Traffic control method and system of traffic guidance robot

Abstract

The invention discloses a traffic control method and system for a traffic guidance robot, and relates to the technical field of traffic control methods. And the traffic dispersion mode of the traffic guidance robot is determined according to the congestion areas of the plurality of traffic congestion areas, the congestion directions of the plurality of traffic congestion areas and the traffic flow concentration direction, so that the accuracy of the traffic dispersion mode of the traffic guidance robot is ensured. The emergency dispersion mode of the traffic guidance robot is determined according to the current congestion area of the traffic congestion area and the congestion areas of the other traffic congestion areas, a previous street of each traffic congestion area is marked based on a town traffic distribution map, and the unmanned aerial vehicle outputs an anti-congestion signal at the previous street of each traffic congestion area; therefore, the multi-dimensional dispersion of the traffic congestion area by the traffic guidance robot is realized, and the traffic control effect of the traffic guidance robot is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of traffic control methods, and in particular, to a traffic control method and system for a traffic command robot. Background Art

[0002] With the development of technology, traffic command robots are gradually applied to people's lives and conduct traffic command on the road surface. A corresponding traffic signal is provided on the periphery of the traffic command robot, and traffic instructions are presented through the display of multiple traffic signals. In the prior art, the traffic command robot only conducts corresponding commands through multiple traffic signals, without considering the change in the area of traffic congestion areas and the traffic status of the previous street of each traffic congestion area, resulting in poor traffic control effects of the existing traffic command robots. Summary of the Invention

[0003] The purpose of the present invention is to overcome the deficiencies of the prior art. The present invention provides a traffic control method and system for a traffic command robot.

[0004] An embodiment of the present invention provides a traffic control method for a traffic command robot, including: The traffic command robot integrates a traffic command main body and a drone; the drone conducts traffic inspections on traffic congestion locations in a town and generates multiple traffic congestion areas; determines a traffic command position according to the multiple traffic congestion areas and the town traffic distribution map, and the traffic command main body moves to the traffic command position; in the traffic command main body, determines a traffic guidance mode of the traffic command robot according to the congestion area of the multiple traffic congestion areas, the congestion direction of the multiple traffic congestion areas, and the direction where the traffic flow is concentrated; if the congestion area of a traffic congestion area gradually increases, determines an emergency guidance mode of the traffic command robot according to the current congestion area of the traffic congestion area and the congestion areas of the remaining traffic congestion areas; marks the previous street of each traffic congestion area based on the town traffic distribution map, and the drone outputs an anti-blocking signal on the previous street of each traffic congestion area to guide the moving direction of the vehicles in the previous street.

[0005] An embodiment of the present invention provides a traffic control system for a traffic command robot. The traffic control system for the traffic command robot is applied to the traffic control method for the traffic command robot as described above. The traffic control system for the traffic command robot includes: A traffic congestion area module, used for the traffic command robot to integrate a traffic command main body and a drone; the drone conducts traffic inspections on traffic congestion locations in a town and generates multiple traffic congestion areas; A traffic command position module, used for determining a traffic command position according to the multiple traffic congestion areas and the town traffic distribution map, and the traffic command main body moves to the traffic command position; A traffic guidance mode module, which is used in a traffic command entity to determine the traffic guidance mode of a traffic command robot according to the congestion areas of multiple traffic congestion regions, the congestion directions of multiple traffic congestion regions, and the direction where the vehicle flow is concentrated; An emergency guidance mode module, which is used to determine the emergency guidance mode of the traffic command robot according to the current congestion area of a traffic congestion region and the congestion areas of the remaining traffic congestion regions if the congestion area of a traffic congestion region gradually increases; A drone guidance module, which is used to mark the previous street of each traffic congestion region based on the urban traffic distribution map, and the drone outputs anti-blocking signals on the previous street of each traffic congestion region to guide the moving direction of the vehicles in the previous street.

[0006] Compared with the prior art, the beneficial effects of the present invention are: In the embodiment of the present invention, through the method in the embodiment of the present invention, the traffic command entity moves to the traffic command position; in the traffic command entity, the traffic guidance mode of the traffic command robot is determined according to the congestion areas of multiple traffic congestion regions, the congestion directions of multiple traffic congestion regions, and the direction where the vehicle flow is concentrated, which comprehensively considers the congestion areas of multiple traffic congestion regions, the congestion directions of multiple traffic congestion regions, and the direction where the vehicle flow is concentrated, and ensures the accuracy of the traffic guidance mode of the traffic command robot.

[0007] Therefore, if the congestion area of a traffic congestion region gradually increases, the emergency guidance mode of the traffic command robot is determined according to the current congestion area of the traffic congestion region and the congestion areas of the remaining traffic congestion regions. The previous street of each traffic congestion region is marked based on the urban traffic distribution map, and the drone outputs anti-blocking signals on the previous street of each traffic congestion region to guide the moving direction of the vehicles in the previous street. The emergency guidance mode is introduced, and the traffic congestion regions are monitored in real time. The traffic command entity conducts on-site guidance for each traffic congestion region at the traffic command position, and the drone is used to conduct advance guidance for the previous street, realizing multi-dimensional guidance of the traffic command robot for traffic congestion regions and improving the traffic control effect of the traffic command robot. Description of the Drawings

[0008] Figure 1 is a flowchart of the traffic control method of the traffic command robot in the embodiment of the present invention; Figure 2 is a flowchart of step S11 in the traffic control method of the traffic command robot in the embodiment of the present invention; Figure 3 is a flowchart of step S12 in the traffic control method of the traffic command robot in the embodiment of the present invention; Figure 4It is a schematic flowchart of step S13 in the traffic control method of the traffic command robot in the embodiment of the present invention; Figure 5 It is a schematic flowchart of step S14 in the traffic control method of the traffic command robot in the embodiment of the present invention; Figure 6 It is a schematic flowchart of step S15 in the traffic control method of the traffic command robot in the embodiment of the present invention; Figure 7 It is a schematic diagram of the structural composition of the traffic control system of the traffic command robot in the embodiment of the present invention. Specific Embodiments

[0009] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention.

[0010] Please refer to Figures 1 to 7 , a traffic control method for a traffic command robot, including: Step S11: The traffic command robot integrates a traffic command main body and a drone; the drone conducts traffic inspections on traffic congestion locations in the town and generates multiple traffic congestion areas; Step S12: Determine the traffic command position according to the multiple traffic congestion areas and the town traffic distribution map, and the traffic command main body moves to the traffic command position; Step S13: In the traffic command main body, determine the traffic guidance mode of the traffic command robot according to the congestion area of the multiple traffic congestion areas, the congestion direction of the multiple traffic congestion areas, and the direction where the traffic flow is concentrated; Step S14: If the congestion area of a traffic congestion area gradually increases, determine the emergency guidance mode of the traffic command robot according to the current congestion area of this traffic congestion area and the congestion areas of the remaining traffic congestion areas; Step S15: Mark the previous street of each traffic congestion area based on the town traffic distribution map, and the drone outputs anti-blocking signals in the previous street of each traffic congestion area to guide the moving direction of the vehicles in the previous street; Refer to Figure 2 , in step S11, the traffic command robot integrates a traffic command main body and a drone; the drone conducts traffic inspections on traffic congestion locations in the town and generates multiple traffic congestion areas; In the specific implementation process of the present invention, the specific steps are as follows: S111: The traffic command robot includes a traffic command main body and a drone. The traffic command main body is used for road surface command. The drone flies relative to the ground and is used for aerial inspection and aerial command; the drone conducts corresponding commands based on the command signals transmitted by the traffic command main body; S112: The urban traffic system collects traffic congestion signals, determines the traffic congestion locations in the town based on the analysis of the traffic congestion signals, and triggers the aerial inspection of the drone. At this time, based on the current position of the drone, the traffic congestion locations, and the urban traffic distribution map, a circular inspection route of the drone relative to the traffic congestion locations is determined; S113: The drone conducts dynamic inspections along the circular inspection route and takes road surface pictures of the traffic congestion locations. The traffic command entity obtains multiple road surface pictures and determines multiple traffic congestion areas based on the multiple road surface pictures and the urban traffic distribution map.

[0011] In the embodiment of the present application, the traffic command robot includes a traffic command entity and a drone. The traffic command entity is used for road surface command. The drone flies relative to the road surface and is used for aerial inspection and aerial command; the drone conducts corresponding commands based on the command signals transmitted by the traffic command entity; this traffic command robot integrates the traffic command entity and the drone.

