UAV Adaptive Path Planning Method and System for Highway Disaster Site

Abstract

The present application discloses a method and system for adaptive path planning of an unmanned aerial vehicle (UAV) at a highway disaster site. The method includes: collecting highway disaster site data in real time; dividing the highway disaster site into multiple sub-regions, where each sub-region corresponds to a set of data collection information sets; calculating the comprehensive information aggregation rate within each sub-region based on the ratio of the number of specific disaster feature road sections in each sub-region to the total number of road sections in the corresponding sub-region; determining the UAV path planning adjustment amount for each sub-region according to the comprehensive information aggregation rate of each sub-region; and adjusting the UAV path planning within the geographical location range corresponding to each sub-region according to the path planning adjustment amount of each sub-region. By the above method, the present application can make the planned UAV path more adaptable to the complex environment of the highway disaster site, effectively improve the safety of UAV flight, and thus improve the task execution efficiency.

Description

Technical Field

[0001] This application relates to the technical field of unmanned aerial vehicle (UAV) path planning, and particularly to a method and system for adaptive path planning of UAVs in highway disaster sites. Background Art

[0002] In the emergency handling of highway disaster sites, UAVs play an important role in on-site monitoring, material transportation, emergency search, etc. due to their flexibility and high efficiency. However, existing UAV path planning technologies have many deficiencies in dealing with the complex environment of highway sites. Traditional path planning algorithms often plan based on a single data source, such as relying only on a single map data, resulting in the planned path being unable to adapt to the actual situation on-site, with low flight safety of UAVs, and thus affecting the task execution efficiency. Summary of the Invention

[0003] The main technical problem to be solved by this application is to provide a method and system for adaptive path planning of UAVs in highway disaster sites, which can effectively improve the flight safety of UAVs and thus enhance the task execution efficiency.

[0004] To solve the above technical problem, a technical solution adopted by this application is: to provide a method for adaptive path planning of UAVs in highway disaster sites, the method comprising: collecting highway disaster site data in real time; dividing the highway disaster site into multiple sub-regions, obtaining a plurality of sub-regions; wherein, each sub-region corresponds to a set of data collection information; calculating the comprehensive information aggregation rate within each sub-region based on the ratio of the number of specific disaster feature sections in each sub-region to the total number of sections in the corresponding sub-region; determining the UAV path planning adjustment amount for each sub-region according to the comprehensive information aggregation rate of each sub-region; and adjusting the UAV path planning within the geographical location range corresponding to each sub-region according to the path planning adjustment amount of each sub-region.

[0005] Wherein, calculating the comprehensive information aggregation rate within each sub-region based on the ratio of the number of specific disaster feature sections in each sub-region to the total number of sections in the corresponding sub-region includes: counting the ratio of the number of sections containing specific disaster features in each sub-region to the total number of sections in the corresponding sub-region as the information aggregation rate of the sub-region regarding the specific disaster feature; assigning weights to each specific disaster feature in each sub-region, and calculating the comprehensive information aggregation rate of each sub-region.

[0006] Among them, according to the comprehensive information aggregation rate of each sub-region, determine the UAV path planning adjustment amount for each sub-region, including: by using the first optimization algorithm, maximizing the sum of the first preset values of all sub-regions to determine the path planning adjustment amount, where the first preset value is calculated based on the estimated comprehensive information aggregation rate, path risk assessment value, task completion degree assessment value, and path length after the new path planning adjustment amount in the sub-region. The first preset value is positively correlated with the estimated comprehensive information aggregation rate and the task completion degree assessment value, and negatively correlated with the path risk assessment value and the path length.

[0007] Among them, according to the comprehensive information aggregation rate of each sub-region, determine the UAV path planning adjustment amount for each sub-region, including: by using the second optimization algorithm, minimizing the sum of the second preset values of all sub-regions to determine the path planning adjustment amount, where the second preset value is calculated based on the estimated comprehensive information aggregation rate and the proportion of the path planning adjustment amount after the new path planning adjustment in the sub-region. The second preset value is negatively correlated with the estimated comprehensive information aggregation rate and positively correlated with the proportion of the path planning adjustment amount.

[0008] Among them, according to the comprehensive information aggregation rate of each sub-region, determine the UAV path planning adjustment amount for each sub-region, including: comparing the comprehensive information aggregation rate of each sub-region with a preset threshold. In response to the comprehensive information aggregation rate being less than the preset threshold, use the preset quantity as the UAV path planning adjustment amount for this sub-region. In response to the comprehensive information aggregation rate being greater than or equal to the preset threshold, determine the path planning adjustment amount based on the difference between the preset threshold and the comprehensive information aggregation rate.

[0009] Among them, assign weights to each specific disaster feature in each sub-region, and calculate the comprehensive information aggregation rate of each sub-region, including: taking the sum of the products obtained by multiplying the information aggregation rate of each specific disaster feature in each sub-region by the corresponding weight as the comprehensive information aggregation rate of this sub-region; where the sum of the weight coefficients of the specific disaster features in each sub-region is 1.

