Multi-UAV joint mission planning method and system for non-site traffic enforcement

Abstract

The present invention provides a multi-UAV joint task planning method and system for non-site traffic law enforcement, and relates to the field of UAV technology. The present invention provides a multi-UAV joint task planning method and system for non-site traffic law enforcement, by acquiring non-site traffic law enforcement task data; generating a UAV flight task pool based on the non-site traffic law enforcement task data; processing the tasks in the UAV flight task pool based on a preset task optimization model and a solution algorithm to generate a flight task sequence for each UAV; generating a flight instruction based on the flight task sequence, and issuing the flight instruction. The method integrates the UAV law enforcement process into the entire non-site traffic law enforcement management process to form a complete task closed loop, systematically manages the UAV law enforcement, and improves law enforcement efficiency.

Description

Technical Field

[0001] The present invention relates to the field of unmanned aerial vehicle (UAV) technology, and in particular to a multi-UAV joint mission planning method and system for non-site traffic law enforcement. Background Art

[0002] There are many practical difficulties in urban road supervision, for example: due to insufficient coverage and angle limitations, it is difficult to capture accident and illegal details through fixed surveillance cameras; traffic capacity restrictions such as road congestion make it difficult to quickly collect evidence for law enforcement; illegal identification equipment is difficult to cover the entire traffic network and has blind spots, etc. To solve the above problems, drones are gradually integrated into the process of non-site traffic law enforcement. As a new type of non-site traffic law enforcement platform, drones can quickly reach the roads in the jurisdiction in a very short time, monitor road traffic conditions in real time, and capture illegal behaviors. At the same time, they use the advantages of drones to fully cover blind spots on the road network and capture illegal behaviors from a high-altitude perspective.

[0003] However, the existing application of drones in non-site traffic enforcement is still at the stage of on-site manual control and has not been integrated into the entire non-site traffic enforcement management process. The specific process is relatively cumbersome, resulting in low overall law enforcement efficiency. In other words, the existing application of drones in non-site traffic enforcement has no systematic management, resulting in low overall law enforcement efficiency. Summary of the invention

[0004] 1. Technical issues to be resolved

[0005] In view of the shortcomings of the existing technology, the present invention provides a multi-UAV joint task planning method and system for non-site traffic enforcement, which solves the technical problem that the existing application of UAVs in non-site traffic enforcement has no systematic management.

[0006] (II) Technical solution

[0007] To achieve the above objectives, the present invention is implemented through the following technical solutions:

[0008] In a first aspect, the present invention provides a multi-UAV joint task planning method for non-site traffic law enforcement, the method comprising:

[0009] Obtaining traffic non-site enforcement task data;

[0010] Generate a drone flight mission pool based on traffic non-site law enforcement mission data;

[0011] Based on the preset task optimization model and solution algorithm, the tasks in the UAV flight task pool are processed to generate a flight task sequence for each UAV;

[0012] A flight instruction is generated based on the flight mission sequence, and the flight instruction is issued.

[0013] Preferably, the preset task optimization model includes: an objective function and constraint conditions;

[0014] The objective function is expressed by formula (1):

[0015]

[0016] The constraints are expressed using formulas (2) to (7):

[0017]

[0018]

[0019]

[0020]

[0021]

[0022] X ijk ∈{0,1} (7)

[0023] Among them: Formula (2) requires that the flight time of each drone cannot be greater than its safe flight time; Formula (3) indicates that each mission point only needs to be observed once; Formula (4) indicates that the take-off and landing positions of all drones are the positions of a certain central point; Formula (5) indicates the path network flow conservation constraint; Formula (6) indicates the elimination of sub-paths; Formula (7) indicates the decision variable value constraint;

[0024] V represents the set of task points V = {0, 1, 2, ..., n}, n = |V|; u i represents the order of visiting nodes i in the path; E represents the set of roads between task points E = {(i, j)|i≠j,ij∈V}; q i represents the time when task point i needs to be observed, i∈V; C represents the set of center points; d ij represents the distance from task point i to task point j, i, j∈V; K represents the set of drones k K={1,2,3,...,m}, m=|K|; q0 represents the observation time of the center point is always 0; v k represents the average flight speed of the kth UAV, k∈K; T k represents the maximum flight time of the kth UAV, k∈K; T represents the total flight time of all UAVs; x ijk represents a 0,1 variable. When drone k leaves node V i Arrival at Node V j When xijk =1,i,j∈V,k∈K.