[0012] At this time, the traffic command robot includes a traffic command entity and a drone. The traffic command entity is the main command unit on the ground, equipped with traffic signal control equipment, communication equipment, and necessary monitoring screens; the traffic command entity is responsible for commanding ground traffic according to the real-time traffic conditions through gestures, signal lights, or other means; The drone serves as an aerial inspection and command unit, equipped with a high-definition camera, an infrared sensor, a GPS positioning system, and a wireless communication module; the drone can conduct aerial inspections in a designated area according to the instructions of the traffic command entity, take pictures of the traffic conditions, and conduct aerial command when necessary.

[0013] The drone conducts inspections in the air according to a preset route or in accordance with real-time instructions; during the inspection process, the drone uses the high-definition camera and the infrared sensor to capture the ground traffic conditions, including vehicle flow, vehicle speed, pedestrian dynamics, etc.; at the same time, the drone maintains real-time communication with the traffic command entity through the wireless communication module; the traffic command entity sends command signals to the drone according to the ground traffic conditions through the communication equipment; after receiving the signal, the drone adjusts its flight altitude, speed, or direction according to the signal content to conduct aerial command; for example, the drone displays traffic indication information through a mounted LED display screen or issues voice instructions through a loudspeaker to guide ground vehicles and pedestrians to drive along the designated route.

[0014] Furthermore, the urban traffic system collects traffic congestion signals, determines the traffic congestion locations in the town based on the analysis of the traffic congestion signals, and triggers the aerial inspection of the drone. At this time, based on the current position of the drone, the traffic congestion locations, and the urban traffic distribution map, a circular inspection route of the drone relative to the traffic congestion locations is determined, ensuring the accuracy of the circular inspection route of the drone relative to the traffic congestion locations.

[0015] At this time, the urban traffic system usually includes various sensors and monitoring devices arranged on key urban roads, such as cameras, traffic flow monitors, vehicle speed monitors, etc. These devices can capture traffic conditions in real time and transmit the data to the central control system; the central control system analyzes this real-time data and identifies signals of traffic congestion, which usually include characteristics such as vehicle queue length, vehicle speed decrease, and traffic flow increase.

[0016] Once a traffic congestion signal is identified, the system determines the specific location where the congestion occurs based on the source of the data (i.e., the location of the sensor or monitoring device), which is usually achieved through a Geographic Information System (GIS) by corresponding the sensor location to the actual road network; the system also evaluates the severity of the congestion, which is usually based on factors such as the length of the vehicle queue, the proportion of vehicle speed decrease, and the increase in traffic flow.

[0017] Based on the evaluation results of the congestion location and severity, the system generates a trigger instruction to require the drone to immediately conduct an aerial inspection. This trigger instruction is transmitted to the drone through a wireless communication network, and at the same time, the system also sends the specific information of the congestion location so that the drone can accurately reach the location.

[0018] After receiving the inspection instruction, the drone first determines its current location through its built-in GPS or other positioning system; the system plans an optimal circular inspection route based on the drone's current location, the traffic congestion location, and the urban traffic distribution map. This route should be able to comprehensively cover the congestion area while avoiding conflicts with ground traffic and ensuring the safe flight of the drone; the planned circular inspection route is transmitted to the drone through a wireless communication network, and the drone then conducts an aerial inspection according to this route.

[0019] Specifically, due to a traffic accident, traffic congestion occurred; the camera arranged on the main road captured the situation of vehicle queue and vehicle speed decrease and transmitted this data to the central control system in real time; the system determined through analyzing this data that the specific location where the congestion occurred was near a certain intersection on the main road and evaluated that the congestion was relatively severe.

[0020] The system immediately generated a trigger command, requiring the drone to conduct an aerial inspection of the congested area immediately. This command was transmitted to the drone patrolling nearby through the wireless communication network. After receiving the command, the drone determined its current position through GPS. Then, based on the position of the drone, the congested position, and the urban traffic distribution map, the system planned a circular inspection route. This route started from the current position of the drone, bypassed the airspace above the congested area, and avoided conflicts with other aircraft and ground traffic at the same time. Subsequently, the drone conducted an aerial inspection along this planned route, took pictures and videos of the congested scene through a high-definition camera, and transmitted this data to the central control system in real time. The system further analyzed the congestion situation based on this data and took corresponding traffic control measures.

[0021] Therefore, the drone conducts dynamic inspections along the circular inspection route and takes pictures of the road surface at the traffic congestion positions. The traffic command entity obtains multiple road surface pictures and determines multiple traffic congestion areas based on the multiple road surface pictures and the urban traffic distribution map, taking into account the overall compatibility of the multiple road surface pictures and the urban traffic distribution map to ensure the accuracy of the multiple traffic congestion areas.

[0022] At this time, after receiving the inspection command, the drone will start flying according to the preset circular inspection route, which is usually comprehensively planned based on the traffic congestion position, the current position of the drone, and the urban traffic distribution map. During the flight, the drone may encounter unexpected situations such as changes in wind direction and airborne obstacles. At this time, the drone needs to have a certain degree of autonomous navigation and obstacle avoidance capabilities to ensure safe flight. At the same time, if the system detects a change in the congestion situation, the drone also needs to dynamically adjust its inspection route.

[0023] Drones are usually equipped with high-definition cameras to capture the ground traffic conditions. These cameras have functions such as automatic focusing and exposure adjustment to ensure clear road surface pictures can be taken under different lighting conditions. The drone takes pictures at preset time intervals or according to the trigger signal issued by the system. The trigger signal comes from the real-time data analysis of the ground traffic system. When a change in the congestion situation is detected, the system will immediately trigger the drone to take pictures.

[0024] The road surface pictures taken by the drone will be transmitted to the traffic command entity in real time through the wireless communication network. This usually requires a stable and high-speed data transmission link to ensure that the pictures can reach the command entity quickly and accurately. The traffic command entity will store these pictures in a dedicated database and perform management operations such as numbering and classification on them, which helps to retrospect and analyze the traffic conditions later.

[0025] The traffic command entity will analyze the collected road surface images using image processing technology and machine learning algorithms. These technologies can automatically identify elements such as vehicles, pedestrians, and road signs in the images and calculate key indicators such as traffic flow and vehicle speed. Based on the results of the image analysis and the urban traffic distribution map, the traffic command entity determines multiple traffic congestion areas, which usually have characteristics such as a long queue length of vehicles and a significant decrease in vehicle speed. At the same time, the system will also sort and classify these areas according to the severity and duration of the congestion.

[0026] In an embodiment of the present application, assume there is a congestion area matching table, which is used to match the captured road surface images with known congestion characteristics to determine the congestion areas. The congestion area matching table is shown in Table 1: Table 1 Congestion Area Matching Table

[0027] In this example, the drone captured multiple road surface images, and each image contained some specific characteristics, such as the queue length of vehicles, the speed of vehicles, and the density of pedestrians. After the traffic command entity obtains these images, it compares these characteristics with the congestion levels in the congestion area matching table to determine the congestion level and congestion area corresponding to each image. For example, if an image shows a very long queue of vehicles, then it matches the characteristic of "long vehicle queue", and thus is determined to have a "high" congestion level and corresponds to "Area A". Similarly, other images are also matched and determined in this way.

[0028] Reference Figure 3 , in step S12, based on multiple traffic congestion areas and the urban traffic distribution map, determine the traffic command position, and the traffic command entity moves to the traffic command position; In the specific implementation process of the present invention, the specific steps are as follows: S121: Collect multiple traffic congestion areas, determine the corresponding streets and the number of congested vehicles for each traffic congestion area according to the traceability of the multiple traffic congestion areas, and determine the congestion level of the corresponding traffic congestion area based on the length of the street and the number of congested vehicles; S122: Match the multiple traffic congestion areas with the urban traffic distribution map, and determine the overall influence area of the multiple traffic congestion areas based on the locations and congestion levels of the multiple traffic congestion areas; S123: In the overall influence area of the multiple traffic congestion areas, determine multiple diversion routes based on the division of the overall influence area, and use the intersection of the multiple diversion routes as the traffic command position. This traffic command position is close to the traffic congestion area with the highest congestion level and gives priority to diverting the traffic congestion area with the highest congestion level; In an embodiment of the present application, multiple traffic congestion areas are collected. Based on the traceability of the multiple traffic congestion areas, the streets corresponding to each traffic congestion area and the number of congested vehicles are determined. And based on the length of the street and the number of congested vehicles, the congestion level of the corresponding traffic congestion area is determined, which takes into account both the length of the street and the number of congested vehicles, ensuring the accuracy of the congestion level of the corresponding traffic congestion area.