[0010] Among them, based on the ratio of the number of specific disaster feature sections in each sub-region to the total number of sections in the corresponding sub-region, calculate the comprehensive information aggregation rate of this sub-region, including: for each sub-region, divide the planned path of the UAV in this sub-region into several sections of a preset length, take the number of sections of the planned path containing each specific disaster feature in this sub-region as the number of specific disaster feature sections in this sub-region, and take the total number of sections of the planned path in this sub-region as the total number of sections in the corresponding sub-region.

[0011] Wherein, the first preset value is equal to the difference between the first product and the second product and the third product; the first product is equal to the product of the estimated comprehensive information aggregation rate and the first weight coefficient, the second product is equal to the product of the path risk assessment value and the second weight coefficient, the third product is equal to the product of the path length and the third weight coefficient, the sum of the first weight coefficient, the second weight coefficient, and the third weight coefficient is 1, and all are greater than 0.

[0012] Wherein, the second preset value is equal to the fourth product minus the fifth product, wherein the fourth product is equal to the product of the proportion of the path planning adjustment amount and the fourth weight coefficient, and the fifth product is equal to the product of the estimated comprehensive information aggregation rate and the fifth weight coefficient.

[0013] To solve the above technical problems, another technical solution adopted by this application is: to provide an unmanned aerial vehicle (UAV) adaptive path planning system for a highway disaster site, the system includes: a collection module, a zoning module, a calculation module, a determination module, and an adjustment module. Among them, the collection module: is used to collect highway disaster site data in real time; the zoning module: is used to divide the highway disaster site into regions to obtain multiple sub-regions; wherein, each sub-region corresponds to a set of data collection information sets; the calculation module: based on the ratio of the number of specific disaster feature sections in each sub-region to the total number of sections in the corresponding sub-region, calculate the comprehensive information aggregation rate in the sub-region; the determination module: according to the comprehensive information aggregation rate of each sub-region, determine the UAV path planning adjustment amount of each sub-region; the adjustment module: is used to adjust the path planning of the UAV within the geographical location range corresponding to each sub-region according to the path planning adjustment amount of each sub-region.

[0014] Different from the prior art, the beneficial effects of this application are: this application collects highway disaster site data in real time, divides the site into regions, calculates the comprehensive information aggregation rate based on the ratio of specific disaster feature sections to the total number of sections in each sub-region, and then determines the UAV path planning adjustment amount of each sub-region according to the aggregation rate, and finally adjusts the UAV path planning within the corresponding geographical location range. Based on the actual data collected on-site and combined with the road section characteristics of different sub-regions, considering comprehensively from multiple dimensions, it overcomes the defect that traditional path planning only relies on a single data source, makes the planned UAV path more adaptable to the complex environment of the highway disaster site, effectively improves the safety of UAV flight, and thus improves the task execution efficiency. Description of the Drawings

[0015] Figure 1 It is a schematic flowchart of an implementation manner of the UAV adaptive path planning method for a highway disaster site in this application.

[0016] Figure 2 It is a schematic structural diagram of an implementation manner of the UAV adaptive path planning system for a highway disaster site in this application. Detailed implementation manners

[0017] To make the objectives, technical solutions and effects of this application clearer and more definite, the following further describes this application in detail with reference to the accompanying drawings and by way of examples.

[0018] In this article, the terms "first" and "second" are only used for descriptive purposes, and cannot be construed as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, features defined with "first" and "second" may explicitly or implicitly include at least one of such features. Moreover, the various embodiments described herein are not necessarily mutually exclusive, because some embodiments can be combined with one or more other embodiments to form new embodiments.

[0019] In some related technologies, path planning algorithms often plan only based on a single data source, such as relying only on map data, without fully considering the environmental factors that change in real time at the disaster site, such as the smoke generated by a fire and the dynamically changing flooded road area caused by a flood. As a result, the planned path cannot adapt to the actual situation at the site, and the flight safety and mission execution efficiency of the unmanned aerial vehicle are relatively low.

[0020] Refer to Figure 1 , Figure 1 is a schematic flowchart of an implementation manner of the method for adaptive path planning of an unmanned aerial vehicle at a highway disaster site in this application. The method includes: Step S11: Collect highway disaster site data in real time.

[0021] When a highway disaster occurs, it is necessary to obtain various information at the site in a timely and comprehensive manner. An unmanned aerial vehicle equipped with a variety of professional sensors can be used for data collection. For example, an optical camera is responsible for obtaining high-resolution highway images, which can clearly record the damage conditions of the road, including the location and size of road cracks and collapses, as well as the distribution of vehicles and personnel; an infrared thermal imager plays a key role in low visibility environments such as at night or when there is thick smoke. By detecting heat sources, it can accurately locate the place where a fire occurs and sense the body temperature signals of personnel; a lidar uses laser beams to construct an accurate three-dimensional terrain model, and can quickly measure the position, height and shape of obstacles; meteorological sensors monitor meteorological parameters such as wind speed, wind direction, precipitation and visibility in real time. The collected data will be transmitted in real time to the storage device carried by the unmanned aerial vehicle or the ground control station through wireless transmission technology.