[0025] Preferably, the non-site traffic law enforcement task data includes: task data information, historical traffic network accident data, drone data information and road section data information.

[0026] Preferably, the generating of the UAV flight mission pool based on the traffic off-site law enforcement mission data includes:

[0027] Based on the traffic non-site law enforcement task data, the historical accident-prone points in the traffic network are obtained, task points are generated according to the historical accident-prone points in the traffic network, and the task points are placed in the drone flight task pool.

[0028] Preferably, after issuing the flight instruction, the method further includes: receiving information on the UAV's mission execution process and generating a violation handling report.

[0029] Preferably, the receiving of the information on the process of the drone executing the mission and generating a violation handling report includes:

[0030] Receive the information on the process of executing the mission of the drone. When the information on the process of executing the mission of the drone includes the illegal picture, determine whether the license plate information, traffic signals and road markings in the illegal picture are clear and complete. If so, identify the illegal information in the picture through image analysis technology; obtain the corresponding illegal code disclosed by the Ministry of Public Security through the illegal information, the illegal information and the illegal code form the illegal data, and superimpose the illegal data on the illegal picture to form the basis of the violation; generate a violation handling report based on the basis of the violation and the illegal data.

[0031] Preferably, before receiving the information about the process of the UAV executing the mission, the method further includes:

[0032] The drone carries a camera and hovers at the mission point to perform filming tasks. During the filming process, the pilot police officer checks the drone's filming content in real time. When an illegal vehicle is found, he clicks the capture button. The system automatically captures the content of the drone camera taking pictures of the illegal vehicle within 3 seconds before and after the click action, and extracts 60 frames of pictures within these 3 seconds to save and upload.

[0033] Preferably, the method further comprises: processing the task execution information to obtain statistical data.

[0034] Preferably, the flight instruction includes the mission number, the number of the UAV to be flown, the order of visiting mission points, the longitude of the mission points, the latitude of the mission points, the mission type and the mission start time.

[0035] In a second aspect, the present invention provides a multi-UAV joint mission planning system for non-site traffic law enforcement, comprising:

[0036] A data acquisition module is used to acquire traffic non-site law enforcement task data;

[0037] A task pool generation module is used to generate a UAV flight task pool based on traffic non-site law enforcement task data;

[0038] The task sequence generation module is used to process the tasks in the UAV flight task pool based on the preset task optimization model and solution algorithm to generate the flight task sequence of each UAV;

[0039] The instruction generation module is used to generate flight instructions based on the flight mission sequence and issue the flight instructions.

[0040] (III) Beneficial effects

[0041] The present invention provides a multi-UAV joint task planning method and system for non-site traffic law enforcement. Compared with the prior art, it has the following beneficial effects:

[0042] The present invention provides a multi-UAV joint task planning method and system for non-site traffic law enforcement, which obtains non-site traffic law enforcement task data; generates a UAV flight task pool based on the non-site traffic law enforcement task data; processes the tasks in the UAV flight task pool based on a preset task optimization model and solution algorithm to generate a flight task sequence for each UAV; generates a flight instruction based on the flight task sequence, and issues the flight instruction. The method integrates the UAV law enforcement process into the entire non-site traffic law enforcement management process to form a complete task closed loop, systematically manages the UAV law enforcement, and improves law enforcement efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0044] Figure 1 Block diagram of a multi-UAV joint mission planning approach for non-site traffic enforcement. DETAILED DESCRIPTION

[0045] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention are clearly and completely described. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0046] The embodiments of the present application provide a multi-UAV joint task planning method and system for non-site traffic law enforcement, thereby solving the problem of lack of systematic management in the existing application of UAVs in non-site traffic law enforcement, realizing the comprehensive application of UAVs in the process, supervising the entire process of non-site traffic law enforcement, and analyzing the data generated in the law enforcement process to form a complete task closed loop, thereby improving the efficiency of traffic law enforcement while completing the non-site traffic law enforcement task.