[0029] At this time, multiple traffic congestion areas are collected. By analyzing the collected data, the specific streets corresponding to each traffic congestion area are determined. This requires spatial analysis in combination with a Geographic Information System (GIS) to match the congestion information with the road network. At the same time, the number of congested vehicles in each congestion area needs to be counted, which is achieved by analyzing the video images captured by traffic monitoring cameras or using the data provided by traffic flow monitors.

[0030] To quantify the congestion level, a congestion index is defined, which is calculated based on the street length and the number of congested vehicles. For example, the number of congested vehicles is divided by the street length to obtain a preliminary congestion density, and then this density is compared with historical data or preset thresholds to determine the congestion level. The congestion level is divided according to the size of the congestion index, such as being divided into mild congestion, moderate congestion, severe congestion, etc. Different levels of congestion require different countermeasures.

[0031] Specifically, information on multiple traffic congestion areas is collected through drone inspections and ground traffic monitoring cameras. During the flight, the drone captures congestion images of multiple sections and transmits this information to the traffic management center in real time. At the same time, the ground traffic monitoring cameras also capture the congestion situation of these sections and provide detailed vehicle flow data. The analysts at the traffic management center determine the streets corresponding to each congestion area through traceability analysis of this data. At the same time, the number of congested vehicles in each congestion area is counted. For example, near a certain intersection, 50 vehicles are counted as congested on a street with a length of 500 meters.

[0032] A congestion index calculation formula was used, where the number of congested vehicles (50 vehicles) was divided by the street length (500 meters) to obtain a congestion density value (0.1 vehicle / meter); then, this density value was compared with the preset congestion level thresholds; in this example, the preset thresholds were: mild congestion (<0.05 vehicle / meter), moderate congestion (0.05 - 0.15 vehicle / meter), and severe congestion (>0.15 vehicle / meter); therefore, this congested area was determined to be moderately congested; from this example, it can be seen that all links in step S121 closely cooperate to jointly achieve the accurate identification of traffic congestion areas and the reasonable classification of congestion levels, which provides strong data support for subsequent traffic guidance and control measures.

[0033] Furthermore, multiple traffic congestion areas are matched with the urban traffic distribution map, and the location and congestion level of multiple traffic congestion areas are used to determine the overall influence area of multiple traffic congestion areas, taking into account the location and congestion level of multiple traffic congestion areas as a whole, and ensuring the accuracy of the overall influence area of multiple traffic congestion areas.

[0034] At this time, a database containing information on multiple traffic congestion areas and an urban traffic distribution map need to be prepared; the congestion area information should include key data such as the congestion location (latitude and longitude coordinates or street name) and congestion level; the urban traffic distribution map shows the road network, traffic nodes, important facilities, etc. of the city; using Geographic Information System (GIS) technology, the congestion area information is overlaid on the traffic distribution map, which usually involves the conversion and matching of spatial coordinates to ensure that the congestion area can be accurately located on the distribution map; after the matching is completed, it is visually displayed through GIS software or a traffic management system to intuitively see the location of the congestion area in the urban traffic network.

[0035] Based on the matching results, confirm the specific location of each congestion area on the urban traffic distribution map, which helps to understand the geographical background where congestion occurs, such as whether it is close to a transportation hub, commercial center, or residential area; at the same time, according to the congestion level information, evaluate the severity of each congestion area; the congestion level is comprehensively obtained based on multiple factors such as vehicle density, driving speed, and congestion duration.

[0036] Based on the location and congestion level of the congestion area, analyze the influence range of each congestion area spreading, which usually involves the application of a traffic flow model to simulate the driving paths and diversion situations of vehicles in case of congestion; according to the analysis results, delimit the overall influence area of each congestion area, and these areas include directly affected streets, adjacent intersections, and alternative roads that bear additional burdens due to detours; finally, comprehensively evaluate the overall influence areas of multiple congestion areas to determine which areas are most severely affected and how these influences are intertwined.

[0037] Specifically, assume that in a certain large city, the traffic management department has identified three traffic congestion areas A, B, and C through step S121 and knows their congestion levels. First, the management department prepares a database containing information on the three congestion areas A, B, and C and a town traffic distribution map. Then, using GIS technology, the congestion area information is overlaid on the distribution map to achieve precise matching. In the visual display, it can be clearly seen that area A is located in the commercial area in the city center, area B is near a large transportation hub, and area C is a traffic node on a main road. Through the matching results, the management department confirms the specific locations and congestion levels of the three congestion areas A, B, and C. Area A has severe congestion, area B has moderate congestion, and area C has mild congestion.

[0038] The management department uses a traffic flow model to analyze the influence ranges of the three congestion areas A, B, and C. The analysis results show that the influence area of area A is extensive, covering many surrounding streets and intersections. The influence of area B is mainly concentrated around the transportation hub. Although the congestion level of area C is relatively low, due to its location on the main road, its influence area is also relatively long. After comprehensive evaluation, the management department believes that the overall influence of area A is the most serious and priority measures should be taken to address it.

[0039] Therefore, among the overall influence areas of multiple traffic congestion areas, multiple diversion routes are determined based on the division of the overall influence area, and the intersection of the multiple diversion routes is used as the traffic command location. This traffic command location is close to the traffic congestion area with the highest congestion level, and priority is given to diverting the traffic congestion area with the highest congestion level, ensuring the accuracy of the traffic command location.

[0040] At this time, carefully analyze the overall influence area determined in step S122, which includes understanding the spread range of the congestion area, the dynamic changes of the traffic flow, and alternative routes. Based on the analysis of the influence area, multiple diversion routes are planned. These routes should be able to effectively guide the traffic flow and divert it from the congestion area to other roads, thereby reducing the congestion pressure. The selection of the diversion routes should consider factors such as road capacity, driving speed, and traffic signals. After planning the diversion routes, it is also necessary to evaluate their diversion effects, which is achieved through traffic simulation software to simulate the changes in traffic flow after the implementation of the diversion routes to ensure that the selected routes can effectively relieve congestion.

[0041] In the planned traffic diversion routes, identify the key intersections, which are usually the crossroads of multiple important roads and areas with high traffic flow; set traffic command positions at the identified intersections, and these positions should be convenient for traffic police or traffic management personnel to conduct real-time monitoring and command to ensure the orderly flow of traffic; optimize the layout of traffic command positions according to the severity of traffic congestion and the distribution of diversion routes; ensure that there is sufficient command force in key areas to handle the emerging traffic conditions.

[0042] Based on the congestion levels determined in steps S121 and S122, identify the traffic congestion area with the highest congestion level, which is usually the area with the greatest traffic pressure and the widest influence range; for the priority area, formulate a detailed diversion plan, which includes increasing the number of diversion routes, strengthening the traffic command force, adjusting traffic signals, etc.; immediately implement the priority diversion after the plan is formulated; ensure the orderly diversion of traffic flow in the priority area through real-time monitoring and flexible command, so as to effectively relieve congestion.

[0043] Specifically, assume that in a certain large city, the traffic management department has identified three traffic congestion areas A, B, and C and determined their overall influence areas through steps S121 and S122; among them, area A has the highest congestion level and is severely congested; the management department first analyzes the overall influence areas of the three congestion areas A, B, and C and plans multiple diversion routes; for area A, since it is located in the commercial area in the city center and the surrounding road capacity is limited, the management department plans multiple detour routes to guide vehicles to divert from the congested area to other roads.

[0044] In the planned diversion routes, the management department identifies the key intersections and sets traffic command positions at these locations; for area A, since it is the area with the highest congestion level, the management department formulates a detailed priority diversion plan; increases the number of diversion routes, strengthens the traffic command force, and adjusts the surrounding traffic signals; after implementing the priority diversion, through real-time monitoring and flexible command, the management department successfully guides the vehicles to divert from area A to other roads, effectively relieving the congestion pressure.

[0045] In an embodiment of the present application, collect the diversion route matching table, and the diversion route matching table is shown in Table 2: Table 2 Diversion Route Matching Table

[0046] The diversion route 1 directly targets the severely congested area A, guiding vehicles to bypass to the ring expressway to relieve the traffic pressure on the commercial center; the intersection of Commercial Avenue / Jiefang Road is set as the command position for real-time traffic monitoring and command; although the diversion routes 2 and 3 mainly target areas B and C, the coordinated diversion with area A is also considered; the intersections of the transportation hub / connector Y and the main road Z / branch line W are respectively set as the command positions to assist in the diversion work of area A; the priority diversion area is clearly area A, and at the same time, the diversion needs of areas B and C are incidentally considered.

