Unmanned aerial vehicle highway inspection method based on fixed nest technology

Abstract

The invention discloses an unmanned aerial vehicle expressway inspection method based on a fixed nest technology, and the method comprises the following steps: S1, collecting expressway GIS information, carrying out the segmentation marking of expressway intervals according to the expressway GIS information, and constructing an expressway inspection task set; s2, traffic flow parameters corresponding to the task intervals are collected, and the task intervals are evaluated and scored in combination with an entropy weight method-Topsis method; s3, constructing a highway roadside unmanned aerial vehicle fixed nest site selection optimization model in combination with an evaluation scoring result, and determining a fixed nest placement position; and S4, constructing an unmanned aerial vehicle routing inspection path planning model based on the fixed nest site selection result range, and calculating a path planning scheme under the coverage of the fixed nest. Through a dynamic segmentation strategy and a double-layer optimization framework, the problems of fuzzy task priority, redundant machine nest deployment and low path efficiency in traditional routing inspection are solved, the coverage precision of high-risk road sections is remarkably improved, and the deployment cost and energy consumption are reduced.

Description

A method for highway inspection using unmanned aerial vehicles (UAVs) based on fixed-nest technology Technical Field

[0001] This invention belongs to the field of intelligent traffic management technology, specifically relating to a method for unmanned aerial vehicle (UAV) highway inspection based on fixed-nest technology. Background Technology

[0002] With the acceleration of urbanization, highway networks are becoming increasingly complex, traffic flow is continuously growing, and the demand for road safety and maintenance is significantly increasing. Traditional highway inspections mainly rely on manual patrols or fixed monitoring equipment, which suffers from low efficiency, limited coverage, and slow response times, making it difficult to meet the needs of real-time monitoring of sudden traffic incidents, accidents, or road infrastructure damage. In recent years, drones have been gradually applied to highway inspection due to their high mobility, flexible deployment, and wide field of view. However, existing drone inspection solutions mostly adopt temporary take-off and landing or single base station deployment modes, which suffer from insufficient endurance, limited coverage, and unscientific task planning, making it difficult to adapt to the long-distance, high-density inspection needs of highways.

[0003] To address the aforementioned issues, some existing research has attempted to optimize UAV deployment and mission execution through fixed-nest technology. Fixed nests can provide UAVs with automatic charging, data transmission, and centralized scheduling support, thereby extending their operational cycle. However, existing fixed-nest-based solutions still have certain shortcomings: Firstly, most solutions lack quantitative differentiation of the importance of inspection tasks, often relying primarily on coverage or distance for deployment and scheduling, making it difficult to prioritize key road sections with high accident rates or congestion sensitivity. Secondly, nest deployment and path planning are often disconnected, and insufficient consideration is given to engineering constraints such as UAV range and return-to-home, easily leading to low overall coverage efficiency or insufficient feasibility of the solution in actual implementation. Summary of the Invention

[0004] The purpose of this invention is to design a method for unmanned aerial vehicle (UAV) highway inspection based on fixed UAV nesting technology. This method determines the optimal location of UAV nests and the global inspection path of the UAVs within the highway network, while simultaneously considering UAV endurance limitations, differences in inspection task priorities, and nesting deployment cost constraints. This method minimizes the number of UAV nests deployed and the total energy consumption of UAVs while ensuring inspection coverage and real-time performance, thereby improving traffic incident response efficiency and providing low-carbon, cost-effective technical support for smart highway management.

[0005] In one aspect, the present invention proposes a method for unmanned aerial vehicle (UAV) highway inspection based on fixed-nest technology. According to an embodiment of the present invention, the method includes the following steps:

[0006] S1: Collect highway GIS information (Geographic Information System), segment and mark highway sections according to highway geographic information, and construct a set of highway inspection tasks;

[0007] S2: Collect relevant traffic flow parameters for the task interval and evaluate and score the task interval using the entropy weight method-TOPSIS method.

[0008] S3: Based on the evaluation and scoring results, construct an optimization model for the location of fixed drone nests on the highway side to determine the placement location of the fixed drone nests;

[0009] S4: Construct a UAV inspection path planning model within the range of fixed UAV nest location results, and calculate the path planning scheme under the coverage of fixed UAV nests.

