Methods and systems for unmanned aerial vehicle (UAV) route planning for low-altitude tourism.

Abstract

This invention relates to the field of control or regulation technology, specifically to a method and system for unmanned aerial vehicle (UAV) route planning for low-altitude tourism. The method includes: determining the theoretical dwell time of the target UAV at a target scenic location by using the target visit order ranking of the initial flight path of the target UAV; determining the criticality of the target UAV at the target scenic location using the theoretical dwell time; determining the queuing cost of the target scenic location for the target UAV using the criticality of each critical node; determining the flight adjustment difficulty of the target UAV at the target scenic location using the queuing cost; and determining the target flight path of the target UAV using the flight adjustment difficulty and the initial flight path. This invention constructs a low-altitude tourism route planning system with overall stable trajectory, meeting the personalized tourism needs of different tourists and enabling UAV swarms to improve the success rate, efficiency, and safe operation of mission execution.

Description

Technical Field

[0001] This invention relates to the field of control or regulation technology, and specifically to a method and system for unmanned aerial vehicle (UAV) route planning for low-altitude tourism. Background Technology

[0002] Drone path planning is a key area of ​​modern scientific research. In recent years, with the rapid development of the low-altitude economy and drone technology, drones, with their flexible, efficient, and low-cost technical characteristics, are disrupting the production methods and service models of traditional industries. As a modern aviation device, drones play an important role in a range of fields, including realistic 3D modeling, agricultural and forestry plant protection, disaster emergency response, power transmission line inspection, railway inspection, and terrain surveying.

[0003] With the development of sensor and communication technologies, drones can acquire real-time map data of their surroundings, such as terrain and obstacle distribution. Through the analysis and processing of this real-time map data, drone swarms can achieve dynamic online planning. Some scenic spots are located in remote areas with complex terrain, making them inaccessible to tourists due to economic, time, and climatic factors. Therefore, new sightseeing models are urgently needed. Utilizing drone technology, through simulated environments, tourists can be immersed in constructed simulated scenes, experiencing the real-time landscape of scenic spots without leaving home.

[0004] Existing methods combine ant colony optimization to determine virtual tour routes for scenic spots using drones, focusing on optimizing single path selection. When multiple tourists use the virtual platform simultaneously, resulting in multiple drones running, the convergence of individual drones to the optimal path leads to conflicts between different drone paths in time and space, easily causing flight path collisions due to the accumulation of a large number of drones at the same location. Summary of the Invention

[0005] To address the technical problem of potential conflicts and flight path collisions between different drones when multiple tourists simultaneously use drones for virtual tours of scenic areas, this invention aims to provide a drone flight path planning method and system for low-altitude tourism. The specific technical solution adopted is as follows:

[0006] This invention provides a method for unmanned aerial vehicle (UAV) route planning for low-altitude tourism, the method comprising:

[0007] Based on the scenic area's terrain data and tourists' travel needs data, the initial flight path of the target drone corresponding to the target tourist is determined.

[0008] By using the ranking of the target landscape locations in the initial flight path to determine the theoretical dwell time of the target UAV at the target landscape location;

[0009] The theoretical dwell time is used to determine the criticality of the target UAV to the target landscape location, and the queuing cost of the target UAV to the target landscape location is determined by the criticality of each critical node.

[0010] Queuing costs are used to determine the difficulty of flight adjustment of the target UAV to the target landscape location, and the target flight path of the target UAV is determined by the flight adjustment difficulty and the initial flight path.

[0011] Furthermore, the step of determining the theoretical dwell time of the target UAV at the target landscape location by utilizing the target visit order ranking of the target landscape location in the initial flight path includes:

[0012] Determine the ratio of the total number of landscapes covered by the target UAV to the number of target landscapes in its initial flight path;

[0013] By using the target visit order ranking and the ratio of the number of landscapes in the initial flight path, the theoretical dwell time of the target UAV at the target landscape location is determined.

[0014] Furthermore, the determination of the criticality of the target UAV to the target landscape location using theoretical dwell time includes:

[0015] Determine the theoretical difference in dwell time between adjacent target landscape locations in the initial flight path;

[0016] By utilizing the theoretical dwell time and the difference between theoretical dwell time at the target landscape location, the criticality of the target UAV at the target landscape location can be determined.

[0017] Furthermore, the determination of the queuing cost of the target landscape location for the target drone using the degree of each key node includes:

[0018] Determine the actual dwell time and criticality of other drones at the target landscape location before the target drone reaches the target landscape location;

[0019] By utilizing the actual dwell time and criticality of each of the other drones at the target landscape location, the queuing cost of the target landscape location for the target drone can be determined.

[0020] Furthermore, determining the queuing cost of the target landscape location for the target drone by utilizing the actual dwell time and criticality of each of the other drones at the target landscape location includes:

[0021] Determine the ideal tour duration for the target landscape location, and obtain the difference in tour duration between the actual stay duration of other drones at the target landscape location and the ideal tour duration;

[0022] By utilizing the criticality of other drones at the target landscape location and the differences in their dwell time, the queuing cost of the target landscape location for the target drone is determined.

