,j) has been visited by moving vehicle k; Used to record whether the kth drone was extended before visiting the (i,j) road segment; A p Indicates road sections that require joint monitoring by drones and vehicles; A d Indicates road sections that require monitoring only by drones; A c This indicates road sections that require monitoring only by vehicles;

[0185] (s,s) represents the starting point of the moving vehicle and the drone. This indicates whether road segment (i,j) is visited by drone k after road segment (s,s). This indicates whether road segment (s,s) is visited by drone k after road segment (i,j). This indicates whether road segment (s,s) is visited by moving car k after road segment (i,j). Indicates whether segment (i,j) is visited by moving car k after segment (s,s); e.g., Z 1 (11,14)(2,7) This indicates that after visiting the required road segment (11, 14), UAV 1 visited the road segment (2, 7). This only considers the road segment required for the mission, not all road segments in the road network.

[0186] This indicates whether road segment (i',j') is visited by drone k after road segment (i,j). This indicates whether road segment (i,j) is visited by drone k after road segment (i',j'). Indicates whether segment (i',j') is visited by moving car k after segment (i,j); Indicates whether segment (i,j) is visited by moving car k after segment (i',j');

[0187] t ij The time cost of the drone flying over road segment (i,j); r ji' This indicates that the shortest distance between road segments (i,j) and (i',j') is from point j to point i'; r ij H1 represents the shortest distance the drone travels from i to j; H2 represents the average speed of the drone; H3 represents the average speed of the moving vehicle; T represents the average speed of the moving vehicle. max Indicates the upper limit of the time for emergency response to urban flooding; This indicates the start time of service for vehicle k on road segment (i,j);

[0188] This represents the start time of drone k's service on road segment (i,j); This represents the start time of drone k's service on road segment (i', j'); M represents a sufficiently large value. This indicates the start time of service for vehicle k on road segment (i', j'); r si T represents the shortest distance from s to i for the drone; d Indicates the longest continuous flight time of the drone;

[0189] Decision variables A value of 0 indicates a negative result, and a value of 1 indicates a positive result.

[0190] S3-5: Solve the traffic monitoring planning model to determine the monitoring paths of the UAV and mobile vehicle, and obtain the optimal collaborative monitoring path scheme.

[0191] The beneficial effects of this invention are:

[0192] (1) This invention takes into account the real road conditions in the flooding scenario and is more suitable for the monitoring planning needs in the actual flooding scenario. It allocates suitable monitoring road sections to mobile vehicles and drones respectively, and introduces the constraint of vehicle group for drone group endurance, etc., to make full use of the respective advantages of drones and ground vehicles to monitor their respective suitable monitoring road sections, avoid the monitoring task being unable to be carried out due to the actual road conditions, give full play to the collaborative advantages, and make up for the limitation of short drone endurance.

[0193] (2) Most traditional inventions focus on minimizing the total time of all patrol tasks, ignoring the time limit of emergency response. This invention establishes an emergency planning model for UAVs and mobile vehicles in the context of urban flooding, which maximizes the coverage of road task requirements within the limited time of emergency tasks. It is more suitable for urban flooding emergency patrol scenarios, thereby improving the efficiency of collaborative monitoring and increasing the response speed of key road sections.