[0047] The technical solution in the embodiment of the present application is to solve the above technical problems, and the overall idea is as follows:

[0048] The existing application of drones in non-site traffic law enforcement is still at the stage of on-site manual control, and has not been integrated into the entire non-site traffic law enforcement management process. The specific process is relatively cumbersome, resulting in low overall law enforcement efficiency. The embodiment of the present invention combines drones with the non-site traffic law enforcement process, fully applies drones to the entire process of non-site traffic law enforcement, and supervises the entire process of non-site traffic law enforcement. At the same time, the data generated during the law enforcement process is analyzed to form a complete task closed loop, and the law enforcement of drones is systematically managed, thereby improving the efficiency of traffic law enforcement while completing the non-site traffic law enforcement task.

[0049] In order to better understand the above technical solution, the above technical solution will be described in detail below in conjunction with the accompanying drawings and specific implementation methods.

[0050] The embodiment of the present invention provides a multi-UAV joint task planning method for non-site traffic law enforcement. Figure 1 As shown, the following steps are included:

[0051] S1. Obtaining traffic non-site enforcement task data;

[0052] S2, generating a UAV flight mission pool based on traffic non-site law enforcement mission data;

[0053] S3, processing the tasks in the UAV flight task pool based on the preset task optimization model and solution algorithm to generate a flight task sequence for each UAV;

[0054] S4. Generate a flight instruction based on the flight mission sequence, and issue the flight instruction.

[0055] The embodiment of the present invention integrates the law enforcement process of drones into the entire non-site traffic law enforcement management process to form a complete task closed loop, systematically manages the law enforcement of drones, and improves law enforcement efficiency.

[0056] Each step is described in detail below.

[0057] In step S1, the traffic off-site enforcement task data is obtained. The specific implementation process is as follows:

[0058] During the specific implementation process, the method is executed through a traffic management system (hardware platform), and the non-site traffic law enforcement task data includes multiple data information: task data information, police data information, historical accident data of the traffic network, drone data information and road section data information, etc.

[0059] in:

[0060] Police officer data information includes: pilot police officer number, pilot police officer status information (idle, on mission, on vacation), etc.

[0061] Drone data information includes: drone number, drone type, drone status information (idle, on mission, charging), etc.

[0062] The historical traffic accident data of the road network include: the longitude, latitude, jurisdiction and road section of the historical traffic accident occurrence point.

[0063] In step S2, a UAV flight mission pool is generated based on the traffic off-site enforcement mission data. The specific implementation process is as follows:

[0064] Based on the traffic non-site law enforcement task data, the historical accident-prone points of the traffic network are obtained, and task points are generated according to the historical accident-prone points of the traffic network, and the task points are placed in the UAV flight task pool. The task points include information such as longitude, latitude, jurisdiction, and road section.

[0065] UAV missions mainly include: UAV data information, police officer data information and mission data information.

[0066] In step S3, the tasks in the UAV flight task pool are processed based on the preset task optimization model and solution algorithm to generate a flight task sequence for each UAV. The specific implementation process is as follows:

[0067] The following problem model is established to describe it:

[0068] The objective function is to minimize the total flight time of the drone:

[0069]

[0070] This problem model is to plan the UAV path x under the premise of satisfying the following constraints ijk Make the objective formula (1) minimum.

[0071] As shown in constraint (2), considering that the drone has a safety power limit during flight, it is required that the flight time of each drone cannot be greater than its safe flight time:

[0072]

[0073] As shown in constraint (3), during the UAV mission, each mission point only needs to be observed once. If a mission point has been observed in this mission, when another UAV passes by the mission point, it can fly away directly without stopping at this mission point, that is:

[0074]

[0075] As shown in constraint (4), this problem model takes the traffic police command center as the center point, the set of center points is C, and the take-off and landing positions of all drones are the positions of a certain center point:

[0076]

[0077] As shown in constraint (5), this constraint is to ensure the conservation of path network flow:

[0078]

[0079] As shown in constraint (6), eliminate the sub-travel path:

[0080]

[0081] As shown in constraint (7), the final constraint is the value constraint of 0 and 1 decision variables:

[0082] x ijk ∈{0,1} (7)