[0023] Furthermore, the method of determining the difficulty of flight adjustments for the target UAV to the target landscape location using queuing costs includes:

[0024] Determine the spatiotemporal distance between adjacent target landscape locations in the initial flight path;

[0025] The difficulty of adjusting the target UAV's flight position to the target landscape location is determined by using queuing costs and landscape spatiotemporal distance.

[0026] Furthermore, the determination of the target flight path of the target UAV using flight adjustment difficulty and initial flight path includes:

[0027] The number of drones queued in front of the target landscape location is determined, and the number of drones queued is positively correlated with the adjustment of the flight order to the target landscape location.

[0028] The initial flight path is adjusted by utilizing the difficulty of flight adjustment and the number of drones in the queue to obtain the target flight path of the target drone.

[0029] Furthermore, the adjustment of the initial flight path using flight adjustment difficulty and the number of drones in the queue to obtain the target flight path of the target drone includes:

[0030] Determine the minimum and standard deviation of the flight adjustment difficulty for all UAVs to the target landscape location;

[0031] Determine the difference in adjustment difficulty between the target UAV's flight adjustment difficulty for the target landscape location and the minimum value;

[0032] The dwell penalty factor of the target UAV for the target landscape location is determined by using the adjustment difficulty difference and the standard deviation;

[0033] The initial flight path is adjusted using the number of drones in the queue and the sojourn penalty factor to obtain the target flight path of the target drone.

[0034] Furthermore, determining the initial flight path of the target drone corresponding to the target tourist based on scenic area terrain data and tourist travel demand data includes:

[0035] Based on the raster scene map model corresponding to the scenic area terrain data, determine the location of the target landscape in the raster scene map model;

[0036] Based on historical actual visit data in the visitor demand data, the average historical stay time at the target scenic spot location is determined and used as its ideal visit time.

[0037] Based on the ant colony algorithm, the distance between the current position of the target drone and the target landscape position is used as the pheromone, and the tour duration under each ideal state is used as the weight to obtain the initial flight path of the target drone corresponding to the target tourist.

[0038] This invention also provides a drone route planning system for low-altitude tourism, the system being used to implement the drone route planning method for low-altitude tourism as described in any of the preceding claims; the system includes:

[0039] The initial path planning module is used to determine the initial flight path of the target drone for the target tourist based on the scenic area terrain data and the tourist's tour demand data.

[0040] The flight cost analysis module is used to determine the theoretical dwell time of the target drone at the target landscape location by using the target visit order ranking of the target landscape location in the initial flight path; it uses the theoretical dwell time to determine the critical node degree of the target drone for the target landscape location; and it uses the degree of each critical node to determine the queuing cost of the target landscape location for the target drone.

[0041] The flight path update module is used to determine the difficulty of the target UAV's flight adjustment to the target landscape location by using queuing costs, and to determine the target flight path of the target UAV by using the flight adjustment difficulty and the initial flight path.

[0042] The present invention has the following beneficial effects:

[0043] This invention addresses drone path planning in high-precision, large-scale scenarios such as karst landforms. By combining the dwell time at different scenic spots, it obtains the initial flight route of the drones, determines the spatiotemporal unit information during the flight process, and closely links the 3D real-world map with the flight path time. Furthermore, based on the differences between the target scenic spots visited by different tourists and the dwell time of different tourists at the same location, it constructs a scenic dwell time penalty factor to adjust the initial flight routes of multiple drone swarms, and builds a low-altitude sightseeing route plan with stable overall trajectory. This meets the personalized sightseeing needs of different tourists. The dynamic planning method based on real-time map data enables drone swarms to better adapt to complex and changing environments, improves the success rate, efficiency, and operational safety of mission execution, and avoids conflicts and collisions between multiple drones in space and time. Attached Figure Description

[0044] To more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0045] Figure 1 A flowchart illustrating the steps of a drone route planning method for low-altitude tourism and sightseeing, provided in one embodiment of the present invention.

[0046] Figure 2 This is a detailed flowchart of step S2 in a drone route planning method for low-altitude tourism provided in an embodiment of the present invention.

[0047] Figure 3 This is a detailed flowchart of step S3 in a drone route planning method for low-altitude tourism provided in an embodiment of the present invention.

[0048] Figure 4 This is a detailed flowchart of step S4 in a drone route planning method for low-altitude tourism provided in an embodiment of the present invention.

[0049] Figure 5 A detailed flowchart of step S4 in a drone route planning method for low-altitude tourism provided in another embodiment of the present invention;

[0050] Figure 6 This is a schematic diagram of the hardware operating environment of the drone route planning equipment for low-altitude tourism and sightseeing involved in the embodiments of the present invention.

