Full-scene adaptive flight method and device, equipment and storage medium

Abstract

The invention discloses a full-scene adaptive flight method, device and equipment and a storage medium, and relates to the technical field of unmanned aerial vehicles. The technical scheme provided by the invention comprises the following steps: determining a real-time control strategy according to first scene information, wherein the real-time control strategy comprises a speed priority control strategy and a terrain priority control strategy; acquiring topographic information collected by the perception sensor in real time, and planning a flight path according to the topographic information and the real-time control strategy; when the unmanned aerial vehicle flies based on the flight path, second scene information is determined according to the terrain information, and a real-time control strategy is adjusted according to the second scene information; and re-planning a flight path according to the adjusted real-time control strategy and terrain information. Through the technical means, autonomous flight of the unmanned aerial vehicle in any terrain scene is achieved, the problem that in the prior art, a user needs to judge terrain features and control the unmanned aerial vehicle to switch the terrain simulation mode is solved, the operation difficulty of the user is simplified, and potential safety hazards caused by misoperation are avoided.

Description

Technical Field

[0001] The present application relates to the field of drone technology, and in particular to a full-scenario adaptive flight method, device, equipment and storage medium. Background Art

[0002] With the rapid development of drones, drones are increasingly used in industries, logistics, agriculture and other fields. In some fields, drones have a variety of operating scenarios, which can be roughly divided into two types: one is a scene with relatively flat terrain, and the other is a scene with relatively rugged terrain. In order to adapt to different scenarios, drones provide two terrain imitation modes, namely two-dimensional terrain imitation mode and three-dimensional terrain imitation mode. In the two-dimensional terrain imitation mode, the drone can move over a large range in the horizontal direction and try to track the terrain in the vertical direction. In the three-dimensional terrain imitation mode, the drone can move over a large range in three dimensions to accurately track the terrain.

[0003] In the prior art, the user obtains the scene type of the drone's operating area in advance. When the drone flies to a flat terrain scene, the user manually controls the drone to switch to a two-dimensional terrain imitation mode. When the drone flies to a rugged terrain scene, the user manually controls the drone to switch to a three-dimensional terrain imitation mode. The drone's operation process requires the user to participate in adjusting the terrain imitation mode throughout the process, which increases the user's operating difficulty and the user's probability of misoperation is high. The drone is prone to safety problems due to user misoperation. Summary of the invention

[0004] The present application provides a full-scenario adaptive flight method, device, equipment and storage medium, which preliminarily determines a real-time control strategy according to first scene information, and adaptively adjusts the real-time control strategy according to second scene information during a flight, thereby adaptively adjusting the flight trajectory according to the real-time control strategy and real-time terrain information to generate a flight trajectory that tracks the terrain and takes speed into account, thereby ensuring the flight safety of the drone and optimizing the flight efficiency of the drone, realizing autonomous flight of the drone in any terrain scenario, solving the problem in the prior art that the user needs to judge the terrain features and control the drone to switch to a terrain-imitation mode, greatly simplifying the user's operating difficulty, and avoiding safety hazards caused by misoperation.

[0005] In a first aspect, the present application provides a full-scenario adaptive flight method, comprising:

[0006] Determine a real-time control strategy according to the first scene information, wherein the real-time control strategy includes a speed priority control strategy and a terrain priority control strategy;

[0007] Acquire terrain information collected by the perception sensor in real time, and plan a flight trajectory according to the terrain information and the real-time control strategy;

[0008] When the UAV is flying based on the flight trajectory, second scene information is determined according to the terrain information, and the real-time control strategy is adjusted according to the second scene information;

[0009] The flight trajectory is replanned according to the adjusted real-time control strategy and the terrain information.

[0010] In a second aspect, the present application provides a full-scenario adaptive flight device, including:

[0011] a strategy determination module, configured to determine a real-time control strategy according to the first scene information, wherein the real-time control strategy includes a speed priority control strategy and a terrain priority control strategy;

[0012] A trajectory planning module is configured to obtain terrain information collected by the perception sensor in real time, and plan a flight trajectory according to the terrain information and the real-time control strategy;

[0013] a strategy adjustment module, configured to determine second scene information according to the terrain information when the UAV flies based on the flight trajectory, and adjust the real-time control strategy according to the second scene information;

[0014] The trajectory adjustment module is configured to re-plan the flight trajectory according to the adjusted real-time control strategy and the terrain information.