[0022] Step S12: Divide the highway disaster site into multiple sub-regions; wherein, each sub-region corresponds to a set of data collection information.

[0023] After obtaining the basic data of the highway disaster site, it is necessary to make a reasonable regional division of the entire disaster site. Specifically, based on the geographical location information of the highway, such as longitude and latitude data, combined with the type of disaster and the actual affected area, the highway disaster site can be divided into multiple sub-regions. Taking a mountain highway affected by a debris flow disaster as an example, the section directly impacted by the debris flow and the surrounding areas that may be affected by secondary disasters can be divided into key sub-regions, while the sections that are farther away but have a certain impact on traffic can be divided into general sub-regions. Each sub-region forms an independent set of data collection information, which covers the disaster-related data in the region, such as the type of disaster, the severity of the disaster, etc., as well as environmental data, such as terrain, meteorology, etc. Before dividing the regions, it is necessary to pre-obtain the basic geographical information of the highway disaster site, including the total mileage of the highway, the direction, the surrounding mountains, rivers and other geographical environment characteristics, as well as the existing UAV path planning information.

[0024] Step S13: Calculate the comprehensive information aggregation rate in each sub-region based on the ratio of the number of specific disaster characteristic sections in each sub-region to the total number of sections in the corresponding sub-region.

[0025] The comprehensive information aggregation rate is calculated by the ratio of the number of specific disaster characteristic sections in the sub-region to the total number of sections in the corresponding sub-region. This ratio can quantitatively represent the complexity of the disaster situation or the concentration of special situations in the sub-region. For example, if the comprehensive information aggregation rate of a sub-region is relatively high, it indicates that there are relatively more specific disaster characteristic sections in the sub-region, and there may be more road damages, obstacles or other factors affecting UAV flight; on the contrary, a lower aggregation rate means that the situation in the sub-region is relatively simple and the road conditions are relatively good. Among them, the sections in each sub-region can be divided according to certain rules. For example, they can be divided according to a fixed length.

[0026] Step S14: Determine the UAV path planning adjustment amount for each sub-region according to the comprehensive information aggregation rate of each sub-region.

[0027] Adjusting the path planning according to the comprehensive information aggregation rate of different sub-regions can enable the UAV to complete tasks more efficiently. In sub-regions with a high comprehensive information aggregation rate, if sufficient path adjustments are not made, the UAV may have to frequently change its flight path or suspend the task due to frequent encounters with disaster obstacles, resulting in a significant extension of the task time. By reasonably increasing the path planning adjustment amount and pre-planning a more suitable path in advance, the UAV can fly more smoothly, quickly reach the target location to perform monitoring, transportation and other tasks, thereby improving the overall task execution efficiency.

[0028] Step S15: Adjust the UAV path planning within the geographical location range corresponding to each sub-region according to the path planning adjustment amount of each sub-region.

[0029] Specifically, a path planning data visualization system can be used to assist in the adjustment. This system takes the map as the core to display the current position of the UAV, the planned path, the disaster site information, etc. Different marks on the map represent elements such as the UAV, the disaster area, and obstacles. Clicking on the mark can view the detailed information.

[0030] In the above solution, by collecting the highway disaster site data in real time, dividing the site into regions, calculating the comprehensive information aggregation rate based on the ratio of the number of specific disaster characteristic sections to the total number of sections in each sub-region, and then determining the UAV path planning adjustment amount for each sub-region according to this aggregation rate, and finally adjusting the UAV path planning within the corresponding geographical location range. Based on the actual data collected on-site and combined with the section characteristics of different sub-regions, considering comprehensively from multiple dimensions, it overcomes the defect that traditional path planning only relies on a single data source, makes the planned UAV path more adaptable to the complex environment of the highway disaster site, effectively improves the safety of UAV flight, and further improves the task execution efficiency.

[0031] In some embodiments, step S13: Calculate the comprehensive information aggregation rate within each sub-region based on the ratio of the number of each specific disaster characteristic section in the sub-region to the total number of sections in the corresponding sub-region. It includes: counting the ratio of the number of sections containing specific disaster characteristics in each sub-region to the total number of sections in the corresponding sub-region as the information aggregation rate of the sub-region regarding the specific disaster characteristic; assigning weights to each specific disaster characteristic in each sub-region and calculating the comprehensive information aggregation rate of each sub-region.

[0032] In some embodiments, assigning weights to each specific disaster characteristic in each sub-region and calculating the comprehensive information aggregation rate of each sub-region includes: taking the sum of the products obtained by multiplying the information aggregation rate of each specific disaster characteristic in each sub-region by the corresponding weight as the comprehensive information aggregation rate of the sub-region; wherein, the sum of the weight coefficients of the specific disaster characteristics in each sub-region is 1.