[0010] In addition, the UAV highway inspection method based on fixed nest technology according to the above embodiments of the present invention may also have the following additional technical features:

[0011] In some embodiments of the present invention, step S1, the step of constructing the highway inspection task set, is as follows:

[0012] S101: Collect GIS information on expressways and select expressway sections with inspection needs;

[0013] S102: The sections of the highway are segmented and marked, with the segment distance set to half of the maximum inspection radius of the drone;

[0014] S103: Constructing a set of highway inspection tasks , where n is the total number of highway inspection task sections (sections after segmentation).

[0015] In some embodiments of the present invention, step S2, the entropy weight method-Topsis method for evaluating and scoring the task interval is as follows:

[0016] S201: Collect traffic flow parameters for each highway inspection section;

[0017] S202: The importance of each traffic flow parameter is calculated using the entropy weight method;

[0018] S203: Combine the Topsis method to construct the ideal optimal solution and the worst solution. By calculating the distance from each interval to the optimal solution and the worst solution, obtain the interval score and form the task priority ranking.

[0019] S205: Output the task interval level classification results based on the score results, providing input basis for subsequent nest location selection and path planning.

[0020] In some embodiments of the present invention, in step S201, the traffic flow parameters include the hourly traffic flow of the interval. Traffic density Average vehicle speed Frequency of accidents Construct feature vectors And further form a feature matrix. .

[0021] In some embodiments of the present invention, the weight calculation method in step S202 is as follows: extract the feature matrix, , Assign task range numbers, The evaluation index is used to positively normalize the eigenvector index; the entropy value is calculated according to the entropy value calculation formula; the entropy weight of each point is calculated according to the entropy weight calculation formula; and the weighted decision is calculated according to the weighted decision matrix formula.

[0022] In some embodiments of the present invention, step S203 includes the calculation process of constructing an ideal solution. With negative ideal solution Calculate distance and score , , In the formula, Indicates the first The distance between each evaluation object and the positive ideal solution; Indicates the first The distance between each evaluation object and the negative ideal solution; Indicates the first The relative progress of each evaluation object.

[0023] In some embodiments of the present invention, step S3, the step of constructing the optimization model for the location of fixed UAV nests on highways, is as follows:

[0024] S301: Retrieve the set of scored highway tasks And set interval scores. A higher score indicates a higher inspection priority;

[0025] S302: A predefined set of candidate locations for deploying fixed nests based on urban planning and geographical conditions. M represents the total number of candidate fixed nest locations, and m represents the final number of nests actually deployed.

[0026] S303: Define the drone from the candidate nest The departure can cover the mission area. binary relation If it can be covered ;

[0027] S304: Construct the following optimization model:

[0028] objective function To ensure that high-priority task ranges are covered first, while maximizing coverage efficiency, x j Let be the deployment decision variable for the j-th candidate nest location;

[0029] Constraint (1) This indicates that the total number of deployed nests does not exceed the budget. ;

[0030] Constraint (2) This indicates that at least one deployment nest covers the mission area. , z i This is the coverage indicator variable for task interval i;

[0031] Constraint (3) Limit the feasible region of decision variables.

[0032] In some embodiments of the present invention, step S4, which involves constructing a UAV inspection path planning model within the range of fixed UAV nest location results, is as follows:

[0033] S401: Based on the fixed nest location results, obtain each nest The set of task points that can be covered These serve as the inspection points that the drones under the nest need to complete;

[0034] S402: One or more drones are assigned to each nest. Each drone must start from the nest, complete its mission, and return to the same nest. The total path length is limited by the drone's maximum flight distance.

[0035] S403: Constructing a multi-path constrained path planning model with the objective of minimizing the total flight distance:

[0036] objective function ;

[0037] Constraint (4) This indicates that the task point must be visited once;

[0038] Constraint (5) This indicates that the starting and ending points of each path are nests;

[0039] Constraint (6) This indicates that the path is correctly connected;

[0040] Constraint (7) , indicating the total constraint on flight distance;

[0041] In the formula: A set of points consisting of mission points and nest points; For point Time Spacing; This represents the maximum flight distance of the drone. This represents the number of available drones under this nest. As a decision variable, if the drone From point Time The value is 1; For drones Access Point The cumulative flight distance afterward; Indicates drone From the hive point to the mission point ; Indicates drone From the mission point Return to the hive point; drones Arrive at (or leave) the mission point The cumulative flight distance is a continuous variable used to ensure path connectivity and eliminate sub-loops.