[0015] In a third aspect, the present application provides a full-scenario adaptive flight device, including:

[0016] One or more processors; a memory storing one or more programs, when the one or more programs are executed by the one or more processors, the one or more processors implement the full-scenario adaptive flight method as described in the first aspect.

[0017] In a fourth aspect, the present application provides a storage medium comprising computer executable instructions, which, when executed by a computer processor, are used to execute the full-scenario adaptive flight method as described in the first aspect.

[0018] In the present application, the real-time control strategy can be preliminarily determined based on the first scene information. During the initial flight, a flight trajectory adapted to the first scene information can be planned based on the real-time control strategy and the terrain information collected in real time by the perception sensor. During the flight, the real-time second scene information can be determined based on the terrain information, and the real-time control strategy can be adaptively adjusted based on the second scene information, so as to plan a flight trajectory adapted to the second scene information based on the adjusted real-time control strategy and the real-time terrain information, ensuring that the flight trajectory of the drone can accurately track the terrain of the scene and take into account the flight speed, thereby improving the flight safety and efficiency of the drone. The real-time control strategy and flight trajectory can be adaptively adjusted during the entire flight process, realizing autonomous flight of the drone in any terrain scene, without the user having to worry about the terrain type and adaptive terrain imitation mode of the scene where the drone is located, solving the problem in the prior art that the user needs to judge the terrain characteristics and control the drone to switch the terrain imitation mode, greatly simplifying the user's operating difficulty, and avoiding safety hazards caused by misoperation. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 is a flow chart of a full-scenario adaptive flight method provided by an embodiment of the present application;

[0020] Figure 2 This is a flow chart of planning a flight trajectory based on a speed priority control strategy and terrain information provided by an embodiment of the present application;

[0021] Figure 3 is a schematic diagram of an operation route provided in an embodiment of the present application;

[0022] Figure 4 is a schematic diagram of a straight line path provided in an embodiment of the present application;

[0023] Figure 5 is a schematic diagram of a straight line trajectory provided in an embodiment of the present application;

[0024] Figure 6 is a schematic diagram of the adjustment trend of the first control point provided in an embodiment of the present application;

[0025] Figure 7 It is one of the schematic diagrams of the flight trajectory provided in the embodiment of the present application;

[0026] Figure 8 This is a flow chart of planning a flight trajectory based on a terrain priority control strategy and terrain information provided by an embodiment of the present application;

[0027] Fig. 9 is a schematic diagram of the third control point before adjusting the height provided in an embodiment of the present application;

[0028] Fig.10 is a schematic diagram of the third control point after adjusting the height provided in the embodiment of the present application;

[0029] Fig.11 is a schematic diagram of a second control point provided in an embodiment of the present application;

[0030] Fig.12 This is the second schematic diagram of the flight trajectory provided in the embodiment of the present application;

[0031] Fig.13 is a flow chart of planning a flight trajectory based on combining control strategy and terrain information provided by an embodiment of the present application;

[0032] Fig.14 is a system framework diagram of a drone provided in an embodiment of the present application;

[0033] Fig.15 It is a structural schematic diagram of a full-scenario adaptive flight device provided in an embodiment of the present application;

[0034] Fig.16 It is a structural schematic diagram of a drone provided in an embodiment of the present application. DETAILED DESCRIPTION

[0035] In order to make the purpose, technical scheme and advantages of the present application clearer, the specific embodiments of the present application are further described in detail below in conjunction with the accompanying drawings. It is understood that the specific embodiments described herein are only used to explain the present application, rather than to limit the present application. It should also be noted that, for the convenience of description, only the part related to the present application but not all the contents are shown in the accompanying drawings. Before discussing the exemplary embodiments in more detail, it should be mentioned that some exemplary embodiments are described as processes or methods depicted as flow charts. Although the flow chart describes each operation (or step) as a sequential process, many of the operations therein can be implemented in parallel, concurrently or simultaneously. In addition, the order of each operation can be rearranged. The process can be terminated when its operation is completed, but it can also have additional steps not included in the accompanying drawings. The process can correspond to a method, a function, a procedure, a subroutine, a subprogram, etc.