[0047] Reference Figure 4 , in step S13, in the traffic command entity, determine the traffic diversion mode of the traffic command robot according to the congestion area of multiple traffic congestion areas, the congestion directions of multiple traffic congestion areas, and the direction where the traffic flow is concentrated; In the specific implementation process of the present invention, the specific steps are as follows: S131: The unmanned aerial vehicle conducts dynamic inspections on multiple traffic congestion areas and transmits the real-time images of multiple traffic congestion areas to the traffic command entity, and the traffic command entity determines the current status map of multiple traffic congestion areas according to the real-time images of multiple traffic congestion areas; S132: Determine the congestion area of multiple traffic congestion areas based on the area detection of the current status map of multiple traffic congestion areas, and determine the first mode coefficient according to the congestion area of multiple traffic congestion areas and the corresponding number of congested vehicles; S133: Determine the congestion directions of multiple traffic congestion areas and the direction where the traffic flow is concentrated based on the direction detection of the current status map of multiple traffic congestion areas, determine the second mode coefficient according to the congestion directions of multiple traffic congestion areas and the direction where the traffic flow is concentrated, and determine the traffic diversion mode of the traffic command robot based on the first mode coefficient, the second mode coefficient, and the mode mapping relationship. The traffic diversion mode includes multi-direction uniform diversion, single-direction bias diversion, and dynamic diversion.

[0048] In the embodiment of the present application, the unmanned aerial vehicle conducts dynamic inspections on multiple traffic congestion areas and transmits the real-time images of multiple traffic congestion areas to the traffic command entity, and the traffic command entity determines the current status map of multiple traffic congestion areas according to the real-time images of multiple traffic congestion areas, and accurately controls the current status map of multiple traffic congestion areas.

[0049] At this time, the drones are deployed into the urban traffic network to conduct dynamic inspections on multiple known or potential traffic congestion areas. These drones are usually equipped with a variety of sensors such as high-definition cameras, infrared sensors, and lidar, and can capture traffic conditions in real time. Optionally, the drones hover or fly slowly over the congestion areas according to the preset flight routes and altitudes to ensure clear traffic images can be captured. At the same time, the drones will also flexibly adjust their flight trajectories according to the changes in traffic flow to obtain more comprehensive traffic information. During the inspection process, the drones continuously collect real-time images and video data of the traffic congestion areas, and these data will be used for subsequent analysis and decision-making.

[0050] The drones transmit the collected real-time images and data to the traffic command entity through wireless communication technologies (such as 4G / 5G, Wi-Fi, or satellite communication). These images and data need to be encrypted to ensure security and privacy protection during the transmission process. After receiving the images and data transmitted by the drones, the traffic command entity (such as a traffic management center, traffic police department, or smart city management platform) stores them in a dedicated database for subsequent analysis and query. At the same time, the traffic command entity also views the images and data transmitted by the drones in real time to promptly understand the real-time situation of traffic congestion.

[0051] The traffic command entity uses image processing technologies and traffic flow analysis algorithms to analyze the real-time images transmitted by the drones. These technologies identify key information such as vehicle density, driving speed, and traffic signal status. Based on the results of the image analysis, the traffic command entity will draw current status maps of multiple traffic congestion areas. These status maps usually display the severity, distribution range, and spread trend of traffic congestion in a graphical manner. The current status maps not only provide the traffic command entity with intuitive traffic congestion information but also serve as an important basis for its decision-making such as formulating traffic diversion strategies and adjusting traffic signal timings.

[0052] Specifically, the drones are deployed to three main traffic congestion areas: Area A (commercial center), Area B (transportation hub), and Area C (main road intersection). The drones conduct inspections over Areas A, B, and C and capture clear traffic images. In Area A, the drones find that there are serious traffic jams on multiple roads around the commercial center, and the vehicles are lined up in long queues. In Area B, there are obvious traffic bottlenecks on the roads near the transportation hub. In Area C, the vehicle density at the main road intersection is high and the driving speed is slow.

[0053] The drone transmits the captured real-time images and data to the traffic control body; after receiving these images and data, the traffic control body immediately encrypts and stores them and monitors them in real time; the traffic control body uses image processing technology and traffic flow analysis algorithms to analyze the received images and data; based on the analysis results, the current status diagrams of the three areas A, B, and C are drawn; in the status diagram of area A, it can be clearly seen that many roads around the commercial center are in a state of serious traffic congestion; in the status diagram of area B, the road bottlenecks near the transportation hub are clearly marked; in the status diagram of area C, the traffic congestion at the intersection of the main roads is also intuitively displayed. These status diagrams provide an important basis for the traffic control body to formulate subsequent traffic diversion strategies.

[0054] Furthermore, the congestion areas of multiple traffic congestion areas are determined based on area detection of current status diagrams of multiple traffic congestion areas, and the first mode coefficient is determined according to the congestion areas of multiple traffic congestion areas and the corresponding number of congested vehicles, which is compatible with the overall consideration of the congestion areas of multiple traffic congestion areas and the corresponding number of congested vehicles, thereby ensuring the accuracy of the first mode coefficient.

[0055] At this time, the current state images of multiple traffic congestion areas obtained from drones or other monitoring equipment are preprocessed, including image enhancement, denoising, color correction, etc., to ensure that the image quality meets the requirements of subsequent processing; image processing techniques such as edge detection, threshold segmentation, morphological processing, etc. are used to identify the congested areas in the image. These technologies help extract the congested parts from complex traffic scenes; after identifying the congested areas, the areas are calculated using methods such as pixel counting and polygon fitting. This step needs to take into account the resolution and scale of the image to ensure the accuracy of the area calculation. Optionally, assume that there is a current state image of a traffic congestion area with an image resolution of 1024x768 pixels; through image processing technology, a congested area is identified, which occupies an area of ​​approximately 200x300 pixels on the image; assuming that the ground resolution of the image is 1 meter x 1 meter per pixel, the area of ​​the congested area is approximately 200 meters x 300 meters = 60,000 square meters, or 0.06 square kilometers.

[0056] In addition to the congestion area, the number of congested vehicles in each congestion area also needs to be collected, which is obtained through traffic flow monitoring devices, video analysis software, or manual counting, etc. After obtaining the congestion area and the number of congested vehicles, the first mode coefficient is calculated according to a preset algorithm or model. This coefficient usually reflects the severity and density of congestion and is an important basis for formulating traffic guidance strategies in the follow-up. Optionally, the first mode coefficient = (congestion area / total area of the region) * (number of congested vehicles / maximum vehicle capacity of the region); where the total area of the region and the maximum vehicle capacity of the region are obtained from historical data or traffic planning materials. Optionally, the total area of the region is 1 square kilometer (i.e., 1,000,000 square meters); the maximum vehicle capacity of the region is 1000 vehicles. Through video analysis software, the number of vehicles in the congestion area is counted as 200 vehicles. Then the first mode coefficient is calculated as: the first mode coefficient = (0.06 / 1) * (200 / 1000) = 0.012. This coefficient indicates that the congestion level in this region is relatively low in the current state; if the coefficient is close to 1, it means the congestion is very severe.

[0057] Therefore, based on the direction detection of the current state maps of multiple traffic congestion areas, the congestion directions and the directions where the traffic flow concentrates in multiple traffic congestion areas are determined. According to the congestion directions and the directions where the traffic flow concentrates in multiple traffic congestion areas, the second mode coefficient is determined. Based on the first mode coefficient, the second mode coefficient, and the mode mapping relationship, the traffic guidance mode of the traffic command robot is determined. The traffic guidance mode includes multi-directional uniform guidance, single-directional biased guidance, and dynamic guidance, which takes into account the overall consideration of the first mode coefficient, the second mode coefficient, and the mode mapping relationship, ensuring the accuracy of the traffic guidance mode of the traffic command robot. At the same time, it takes into account the overall consideration of the congestion areas of multiple traffic congestion areas, the congestion directions of multiple traffic congestion areas, and the directions where the traffic flow concentrates, further ensuring the accuracy of the traffic guidance mode of the traffic command robot.

[0058] At this time, a directional analysis is performed on the current state maps of multiple traffic congestion areas. These technologies help identify the main directions of the traffic flow and the trend of congestion spread. Through image analysis, the main congestion directions and the directions where the traffic flow concentrates in each congestion area are determined. These directions are usually represented in the form of angles or vectors, reflecting the dynamic changes of the traffic flow. The direction data of multiple congestion areas are fused to form a global traffic flow direction map, which helps to more comprehensively understand the congestion status and traffic flow dynamics of the entire traffic network. Optionally, assume there are two traffic congestion areas A and B. Through image processing technology, the following direction information is obtained: Area A: the congestion direction is from east to west, and the direction where the traffic flow concentrates is also from east to west; Area B: the congestion direction is from south to north, but the direction where the traffic flow concentrates is slightly skewed, towards the northwest direction.