[0051] Figure 7 This is a schematic diagram of the framework structure of an unmanned aerial vehicle (UAV) route planning system for low-altitude tourism and sightseeing, as described in an embodiment of the present invention. Detailed Implementation

[0052] To further illustrate the technical means and effects adopted by the present invention to achieve its intended purpose, the following, in conjunction with the accompanying drawings and preferred embodiments, details the specific implementation, structure, features, and effects of a drone route planning method for low-altitude tourism proposed according to the present invention. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics in one or more embodiments can be combined in any suitable form.

[0053] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains.

[0054] Before proceeding with the various embodiments of the technical solution of this invention, the purpose of this invention and the specific scenarios it addresses will be briefly explained.

[0055] The purpose of this invention is to dynamically adjust the flight path of drone swarms by taking into account tourists' personalized tour needs for different landscapes, so as to avoid flight path collisions caused by a large number of drones accumulating in the same location.

[0056] This invention addresses the specific scenario of using drones to capture three-dimensional environmental data of karst peaks, depressions, shafts, and caves, generating virtual tour scenes by combining them with panoramic images. By integrating drone technology with VR and AR technologies, an immersive tour experience can be provided. Tourists can "virtually tour" scenic spots from the comfort of their homes using drone aerial photography and VR panoramas, enjoying different perspectives of the landscape. However, in actual use, multiple drones operate simultaneously within the scenic area. Existing ant colony algorithms for planning drone flight paths do not fully consider the personalized differences in the tour experience of different tourists, leading to flight congestion or route collisions. Therefore, this invention considers the actual tour needs of different tourists and combines the flight characteristics of the landscape to dynamically adjust the flight paths of the drone swarm, avoiding flight path collisions caused by a large number of drones accumulating at the same location.

[0057] The following describes in detail, with reference to the accompanying drawings, a specific scheme of the unmanned aerial vehicle (UAV) route planning method for low-altitude tourism provided by the present invention.

[0058] Example 1:

[0059] For the drone route planning method for low-altitude tourism provided by this invention, please refer to [link to relevant documentation]. Figure 1 The diagram illustrates a flowchart of a method for planning unmanned aerial vehicle (UAV) routes for low-altitude tourism, provided by an embodiment of the present invention.

[0060] The drone route planning method for low-altitude tourism includes:

[0061] Step S1: Based on the scenic area terrain data and the tourists' tour demand data, determine the initial flight path of the target drone corresponding to the target tourists;

[0062] In this embodiment, the methods for collecting and processing scenic area terrain data and tourist visitation demand data are as follows:

[0063] Scenic Area Topographic Data: Drones equipped with LiDAR are used to scan the entire scenic area to obtain high-precision elevation data, including vegetation cover data and complex terrain information. Images are transmitted back to ground base stations in real time to generate a 3D real-scene model.

[0064] Tourist demand data: including historical actual visit data and virtual visit platform data;

[0065] Historical visitor data was collected offline by setting up visitor flow monitoring devices at the entrances of various scenic trails in the scenic area; virtual tour platform data was collected online through questionnaires to survey tourists' tour preferences, soliciting information such as target landscapes, shooting angles for target landscapes, scenic spots they would like to see by drone, and the duration of their tour.

[0066] The photos taken by the drone, the terrain data of the aforementioned scenic area collected, and its built-in POS (position, attitude) data are imported into existing 3D reality modeling software to generate a high-precision 3D reality model with realistic textures. The collected tourist visitor demand data is then standardized.

[0067] When multiple drones provide virtual tour services to different tourists in the airspace of a scenic area, the number of landscapes in the same scenic area is limited, the distance between different landscapes is relatively fixed, and the take-off base stations of multiple drones are different. Therefore, the ant colony algorithm can be used to analyze and obtain the minimum flight distance route of the drones during the current tourist's tour.

[0068] Specifically, step S1 includes:

[0069] Based on the raster scene map model corresponding to the scenic area terrain data, determine the location of the target landscape in the raster scene map model;

[0070] Based on historical actual visit data in the visitor demand data, the average historical stay time at the target scenic spot location is determined and used as its ideal visit time.

[0071] Based on the ant colony algorithm, the distance between the current position of the target drone and the target landscape position is used as the pheromone, and the tour duration under each ideal state is used as the weight to obtain the initial flight path of the target drone corresponding to the target tourist.

[0072] The collected scenic area terrain data and the corresponding 3D real-scene model information of the scenic area are discretized and converted into a raster scene map. Based on the raster scene map, a raster scene map model is generated. All target landscape locations of the target tourist (referring to any tourist) are marked on the map (the target landscape location refers to any landscape location selected by the target tourist), as well as the current position point of the i-th drone corresponding to the tourist. The positional distance between the current drone and all target landscape locations of the tourist is determined. The target landscape locations are the actual landscape locations existing in the scene map model information.