[0036] The terms "first", "second", etc. in the specification and claims of the present application are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable under appropriate circumstances, so that the embodiments of the present application can be implemented in an order other than those illustrated or described here, and the objects distinguished by "first", "second", etc. are generally of one type, and the number of objects is not limited. For example, the first object can be one or more. In addition, "and / or" in the specification and claims represents at least one of the connected objects, and the character " / " generally indicates that the objects associated with each other are in an "or" relationship.

[0037] In the relevant implementation method, the user manually selects the terrain type of the operation scene as flat terrain or rugged terrain before the operation of the drone. When the drone is operating, it automatically selects the two-dimensional terrain imitation mode or the three-dimensional terrain imitation mode for flight operation according to the operation scene of flat terrain or rugged terrain. In the two-dimensional terrain imitation mode, the drone generally only moves in a large range in the horizontal direction, and allows a small movement in the vertical direction. Since the two-dimensional terrain imitation mode generally gives priority to the horizontal direction, the flight efficiency is relatively high, and the vertical direction often only needs to try its best to track the terrain. The three-dimensional terrain imitation mode allows the drone to move in a large range in three dimensions, so even scenes with large terrain changes can be tracked relatively accurately. Since the three-dimensional terrain imitation mode is affected by the vertical direction during flight, the speed in the horizontal direction is subject to certain restrictions. Obviously, the two-dimensional terrain imitation mode is suitable for operation scenes with flat terrain, and the three-dimensional terrain imitation mode is suitable for operation scenes with rugged terrain. However, in general operation scenes, both types of terrain may exist at the same time. Therefore, when the drone is flying, the user needs to determine which type of terrain the area the drone is flying to belongs to. If the drone flies from rugged terrain to flat terrain, the drone is manually controlled to switch from 3D terrain imitation mode to 2D terrain imitation mode. If the drone flies from flat terrain to rugged terrain, the drone is manually controlled to switch from 2D terrain imitation mode to 3D terrain imitation mode. In order to ensure the flight safety of the drone, the user must pay full attention to the terrain changes in the operation scene during the entire operation process, so as to switch the drone's terrain imitation mode in time, which increases the user's operation difficulty. In addition, the user's probability of misoperation is high under frequent mode operations, and the drone is prone to safety problems due to user misoperation. In addition, the terrain in some areas is a transitional terrain between flat terrain and rugged terrain. For this kind of terrain, users may be entangled in which terrain imitation mode to use, resulting in the drone being unable to switch to the appropriate terrain imitation mode in time, thus affecting the drone's flight safety and flight efficiency.

[0038] In order to solve the problems existing in the above implementation methods, the present embodiment provides a full-scenario adaptive flight method, which preliminarily determines the real-time control strategy according to the first scene information, and adaptively adjusts the real-time control strategy according to the second scene information during the flight, so as to adaptively adjust the flight trajectory according to the real-time control strategy and the real-time terrain information to generate a flight trajectory that tracks the terrain and takes into account the speed, thereby ensuring the flight safety of the UAV and optimizing the flight efficiency of the UAV. There is no need for the user to judge the terrain features and control the UAV to switch to the terrain imitation mode, which greatly simplifies the user's operation difficulty and avoids safety hazards caused by misoperation.

[0039] The full-scenario adaptive flight method provided in this embodiment can be executed by a full-scenario adaptive flight device, which can be implemented by software and / or hardware, and can be composed of two or more physical entities, or one physical entity. For example, the full-scenario adaptive flight device can be a drone, or a processor of the drone.

[0040] The full-scenario adaptive flight device is installed with at least one type of operating system, and the full-scenario adaptive flight device can install at least one application based on the operating system, and the application can be an application that comes with the operating system, or an application downloaded from a third-party device or server. In this embodiment, the full-scenario adaptive flight device has at least an application that can execute the full-scenario adaptive flight method.