[0033] In some embodiments, calculating the comprehensive information aggregation rate within each sub-region based on the ratio of the number of each specific disaster characteristic section in the sub-region to the total number of sections in the corresponding sub-region includes: for each sub-region, dividing the planned path of the UAV in the sub-region into several preset-length sections, taking the number of sections of the planned path containing each specific disaster characteristic in the sub-region as the number of each specific disaster characteristic section in the sub-region, and taking the total number of sections of the planned path in the sub-region as the total number of sections in the corresponding sub-region.

[0034] In some specific embodiments, a specific disaster characteristic section refers to a section within a sub-region that has specific disaster characteristics. For example, in a fire disaster, the section affected by the fire is a specific disaster characteristic section; in a road collapse disaster, the collapsed section is the specific disaster characteristic section.

[0035] For each sub-region, first determine the disaster characteristic associated regions corresponding to different disaster types. For example, for a flood disaster, based on the boundary of the flood inundation area, combined with the water flow velocity and direction, determine the road areas that may be affected by flood impact as the associated regions; for an earthquake disaster, according to the earthquake intensity distribution, delimit the regions where sections with disaster characteristics such as road collapse and ground cracks may occur as the associated regions. Then, divide the planned path of the unmanned aerial vehicle (UAV) within the sub-region into several small sections of equal length, and the length of each section can be set according to the actual situation, such as 50 meters or 100 meters. Next, count the number of sections containing specific disaster characteristics.

[0036] Assume that the total number of sections in a certain sub-region is N total , and the number of sections covered by a certain type of disaster characteristic is N covered , then the calculation formula for the information aggregation rate r of this sub-region regarding this disaster characteristic is: .

[0037] When there are multiple disaster characteristics, corresponding disaster characteristic weights can be assigned to the information aggregation rate of each disaster characteristic according to the severity of the impact of different disaster characteristics on the UAV path planning. For example, in a sub-region with both a fire and a road collapse, the fire poses a greater threat to the flight safety of the UAV, so a higher weight is assigned to the fire characteristic; while if the road collapse has a relatively smaller impact on the UAV flight path, a lower weight is assigned. Assume there are k types of disaster characteristics, the information aggregation rate of the th type of disaster characteristic is , and the weight is , where , then the comprehensive information aggregation rate R of this sub-region is: .

[0038] The determination of the disaster characteristic weights can be carried out through methods such as expert evaluation and historical data statistical analysis, and set in combination with the impact degree of different disasters on the UAV flight in actual situations.

[0039] In some embodiments, multiple methods can be used to determine the path planning adjustment amount. For example, through an optimization algorithm, maximize or minimize the sum of certain preset values to determine the adjustment amount; or compare the comprehensive information aggregation rate with a preset threshold, and determine the adjustment amount according to the comparison result.

[0040] In some application scenarios, step S14: Determine the UAV path planning adjustment amount for each sub-region according to the comprehensive information aggregation rate of each sub-region, including: By using a first optimization algorithm, maximize the sum of the first preset values of all sub-regions to determine the path planning adjustment amount, where the first preset value is calculated based on the estimated comprehensive information aggregation rate, path risk assessment value, task completion degree assessment value, and path length after the new path planning adjustment amount for the sub-region. The first preset value is positively correlated with the estimated comprehensive information aggregation rate and the task completion degree assessment value, and negatively correlated with the path risk assessment value and the path length.

[0041] In some embodiments, the first preset value is equal to the difference between the first product and the second product and the third product; the first product is equal to the product of the estimated comprehensive information aggregation rate and the first weight coefficient, the second product is equal to the product of the path risk assessment value and the second weight coefficient, the third product is equal to the product of the path length and the third weight coefficient, and the sum of the first weight coefficient, the second weight coefficient, and the third weight coefficient is 1, and all are greater than 0.

[0042] In some specific embodiments, use an optimization algorithm to maximize the sum of the preset values of all sub-regions to determine the path planning adjustment amount. For the path planning adjustment amount of the th region, For the existing path planning quantity of the th region, For the path risk assessment value of the th region (the higher the risk, the larger the value, which can be determined according to factors such as disaster type, meteorological conditions, terrain complexity, etc. For example, near a fire area, the risk assessment value is relatively high; in an area with bad weather and strong wind, the risk assessment value also increases accordingly), For the task completion degree assessment value of the th region (the higher the completion degree, the larger the value. For example, if the task of the UAV is to comprehensively monitor a disaster site, the higher the proportion of the monitored area to the total target area, the larger the task completion degree assessment value), For the path length of the th region, For the weight coefficient, and . The custom utility function can be defined as: .

[0043] The first preset value of this sub-region is equal to the difference between the first product and the second product and the third product, that is: .

[0044] Among them, the first product: .

[0045] This item reflects the impact of task completion on the first preset value. Among them, is the current task completion evaluation value of the th area, is the estimated task completion evaluation value after adding the path planning adjustment amount, is the existing number of path plans, is the path planning adjustment amount. represents the contribution of the existing path plan to task completion, is the expected contribution of the added path planning adjustment amount to task completion. is the total number of path plans after adjustment. The first product is positively correlated with task completion. The higher the task completion, the larger the first product, and the greater the positive contribution to the first preset value.