[0073] Based on historical actual visit data from tourist visit demand data, the average stay time of all tourists at the x-th scenic location (as the target scenic location) during their historical visits is calculated (historical average stay time), which is used as the ideal visit time for the current x-th scenic location. ;

[0074] Based on existing ant colony optimization algorithms, the distances between the current location of the i-th drone (as the target drone) and the locations of each target scenic spot for the tourist are used as pheromones in the ant colony optimization algorithm. The ideal tour duration for different scenic spots is... Using the weights, obtain the landscape spatial units that the current UAV i needs to traverse at time t. ;

[0075] Iterate through all drone tour data of tourists on the current platform, i.e., historical actual tour data, and expand the 3D spatial map into a 4D spatiotemporal map with spatial and temporal dimensions. Any grid cell in the map... This is called a "spatiotemporal unit," arranged in chronological order to obtain the initial tour sequence for the target tourists. Let be the initial flight path of the i-th UAV.

[0076] It should be noted that the above initial flight path can also be obtained using existing ant colony algorithms or other algorithms, and no restrictions are imposed here.

[0077] Step S2: Using the target visit order ranking of the target landscape locations in the initial flight path, determine the theoretical dwell time of the target UAV at the target landscape location;

[0078] Based on the above embodiments, the initial flight paths of drones for different tourists are obtained. Since different tourists have different levels of interest in the landscapes at different locations within the scenic area, the actual flight of the drones will be affected by the tourists' sightseeing time and other factors. At the same time, since the drones fly continuously throughout the entire tour, there is a difference between the actual flight process and the ideal state in terms of the dwell time at each landscape location, resulting in flight deviations. Therefore, this embodiment needs to analyze the sightseeing and dwell time of different tourists at the same location, construct a landscape dwelling penalty factor, adjust the initial flight path of multiple drone groups, and construct a low-altitude sightseeing route plan with a stable overall trajectory to meet the personalized tour needs of different tourists.

[0079] Specifically, please refer to Figure 2 Step S2 includes:

[0080] Step S21: Determine the ratio of the total number of landscapes covered by the target UAV to the number of target landscapes in its initial flight path;

[0081] Step S22: Using the target visit order ranking and the ratio of the number of landscapes in the initial flight path, determine the theoretical dwell time of the target UAV at the target landscape location.

[0082] In this embodiment, the tourist's tour demand data is analyzed. When the online tour duration is fixed, the more target landscapes a tourist has, the less time is allocated to each landscape. Furthermore, the order in which target landscapes are visited also affects the level of visitation. Therefore, the theoretical dwell time of the i-th drone corresponding to the tourist at the x-th landscape location is determined by using the tourist's target level of visitation at the x-th landscape location. :

[0083] ;

[0084] in The value represents the ranking of the i-th drone's target visit order at the x-th scenic location. The higher the ranking (e.g., 1st, 2nd, 3rd, etc., the smaller the value, the higher the ranking), the more time the drone spends at the target scenic location. Ni represents the total number of scenic spots that the i-th drone can cover. This represents the number of target landscapes included in the initial flight path of the i-th UAV, and its value is not 0; The ratio of the total number of sights visited to the number of target sights reflects the time that may be spent visiting the target sights. The fewer target sights tourists select, the more detailed the tourists' appreciation of the current target sights is, and the longer they should stay at the target sights.

[0085] Step S3: Determine the critical node degree of the target UAV for the target landscape location using the theoretical dwell time degree, and determine the queuing cost of the target landscape location for the target UAV using the degree of each critical node degree.

[0086] Specifically, in one embodiment, step S3, which determines the criticality of the target UAV to the target landscape location using theoretical dwell time, includes:

[0087] Determine the theoretical difference in dwell time between adjacent target landscape locations in the initial flight path;

[0088] By utilizing the theoretical dwell time and the difference between theoretical dwell time at the target landscape location, the criticality of the target UAV at the target landscape location can be determined.

[0089] In this embodiment, based on the different degrees to which the i-th drone lingers in different scenic locations during its flight, the regional time offset (also denoted as critical node degree) of the i-th drone during its actual flight is calculated. Here, the critical node degree of the target drone i relative to the target scenic location x is used. Let's take an example to illustrate:

[0090] ;

[0091] Where Ni represents the total number of landscapes that the i-th drone can cover; This represents the theoretical dwell time of the i-th UAV at the target landscape location x; This represents the theoretical dwell time of the i-th UAV at the target landscape location m; This represents the theoretical dwell time of the i-th UAV at landscape location m+1 adjacent to the target landscape location m; This refers to the theoretical difference in dwell time between adjacent target landscape locations; it should be noted that if This case can be ignored, that is, the calculation results are not accumulated.

[0092] By calculating the differences in theoretical dwell times among all landscape locations during the actual flight of the drone. This reflects the fluctuation of the interest route along the entire flight path. Combined with the ratio of the drone's dwell time in the xth landscape area to the overall route fluctuation, it reflects the weight of the target landscape location x on the overall flight time disturbance. The larger the ratio, the more likely the target landscape x is to become a key node in the spatiotemporal offset of the entire flight process.

[0093] Specifically, in one embodiment, please refer to Figure 3 Step S3, which determines the queuing cost of the target landscape location for the target drone using the degree of each key node, includes:

[0094] Step S31: Determine the actual dwell time and criticality of the target landscape location by the other drones before the target drone reaches the target landscape location.