[0042] Compared with the prior art, the beneficial effects of the present invention are:

[0043] (1) This invention addresses the problems of ambiguous task priorities, redundant nest deployment, and inefficient path planning in highway UAV inspection scenarios. It constructs an entropy weight method-Topsis priority quantification model that integrates multi-dimensional traffic flow assessment and a two-layer optimization framework of nest location selection and path planning. By introducing a nest location selection objective driven by coverage probability and a multi-UAV collaborative path planning model, the coverage accuracy and resource allocation rationality of high-priority road sections are significantly improved. In addition, this invention proposes a dynamic segmentation marking strategy based on half of the maximum inspection radius of UAVs. Combined with a multi-nest task collaborative scheduling mechanism, it breaks through the limitations of traditional fixed segmentation and single-nest scheduling. While eliminating inspection blind spots, it reduces nest deployment costs and UAV flight energy consumption, providing a highly scalable, low-cost, and low-carbon solution for intelligent traffic management.

[0044] (2) Based on traffic operation data, this invention performs feature modeling on the inspection section and calculates the task priority. Under constraints such as budget and flight distance, it jointly optimizes the fixed nest deployment and inspection task execution strategy, thereby achieving priority coverage of high-priority road sections and improving the overall efficiency and feasibility of the inspection plan.

[0045] Based on the above reasons, this invention can be widely promoted in the field of highway inspection. Attached Figure Description

[0046] Figure 1 is a flowchart of a UAV highway inspection method based on fixed nest technology in an embodiment of the present invention. Detailed Implementation

[0047] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present invention.

[0048] As shown in Figure 1, a method for highway inspection using unmanned aerial vehicles (UAVs) based on fixed-nest technology includes the following steps:

[0049] S1: Collect GIS information on highways, segment and mark highway sections according to the highway geographic information, and construct a task set.

[0050] S101. Collect GIS information on expressways and select expressway sections with inspection needs;

[0051] S102. The sections of the expressway are divided into segments and marked, with the segment distance set to half of the maximum inspection radius of the drone.

[0052] S103. Based on the segmentation results, construct a set of highway inspection tasks. , where n is the total number of highway inspection task sections (sections after segmentation).

[0053] S2: Collect relevant traffic flow property parameters for the task interval and evaluate and score the task interval using the entropy weight method-TOPSIS method.

[0054] S201. Collect traffic flow parameters for each highway inspection section, including hourly traffic flow within the section. Traffic density Average vehicle speed Frequency of accidents Constructing feature vectors from multi-dimensional features X i Let be the traffic flow feature vector of the i-th task interval, and further form a feature matrix. ;

[0055] S202. The importance of each parameter index is calculated using the entropy weight method, including:

[0056] Extract the feature matrix. , Assign task range numbers, As the evaluation metric, X is the feature matrix formed by stacking all interval feature vectors;

[0057] Eigenvector index positive normalization ;

[0058] Entropy calculation , , ;

[0059] Entropy weight calculation ;

[0060] Weighted decision matrix .

[0061] S203. Construct ideal optimal and worst solutions using the Topsis method. Calculate the distance from each interval to the optimal and worst solutions to obtain interval scores and form a task priority ranking. The calculation method is as follows:

[0062] Constructing the ideal solution and the negative ideal solution , ;

[0063] Calculate distance and score , , ;

[0064] In the formula, Indicates the first The distance between each evaluation object and the positive ideal solution; Indicates the first The distance between each evaluation object and the negative ideal solution; Indicates the first The relative progress of each evaluation object

[0065] S3: Based on the evaluation and scoring results, construct an optimization model for the location of fixed drone nests on the highway side to determine the placement location of the fixed drone nests.