[0059] Assign a weight to each congested direction and the direction with concentrated traffic volume. This weight is determined according to the degree of influence of the direction on the traffic flow. For example, if there is heavy congestion and a large traffic volume in a certain direction, then the weight of this direction will be relatively high. Based on the direction weight and the degree of congestion (measured by the first mode coefficient or other indicators), calculate the second mode coefficient, which reflects the degree of influence of the traffic flow direction on the congestion situation. Optionally, the congested direction and the direction with concentrated traffic volume in area A are the same, and the degree of congestion is relatively high (assuming the first mode coefficient is 0.6), so a relatively high weight, such as 0.8, is assigned. The congested direction and the direction with concentrated traffic volume in area B deviate slightly, and the degree of congestion is relatively low (assuming the first mode coefficient is 0.4), so a relatively low weight, such as 0.6, is assigned. Then, the second mode coefficient is calculated as follows: Second mode coefficient = (Weight of area A * First mode coefficient of area A + Weight of area B * First mode coefficient of area B) / (Weight of area A + Weight of area B) = (0.8 * 0.6 + 0.6 * 0.4) / (0.8 + 0.6) = 0.514. This coefficient indicates that in the current state, the direction of the traffic flow has a certain influence on the congestion situation, but the degree of influence is moderate.

[0060] Collect the preset mode mapping relationship, and map the first mode coefficient and the second mode coefficient to different traffic guidance modes. This mode mapping relationship is formulated according to the actual traffic conditions and guidance requirements. According to the calculated first mode coefficient and second mode coefficient, select the appropriate traffic guidance mode in the mode mapping relationship table or model. According to the selected traffic guidance mode, formulate specific traffic guidance strategies, such as adjusting the signal timing, dispatching traffic command robots for guidance, etc. Optionally, assume there is the following mode mapping relationship: when both the first mode coefficient and the second mode coefficient are relatively low, select the multi-direction uniform guidance mode; when the first mode coefficient is relatively high and the second mode coefficient indicates a clear congested direction, select the single-direction biased guidance mode; when both the first mode coefficient and the second mode coefficient are relatively high and the traffic flow direction is variable, select the dynamic guidance mode. According to the previous calculation, the obtained first mode coefficient (assuming it is a certain comprehensive value, such as 0.5) and the second mode coefficient is 0.571. Assume this combination falls within the range of the dynamic guidance mode, then select the dynamic guidance mode as the current traffic guidance strategy. To sum up, step S133 provides a method for formulating traffic guidance strategies based on the traffic flow direction and congestion situation through direction detection and coefficient calculation. This method is flexibly adjusted according to the actual situation to ensure the smooth operation of the traffic network.

[0061] In an embodiment of the present application, traffic congestion area: XX district; first mode coefficient: 0.7; second mode coefficient (obtained through a matching table): 0.8; comprehensive score: 0.74; traffic guidance mode: one-way biased guidance; recommended guidance direction: according to the direction detection result, it is recommended to bias towards the XX direction for guidance; by this method, according to the real-time state of the traffic congestion area, the traffic guidance mode is dynamically determined and specific guidance suggestions are given, which helps to improve the efficiency and accuracy of traffic guidance and relieve the traffic congestion problem.

[0062] Reference Figure 5 , in step S14, if the congestion area of a traffic congestion area gradually increases, the emergency guidance mode of the traffic command robot is determined according to the current congestion area of the traffic congestion area and the congestion areas of the remaining traffic congestion areas; In the specific implementation process of the present invention, the specific steps are as follows: S141: The traffic command entity collects the congestion areas of each traffic congestion area, determines a congestion area dynamic map according to the congestion areas of each traffic congestion area, and determines an abnormal congestion area based on the congestion area dynamic map. The abnormal congestion area is a traffic congestion area with a gradually increasing congestion area; S142: Determine the current congestion area of the abnormal congestion area based on the detection of the abnormal congestion area, determine the congestion area excess of the abnormal congestion area according to the comparison between the current congestion area of the abnormal congestion area and a preset congestion area threshold, and match the corresponding emergency event according to the congestion area excess; S143: Determine the emergency guidance mode of the traffic command robot according to the congestion areas of the remaining traffic congestion areas and the emergency event corresponding to the abnormal congestion area. The emergency guidance mode is biased towards the guidance of the abnormal congestion area and evenly guides the remaining traffic congestion areas.

[0063] In an embodiment of the present application, the traffic command entity collects the congestion areas of each traffic congestion area, determines a congestion area dynamic map according to the congestion areas of each traffic congestion area, and determines an abnormal congestion area based on the congestion area dynamic map. The abnormal congestion area is a traffic congestion area with a gradually increasing congestion area, and the abnormal congestion area is introduced to accurately control the abnormal congestion area.

[0064] At this time, the congestion area of ​​each traffic congestion area is collected. After obtaining the congestion area of ​​each traffic congestion area, the traffic control body will integrate these data to form a dynamic map of the congestion area. This dynamic map is real-time and based on historical data; it shows the changes in the area of ​​each congestion area at different time points, which helps to understand the evolution trend of congestion; optionally, use a geographic information system (GIS) or data visualization tool to display the area data of each congestion area in the form of a chart or map; as time changes, the color or value on these charts or maps will change to reflect the increase or decrease in the congestion area.

[0065] Based on the dynamic map of congestion area, the traffic control body needs to identify which areas have gradually increasing congestion areas. These areas are regarded as abnormally congested areas because they represent serious imbalances in traffic flow or bottlenecks in traffic facilities. Optionally, by observing the dynamic map of congestion area, if it is found that the congestion area of ​​a certain area is continuously expanding and the growth rate exceeds that of other areas, then this area is marked as an abnormally congested area. Further analysis requires checking the traffic flow data, road conditions, traffic light settings, etc. in the area to determine the cause of the congestion.

[0066] Specifically, suppose that during rush hour in a certain city, the traffic control body collected the following data through surveillance cameras and sensors: Area A (a main road): the congested area is about 200 square meters, and it has increased by 10% in the past half hour; Area B (an intersection): the congested area is about 100 square meters, but it has increased by 30% in the past half hour; Area C (another secondary road): the congested area is about 50 square meters, and it remains basically unchanged.

[0067] After integrating these data into the dynamic map of congested area, the traffic control body found that the congested area in area B was growing significantly faster than that in other areas; therefore, area B was marked as an abnormally congested area; further analysis found that the traffic lights in area B were not set reasonably, resulting in long waiting times for vehicles, thus aggravating the congestion; therefore, the traffic control body took corresponding measures, such as adjusting the duration of traffic lights, increasing the number of traffic police to direct traffic, etc., to alleviate the congestion in area B.

[0068] Furthermore, based on the detection of abnormal congested areas, the current congested area of ​​the abnormal congested area is determined, and the congested area excess of the abnormal congested area is determined based on the comparison between the current congested area of ​​the abnormal congested area and a preset congested area threshold. The corresponding emergency event is matched according to the congested area excess, which is compatible with the overall consideration of the comparison between the current congested area of ​​the abnormal congested area and the preset congested area threshold, thereby ensuring the accuracy of the congested area excess of the abnormal congested area.

[0069] At this time, based on the previously detected abnormally congested area, the current congested area of this area is further determined, which is usually done through real-time monitoring data or recently collected data to ensure that the latest congestion situation is obtained; optionally, through traffic monitoring cameras, sensor networks or intelligent transportation systems, information such as vehicle density and queue length in the abnormally congested area is obtained in real time, and the current congested area is calculated accordingly.

[0070] The current congested area of the abnormally congested area is compared with a preset congested area threshold, which is set according to historical data, traffic planning standards or the experience of the traffic management department to judge the severity of congestion; if the current congested area exceeds the threshold, the excess amount needs to be calculated, that is, the difference between the current congested area and the threshold; optionally, for example, assume that the set congested area threshold is 200 square meters; if the current congested area of the abnormally congested area is 250 square meters, then the congested area excess amount is 50 square meters.

[0071] According to the size of the congested area excess amount, one or more corresponding emergency events are matched. These emergency events are preset countermeasures for different degrees of congestion, such as dispatching additional traffic police, adjusting traffic lights, starting traffic broadcasts, etc.; optionally, a rule is set: if the congested area excess amount is within 50 square meters, start the traffic broadcast to remind drivers; if the excess amount is between 50 and 100 square meters, dispatch additional traffic police to direct on-site; if the excess amount exceeds 100 square meters, the traffic light duration needs to be adjusted or temporary traffic control measures need to be enabled.