[0095] Step S32: Determine the queuing cost of the target landscape location for the target drone by using the actual dwell time and criticality of each of the other drones at the target landscape location.

[0096] More specifically, step S32 includes:

[0097] Determine the ideal tour duration for the target landscape location, and obtain the difference in tour duration between the actual stay duration of other drones at the target landscape location and the ideal tour duration;

[0098] By utilizing the criticality of other drones at the target landscape location and the differences in their dwell time, the queuing cost of the target landscape location for the target drone is determined.

[0099] In this embodiment, for different flight routes, due to differences in the initial flight path performance and regional time offsets (critical node degree) during actual flight, the actual arrival time of drones for different tourists at the same landscape x will be different. Considering the queuing time that drones may spend in the predetermined queuing position before the target landscape x, the queuing cost of the i-th drone before the x-th landscape is calculated. :

[0100] ;

[0101] in, This represents the actual dwell time of the j-th drone (or any other drone) in the x-th landscape before the i-th drone arrives at the x-th landscape. This represents the ideal tour duration for the x-th landscape. This represents the remaining drones that stayed in the x-th landscape before the i-th drone reached the x-th landscape. Number; the remaining drones lingering in the xth landscape The quantity can be understood as the remaining drones that stayed during this period (which can be measured in days or hours). The number or remaining drones quantity; Indicates the remaining drones For the criticality of the x-th landscape node, norm represents the maximum and minimum value normalization.

[0102] By analyzing the drones preceding the i-th drone... The difference between the length of stay and the ideal length of visit Accumulate the costs to determine the queuing cost and dwell time difference for drone i at the corresponding landscape location x. The longer the distance, the more likely the current landscape location x is to become a key node in the spatiotemporal shift of the entire flight process. In this case, the queuing (waiting) cost of the current landscape location x for drone i is higher, and the greater the possibility that the drone needs to replan its route.

[0103] Step S4: Use queuing costs to determine the flight adjustment difficulty of the target UAV for the target landscape location, and use the flight adjustment difficulty and the initial flight path to determine the target flight path of the target UAV.

[0104] Specifically, in one embodiment, please refer to Figure 4Step S4, which uses queuing costs to determine the difficulty of the target UAV's flight adjustment to the target landscape location, includes:

[0105] Step S41: Determine the spatiotemporal distance between adjacent target landscape locations in the initial flight path;

[0106] Step S42: Determine the difficulty of the target UAV's flight adjustment to the target landscape location using queuing costs and landscape spatiotemporal distance.

[0107] In this embodiment, the difficulty of adjusting the flight path of the i-th UAV to the target landscape position x is quantified by combining the queuing cost of all target landscapes in the initial flight path and the positional distance between different landscapes. :

[0108] ;

[0109] in, Let $\frac{i}{x}$ represent the queuing cost of the i-th drone in front of the x-th landscape. The higher the queuing cost, the more difficult it is for drone i to make relative flight adjustments to the x-th landscape position.

[0110] This represents the spatiotemporal distance (landscape spatiotemporal distance) between adjacent target landscape positions x and x+1 in the initial flight path of the i-th UAV. It is obtained by calculating the Euclidean distance between the spatiotemporal units of adjacent landscapes in the UAV flight path. The larger this value is, the greater the spatiotemporal interval between different landscapes in the flight path. This indicates that the adjacent landscape positions in the route are relatively not concentrated. Therefore, even if the cost of queuing and waiting at position x is too high during the flight, the large spatiotemporal distance between landscapes can be handled by slowing down or detouring by the UAV, thereby reducing the interference of collisions or flight conflicts and reducing the difficulty of flight.

[0111] Specifically, in another embodiment, please refer to Figure 5 Step S4, which determines the target flight path of the target UAV using flight adjustment difficulty and initial flight path, includes:

[0112] Step S401: Determine the number of drones queuing in front of the target landscape location. The number of drones queuing is positively correlated with the adjustment of the flight order of the target landscape location.

[0113] Step S402: Adjust the initial flight path using the flight adjustment difficulty and the number of drones in the queue to obtain the target flight path of the target drone.

[0114] More specifically, step S402 includes:

[0115] Determine the minimum and standard deviation of the flight adjustment difficulty for all UAVs to the target landscape location;

[0116] Determine the difference in adjustment difficulty between the target UAV's flight adjustment difficulty for the target landscape location and the minimum value;

[0117] The dwell penalty factor of the target UAV for the target landscape location is determined by using the adjustment difficulty difference and the standard deviation;

[0118] The initial flight path is adjusted using the number of drones in the queue and the sojourn penalty factor to obtain the target flight path of the target drone.

[0119] In this embodiment, the difficulty of flight adjustment for several UAVs at landscape location x is evaluated, and the dwell penalty factor of the i-th UAV at the target landscape location x during flight is calculated. :

[0120] ;

[0121] in; This represents the difficulty of the target drone i adjusting its flight relative to the target landscape position x. This represents the minimum difficulty of adjusting the flight path to the target landscape location x among all drone flight paths (initial flight paths) in the current scenic area. This indicates the difference in the difficulty of adjusting the two. This represents the standard deviation of the difficulty of adjusting the flight path for the target landscape location x across all drone flight routes in the current scenic area. Adding 0.1 to the denominator prevents formula errors caused by a denominator of 0. Under normal circumstances... If the value is not 0, this part can be removed.