[0066] S301. First, obtain the set of highway task intervals that have been scored. And set interval scores. A higher score indicates a higher inspection priority;

[0067] S302. Based on urban planning and geographical conditions, predefine a set of candidate locations for deploying fixed nests. M represents the total number of candidate fixed nest locations, and m represents the final number of nests actually deployed.

[0068] S303, Define the drone from the candidate nest The departure can cover the mission area. binary relation If it can be covered If it cannot be covered, then the value is 0;

[0069] S304. Construct an optimization model and design the objective function. x j Let be the deployment decision variable for the j-th candidate nest location.

[0070] The objective function represents maximizing the coverage probability of high-priority task intervals. Weighted summation ensures that intervals with higher scores have a higher probability of being covered, thus prioritizing the inspection needs of critical road sections.

[0071] Constraint (1) This indicates that the total number of deployed nests does not exceed the budget B;

[0072] Constraint (2) This indicates that at least one deployment nest covers the mission area. , z i This is the coverage indicator variable for task interval i;

[0073] Constraint (3) This indicates that the model is guaranteed to be an integer programming problem;

[0074] S4: Construct a UAV inspection path planning model based on the fixed nest location results, and calculate the path planning scheme under the coverage of the fixed nest;

[0075] S401. Based on the fixed nest location results, obtain each nest The set of task points that can be covered This serves as the inspection point that the drones under the nest need to complete.

[0076] S402. Allocate one or more drones to each drone nest. Each drone must depart from the drone nest, complete its mission, and return to the same drone nest. The total path length is limited by the maximum flight distance of the drone.

[0077] S403. Construct a multi-path constrained path planning model with the objective of minimizing the total flight distance:

[0078] Design the objective function This indicates that the objective is to minimize the total flight distance.

[0079] Constraint (4) This means that the task point must be visited at least once;

[0080] Constraint (5) This indicates that the starting and ending points of each path are the nests;

[0081] Constraint (6) This indicates that the path is correctly connected.

[0082] Constraint (7) Indicates the total flight distance constraint;

[0083] In the formula: A set of points consisting of mission points and nest points; For point Time Spacing; This represents the maximum flight distance of the drone. This represents the number of available drones under this nest. As a decision variable, if the drone From point Time The value is 1; For drones Access Point The cumulative flight distance afterward; Indicates drone From the hive point to the mission point ; Indicates drone From the mission point Return to the hive point; drones Arrive at (or leave) the mission point The cumulative flight distance is a continuous variable used to ensure path connectivity and eliminate sub-loops.

[0084] The variables used in the model and their corresponding definitions are shown in Table 1:

[0085] Table 1. Definitions of sets, parameters, and variables in the model.

[0086]

[0087] The above description is merely an example and illustration of the structure of the present invention. Those skilled in the art can make various modifications or additions to the specific embodiments described, or use similar methods to replace them, as long as they do not deviate from the structure of the present invention or exceed the scope defined in the claims, all of which should fall within the protection scope of the present invention.

Claims

1. A method for highway inspection using unmanned aerial vehicles (UAVs) based on fixed-nest technology, characterized in that, Includes the following steps: S1: Collect GIS information on highways, segment and mark highway sections according to the highway geographic information, and construct a set of highway inspection tasks; S2: Collect relevant traffic flow parameters for the task section and evaluate and score the task section using the entropy weight method-Topsis method; S3: Based on the evaluation and scoring results, construct an optimization model for the location of fixed drone nests on the highway side and determine the placement location of the fixed drone nests; S4: Construct a drone inspection path planning model within the range of the fixed drone nest location results and calculate the path planning scheme under the coverage of the fixed drone nests.

2. The method for unmanned aerial vehicle (UAV) highway inspection based on fixed-nest technology according to claim 1, characterized in that, In step S1, the steps for constructing the highway inspection task set are as follows: S101: Collect highway GIS information and select highway sections with inspection needs; S102: Divide the highway sections into segments and mark them, with the segment distance set to half of the maximum inspection radius of the UAV; S103: Construct the highway inspection task set. , where n is the total number of highway inspection task sections.