[0046] Second product: .

[0047] This item is used to measure the impact of path risk on the first preset value. Among them, is the current path risk evaluation value, is the estimated path risk evaluation value after adding the path planning adjustment amount. is the risk situation of the existing path, is the risk situation of the added path. The larger the second product, the greater the negative impact on the first preset value.

[0048] Third product: .

[0049] This item takes into account the path length, is the current path length, is the estimated path length after adding the path planning adjustment amount. The larger the third product, the greater the negative impact on the first preset value.

[0050] is used to balance the relative importance of task completion, path risk, and path length in the calculation of the first preset value. For example, in the target task, if more attention is paid to task completion, can be appropriately increased. If the risk at the disaster site is high, to ensure the safety of the UAV, can be increased.

[0051] After calculating the first preset value of each sub-area After that, common optimization algorithms such as the gradient descent method, genetic algorithm, or simulated annealing algorithm can be used to maximize the utility function, and finally, the path planning adjustment amount for each sub-region can be obtained. In actual operation, the calculation process of the optimization algorithm can be implemented by computer programming, and the path planning adjustment amount can be continuously adjusted through iterative calculation until the solution that maximizes the utility function is found.

[0052] In some other application scenarios, step S14: Determine the UAV path planning adjustment amount for each sub-region according to the comprehensive information aggregation rate of each sub-region, including: determining the path planning adjustment amount by minimizing the sum of the second preset values of all sub-regions through a second optimization algorithm, where the second preset value is calculated based on the estimated comprehensive information aggregation rate and the proportion of the path planning adjustment amount after the new path planning adjustment in the sub-region. The second preset value is negatively correlated with the estimated comprehensive information aggregation rate and positively correlated with the proportion of the path planning adjustment amount.

[0053] In some embodiments, the second preset value is equal to the fourth product minus the fifth product, where the fourth product is equal to the product of the proportion of the path planning adjustment amount and the fourth weight coefficient, and the fifth product is equal to the product of the estimated comprehensive information aggregation rate and the fifth weight coefficient.

[0054] In some specific embodiments, the path planning adjustment amount is determined by minimizing the sum of the second preset values of all sub-regions through an optimization algorithm. In the th sub-region, represents the estimated comprehensive information aggregation rate after the new path planning adjustment amount, represents the proportion of the path planning adjustment amount, is the fourth weight coefficient, is the fifth weight coefficient. Among them, , which is used to balance the influence degrees of the two factors and can be adjusted according to the actual situation. Then the second preset value of the th sub-region is equal to the fourth product minus the fifth product, that is: ; among them, the proportion of the path planning adjustment amount can be calculated by the ratio of the path planning adjustment amount of the th sub-region to the total sum of the path planning adjustment amounts of all sub-regions, that is:

[0055] The calculation of the estimated comprehensive information aggregation rate considers factors such as the comprehensive information aggregation rate of the current sub-region, the existing number of path plans , and the path planning adjustment amount . Its calculation method is: ; In this formula, is an adjustable coefficient used to reflect the influence degree of the adjustment amount of the new path planning on the estimated comprehensive information aggregation rate. Through these formulas, the second preset value of each sub-region can be calculated , and then, through optimization algorithms such as the gradient descent method and the genetic algorithm, minimize the sum of the second preset values of all sub-regions , and finally determine the adjustment amount of the UAV path planning for each sub-region. In practical applications, appropriate , and values can be determined based on multiple tests and data analysis to improve the accuracy of determining the adjustment amount of the path planning.

[0056] For example, when performing an emergency mission, more attention is paid to the impact of the adjustment amount of the path planning on mission completion. At this time, the value can be appropriately increased; while in a regular monitoring mission, to ensure the stability of the path planning, the size can be reasonably adjusted to balance the relationship between the estimated comprehensive information aggregation rate and the proportion of the adjustment amount of the path planning. At the same time, with the real-time change of the disaster site situation, these two weight coefficients can also be dynamically adjusted to ensure the accuracy and rationality of the adjustment amount of the path planning, so that the UAV can better adapt to the complex environment of the disaster site.

[0057] In some other application scenarios, step S14: Determine the adjustment amount of the UAV path planning for each sub-region according to the comprehensive information aggregation rate of each sub-region, including: comparing the comprehensive information aggregation rate of each sub-region with a preset threshold, and in response to the comprehensive information aggregation rate being less than the preset threshold, taking the preset quantity as the adjustment amount of the UAV path planning for this sub-region, and in response to the comprehensive information aggregation rate being greater than or equal to the preset threshold, determining the adjustment amount of the path planning based on the difference between the preset threshold and the comprehensive information aggregation rate.