[0041] For ease of understanding, this embodiment is described by taking a drone as an example of a subject that performs the full-scenario adaptive flight method.

[0042] Figure 1 A flowchart of a full-scenario adaptive flight method provided by an embodiment of the present application is given. Figure 1 , the full-scenario adaptive flight method specifically includes:

[0043] S110. Determine a real-time control strategy according to the first scene information, where the real-time control strategy includes a speed priority control strategy and a terrain priority control strategy.

[0044] Exemplarily, before executing this flight, the UAV obtains the first scene information of the operation scene of this flight, and the first scene information is information characterizing the terrain type of the operation scene. For example, the first scene information can be the terrain type of the operation scene, and the terrain type includes flat terrain and rugged terrain. If the terrain type of the operation scene is flat terrain, the real-time control strategy of the flight is preliminarily determined to be the speed priority control strategy; if the terrain type of the operation scene is rugged terrain, the real-time control strategy of the flight is preliminarily determined to be the terrain priority control strategy. The real-time control strategy is a strategy for real-time control of the UAV to perform terrain-like flight in the operation scene. The speed priority control strategy is a strategy that gives priority to the flight speed to control the UAV to perform terrain-like flight in the operation scene. The terrain priority control strategy is a strategy that gives priority to the terrain to control the UAV to perform terrain-like flight in the operation scene. The real-time control strategy is determined according to the first scene information, that is, one of the speed priority control strategy and the terrain priority control strategy is determined as the real-time control strategy. In the operation scenario of flat terrain, since the terrain height will not change much, the UAV can track the terrain by fine-tuning in the vertical direction, so that the UAV can fly at high speed in the horizontal direction. Therefore, the speed priority control strategy is used to plan the flight trajectory of the UAV to improve the flight efficiency of the UAV. In the operation scenario of rugged terrain, since the terrain height will change frequently, the UAV must often adjust in the vertical direction to track the terrain, which limits the speed of the UAV in the horizontal direction. Therefore, the terrain priority control strategy is used to plan the flight trajectory of the UAV to ensure the flight safety of the UAV.

[0045] It should be noted that the first scene information can be understood as the preliminary estimated terrain type of the operation scene, which cannot accurately represent the terrain type of the operation scene. Therefore, the real-time control strategy determined by the first scene information is a preliminary real-time control strategy, which will be used to plan the flight trajectory when the UAV initially performs a flight sortie. However, as the UAV flies, when the UAV obtains the actual terrain information of the operation scene, it can accurately determine the terrain type of the operation scene based on the actual terrain information, and thus adjust the real-time control strategy based on the terrain type, so that the adjusted real-time control strategy adapts to the terrain of the operation scene.

[0046] Optionally, the first scene information can be manually configured by the user. For example, when the user configures the operation task in the remote control device, the user can add the first scene information, flight speed, flight acceleration and other information to the operation task. The remote control device sends the operation task to the drone, and the drone performs the corresponding flight according to the operation task. Before performing the flight, the drone obtains the first scene information from the operation task and determines the real-time control strategy according to the first scene information.

[0047] In addition, the drone can also determine the first scene information based on the third scene information of the last flight. Among them, the third scene information is information that characterizes the terrain type of the operation scene of the last flight. Exemplarily, when the operation plot is large, multiple flights are required to perform the operation. The operation scenes corresponding to the two adjacent flights are close, and the terrain will not change much. The terrain type of the operation scene of the last flight is the same or similar to the terrain type of the operation scene corresponding to the current flight. Therefore, the first scene information can be determined based on the third scene information of the last flight. Specifically, the third scene information of the last flight is determined as the first scene information of this flight. For example, the terrain type of the operation scene of the last flight can be determined as the terrain type of the operation scene of the current flight. Alternatively, when the third scene information includes a third terrain priority weight and a third scene priority weight, the third terrain priority weight and the third scene priority weight can be correspondingly determined as the first terrain priority weight and the first scene priority weight in the first scene information.