[0072] Specifically, an abnormally congested area is detected, and its current congested area is determined to be 300 square meters; the set congested area threshold is 200 square meters; the current congested area of the abnormally congested area is 300 square meters; congested area excess amount: 300 square meters - 200 square meters = 100 square meters; according to the set rule, when the congested area excess amount is between 50 and 100 square meters, additional traffic police need to be dispatched to direct on-site; therefore, the corresponding emergency response mechanism is activated, and additional traffic police are dispatched to the scene for traffic guidance.

[0073] Therefore, according to the congested areas of the remaining traffic congestion areas and the emergency events corresponding to the abnormally congested area, the emergency guidance mode of the traffic command robot is determined. This emergency guidance mode is biased towards the guidance of the abnormally congested area and evenly guides the remaining traffic congestion areas, taking into account the overall consideration of the congested areas of the remaining traffic congestion areas and the emergency events corresponding to the abnormally congested area, ensuring the accuracy of the emergency guidance mode of the traffic command robot.

[0074] At this time, consider the congestion conditions in other traffic congestion areas except for the extremely congested areas. Although the congestion areas of these areas do not reach the level of extreme congestion, certain dredging measures are still needed to relieve traffic pressure; according to the size of the congestion areas of these areas, initially determine the basic dredging needs of each area; optionally, through the traffic monitoring system, obtain the real-time congestion area data of each congestion area; for non-extremely congested areas, divide them into different levels according to the size of the congestion area, such as mild congestion, moderate congestion, etc., and set corresponding dredging needs for each level, such as increasing the patrol frequency, adjusting the signal light timing, etc.

[0075] Determine the key dredging direction of the traffic command robot according to the emergency event corresponding to the extremely congested area; since the congestion condition in the extremely congested area is more serious, more resources and attention need to be invested in the dredging work of this area; at the same time, targeted dredging measures also need to be formulated according to the specific type and requirements of the emergency event; optionally, if the extremely congested area is caused by a traffic accident, then immediately dispatch the traffic command robot to the scene to handle the accident and restore traffic order as soon as possible; if the extremely congested area is caused by road construction or traffic control, then adjust the traffic flow line, guide the vehicle to detour, and strengthen the traffic management in the construction area.

[0076] It is necessary to comprehensively consider the information in the above two steps to determine the emergency dredging mode of the traffic command robot. This mode should be able to give priority to handling the problems in the extremely congested area and also take into account the dredging needs of other traffic congestion areas; at the same time, it is also necessary to ensure that the dredging measures of the traffic command robot are efficient, safe and sustainable; optionally, formulate an emergency dredging mode, in which the traffic command robot first gives priority to handling the problems in the extremely congested area, such as guiding the accident vehicle to evacuate quickly, adjusting the signal light timing to speed up the vehicle passing speed, etc.; at the same time, for other traffic congestion areas, arrange the traffic command robot to patrol and monitor, and timely discover and solve potential traffic problems; in addition, also use the intelligent dispatching system of the traffic command robot to dynamically adjust the dredging measures according to the real-time traffic data to ensure the smooth operation of the entire traffic system.

[0077] Specifically, an extremely congested area A is detected, and the corresponding emergency event is determined to be traffic accident handling; at the same time, several other mild congestion areas B, C and D are also detected; for the mild congestion areas B, C and D, arrange the traffic command robot to patrol and monitor, and timely discover and solve potential traffic problems; at the same time, appropriately adjust the signal light timing and patrol frequency according to the size of the congestion areas of these areas.

[0078] For the abnormally congested area A, traffic command robots need to be immediately dispatched to the scene for accident handling; the traffic command robots guide the accident vehicles to quickly evacuate the scene and adjust the signal timing to speed up the passing speed of other vehicles; at the same time, it is also necessary to strengthen the traffic management at the accident scene to ensure the order and safety of the scene; based on the above information, determine an emergency evacuation mode; in this mode, the traffic command robots will give priority to handling the problems in the abnormally congested area A and restore the traffic order in this area as soon as possible; at the same time, for other slightly congested areas B, C, and D, the traffic command robots will conduct patrols and monitoring, and dynamically adjust the evacuation measures according to real-time traffic data; in addition, the intelligent dispatching system of the traffic command robots is also used to conduct real-time monitoring and dispatching of the entire traffic system to ensure the smooth operation of the traffic in the whole city.

[0079] In an embodiment of the present application, an emergency evacuation mode matching table is collected, and different congestion situations are corresponded to the emergency evacuation modes; the emergency evacuation mode matching table is shown in Table 3; Table 3 Emergency Evacuation Mode Matching Table

[0080] In this emergency evacuation mode matching table, according to the actual congestion situation and emergency events, quickly find the corresponding emergency evacuation mode; for example, if an abnormally congested area is detected and the emergency event is a traffic accident, then according to the instructions in the emergency evacuation mode matching table, give priority to dispatching traffic command robots to handle the accident and take corresponding traffic management measures.

[0081] Refer to Figure 6 , in step S15, based on the urban traffic distribution map, mark the previous street of each traffic congestion area, and the unmanned aerial vehicle outputs an anti-blocking signal in the previous street of each traffic congestion area to guide the moving direction of the vehicles in the previous street; In the specific implementation process of the present invention, the specific steps are as follows: S151: Mark each traffic congestion area in the urban traffic distribution map, determine the previous street of each traffic congestion area according to the traversal of each traffic congestion area, and mark the previous street of each traffic congestion area in the urban traffic distribution map; S152: Based on the unmanned aerial vehicle, conduct dynamic inspections on the previous street of each traffic congestion area. The traffic command entity determines the anti-blocking signal of the previous street based on the inspection images of the previous street by the unmanned aerial vehicle and the congestion area of the corresponding traffic congestion area. The anti-blocking signal includes steering instructions, deceleration instructions, and parking instructions; S153: The drone receives the anti - congestion signal transmitted by the traffic control entity, the drone matches the corresponding output mode for the anti - congestion signal, and guides the moving direction of the vehicles in the previous street according to the anti - congestion signal output by the drone. The output mode is voice output, display screen output or attitude output.

[0082] In the embodiment of the present application, each traffic congestion area is marked in the urban traffic distribution map, and the previous street of each traffic congestion area is determined according to the traversal of each traffic congestion area, and the previous street of each traffic congestion area is marked in the urban traffic distribution map.

[0083] At this time, collect the traffic data of the town, which includes real - time traffic flow, vehicle speed, traffic accident reports, road construction information, etc. These data come from traffic monitoring cameras, traffic sensors, traffic police reports or public feedback; use traffic management software or GIS system to analyze the collected data to identify traffic congestion areas, which usually involves monitoring indicators such as vehicle speed and traffic flow, and comparing with historical data; on the urban traffic distribution map, mark the congestion areas according to the analysis results, and these areas are distinguished by different colors, icons or borders for easy identification. Optionally, the traffic management department collects through traffic monitoring cameras and sensors that the vehicle speed in a certain area of the city center has decreased significantly and the traffic flow has increased significantly; after analysis, it is determined that this area is a traffic congestion area and is marked in red on the traffic distribution map.

[0084] For each marked congestion area, it is necessary to trace the source of its traffic flow, which usually involves analyzing traffic monitoring data, especially the paths of vehicles entering the congestion area; by tracing the traffic flow, determine the main streets that cause congestion, that is, the "previous streets", which are the main roads directly connected to the congestion area or the roads connected to the congestion area through intersections; on the traffic distribution map, record and mark the previous streets of each congestion area, which helps to take targeted traffic management measures in the follow - up. Optionally, the traffic management department analyzes traffic monitoring data and finds that the vehicles entering the congestion area in the city center mainly come from two streets: one is the east - west "main road A" and the other is the north - south "secondary road B"; therefore, on the traffic distribution map, these two streets are marked as the previous streets of the congestion area.

[0085] Specifically, the traffic management department detected a congested area in the city center through the traffic monitoring system and data analysis software; this area is located in a major commercial district, surrounded by several busy streets; the congested area is marked in red on the traffic distribution map, which covers the core part of the commercial district, including several major shopping centers and office buildings; by analyzing the traffic monitoring data, the traffic management department determined the main streets that caused this congested area, including the east-west "Main Road A" which connects the east and west sides of the city, and the north-south "Secondary Road B" which runs through the north and south of the commercial district; therefore, on the traffic distribution map, these two streets are marked as the previous streets of the congested area and are distinguished by different colors or icons.