[0058] Specifically, the comprehensive information aggregation rate of each sub-region is compared with a preset threshold. The preset threshold can be determined based on historical disaster data and experience, combined with different disaster types and UAV performance. For example, for areas with severe fire disasters, a higher threshold is set; for disaster areas such as general road waterlogging, a relatively lower threshold is set. If the comprehensive information aggregation rate is less than the threshold, it indicates that the path in this area is greatly affected by the disaster, and the path planning may require significant adjustment. The preset quantity can be used as the path planning adjustment amount for this sub-region. The preset quantity can also be set according to the actual situation, such as determined by factors such as the area size and disaster severity of the sub-region. For sub-regions with a large area and severe disasters, the preset quantity can be appropriately increased. If the comprehensive information aggregation rate is greater than or equal to the threshold, it indicates that the path in this area is relatively less affected by the disaster, and the path planning is relatively reasonable, and the path planning adjustment amount for this sub-region is 0. Or, the path planning adjustment amount is determined based on the difference between the threshold and the comprehensive information aggregation rate. The greater the difference, the greater the path planning adjustment amount, and the two are positively correlated. For example, for every 0.1 increase in the difference, the path planning adjustment amount increases by 1. In actual operation, the automation process of threshold judgment and adjustment amount calculation can be realized through programming to improve the efficiency of path planning adjustment.

[0059] In some embodiments, in step S15, according to the path planning adjustment amount determined for each sub-region, the path planning of the drone is adjusted within the geographical location range corresponding to the sub-region. The path planning data visualization system is used to assist in the adjustment. This system takes the map as the core to display the current position of the drone, the planned path, the disaster site information, etc. Different marks are used on the map to represent the drone, the disaster area, the obstacles, etc. Clicking on the mark can view the detailed information. The system includes a menu bar that provides function options such as "Path View", "Optimization Suggestion", and "Parameter Setting". The "Path View" function responds to the click on the path mark on the map and displays the detailed information of the path, such as the path length, waypoints, estimated flight time, etc. It can also view the path historical data, such as the path adjustment records at different times. The "Optimization Suggestion" function automatically calculates and gives the optimized path suggestion according to the path planning adjustment amount of the sub-region and the real-time disaster situation, including adjusting the waypoints, flight altitude, etc. of the path. The system provides an "Optimization Execution" button. After clicking, it automatically adjusts the path planning of the drone and updates the map and the information panel. The "Parameter Setting" interface is used to manually set some parameters, such as the weight value, the number of area divisions, etc. After setting, click the "Apply Settings" button, and the system recalculates and updates the map and the information panel. In addition, the system also has a search function and a data export function. The search function can quickly locate relevant information by inputting keywords, such as the drone number, the name of the disaster area, etc. The data export function can export the historical path planning data, monitoring data, etc., which is convenient for further analysis. During the path planning adjustment process, adaptive adjustment is made according to the real-time collected meteorological data. In case of strong wind, the flight altitude is appropriately reduced, the flight direction is adjusted according to the wind direction, and at the same time, the path is adjusted to avoid the strong wind area. In case of low visibility, the flight speed is reduced, the sensor scanning frequency is increased, and the infrared thermal imager is used to assist in navigation. The task priority and path planning strategy are dynamically adjusted according to the development trend of the disaster. For example, in a fire disaster, if the fire spreads and expands, the path to the direction of the fire spread is preferentially planned to strengthen the monitoring. If a new target location is found, the path is adjusted to go for rescue.

[0060] In the above solution, by collecting the highway disaster site data in real time, dividing the site into regions, calculating the comprehensive information aggregation rate based on the ratio of the specific disaster characteristic sections to the total number of sections in each sub-region, and then determining the drone path planning adjustment amount for each sub-region according to this aggregation rate, and finally adjusting the drone path planning within the corresponding geographical location range. In this way, based on the actually collected data on the site and combined with the section characteristics of different sub-regions, considering comprehensively from multiple dimensions, it overcomes the defect that the traditional path planning only relies on a single data source, makes the planned drone path more adaptable to the complex environment of the highway disaster site, effectively improves the safety of the drone flight, and further improves the task execution efficiency.

[0061] Please refer to Figure 2 , Figure 2It is a schematic structural diagram of an implementation manner of the UAV adaptive path planning system for highway disaster sites in the present application.

[0062] The UAV adaptive path planning system 20 for highway disaster sites includes: a collection module 21, a zoning module 22, a calculation module 23, a determination module 24, and an adjustment module 25. Among them, the collection module 21 is used to collect highway disaster site data in real time; the zoning module 22 is used to divide the highway disaster site into regions to obtain multiple sub-regions; among them, each sub-region corresponds to a set of data collection information sets; the calculation module 23 calculates the comprehensive information aggregation rate in the sub-region based on the ratio of the number of specific disaster characteristic road sections in each sub-region to the total number of road sections in the corresponding sub-region; the determination module 24 determines the UAV path planning adjustment amount for each sub-region according to the comprehensive information aggregation rate of each sub-region; the adjustment module 25 is used to adjust the UAV path planning within the geographical location range corresponding to the sub-region according to the path planning adjustment amount of each sub-region.