[0194] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A traffic monitoring and planning method for unmanned aerial vehicles (UAVs) and mobile vehicles in a flood-prone scenario, characterized in that: include: S1: Based on rainfall data, traffic flow data, and predicted water accumulation, obtain the monitoring task requirements under the scenario of urban flooding; S2: Based on the monitoring task requirements, extract the road condition features of the monitoring area from the actual road conditions, and assign suitable monitoring sections to the drones and mobile vehicles respectively. S3: Based on the monitored road sections, establish a traffic monitoring planning model for UAV-assisted mobile vehicles in the context of urban flooding, and determine the objective function of the model as maximizing the coverage of the collaborative monitoring task requirements within the time limit; the specific implementation process is as follows: S3-1: Construct a traffic monitoring planning model for UAVs and mobile vehicles in the scenario of urban flooding, and determine the objective function of the model as maximizing the coverage of collaborative monitoring task requirements within the time limit; S3-2: Determine the upper limit of the emergency monitoring task in the case of waterlogging, set the starting point constraints and access order constraints for mobile vehicles and drone swarms, and avoid sub-loops; S3-3: Set the collaborative association constraints and endurance constraints between the drone and the mobile workshop, and construct the access number constraints for the required road segments to ensure that the monitoring and patrol of all task road segments are completed collaboratively. S3-4: Establish a traffic monitoring planning model for UAV-assisted mobile vehicles in urban flooding scenarios to maximize the coverage of road segment monitoring tasks within the emergency mission time limit; the traffic monitoring planning model is as follows: satisfy: in, w This represents the objective function for maximizing the coverage required by the road segment monitoring task; K represents the set of UAV sequences and the corresponding set of mobile vehicle sequences, and k represents the kth UAV or mobile vehicle; This represents the demand profit value of road segment (i, j); Used to indicate road segments Whether it was accessed by drone k; Indicates road segment Is it accessed by the mobile vehicle? Used to record whether the kth drone was extended before visiting the (i,j) segment; A p This indicates road sections that require joint monitoring by drones and vehicles; A d This indicates road sections that can only be monitored by drones; A c This indicates road sections that require monitoring only by vehicles; (s,s) represents the starting point of the moving vehicle and the drone. On the road section , Represents road segment (s,s) On the road section express ， ， ； ； t ij This represents the time cost for the drone to fly over road segment (i,j); Indicates the drone from j to The shortest distance; r ij This represents the shortest distance the drone travels from i to j; H 1 represents the average speed of the drone; H 2 represents the average speed of the moving vehicle; Indicates the upper limit of the time for emergency response to urban flooding; This indicates the start time of service for vehicle k on road segment (i, j); This represents the start time of drone k's service on road segment (i,j); Drones on road sections The start time of service; M This represents a sufficiently large value; Moving vehicle k pairs of road sections The start time of service; Indicates that the drone is from s arrive The shortest distance; Indicates the longest continuous flight time of the drone; Decision variables A value of 0 indicates a negative result, and a value of 1 indicates a positive result. S3-5: Solve the traffic monitoring planning model to determine the monitoring paths of the UAV and mobile vehicle, and obtain the optimal collaborative monitoring path scheme. S4: Solve the traffic monitoring planning model to determine the optimal monitoring path for the UAV and mobile vehicle, and obtain the optimal collaborative monitoring path scheme.

2. The traffic monitoring and planning method for unmanned aerial vehicles (UAVs) in conjunction with mobile vehicles in a flood-prone scenario as described in claim 1, characterized in that: The specific implementation process of step S1 is as follows: S1-1: Obtain near-real-time rainfall values ​​before executing the monitoring task; S1-2: Obtain statistical data on past traffic flow on the road to determine the congestion risk of each road; S1-3: Extract the predicted water accumulation values ​​of road sections obtained from the water accumulation simulation, and determine the water accumulation risk value of each road section; S1-4: Use weighted analysis to process near-real-time rainfall values, past traffic flow data, and predicted water accumulation values, and select a set of road segments that need to be monitored from the task area.

3. The traffic monitoring and planning method for unmanned aerial vehicles (UAVs) in conjunction with mobile vehicles in a flood-prone scenario as described in claim 1, characterized in that: The specific implementation process of step S2 is as follows: S2-1: Obtain the actual road condition characteristics within the monitoring area and mark the road segment characteristics that have a direct impact on the monitoring methods; S2-2: Assign vehicle-restricted task sections to sections that can only be monitored by drones; S2-3: Mark road sections where drones are restricted as road sections that can only be monitored by vehicles; S2-4: The remaining task segments consist of task segments that can be monitored by vehicles and drones working together.