[0083] Where: V represents the set of task points V = {0, 1, 2, ..., n}, n = |V|; u i represents the order of visiting nodes i in the path; E represents the set of roads between task points E = {(i, j)|i≠j,ij∈V}; q i represents the time when task point i needs to be observed, i∈V; C represents the set of take-off / landing points of the drone, i.e., the set of center points; d ijrepresents the distance from task point i to task point j, i, j∈V; K represents the set of drones k K={1,2,3,...,m}, m=|K|; q0 represents the observation time of the center point is always 0 (q0=0); v k represents the average flight speed of the kth UAV, k∈K; T k represents the maximum flight time of the kth UAV, k∈K; T represents the total flight time of all UAVs; x ijk represents a 0,1 variable. When drone k leaves node V i Arrival at Node V j When x ijk =1,i,j∈V,k∈K.

[0084] The above constraints and objective functions can be used to determine the basic mathematical model for the multi-UAV joint mission planning problem for non-site traffic enforcement.

[0085] In an embodiment of the present invention, the model is solved by an algorithm library. The algorithm library includes a variety of drone traffic non-site law enforcement path planning algorithms, including a large number of heuristic algorithms (such as genetic algorithms), and uses these heuristic algorithms as the basic optimization algorithms for path planning. After receiving the relevant information of the task, the above information is analyzed and processed by using the algorithm library, and the various constraints in the above modeling are used to divide it into multiple tasks, and the appropriate fitness function is used to find the best result that meets the model from all the results as the result of multi-drone task allocation and trajectory planning, so that the task is divided into multiple tasks that meet the model, and multiple tasks are planned for drones to execute.

[0086] The algorithm is divided into multiple parts, including runtime library, information library and algorithm library. The optimization algorithm can be modified by modifying the referenced algorithm library, that is, different algorithms (such as genetic algorithm, ant colony algorithm, etc.) can be used.

[0087] It should be noted that in the specific implementation process, the method also includes: the final calculation result is submitted to the police officer at the command seat for review. If the review is passed, the calculation result is used to generate a flight task sequence and enter the task allocation stage. If the current calculation result is not satisfactory, the algorithm in the algorithm library is replaced to re-split the task.

[0088] In step S4, a flight instruction is generated based on the flight mission sequence and the flight instruction is issued. The specific implementation process is as follows:

[0089] Generate flight instructions based on the flight mission sequence and issue them. The flight instructions include the mission number, the number of the UAV to be flown, the order of mission point visits, the longitude and latitude of the mission point, the mission type and the mission start time.

[0090] In the specific implementation process, the traffic management system also needs to match pilots and police officers for drones to perform tasks. The pilot police officer status is divided into task-in-progress and idle, accompanied by the received task status information (unassigned, task-in-progress, and end of mutual conversion). When the police officer status information is idle, they can receive tasks. Select the police officer with idle status and match it with the number of the drone to be flown. The traffic police brigade selects the payload that the drone needs to carry during the mission according to the mission type. The payload can be specifically divided into infrared thermal imagers, depth of field cameras, loudspeakers, speedometers, etc. The infrared thermal imager payload allows drones to track and monitor special traffic incidents at night and in harsh environments, and capture heat to conceal and quickly discover targets. Depth of field cameras, loudspeakers, and speedometers can be well applied in conventional non-site traffic law enforcement events. With the use of drones, traffic monitoring can be completed more flexibly, assisting traffic police in efficiently conducting non-site traffic law enforcement.

[0091] In the implementation of the present invention, the method further includes: S5, receiving information about the process of the drone executing the mission, and generating a violation handling report. The specific implementation process is as follows:

[0092] In the specific implementation process, before receiving the information about the drone's mission execution process, the drone must first execute the mission. The S500 drone carries a camera and hovers at the mission point to perform the shooting task. During the shooting process, the pilot police officer views the drone's shooting content in real time. When an illegal vehicle is found, click the capture button. The system automatically captures the camera's shooting of the illegal vehicle within 3 seconds before and after the click action, and extracts 60 frames of pictures within these 3 seconds to save and upload. Specifically:

[0093] After the flight command is issued, the pilot police officer and the drone work together to perform the task. Taking the flight mission sequence of illegal capture as an example, the drone needs to be equipped with a depth of field camera and arrive at the mission point according to the flight command generated by the traffic management system, hover and perform the shooting task. During the shooting process, the pilot police officer checks the shooting content of the drone in real time. When an illegal vehicle is found, click the capture button. The system automatically captures the camera's shooting of the illegal vehicle within 3 seconds before and after the click action, and extracts 60 frames of pictures within these 3 seconds, saves and uploads them to the corresponding task details. The extracted pictures are associated with the task number, and each task number can correspond to multiple frames of pictures.