[0122] By calculating the contribution value of flight adjustment difficulty in each drone's flight path and the standard deviation of all flight difficulties in the scenic area, the flight risk of the i-th drone staying at different scenic locations is determined. The greater the relative flight difficulty of the drone at different scenic locations, the greater the calculated landscape stay penalty factor, and the greater the degree to which the current flight path can be adjusted according to the calculation results.

[0123] When multiple drones simultaneously tour a scenic route, the penalty factor for the i-th drone's stay at scenic location x during its flight is calculated. The initial flight sequence (i.e., the corresponding target visit sequence) in the initial flight path of the UAV is determined and adjusted to obtain the results of each flight transfer. :

[0124] ;

[0125] in, This represents the initial flight order value corresponding to landscape position x in the initial flight path of the i-th UAV, that is, the landscape position x is in the i-th position in the initial flight path. A tour sequence; This indicates the number of drones queuing in front of the xth landscape location. The number, or the number of drones in the queue, is the greater the number of drones in the queue in front of the current landscape x. This increases the likelihood that the flight order of drone i relative to landscape x will need to be adjusted backward.

[0126] Based on flight transfer results The flight sequence of each landscape in the initial flight path is adjusted to obtain the real-time planned flight route, i.e., the target flight path. .

[0127] This invention addresses drone path planning in high-precision, large-scale scenarios such as karst landforms. By combining the dwell time at different scenic spots, it obtains the initial flight route of the drones, determines the spatiotemporal unit information during the flight process, and closely links the 3D real-world map with the flight path time. Furthermore, based on the differences between the target scenic spots visited by different tourists and the dwell time of different tourists at the same location, it constructs a scenic dwell time penalty factor to adjust the initial flight routes of multiple drone swarms, and builds a low-altitude sightseeing route plan with stable overall trajectory. This meets the personalized sightseeing needs of different tourists. The dynamic planning method based on real-time map data enables drone swarms to better adapt to complex and changing environments, improves the success rate, efficiency, and operational safety of mission execution, and avoids conflicts and collisions between multiple drones in space and time.

[0128] Example 2:

[0129] This invention also proposes a drone flight path planning device for low-altitude tourism. The device can be a drone, a computer, a server, or a combination of multiple devices for data analysis and computation.

[0130] like Figure 6 As shown, Figure 6 This is a schematic diagram of the hardware operating environment of the unmanned aerial vehicle (UAV) route planning equipment for low-altitude tourism and sightseeing, which is involved in the embodiments of the present invention.

[0131] like Figure 6As shown, the drone flight path planning device for low-altitude tourism may include: a processor 1001, such as a CPU; a network interface 1004; a user interface 1003; a memory 1005; and a communication bus 1002. The communication bus 1002 is used to establish communication between these components. The user interface 1003 may include a display or an input unit such as a control panel; optionally, the user interface 1003 may also include a standard wired interface or a wireless interface. The network interface 1004 may optionally include a standard wired interface or a wireless interface (such as a Wi-Fi interface). The memory 1005 may be high-speed RAM or non-volatile memory, such as a disk drive. Optionally, the memory 1005 may also be a storage device independent of the aforementioned processor 1001. The memory 1005, as a computer storage medium, may include a drone flight path planning program.

[0132] Those skilled in the art will understand that Figure 6 The hardware structure shown does not constitute a limitation on the device and may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0133] Continue to refer to Figure 6 , Figure 6 The memory 1005, which is a computer-readable storage medium, may include an operating system, a user interface module, a network communication module, and an unmanned aerial vehicle (UAV) route planning program.

[0134] exist Figure 6 In this embodiment, the network communication module is mainly used to connect to the server and can communicate with the server for data; while the processor 1001 can call the UAV route planning program stored in the memory 1005 and execute the steps in the above embodiments.

[0135] Based on the hardware structure of the above-mentioned UAV route planning equipment for low-altitude tourism, various embodiments of the UAV route planning method for low-altitude tourism of the present invention are implemented.

[0136] In addition, this invention also provides a drone route planning system for low-altitude tourism (hereinafter referred to as the "drone route planning system"), please refer to... Figure 7 The unmanned aerial vehicle (UAV) route planning system for low-altitude tourism includes:

[0137] The initial path planning module A10 is used to determine the initial flight path of the target drone corresponding to the target tourist based on the scenic area terrain data and the tourist's tour demand data.

[0138] The flight cost analysis module A20 is used to determine the theoretical dwell time of the target UAV at the target landscape location by using the target visit order ranking of the target landscape location in the initial flight path; to determine the critical node degree of the target UAV for the target landscape location by using the theoretical dwell time; and to determine the queuing cost of the target landscape location for the target UAV by using the degree of each critical node.