[0048] Alternatively, the UAV determines the first scene information according to the action mission information. The action mission information includes a preset flight speed and / or an operation area parameter. The preset flight speed is the planned flight speed of the UAV in this flight, which limits the maximum flight speed of the UAV when executing this flight. The operation area parameter is the unit amount of material that the UAV plans to spray or spread in the operation area in this flight, such as the amount per mu.

[0049] For example, the preset flight speed is generally determined by the user based on the terrain of the operating scene. Therefore, a higher preset flight speed indicates that the terrain of the operating scene of this flight is flatter, and a lower preset flight speed indicates that the terrain of the operating scene of this flight is more rugged.

[0050] Optionally, when this flight sortie is the first flight sortie, the preset flight speed in the operation task information is obtained. If the preset flight speed is greater than the first speed threshold, the first scene information is determined to be the first scene. If the preset flight speed is not greater than the first speed threshold, the first scene information is determined to be the second scene. The first scene is a scene in which the terrain type is flat terrain, and the second scene is a scene in which the terrain type is rugged terrain. For example, the maximum flight speed in the operation scene of rugged terrain is pre-set as the flight speed threshold. When the preset flight speed in the operation task information is greater than the flight speed threshold, the terrain type of the operation scene of this flight sortie is determined to be flat terrain. When the preset flight speed in the operation task information is less than or equal to the flight speed threshold, the terrain type of the operation scene of this flight sortie is determined to be rugged terrain.

[0051] If the drone is an agricultural drone, it will load materials for spraying or sowing operations. In the spraying or sowing scenario, the operating area parameter of the operation scene in the rugged terrain is much greater than the operating area parameter of the operation scene in the flat terrain. The operating area parameter can be, for example, the amount per mu, or other parameters used to represent the area where the drone performs operations, which are not limited here. In the case where this flight is the first flight, the operating area parameter in the operation task information is obtained. If the operating area parameter is greater than the first area parameter threshold, the first scene information is determined to be the second scene. If the operating area parameter is not greater than the first area parameter threshold, the first scene information is determined to be the first scene. For example, the maximum operating area parameter in the operation scene of flat terrain is pre-set as the first area parameter threshold. When the operating area parameter in the operation task information is greater than the first area parameter threshold, the terrain type of the operation scene of this flight is determined to be rugged terrain. When the operating area parameter in the operation task information is less than or equal to the first area parameter threshold, the terrain type of the operation scene of this flight is determined to be flat terrain.

[0052] In one embodiment, the first scene information includes a first terrain priority weight and a first speed priority weight, and the sum of the first terrain priority weight and the first speed priority weight is equal to one. Among them, the terrain priority weight can characterize the adaptability of the terrain in the corresponding scene to the terrain priority control strategy, and the speed priority weight can characterize the adaptability of the terrain in the corresponding scene to the speed priority control strategy. The higher the terrain priority weight, the more adapted the terrain of the corresponding scene is to the terrain priority control strategy, that is, the more rugged the terrain of the corresponding scene is, so the terrain priority weight can also be understood as the ruggedness of the terrain in the corresponding scene. The higher the speed priority weight, the more adapted the terrain of the corresponding scene is to the flatness priority control strategy, that is, the flatter the terrain of the corresponding scene is, so the speed priority weight can also be understood as the flatness of the terrain in the corresponding scene.

[0053] Correspondingly, when this flight is the first flight, the preset flight speed and the preset maximum speed in the operation task information are obtained; the speed ratio of the preset flight speed and the preset maximum speed is determined; wherein the preset maximum speed is the maximum flight speed allowed for the UAV, and the preset flight speed is the planned flight speed of the UAV in this flight; the first terrain priority weight and the first speed priority weight are determined according to the speed ratio and the preset second terrain priority weight and the second speed priority weight, and the second terrain priority weight and the second speed priority weight are equal and the sum is equal to one. Exemplarily, when the speed ratio of the preset flight speed to the preset maximum speed is larger, it indicates that the terrain of the operation scene of this flight is flatter, and when the speed ratio is smaller, it indicates that the terrain of the operation scene of this flight is more rugged. The second terrain priority weight and the second speed priority weight can be regarded as the initialized terrain priority weight and speed priority weight, which assume that the flatness and ruggedness of the current operation scene are the same. At this time, the flatness and ruggedness of the current operation scene can be determined in combination with the speed ratio, and then the first speed priority weight and the first terrain priority weight in the first scene information are determined.