[0094] It should be noted that the pilot police officer monitors the execution of the drone's mission at any time. When the drone deviates from the route, loses signal, runs out of power, or is damaged, they will immediately seize control of the drone and perform emergency treatment to ensure the safety of the drone and the traffic section. After completing the mission, the drone will follow the route planned by the traffic management system, and after the drone returns to the traffic police center, it will be recovered and charged. The drone information status will be updated in real time in the traffic management system. When the battery is healthy, the traffic police brigade can assign the flight mission sequence again.

[0095] The traffic management system receives the information about the mission execution process of the above-mentioned drone. When the mission execution information includes the violation picture, it determines whether the license plate information, traffic signals and markings in the violation picture are clear and complete. If so, it identifies the violation information in the picture through image analysis technology; obtains the corresponding violation code disclosed by the Ministry of Public Security through the violation information, and the violation information and violation code form the violation data, which is superimposed on the violation picture to form the violation basis; generates a violation handling report based on the violation basis and the violation data. Specifically including:

[0096] S501. Illegal behavior evidence verification, including:

[0097] The traffic management system determines whether the license plate information in the violation picture is clear and complete, and whether the relevant traffic signals and markings are clear and complete. If the judgment is passed, it proves that the violation picture is shot effectively and enters the violation information superposition step.

[0098] S502, illegal information superposition, specifically including:

[0099] The license plate number and violation type in the image are identified through image analysis technology. The violation code published by the Ministry of Public Security is searched through the violation type. The shooting time, shooting location, direction, drone number, and flying police officer number are superimposed on the upper left corner of the image. The violation code, violation type, and license plate number are superimposed on the lower left corner of the image, and the superposition is the basis for the violation. The above-mentioned shooting time, shooting location, direction, drone number, flying police officer number, violation type, and license plate number are violation information, and the violation information and violation code constitute violation data.

[0100] S503. Upload the illegal disposal report, including:

[0101] The violation basis and violation data are combined to generate a violation basis report (for specific requirements, please refer to the 832 standard) and uploaded to the corresponding system of the traffic management department.

[0102] In a specific implementation process, the method further includes: S6, processing the task execution information to obtain statistical data. The specific implementation process is as follows:

[0103] After the UAV executes the flight mission sequence, it sends the mission execution information (such as images) in the mission to the traffic management system, and the traffic management system receives the mission execution information of the UAV. The mission execution information is processed to obtain statistical data. The specific implementation process is as follows:

[0104] Data statistics are conducted after the mission is completed, and the data is analyzed and processed from the perspectives of drones, missions, police officers, regions, etc., to conduct a comprehensive evaluation of the mission execution results.

[0105] Analysis from the perspective of drones: the number of missions and mission types performed by drones, the snapshots taken by drones during missions, the number of mission points passed, the number of faults and their types. The snapshot situation refers to whether illegal behavior is captured, the type of violation captured (illegal parking in the emergency lane, illegal parking, changing lanes on the solid line, cutting in, etc.) and the corresponding number of times. Drone failures include deviation from the route, inability to hover at a fixed point, takeoff tilt, inability to take off, automatic return, etc. The above data can be displayed in a bar chart, which can intuitively reflect the size of each data and make it easy to compare the differences between data.

[0106] Analyze from the perspective of tasks: mainly the total number of tasks, the number of completed tasks, and the number of uncompleted tasks under a task. Use a pie chart to display tasks at a single time point, and you can intuitively see the proportion of the number of tasks in each part; use a line chart to display the task status at multiple time points, reflecting the changing trend of the number of tasks in each part over a period of time.

[0107] From the perspective of police officers: the number of tasks performed by a police officer in a certain period of time.