[0139] The flight path update module A30 is used to determine the difficulty of the target UAV's flight adjustment to the target landscape location by using queuing costs, and to determine the target flight path of the target UAV by using the flight adjustment difficulty and the initial flight path.

[0140] Furthermore, the flight cost analysis module A20 is also used for:

[0141] Determine the ratio of the total number of landscapes covered by the target UAV to the number of target landscapes in its initial flight path;

[0142] By using the target visit order ranking and the ratio of the number of landscapes in the initial flight path, the theoretical dwell time of the target UAV at the target landscape location is determined.

[0143] Furthermore, the flight cost analysis module A20 is also used for:

[0144] Determine the theoretical difference in dwell time between adjacent target landscape locations in the initial flight path;

[0145] By utilizing the theoretical dwell time and the difference between theoretical dwell time at the target landscape location, the criticality of the target UAV at the target landscape location can be determined.

[0146] Furthermore, the flight cost analysis module A20 is also used for:

[0147] Determine the actual dwell time and criticality of other drones at the target landscape location before the target drone reaches the target landscape location;

[0148] By utilizing the actual dwell time and criticality of each of the other drones at the target landscape location, the queuing cost of the target landscape location for the target drone can be determined.

[0149] Furthermore, the flight cost analysis module A20 is also used for:

[0150] Determine the ideal tour duration for the target landscape location, and obtain the difference in tour duration between the actual stay duration of other drones at the target landscape location and the ideal tour duration;

[0151] By utilizing the criticality of other drones at the target landscape location and the differences in their dwell time, the queuing cost of the target landscape location for the target drone is determined.

[0152] Furthermore, the flight path update module A30 is also used for:

[0153] Determine the spatiotemporal distance between adjacent target landscape locations in the initial flight path;

[0154] The difficulty of adjusting the target UAV's flight position to the target landscape location is determined by using queuing costs and landscape spatiotemporal distance.

[0155] Furthermore, the flight path update module A30 is also used for:

[0156] The number of drones queued in front of the target landscape location is determined, and the number of drones queued is positively correlated with the adjustment of the flight order to the target landscape location.

[0157] The initial flight path is adjusted by utilizing the difficulty of flight adjustment and the number of drones in the queue to obtain the target flight path of the target drone.

[0158] Furthermore, the flight path update module A30 is also used for:

[0159] Determine the minimum and standard deviation of the flight adjustment difficulty for all UAVs to the target landscape location;

[0160] Determine the difference in adjustment difficulty between the target UAV's flight adjustment difficulty for the target landscape location and the minimum value;

[0161] The dwell penalty factor of the target UAV for the target landscape location is determined by using the adjustment difficulty difference and the standard deviation;

[0162] The initial flight path is adjusted using the number of drones in the queue and the sojourn penalty factor to obtain the target flight path of the target drone.

[0163] Furthermore, the initial path planning module A10 is also used for:

[0164] Based on the raster scene map model corresponding to the scenic area terrain data, determine the location of the target landscape in the raster scene map model;

[0165] Based on historical actual visit data in the visitor demand data, the average historical stay time at the target scenic spot location is determined and used as its ideal visit time.

[0166] Based on the ant colony algorithm, the distance between the current position of the target drone and the target landscape position is used as the pheromone, and the tour duration under each ideal state is used as the weight to obtain the initial flight path of the target drone corresponding to the target tourist.

[0167] The specific implementation of the UAV route planning system for low-altitude tourism of the present invention is basically the same as the embodiments of the UAV route planning method for low-altitude tourism described above, and will not be repeated here.

[0168] Furthermore, the present invention also provides a computer-readable storage medium. The computer-readable storage medium stores a drone flight path planning program, wherein when executed by a processor, the drone flight path planning program implements the steps of the drone flight path planning method for low-altitude tourism described above.

[0169] The method implemented when the UAV route planning program is executed can be referred to in various embodiments of the UAV route planning method for low-altitude tourism of the present invention, and will not be repeated here.

[0170] It should be noted that the order of the above embodiments of the present invention is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. The processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0171] The various embodiments in this specification are described in a progressive manner. The same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on describing the differences from other embodiments.

[0172] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0173] The above description is only a preferred embodiment of the present invention and does not limit the scope of protection of the present invention. All equivalent structural / method transformations made under the inventive concept of the present invention using the contents of the present invention specification and drawings, or direct / indirect applications in other related technical fields, are included within the scope of protection of the present invention.