[0054] Optionally, the product of the second terrain priority weight and the preset weight coefficient plus the product of the speed ratio and the second speed priority weight can be added to obtain the first speed priority weight, and the first terrain priority weight can be determined according to the first speed priority weight; wherein the preset weight coefficient is equal to 0.5. For example, the calculation expression of the first speed priority weight u1 is 0.5*w2+f*u2, w2 is the second terrain priority weight, u2 is the second speed priority weight, u2=1-w2, and f is the ratio of the preset flight speed to the preset maximum speed. Since the second speed priority weight and the second terrain priority weight are equal and the sum is equal to one, the second terrain priority weight w2=u2=0.5. Substituting the second terrain priority weight and the speed ratio into the above calculation expression can obtain the first speed priority weight u1, and subtracting the first speed priority weight u1 from 1 to obtain the first terrain priority weight w1. It can be understood that in the calculation expression 0.5*w2+f*u2, 0.5 and f are the weight coefficients of the second terrain priority weight w2 and the second speed priority weight u2, respectively. In the case of unknown terrain, the weight coefficient of the second terrain priority weight is 0.5, and the weight coefficient of the second speed priority weight is the speed ratio. When the preset flight speed is greater than half of the maximum speed, the weight coefficient of the second speed priority weight is greater than 0.5, and the first speed priority weight is also greater than 0.5, that is, the terrain of this flight sortie is highly compatible with the speed priority control strategy, matching the preset larger flight speed setting. When the preset flight speed is less than half of the maximum speed, the weight coefficient of the second speed priority weight is less than 0.5, the first speed priority weight is also less than 0.5, and the first terrain priority weight is greater than 0.5, that is, the terrain of this flight sortie is highly compatible with the terrain priority control strategy, matching the preset smaller flight speed setting. In this embodiment, the terrain type of the operation scene is characterized by the first speed priority weight and the first terrain priority weight, so as to determine the first speed priority weight and the first terrain priority weight that are adapted to the preset flight speed according to the preset second speed priority weight and the second speed priority weight, so as to improve the accuracy of the estimation of the terrain type, thereby reducing the adjustment frequency of the subsequent real-time control strategy and the flight trajectory, which is conducive to improving the control stability of the UAV.

[0055] Of course, the drone can also determine the first scene information based on the third scene information and the operation task information of the last flight sortie. For example, the drone can determine the first scene information based on the third scene information of the last flight sortie and the preset flight speed in the operation task information, or determine the first scene information based on the third scene information of the last flight sortie and the operation area parameter in the operation task information, or determine the first scene information based on the third scene information of the last flight sortie and the preset flight speed and operation area parameter in the operation task information.

[0056] For example, when the current flight is not the first flight, the third terrain priority weight and the third speed priority weight in the third scene information of the previous flight are obtained; the preset flight speed and the preset maximum speed in the operation task information are obtained, and the speed ratio of the preset flight speed and the preset maximum speed is determined; the first terrain priority weight and the first speed priority weight are determined according to the speed ratio and the third terrain priority weight and the third speed priority weight. Among them, the sum of the third terrain priority weight and the third speed priority weight is equal to 1. Exemplarily, when the speed ratio of the preset flight speed to the preset maximum speed is larger, it indicates that the terrain of the operation scene of this flight is flatter, and when the speed ratio is smaller, it indicates that the terrain of the operation scene of this flight is more rugged. The third terrain priority weight and the third speed priority weight represent the flatness and ruggedness of the operation scene of the previous flight, which also affects the terrain type of the operation scene of this flight. At this time, the flatness and ruggedness of the current operation scene can be determined in combination with the speed ratio, and then the first speed priority weight and the first terrain priority weight in the first scene information are determined.