[0086] Furthermore, based on the dynamic inspection of the previous streets of each traffic congested area by drones, the traffic command entity determines the anti-blocking signals for the previous streets based on the inspection images of the previous streets by drones and the congested areas of the corresponding traffic congested areas. The anti-blocking signals include steering instructions, deceleration instructions, and stop instructions. By introducing the anti-blocking signals for the previous streets, the control of the previous streets is achieved.

[0087] At this time, after detecting the traffic congested area and determining its previous streets, drones will be quickly deployed to these key positions; the selection of drones should consider flight stability, endurance, and the ability to carry necessary sensors (such as high-definition cameras, thermal imagers, etc.); according to the geographical characteristics and traffic conditions of the previous streets, an efficient and safe inspection route is set for the drones, which usually involves hovering or flying at low altitude at key intersections, bottleneck sections, and potential congestion points to obtain detailed traffic information; during the inspection process, the drones will collect information such as traffic flow, vehicle speed, vehicle type, and pedestrian activities in real time. These information are collected by the sensors on the drones and transmitted to the traffic command entity in real time. Optionally, for example, after detecting a traffic congested area in the city center commercial district, the drone is quickly dispatched to its previous street - a busy main road connecting the highway and the congested area; the drone flies along the main road, especially hovering at several key intersections close to the congested area, and uses a high-definition camera to capture the real-time traffic conditions.

[0088] After receiving the inspection images transmitted back by the drone, the traffic command entity will analyze these images using image processing software and traffic management algorithms; the key points of the analysis are to identify key indicators such as traffic bottlenecks, vehicle queue lengths, and vehicle speed changes; combining the drone inspection data and historical traffic data, the traffic command entity will evaluate the area and severity of the current congested area, which helps to determine what level of anti-congestion measures to take; based on the results of the image analysis and the congested area assessment, the traffic command entity will decide which anti-congestion signals to implement on the previous street, and these signals include turning instructions (guiding vehicles to bypass the congested area), deceleration instructions (reducing the vehicle speed to reduce traffic pressure), and stop instructions (preventing vehicles from entering the congested area when necessary); optionally, the traffic command entity analyzes the inspection images transmitted back by the drone and finds that the vehicle queue length on the main road is increasing rapidly and the vehicle speed is significantly slowing down; combining the historical data and the area assessment of the current congested area, it decides to implement turning instructions and deceleration instructions on the previous street; specifically, a voice prompt is sent to the driver through the speaker on the drone: "There is congestion ahead, please slow down in advance and consider turning right to bypass; " At the same time, the display screen on the drone also shows the corresponding turning arrow and deceleration sign.

[0089] Specifically, in the case of traffic congestion in the downtown business district, the drone is quickly dispatched to the previous street of the congested area for dynamic inspection; through the real-time traffic images captured by the high-definition camera, the traffic command entity analyzes the traffic bottlenecks and vehicle queues; combining the area assessment of the congested area, it decides to implement turning instructions and deceleration instructions on the previous street, and these signals are conveyed to the driver through the voice prompt and display screen on the drone, guiding them to slow down in advance and consider bypassing the congested area, and this process effectively relieves traffic pressure and improves road capacity.

[0090] Therefore, the drone receives the anti-congestion signal transmitted by the traffic command entity, the drone matches the corresponding output method for the anti-congestion signal, and guides the moving direction of the vehicles in the previous street according to the anti-congestion signal output by the drone. This output method is voice output, display screen output or attitude output. It introduces an emergency guidance mode and conducts real-time monitoring of the traffic congested area. The traffic command entity conducts on-site guidance for each traffic congested area at the traffic command position, and uses the drone to conduct advance guidance for the previous street, realizing multi-dimensional guidance of the traffic congested area by the traffic command robot and improving the traffic control effect of the traffic command robot.

[0091] At this time, after determining the anti-jam signals (such as turning instructions, deceleration instructions or stop instructions), the traffic command entity will transmit these signals to the drone through wireless communication technologies (such as 4G / 5G, Wi-Fi or dedicated frequency bands); the drone is equipped with a signal receiver for receiving the anti-jam signals from the traffic command entity, and these signals are usually transmitted in the form of digital codes, and the drone needs to decode these signals to obtain the specific instruction content; after receiving the signal, the drone will also perform signal verification to ensure that the received signal is valid and accurate, which usually involves checking the integrity, source and encryption status of the signal; optionally, for example, after detecting traffic congestion and deciding to implement a turning instruction, the traffic command entity sends the turning instruction signal to the drone through a dedicated frequency band; after the receiver on the drone receives the signal, it decodes and verifies it to confirm that the received signal is a valid turning instruction.

[0092] The drone selects a suitable output method according to the type of anti-jam signal received (turning, decelerating or stopping), as well as the current flight state, environmental conditions (such as weather, light) and traffic conditions; the output methods include voice output (playing the instruction information through a speaker), display screen output (installing a display screen on the drone to display the instruction information) or attitude output (transmitting the instruction information through the flight attitude, lights or signs of the drone); once the output method is selected, the drone needs to prepare the corresponding output content, which involves converting the instruction information into a voice script, designing the graphical interface on the display screen or adjusting the flight attitude and light settings of the drone. Optionally, the drone selects a combination of voice output and display screen output according to the received turning instruction signal; it prepares a voice script: "There is congestion ahead, please turn right and detour", and designs the corresponding turning arrow and prompt information on the display screen.

[0093] The drone outputs the anti-jam signal to the vehicles in the previous street according to the selected output method, which involves playing voice prompts, displaying graphical interfaces or adjusting the flight attitude, etc.; the output anti-jam signal is intended to guide the vehicle to take appropriate actions, such as turning, decelerating or stopping; the drone needs to ensure that the signal is clear, accurate and easy to understand so that the driver can react quickly; after outputting the signal, the drone continues to monitor the traffic conditions to evaluate the effect of the anti-jam measures, which helps the traffic command entity to adjust the subsequent strategy according to the real-time feedback; optionally, the drone plays a voice prompt through the speaker: "There is congestion ahead, please turn right and detour", and displays the turning arrow and prompt information on the display screen; after the driver hears the prompt and sees the information on the display screen, he quickly makes a turning decision, thus effectively alleviating the traffic congestion; the drone continues to monitor the traffic conditions in this area and feeds back the real-time data to the traffic command entity for further adjustment as needed.

[0094] Specifically, in the case of traffic congestion in the city center, the drone received the steering instruction signal transmitted by the traffic command entity; the drone selected a combination of voice output and display screen output to output clear steering prompts to the vehicles in the previous street; after the driver heard and saw the prompt information, a quick decision to steer was made, thus effectively alleviating traffic congestion; the drone continued to monitor the traffic condition and fed back the real-time data to the traffic command entity for subsequent adjustment and optimization as needed. This process demonstrated the application potential of drones in traffic management and how to improve road traffic capacity and traffic safety level through advanced technical means.

[0095] In an embodiment of the present application, there is a collection and output mode matching table for matching different types of anti-blocking signals with the output modes of the drone; the output mode matching table is shown in Table IV; Table IV Output Mode Matching Table

[0096] In this output mode matching table, each type of anti-blocking signal corresponds to one or more combinations of output modes; for example, for the steering instruction, the drone will simultaneously adopt the voice output and display screen output modes, play the steering prompt through the speaker, and display the steering arrow on the display screen.

[0097] Please refer to Figure 7 , Figure 7 which is a schematic structural composition diagram of the traffic control system of the traffic command robot in the embodiment of the present invention; the traffic control system of the traffic command robot includes: The traffic congestion area module 21 is used for the traffic command robot to integrate the traffic command entity and the drone; the drone conducts traffic inspections on the traffic congestion locations in the town and generates multiple traffic congestion areas; The traffic command position module 22 is used to determine the traffic command position according to the multiple traffic congestion areas and the town traffic distribution map, and the traffic command entity moves to the traffic command position; The traffic guidance mode module 23 is used in the traffic command entity to determine the traffic guidance mode of the traffic command robot according to the congestion area of the multiple traffic congestion areas, the congestion direction of the multiple traffic congestion areas, and the direction where the traffic flow is concentrated; The emergency guidance mode module 24 is used to, if the congestion area of a traffic congestion area gradually increases, determine the emergency guidance mode of the traffic command robot according to the current congestion area of this traffic congestion area and the congestion areas of the other traffic congestion areas; The UAV guidance module 25 is used to mark the previous street of each traffic congestion area based on the urban traffic distribution map. The UAV outputs an anti-blocking signal on the previous street of each traffic congestion area to guide the moving direction of the vehicles in the previous street.