[0063] In some embodiments, the calculation module 23 calculates the comprehensive information aggregation rate in the sub-region based on the ratio of the number of specific disaster characteristic road sections in each sub-region to the total number of road sections in the corresponding sub-region, including: statistically calculating the ratio of the number of road sections containing specific disaster characteristics in each sub-region to the total number of road sections in the corresponding sub-region as the information aggregation rate of the sub-region regarding the specific disaster characteristics; assigning weights to each specific disaster characteristic in each sub-region and calculating the comprehensive information aggregation rate of each sub-region.

[0064] In some embodiments, the determination module 24 determines the UAV path planning adjustment amount for each sub-region according to the comprehensive information aggregation rate of each sub-region, including: determining the path planning adjustment amount by maximizing the sum of the first preset values of all sub-regions through the first optimization algorithm, where the first preset value is calculated based on the estimated comprehensive information aggregation rate, path risk assessment value, task completion degree assessment value, and path length after the new path planning adjustment amount in the sub-region, the first preset value is positively correlated with the estimated comprehensive information aggregation rate and the task completion degree assessment value, and the first preset value is negatively correlated with the path risk assessment value and the path length.

[0065] Among them, the first preset value is equal to the difference between the first product and the second product and the third product; the first product is equal to the product of the estimated comprehensive information aggregation rate and the first weight coefficient, the second product is equal to the product of the path risk assessment value and the second weight coefficient, the third product is equal to the product of the path length and the third weight coefficient, and the sum of the first weight coefficient, the second weight coefficient, and the third weight coefficient is 1, and all are greater than 0.

[0066] In some embodiments, the determining module 24 determines the UAV path planning adjustment amount for each sub-region according to the comprehensive information aggregation rate of each sub-region, including: determining the path planning adjustment amount by minimizing the sum of the second preset values of all sub-regions through a second optimization algorithm, where the second preset value is calculated according to the estimated comprehensive information aggregation rate after the new path planning adjustment of the sub-region and the proportion of the path planning adjustment amount, the second preset value is negatively correlated with the estimated comprehensive information aggregation rate, and the second preset value is positively correlated with the proportion of the path planning adjustment amount.

[0067] Wherein, the second preset value is equal to the fourth product minus the fifth product, wherein the fourth product is equal to the product of the proportion of the path planning adjustment amount and the fourth weight coefficient, and the fifth product is equal to the product of the estimated comprehensive information aggregation rate and the fifth weight coefficient.

[0068] In some embodiments, the determining module 24 determines the UAV path planning adjustment amount for each sub-region according to the comprehensive information aggregation rate of each sub-region, including: comparing the comprehensive information aggregation rate of each sub-region with a preset threshold, and in response to the comprehensive information aggregation rate being less than the preset threshold, taking the preset quantity as the UAV path planning adjustment amount for the sub-region, and in response to the comprehensive information aggregation rate being greater than or equal to the preset threshold, determining the path planning adjustment amount based on the difference between the preset threshold and the comprehensive information aggregation rate.

[0069] In some embodiments, the calculating module 23 assigns weights to each specific disaster feature in each sub-region and calculates the comprehensive information aggregation rate of each sub-region, including: taking the sum of the products obtained by multiplying the information aggregation rate of each specific disaster feature in each sub-region by the corresponding weight as the comprehensive information aggregation rate of the sub-region; wherein, the sum of the specific disaster feature weight coefficients in each sub-region is 1.

[0070] In some embodiments, the calculating module 23 calculates the comprehensive information aggregation rate within each sub-region based on the ratio of the number of segments of each specific disaster feature in each sub-region to the total number of segments in the corresponding sub-region, including: for each sub-region, dividing the planned path of the UAV in the sub-region into several segments of a preset length, taking the number of segments of the planned path containing each specific disaster feature in the sub-region as the number of segments of each specific disaster feature in the sub-region, and taking the total number of segments of the planned path in the sub-region as the total number of segments in the corresponding sub-region.

[0071] In the above solution, by collecting the data of the highway disaster site in real time, dividing the site into regions, calculating the comprehensive information aggregation rate based on the ratio of the number of specific disaster characteristic sections to the total number of sections in each sub-region, and then determining the adjustment amount of the UAV path planning for each sub-region according to this aggregation rate, and finally adjusting the UAV path planning within the corresponding geographical location range. In this way, based on the data actually collected on site, combined with the section characteristics of different sub-regions, considering comprehensively from multiple dimensions, it overcomes the defect that traditional path planning only relies on a single data source, makes the planned UAV path more adaptable to the complex environment of the highway disaster site, effectively improves the safety of UAV flight, and then improves the task execution efficiency.

[0072] The above are only the implementation manners of the present application, and do not limit the scope of the present application accordingly. Any equivalent structure or equivalent process transformation made by using the content of the specification and drawings of the present application, or directly or indirectly applied in other related technical fields, shall be equally included in the protection scope of the present application.