Claims

1. A method for unmanned aerial vehicle (UAV) route planning for low-altitude tourism, characterized in that, The method includes: Based on the scenic area's terrain data and tourists' travel needs data, the initial flight path of the target drone corresponding to the target tourist is determined. By using the ranking of the target landscape locations in the initial flight path to determine the theoretical dwell time of the target UAV at the target landscape location; The theoretical dwell time is used to determine the criticality of the target UAV to the target landscape location, and the queuing cost of the target UAV to the target landscape location is determined by the criticality of each critical node. Queuing costs are used to determine the difficulty of flight adjustment of the target UAV to the target landscape location, and the target flight path of the target UAV is determined by the flight adjustment difficulty and the initial flight path. Methods for determining the degree of criticality include: Determine the theoretical difference in dwell time between adjacent target landscape locations in the initial flight path; By utilizing the theoretical dwell time and the difference between theoretical dwell times at the target landscape location, the criticality of the target UAV at the target landscape location is determined; this corresponds to the criticality of target UAV i at the target landscape location x. The calculation formula is: Where Ni represents the total number of landscapes that the i-th drone can cover; This represents the theoretical dwell time of the i-th UAV at the target landscape location x; This represents the theoretical dwell time of the i-th UAV at the target landscape location m; This represents the theoretical dwell time of the i-th UAV at landscape location m+1 adjacent to the target landscape location m; That is, the theoretical difference in the degree of dwell time between adjacent target landscape locations; Methods for determining the queuing cost of the target drone include: Determine the actual dwell time and criticality of other drones at the target landscape location before the target drone reaches the target landscape location; Determine the ideal tour duration for the target landscape location, and obtain the difference in tour duration between the actual stay duration of other drones at the target landscape location and the ideal tour duration; By utilizing the criticality of other drones to the target landscape location and the differences in their dwell time, the queuing cost for the target drone at the target landscape location is determined; this corresponds to the queuing cost of the i-th drone before the x-th landscape. The calculation formula is: ;in, This represents the actual dwell time of the i-th drone in the x-th landscape before the j-th drone reaches the x-th landscape; This represents the ideal tour duration for the x-th landscape. This represents the remaining drones that stayed in the x-th landscape before the i-th drone reached the x-th landscape. Number; the remaining drones lingering in the xth landscape The number is the same as the other drones that stayed there this time. The number or remaining drones quantity; Indicates the remaining drones For the criticality of the x-th landscape node, norm represents the maximum and minimum value normalization; Methods for determining the target flight path include: The number of drones queued in front of the target landscape location is determined, and the number of drones queued is positively correlated with the adjustment of the flight order to the target landscape location. Determine the minimum and standard deviation of the flight adjustment difficulty for all UAVs to the target landscape location; Determine the difference in adjustment difficulty between the target UAV's flight adjustment difficulty for the target landscape location and the minimum value; The dwell penalty factor of the target UAV for the target landscape location is determined by using the adjustment difficulty difference and the standard deviation; The initial flight path is adjusted using the number of drones in the queue and the sojourn penalty factor to obtain the target flight path of the target drone.

2. The method for unmanned aerial vehicle (UAV) route planning for low-altitude tourism and sightseeing according to claim 1, characterized in that, The method of determining the theoretical dwell time of the target UAV at the target landscape location by ranking the target visit order of the target landscape location in the initial flight path includes: Determine the ratio of the total number of landscapes covered by the target UAV to the number of target landscapes in its initial flight path; By using the target visit order ranking and the ratio of the number of landscapes in the initial flight path, the theoretical dwell time of the target UAV at the target landscape location is determined.

3. The method for unmanned aerial vehicle (UAV) route planning for low-altitude tourism and sightseeing according to claim 1, characterized in that, The method of determining the difficulty of flight adjustments for a target UAV to a target landscape location using queuing costs includes: Determine the spatiotemporal distance between adjacent target landscape locations in the initial flight path; The difficulty of adjusting the target UAV's flight position to the target landscape location is determined by using queuing costs and landscape spatiotemporal distance.

4. The method for unmanned aerial vehicle (UAV) route planning for low-altitude tourism and sightseeing according to claim 1, characterized in that, The process of determining the initial flight path of the target drone for the target tourist, based on scenic area terrain data and tourist travel demand data, includes: Based on the raster scene map model corresponding to the scenic area terrain data, determine the location of the target landscape in the raster scene map model; Based on historical actual visit data in the visitor demand data, the average historical stay time at the target scenic spot location is determined and used as its ideal visit time. Based on the ant colony algorithm, the distance between the current position of the target drone and the target landscape position is used as the pheromone, and the tour duration under each ideal state is used as the weight to obtain the initial flight path of the target drone corresponding to the target tourist.

5. A drone route planning system for low-altitude tourism, characterized in that, The system is used to implement the unmanned aerial vehicle (UAV) route planning method for low-altitude tourism as described in any one of claims 1 to 4; the system includes: The initial path planning module is used to determine the initial flight path of the target drone for the target tourist based on the scenic area terrain data and the tourist's tour demand data. The flight cost analysis module is used to determine the theoretical dwell time of the target drone at the target landscape location by using the target visit order ranking of the target landscape location in the initial flight path; it uses the theoretical dwell time to determine the critical node degree of the target drone for the target landscape location; and it uses the degree of each critical node to determine the queuing cost of the target landscape location for the target drone. The flight path update module is used to determine the difficulty of the target UAV's flight adjustment to the target landscape location by using queuing costs, and to determine the target flight path of the target UAV by using the flight adjustment difficulty and the initial flight path.

Images