4. A traffic monitoring and planning system for unmanned aerial vehicles (UAVs) and mobile vehicles in a flood-prone scenario, characterized in that: include: The task requirement acquisition module is used to obtain monitoring task requirements in urban flooding scenarios based on rainfall values, traffic flow data, and predicted water accumulation values. The monitoring segment allocation module is used to extract the road condition features of the monitoring area from the actual road conditions according to the monitoring task requirements, and allocate suitable monitoring segments to the drones and mobile vehicles respectively. The traffic monitoring planning model building module is used to establish a traffic monitoring planning model for UAVs and mobile vehicles in a flood-prone scenario based on the monitored road segment. The objective function of the model is to maximize the coverage of the collaborative monitoring task within the time limit. The specific implementation process is as follows: S3-1: Construct a traffic monitoring planning model for UAVs and mobile vehicles in the scenario of urban flooding, and determine the objective function of the model as maximizing the coverage of collaborative monitoring task requirements within the time limit; S3-2: Determine the upper limit of the emergency monitoring task in the case of waterlogging, set the starting point constraints and access order constraints for mobile vehicles and drone swarms, and avoid sub-loops; S3-3: Set the collaborative association constraints and endurance constraints between the drone and the mobile workshop, and construct the access number constraints for the required road segments to ensure that the monitoring and patrol of all task road segments are completed collaboratively. S3-4: Establish a traffic monitoring planning model for UAV-assisted mobile vehicles in urban flooding scenarios to maximize the coverage of road segment monitoring tasks within the emergency mission time limit; the traffic monitoring planning model is as follows: satisfy: in, w This represents the objective function for maximizing the coverage required by the road segment monitoring task; K represents the set of UAV sequences and the corresponding set of mobile vehicle sequences, and k represents the kth UAV or mobile vehicle; This represents the demand profit value of road segment (i,j); Used to indicate road segments Whether it was accessed by drone k; Indicates road segment Is it accessed by the mobile vehicle? Used to record whether the kth drone was extended before visiting the (i,j) segment; A p This indicates road sections that require joint monitoring by drones and vehicles; A d This indicates road sections that can only be monitored by drones; A c This indicates road sections that require monitoring only by vehicles; (s,s) represents the starting point of the moving vehicle and the drone. On the road section , Represents road segment (s,s) On the road section express ， ， ； ； t ij This represents the time cost for the drone to fly over road segment (i,j); Indicates road segment ( i,j )and The shortest distance between them is from point j to point j. ; r ij This represents the shortest distance the drone travels from i to j; H 1 represents the average speed of the drone; H 2 represents the average speed of the moving vehicle; Indicates the upper limit of the time for emergency response to urban flooding; This indicates the start time of service for vehicle k on road segment (i, j); This represents the start time of drone k's service on road segment (i,j); Drones on road sections The start time of service; M This represents a sufficiently large value; Moving vehicle k pairs of road sections The start time of service; Indicates that the drone is from s arrive The shortest distance; Indicates the longest continuous flight time of the drone; Decision variables A value of 0 indicates a negative result, and a value of 1 indicates a positive result. S3-5: Solve the traffic monitoring planning model to determine the monitoring paths of the UAV and mobile vehicle, and obtain the optimal collaborative monitoring path scheme. The optimal surveillance path determination module is used to determine the optimal surveillance path for the UAV and mobile vehicle by solving the traffic surveillance planning model, thereby obtaining the optimal collaborative surveillance path scheme.

5. The system as described in claim 4, characterized in that: The specific implementation process of the task requirement acquisition module is as follows: S1-1: Obtain near-real-time rainfall values ​​before executing the monitoring task, and obtain the near-real-time rainfall grid cumulative values ​​for each road within the task range through spatial interpolation; S1-2: Obtain statistical data on past traffic flow on the road to determine the congestion risk of each road; S1-3: Extract the predicted water accumulation values ​​of road sections obtained from the water accumulation simulation, and determine the water accumulation risk value of each road section; S1-4: Use weighted analysis to process near-real-time rainfall values, past traffic flow data, and predicted water accumulation values, and select a set of road segments that need to be monitored from the task area.

6. The system as described in claim 4, characterized in that: The specific implementation process of the monitored road segment allocation module is as follows: S2-1: Obtain the actual road condition characteristics within the monitoring area and mark the road segment characteristics that have a direct impact on the monitoring methods; S2-2: Assign vehicle-restricted task sections to sections that can only be monitored by drones; S2-3: Mark road sections where drones are restricted as road sections that can only be monitored by vehicles; S2-4: The remaining task segments consist of task segments that can be monitored by vehicles and drones working together.

Images