[0098] For any combination of the technical features of the above embodiments, in order to make the description more concise, not all combinations of the technical features in the above embodiments are described. However, as long as there are no technical contradictions in the combinations of these technical features, they should all be considered as the main scope recorded in this specification.

Claims

1. A traffic control method for a traffic command robot, characterized in that, Including: The traffic command robot integrates a traffic command main body and a drone; the drone conducts traffic inspections on the traffic congestion locations in the town and generates multiple traffic congestion areas; Determine the traffic command position according to the multiple traffic congestion areas and the town traffic distribution map, and the traffic command main body moves to the traffic command position; In the traffic command main body, determine the traffic guidance mode of the traffic command robot according to the congestion area of the multiple traffic congestion areas, the congestion direction of the multiple traffic congestion areas, and the direction where the traffic flow is concentrated; If the congestion area of a traffic congestion area gradually increases, determine the emergency guidance mode of the traffic command robot according to the current congestion area of the traffic congestion area and the congestion areas of the other traffic congestion areas; Based on the town traffic distribution map, mark the previous street of each traffic congestion area, and the drone outputs anti-blocking signals on the previous street of each traffic congestion area to guide the moving direction of the vehicles in the previous street.

2. The traffic control method of the traffic command robot according to claim 1, characterized in that, The traffic command robot integrates a traffic command main body and a drone; the drone conducts traffic inspections on the traffic congestion locations in the town and generates multiple traffic congestion areas, including: The traffic command robot includes a traffic command main body and a drone. The traffic command main body is used for road surface command, and the drone flies relative to the ground and is used for aerial inspection and aerial command; the drone conducts corresponding commands based on the command signals transmitted by the traffic command main body; The town traffic system collects traffic congestion signals, determines the traffic congestion locations in the town according to the analysis of the traffic congestion signals, and triggers the aerial inspection of the drone. At this time, determine the circular inspection route of the drone relative to the traffic congestion location according to the current position of the drone, the traffic congestion location, and the town traffic distribution map; The drone conducts dynamic inspections along the circular inspection route and takes road surface pictures of the traffic congestion locations. The traffic command main body obtains multiple road surface pictures and determines multiple traffic congestion areas according to the multiple road surface pictures and the town traffic distribution map.

3. The traffic control method of the traffic command robot according to claim 1, characterized in that, The determining the traffic command position according to the multiple traffic congestion areas and the town traffic distribution map, and the traffic command main body moves to the traffic command position, including: Collect multiple traffic congestion areas, determine the corresponding streets and the number of congested vehicles of each traffic congestion area according to the traceability of the multiple traffic congestion areas, and determine the congestion level of the corresponding traffic congestion area based on the length of the street and the number of congested vehicles; Match the multiple traffic congestion areas with the town traffic distribution map, and determine the overall influence area of the multiple traffic congestion areas based on the locations and congestion levels of the multiple traffic congestion areas; In the overall influence area of the multiple traffic congestion areas, determine multiple guidance routes based on the division of the overall influence area, and use the intersection of the multiple guidance routes as the traffic command position. This traffic command position is close to the traffic congestion area with the highest congestion level and gives priority to guiding the traffic congestion area with the highest congestion level.

4. The traffic control method of the traffic command robot according to claim 1, characterized in that, The determining the traffic guidance mode of the traffic command robot according to the congestion area of the multiple traffic congestion areas, the congestion direction of the multiple traffic congestion areas, and the direction where the traffic flow is concentrated in the traffic command main body, including: The drone conducts dynamic inspections on multiple traffic congestion areas and transmits real-time images of the multiple traffic congestion areas to the traffic command entity. The traffic command entity determines the current status map of the multiple traffic congestion areas based on the real-time images of the multiple traffic congestion areas.

5. The traffic control method of the traffic command robot according to claim 4, characterized in that, In the traffic command entity, determining the traffic guidance mode of the traffic command robot according to the congestion area of the multiple traffic congestion areas, the congestion direction of the multiple traffic congestion areas, and the direction where the vehicle flow is concentrated further includes: Determining the congestion area of the multiple traffic congestion areas based on the area detection of the current status map of the multiple traffic congestion areas, and determining the first mode coefficient according to the congestion area of the multiple traffic congestion areas and the corresponding number of congested vehicles; Determining the congestion direction of the multiple traffic congestion areas and the direction where the vehicle flow is concentrated based on the direction detection of the current status map of the multiple traffic congestion areas, determining the second mode coefficient according to the congestion direction of the multiple traffic congestion areas and the direction where the vehicle flow is concentrated, and determining the traffic guidance mode of the traffic command robot based on the first mode coefficient, the second mode coefficient, and the mode mapping relationship. The traffic guidance mode includes multi-directional uniform guidance, single-directional deviation guidance, and dynamic guidance.

6. The traffic control method of the traffic command robot according to claim 1, characterized in that If the congestion area of a traffic congestion area gradually increases, determining the emergency guidance mode of the traffic command robot according to the current congestion area of the traffic congestion area and the congestion areas of the other traffic congestion areas, including: The traffic command entity collects the congestion areas of each traffic congestion area, determines the congestion area dynamic map according to the congestion areas of each traffic congestion area, and determines the abnormal congestion area based on the congestion area dynamic map. The abnormal congestion area is the traffic congestion area where the congestion area gradually increases.

7. The traffic control method of the traffic command robot according to claim 6, wherein If the congestion area of a traffic congestion area gradually increases, determining the emergency guidance mode of the traffic command robot according to the current congestion area of the traffic congestion area and the congestion areas of the other traffic congestion areas further includes: Determining the current congestion area of the abnormal congestion area based on the detection of the abnormal congestion area, determining the congestion area excess of the abnormal congestion area according to the comparison between the current congestion area of the abnormal congestion area and the preset congestion area threshold, and matching the corresponding emergency event according to the congestion area excess; Determining the emergency guidance mode of the traffic command robot according to the congestion areas of the other traffic congestion areas and the emergency event corresponding to the abnormal congestion area. The emergency guidance mode is biased towards the guidance of the abnormal congestion area and conducts uniform guidance on the other traffic congestion areas.

8. The traffic control method of the traffic command robot according to claim 1, wherein, Marking the previous street of each traffic congestion area based on the urban traffic distribution map, and the drone outputs a traffic jam prevention signal at the previous street of each traffic congestion area to guide the moving direction of the vehicles in the previous street, including: Marking each traffic congestion area in the urban traffic distribution map, determining the previous street of each traffic congestion area according to the traversal of each traffic congestion area, and marking the previous street of each traffic congestion area in the urban traffic distribution map; Based on the dynamic inspection of the previous street in each traffic congestion area by a drone, the traffic command entity determines the anti-blockage signal for the previous street based on the inspection image of the previous street by the drone and the congestion area of each corresponding traffic congestion area. The anti-blockage signal includes a steering indication, a deceleration indication, and a stop indication.

9. The traffic control method of the traffic command robot according to claim 8, characterized in that, Mark the previous street of each traffic congestion area based on the urban traffic distribution map. The drone outputs an anti-blockage signal in the previous street of each traffic congestion area to guide the moving direction of the vehicles in the previous street. It further includes: The drone receives the anti-blockage signal transmitted by the traffic command entity. The drone matches the corresponding output mode for the anti-blockage signal and guides the moving direction of the vehicles in the previous street according to the anti-blockage signal output by the drone. The output mode is voice output, display screen output, or attitude output.

10. A traffic control system for a traffic command robot, characterized in that, The traffic control system of the traffic command robot is applied to the traffic control method of the traffic command robot as described in any one of claims 1-9. The traffic control system of the traffic command robot includes: A traffic congestion area module for integrating a traffic command entity and a drone in the traffic command robot; the drone conducts traffic inspections on the traffic congestion locations in the town and generates multiple traffic congestion areas; A traffic command location module for determining the traffic command location according to the multiple traffic congestion areas and the urban traffic distribution map, and the traffic command entity moves to the traffic command location; A traffic guidance mode module for determining the traffic guidance mode of the traffic command robot in the traffic command entity according to the congestion area of the multiple traffic congestion areas, the congestion direction of the multiple traffic congestion areas, and the direction of concentrated vehicle flow; An emergency guidance mode module for, if the congestion area of a traffic congestion area gradually increases, determining the emergency guidance mode of the traffic command robot according to the current congestion area of the traffic congestion area and the congestion areas of the remaining traffic congestion areas; A drone guidance module for marking the previous street of each traffic congestion area based on the urban traffic distribution map, and the drone outputs an anti-blockage signal in the previous street of each traffic congestion area to guide the moving direction of the vehicles in the previous street.

Images