Claims

1. A method for adaptive path planning of unmanned aerial vehicles at a highway disaster site, characterized in that: The method comprises: collecting data on the highway disaster site in real time; dividing the highway disaster site into regions to obtain a plurality of sub-regions; wherein each sub-region corresponds to a set of data collection information; calculating the comprehensive information aggregation rate in the sub-region based on the ratio of the number of each disaster characteristic road section in each sub-region to the total number of road sections in the corresponding sub-region; determining the adjustment amount of the path planning of the unmanned aerial vehicle in each sub-region according to the comprehensive information aggregation rate of each sub-region; and adjusting the path planning of the unmanned aerial vehicle in the geographical location range corresponding to the sub-region according to the path planning adjustment amount of each sub-region; Determining the path planning adjustment amount of the drone in each sub-area according to the comprehensive information aggregation rate of each sub-area includes: determining the path planning adjustment amount by minimizing the sum of second preset values ​​of all sub-areas through a second optimization algorithm, wherein the second preset value is calculated based on the estimated comprehensive information aggregation rate and the proportion of the path planning adjustment amount after the new path planning adjustment of the sub-area, the second preset value is negatively correlated with the estimated comprehensive information aggregation rate, and the second preset value is positively correlated with the proportion of the path planning adjustment amount; Among them, the proportion of path planning adjustment The amount of adjustment that can be made through the path planning of the i-th sub-area The sum of all sub-area path planning adjustments The ratio is calculated, that is: ; Estimated comprehensive information aggregation rate The calculation considers the comprehensive information aggregation rate of the current sub-region 、Number of existing path planning , Path planning adjustment ; The calculation method is: ; in, It is an adjustable coefficient used to reflect the impact of the additional path planning adjustment on the estimated comprehensive information aggregation rate.

2. The method according to claim 1, characterized in that The method calculates the comprehensive information aggregation rate in each sub-region based on the ratio of the number of sections with disaster characteristics in each sub-region to the total number of sections in the corresponding sub-region, including: counting the ratio of the number of sections containing disaster characteristics in each sub-region to the total number of sections in the corresponding sub-region as the information aggregation rate of the disaster characteristics in the sub-region; assigning a weight to each disaster characteristic in each sub-region, and calculating the comprehensive information aggregation rate of each sub-region.

3. The method according to claim 2, characterized in that The step of assigning a weight to each disaster feature in each sub-region and calculating the comprehensive information aggregation rate of each sub-region includes: taking the sum of the products obtained by multiplying the information aggregation rate of each disaster feature in each sub-region by the corresponding weight as the comprehensive information aggregation rate of the sub-region; wherein the sum of the disaster feature weight coefficients in each sub-region is 1, and the weight of each disaster feature is greater than 0.

4. The method according to claim 1 or 2, characterized in that: The method calculates the comprehensive information aggregation rate in each sub-region based on the ratio of the number of each disaster characteristic section in each sub-region to the total number of sections in the corresponding sub-region, including: for each sub-region, dividing the planned path of the UAV in the sub-region into a number of sections of preset lengths, taking the number of sections of the planned path containing each disaster characteristic in the sub-region as the number of each disaster characteristic section in the sub-region, and taking the total number of sections of the planned path in the sub-region as the total number of sections in the corresponding sub-region.

5. The method according to claim 4, characterized in that The second preset value is equal to the fourth product minus the fifth product, wherein the fourth product is equal to the product of the path planning adjustment ratio and the fourth weight coefficient, and the fifth product is equal to the product of the estimated comprehensive information aggregation rate and the fifth weight coefficient.

6. An adaptive path planning system for unmanned aerial vehicles at highway disaster sites, characterized in that: include: Collection module: used to collect highway disaster site data in real time; Partitioning module: used to divide the highway disaster site into multiple sub-areas; each sub-area corresponds to a set of data collection information; calculation module: based on the ratio of the number of each disaster characteristic road section in each sub-area to the total number of road sections in the corresponding sub-area, calculate the comprehensive information aggregation rate in the sub-area; determination module: according to the comprehensive information aggregation rate of each sub-area, determine the adjustment amount of the drone path planning in each sub-area; adjustment module: according to the path planning adjustment amount of each sub-area, adjust the path planning of the drone in the geographical location range corresponding to the sub-area; Determining the path planning adjustment amount of the drone in each sub-area according to the comprehensive information aggregation rate of each sub-area includes: determining the path planning adjustment amount by minimizing the sum of second preset values ​​of all sub-areas through a second optimization algorithm, wherein the second preset value is calculated based on the estimated comprehensive information aggregation rate and the proportion of the path planning adjustment amount after the new path planning adjustment of the sub-area, the second preset value is negatively correlated with the estimated comprehensive information aggregation rate, and the second preset value is positively correlated with the proportion of the path planning adjustment amount; Among them, the proportion of path planning adjustment The amount of adjustment that can be made through the path planning of the i-th sub-area The sum of all sub-area path planning adjustments The ratio is calculated, that is: ; Estimated comprehensive information aggregation rate The calculation considers the comprehensive information aggregation rate of the current sub-region 、Number of existing path planning , Path planning adjustment ; The calculation method is: ; in, It is an adjustable coefficient used to reflect the impact of the additional path planning adjustment on the estimated comprehensive information aggregation rate.

Images