[0108] Analysis from the regional perspective: the number and type of violations found on each road section in a region, and the sections where violations are most likely to occur. The above data can be displayed in combination with bar charts and fan charts to facilitate the overall situation in the region.

[0109] The embodiment of the present invention also provides a multi-UAV joint mission planning system for non-site traffic law enforcement, including:

[0110] A data acquisition module is used to acquire traffic non-site law enforcement task data;

[0111] A task pool generation module is used to generate a UAV flight task pool based on traffic non-site law enforcement task data;

[0112] The task sequence generation module is used to process the tasks in the UAV flight task pool based on the preset task optimization model and solution algorithm to generate the flight task sequence of each UAV;

[0113] The instruction generation module is used to generate flight instructions based on the flight mission sequence and issue the flight instructions.

[0114] It can be understood that the multi-UAV joint task planning system for non-site traffic enforcement provided by an embodiment of the present invention corresponds to the above-mentioned multi-UAV joint task planning method for non-site traffic enforcement. The explanation, examples, beneficial effects and other parts of the relevant contents can refer to the corresponding contents in the multi-UAV joint task planning method for non-site traffic enforcement, and will not be repeated here.

[0115] In summary, compared with the prior art, the present invention has the following beneficial effects:

[0116] 1. The embodiment of the present invention combines drones with the process of non-site traffic law enforcement, fully applies drones to the entire process of non-site traffic law enforcement, and supervises the entire process of non-site traffic law enforcement. At the same time, the data generated in the law enforcement process is analyzed to form a complete task closed loop, and the law enforcement of drones is systematically managed, thereby improving the efficiency of traffic law enforcement while completing the task of non-site traffic law enforcement.

[0117] 2. When executing a task, the drone of the embodiment of the present invention can find out the image information that serves as the basis for the violation through comprehensive monitoring and extraction of key frames of the images before and after the capture action, thereby realizing the monitoring of the illegal behavior.

[0118] 3. After the mission is completed, the embodiment of the present invention can count, analyze and process the data from the perspectives of drones, missions, police officers, areas, etc., conduct a comprehensive evaluation of the mission execution results, and optimize future illegal capture mission points based on the evaluation results of the current mission execution.

[0119] It should be noted that, through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform. Based on such an understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0120] In this article, relational terms such as first and second, etc. are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "comprise", "include" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the statement "comprise a ..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0121] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A multi-UAV joint mission planning method for non-site traffic law enforcement, characterized in that: The method comprises: Obtaining traffic non-site enforcement task data; Generate a drone flight mission pool based on traffic non-site law enforcement mission data; Based on the preset task optimization model and solution algorithm, the tasks in the UAV flight task pool are processed to generate a flight task sequence for each UAV; Generate flight instructions based on the flight mission sequence, and issue the flight instructions; The preset task optimization model includes: an objective function and constraint conditions; The objective function is expressed by formula (1): The constraints are expressed using formulas (2) to (7): x ijk ∈{0,1}(7) Among them: Formula (2) requires that the flight time of each drone cannot be greater than its safe flight time; Formula (3) indicates that each mission point only needs to be observed once; Formula (4) indicates that the take-off and landing positions of all drones are the positions of a certain central point; Formula (5) indicates the path network flow conservation constraint; Formula (6) indicates the elimination of sub-paths; Formula (7) indicates the decision variable value constraint; V represents the set of task points V = {0, 1, 2, ..., n}, n = |V|; u i represents the order of visiting nodes i in the path; E represents the set of roads between task points E = {(i, j)|i≠j,ij∈V}; q i represents the time when task point i needs to be observed, i∈V; C represents the set of center points; d ij represents the distance from task point i to task point j, i, j∈V; K represents the set of drones k K={1,2,3,...,m}, m=|K|; q0 represents the observation time of the center point is always 0; v k represents the average flight speed of the kth UAV, k∈K; T k represents the maximum flight time of the kth UAV, k∈K; T represents the total flight time of all UAVs; x ijk represents a 0,1 variable. When drone k leaves node V i Arrival at Node V j When x ijk =1,i,j∈V,k∈K.

2. The multi-UAV joint mission planning method for non-site traffic law enforcement as claimed in claim 1 is characterized in that: The non-site traffic law enforcement task data includes: task data information, historical traffic network accident data, drone data information and road section data information.