3. The method for unmanned aerial vehicle (UAV) highway inspection based on fixed-nest technology according to claim 1, characterized in that, In step S2, the entropy weight method-Topsis method evaluates and scores the task intervals as follows: S201: Collect traffic flow parameters for each highway inspection interval; S202: Calculate the importance of each traffic flow parameter using the entropy weight method; S203: Construct the ideal optimal solution and the worst solution using the Topsis method, obtain the interval score by calculating the distance from each interval to the optimal and worst solutions, and form a task priority ranking; S205: Output the task interval level classification results based on the score results, providing input basis for subsequent nest location selection and route planning.

4. The method for unmanned aerial vehicle (UAV) highway inspection based on fixed-nest technology according to claim 3, characterized in that: In step S201, the traffic flow parameters include the hourly traffic flow within the interval. Traffic density Average vehicle speed Frequency of accidents Construct feature vectors X i Let be the traffic flow feature vector of the i-th task interval, and further form a feature matrix. 。 5. The method for unmanned aerial vehicle (UAV) highway inspection based on fixed-nest technology according to claim 3, characterized in that: In step S202, the weight calculation method is as follows: extract the feature matrix, ， Assign task range numbers, As the evaluation metric, X is the feature matrix formed by stacking all interval feature vectors; Forward normalization of the feature vector index; calculation of entropy value according to the entropy value calculation formula; calculation of entropy weight of each point according to the entropy weight calculation formula; Calculate the weighted decision based on the weighted decision matrix formula.

6. The method for unmanned aerial vehicle (UAV) highway inspection based on fixed-nest technology according to claim 3, characterized in that: In step S203, the calculation process includes: constructing the ideal solution. With negative ideal solution Calculate distance and score ， ， In the formula, Indicates the first The distance between each evaluation object and the positive ideal solution; Indicates the first The distance between each evaluation object and the negative ideal solution; Indicates the first The relative progress of each evaluation object.

7. A method for unmanned aerial vehicle (UAV) highway inspection based on fixed-nest technology according to claim 1, characterized in that, In step S3, the steps for constructing the highway roadside UAV fixed nest location optimization model are as follows: S301: Obtain the scored highway task set. And set interval scores. A higher score indicates a higher inspection priority; S302: A predefined set of candidate locations for deploying fixed nests based on urban planning and geographical conditions. M represents the total number of candidate fixed nest locations, and m represents the final number of nests actually deployed; S303: Defines the number of drones from candidate nests. The departure can cover the mission area. binary relation If it can be covered S304: Construct the following optimization model: Objective function To ensure that high-priority task ranges are covered first, while maximizing coverage efficiency, x j Let represent the deployment decision variable for the j-th candidate nest location; constraint (1) This indicates that the total number of deployed nests does not exceed the budget. Constraint (2) This indicates that at least one deployment nest covers the mission area. , z i The variable representing the coverage indicator for task interval i; constraint (3) Limit the feasible region of decision variables.

8. A method for unmanned aerial vehicle (UAV) highway inspection based on fixed-nest technology according to claim 1, characterized in that, In step S4, the steps for constructing the UAV inspection path planning model within the range of fixed nest location results are as follows: S401: Based on the fixed nest location results, obtain the location of each UAV nest. The set of task points that can be covered S402: Assign one or more drones to each drone nest, each drone must start from that nest, complete its task, and return to the same nest. The total path length is limited by the maximum flight distance of the drones. S403: Construct a multi-path constrained path planning model with the goal of minimizing the total flight distance: Objective function ； Constraint (4) This indicates that the task point must be visited once; constraint (5) , indicating that the starting and ending points of each path are nests; constraint (6) , indicating that the correct connectivity of the determined path is confirmed; constraint (7) , representing the total flight distance constraint; where: A set of points consisting of mission points and nest points; For point Time Spacing; This represents the maximum flight distance of the drone. This represents the number of available drones under this nest. As a decision variable, if the drone From point Time The value is 1; For drones Access Point The cumulative flight distance afterward; Indicates drone From the hive point to the mission point ； Indicates drone From the mission point Return to the hive point; drones Arrival or departure from the mission point The cumulative flight distance is a continuous variable used to ensure path connectivity and eliminate sub-loops.

Images