3. The multi-UAV joint mission planning method for non-site traffic law enforcement as claimed in claim 2 is characterized in that: The generating of the UAV flight mission pool based on the traffic non-site law enforcement mission data includes: Based on the traffic non-site law enforcement task data, the historical accident-prone points in the traffic network are obtained, task points are generated according to the historical accident-prone points in the traffic network, and the task points are placed in the drone flight task pool.

4. The multi-UAV joint mission planning method for non-site traffic law enforcement as described in any one of claims 1 to 3, characterized in that: After issuing the flight instruction, the method further includes: receiving information on the process of the UAV executing the mission and generating a violation handling report.

5. The multi-UAV joint mission planning method for non-site traffic law enforcement as claimed in claim 4 is characterized in that: The receiving of the information on the process of the drone executing the mission and the generation of the illegal disposal report include: Receive the information on the process of the drone executing the mission. When the information on the process of the drone executing the mission includes the illegal picture, determine whether the license plate information, traffic signals and road markings in the illegal picture are clear and complete. If so, identify the illegal information in the picture through image analysis technology; obtain the corresponding illegal code disclosed by the Ministry of Public Security through the illegal information, the illegal information and the illegal code form the illegal data, and superimpose the illegal data on the illegal picture to form the basis of the violation; generate a violation handling report based on the basis of the violation and the illegal data.

6. The multi-UAV joint mission planning method for non-site traffic law enforcement as claimed in claim 4 is characterized in that: Before receiving the information about the process of the UAV executing the mission, the method further includes: The drone carries a camera and hovers at the mission point to perform filming tasks. During the filming process, the pilot police officer checks the drone's filming content in real time. When an illegal vehicle is found, he clicks the capture button. The system automatically captures the content of the drone camera taking pictures of the illegal vehicle within 3 seconds before and after the click action, and extracts 60 frames of pictures within these 3 seconds to save and upload.

7. The multi-UAV joint mission planning method for non-site traffic law enforcement as claimed in claim 4 is characterized in that: The method further includes: processing the task execution information to obtain statistical data.

8. The multi-UAV joint mission planning method for non-site traffic law enforcement according to any one of claims 1 to 3, characterized in that: The flight instruction includes the mission number, the number of the UAV to be flown, the order of visiting mission points, the longitude of the mission points, the latitude of the mission points, the mission type and the mission start time.

9. A multi-UAV joint mission planning system for non-site traffic law enforcement, characterized in that: include: A data acquisition module is used to acquire traffic non-site law enforcement task data; A task pool generation module is used to generate a UAV flight task pool based on traffic non-site law enforcement task data; The task sequence generation module is used to process the tasks in the UAV flight task pool based on the preset task optimization model and solution algorithm to generate the flight task sequence of each UAV; An instruction generation module, used to generate flight instructions based on the flight mission sequence and issue the flight instructions; The preset task optimization model includes: an objective function and constraint conditions; The objective function is expressed by formula (1): The constraints are expressed using formulas (2) to (7): x ijk ∈{0,1} (7) Among them: Formula (2) requires that the flight time of each drone cannot be greater than its safe flight time; Formula (3) indicates that each mission point only needs to be observed once; Formula (4) indicates that the take-off and landing positions of all drones are the positions of a certain central point; Formula (5) indicates the path network flow conservation constraint; Formula (6) indicates the elimination of sub-paths; Formula (7) indicates the decision variable value constraint; V represents the set of task points V = {0, 1, 2, ..., n}, n = |V|; u i represents the order of visiting nodes i in the path; E represents the set of roads between task points E = {(i, j)|i≠j,ij∈V}; q i represents the time when task point i needs to be observed, i∈V; C represents the set of center points; d ij represents the distance from task point i to task point j, i, j∈V; K represents the set of drones k K={1,2,3,...,m}, m=|K|; q0 represents the observation time of the center point is always 0; v k represents the average flight speed of the kth UAV, k∈K; T k represents the maximum flight time of the kth UAV, k∈K; T represents the total flight time of all UAVs; x ijk represents a 0,1 variable. When drone k leaves node V i Arrival at Node V j When x ijk =1,i,j∈V,k∈K.

Images