[0057] Optionally, when the third terrain priority weight is greater than the third speed priority weight, the product of the third speed priority weight and the speed ratio is determined as the first speed priority weight, and the first terrain priority weight is determined according to the first speed priority weight; when the third terrain priority weight is less than the third speed priority weight, the product of the third speed priority weight and the speed ratio is added to the third terrain priority weight to obtain the first speed priority weight, and the first terrain priority weight is determined according to the first speed priority weight. Exemplarily, when the third terrain priority weight is greater than the third speed priority weight, the calculation expression of the first speed priority weight u1 is u1=f*u3+0*w3, u3 is the third speed priority weight, and w3 is the third terrain priority weight. When the third terrain priority weight is less than the third speed priority weight, the calculation expression of the first speed priority weight u1 is w1=w3+u3*f. After that, the first terrain priority weight w1 is obtained by subtracting the first speed priority weight u1 from 1. It can be understood that in 0*w3+(1-w3)*f, 0 and f are weight coefficients of the third terrain priority weight w3 and the third speed priority weight u3, respectively. When the third speed priority weight is less than the third terrain priority weight, the third speed priority weight is less than 0.5. Since the speed ratio is less than 1, no matter how large the preset flight speed is, the first speed priority weight will be less than 0.5, that is, the terrain of this flight has a higher degree of adaptability to the terrain priority control strategy, matching the terrain type of the previous flight. When the preset flight speed is less than half of the maximum speed, the first speed priority weight is less than the third speed priority weight, that is, compared with the previous flight, the terrain of the operating scene of this flight has a higher degree of adaptability to the terrain priority control strategy. In the calculation expression w1=w3+(1-w3)*f, 1 and f are the weight coefficients of the third terrain priority weight w3 and the third speed priority weight u3, respectively. When the third speed priority weight is greater than the third terrain priority weight, the third terrain priority weight is less than 0.5, and the first speed priority weight is determined by the preset flight speed and the third speed priority weight, that is, when the third speed priority weight is larger or the preset flight speed is larger, the first speed priority weight is greater than 0.5, that is, the terrain of this flight is more compatible with the speed priority control strategy, matching the terrain type of the previous flight or the setting of a larger preset flight speed. When the third speed priority weight is smaller and the preset flight speed is smaller, the first speed priority weight is less than 0.5, that is, the terrain of this flight is more compatible with the terrain priority control strategy, matching the setting of a smaller preset flight speed.This embodiment characterizes the terrain type of the operating scene through the first speed priority weight and the first terrain priority weight, so as to determine the first speed priority weight and the first terrain priority weight that are adapted to the preset flight speed and the third speed priority weight and the third terrain priority weight of the previous flight, thereby improving the accuracy of terrain type estimation, thereby reducing the frequency of subsequent real-time control strategies and flight trajectory adjustments, and is conducive to improving the control stability of the UAV.

[0058] This embodiment determines the terrain type of the current flight by combining the flight speed and the terrain type of the previous flight to improve the accuracy of terrain type estimation, thereby reducing the frequency of subsequent real-time control strategies and flight trajectory adjustments, which is beneficial to improving the control stability of the UAV.

[0059] After determining that the first scene information is the first scene or the second scene, the corresponding real-time control strategy can be determined as the speed priority control strategy according to the first scene; or, the corresponding real-time control strategy can be determined as the terrain priority control strategy according to the second scene. That is, when the operating scene is flat terrain, the speed priority control strategy is preliminarily determined as the real-time control strategy. When the terrain safety factor is high, the flight speed of the UAV is prioritized to improve the flight efficiency of the UAV. When the operating scene is rugged terrain, the terrain priority control strategy is preliminarily determined as the real-time control strategy. When the terrain safety factor is low, the UAV is prioritized to accurately track terrain changes and improve the flight safety of the UAV.

[0060] After determining the first terrain priority weight and the first speed priority weight, the first terrain priority weight and the first speed priority weight can be compared, and the real-time control strategy can be determined according to the comparison result. Wherein, when the first speed priority weight is greater than the first terrain priority weight, the real-time control strategy is determined to be the speed priority control strategy; when the first speed priority weight is less than the first terrain priority weight, the real-time control strategy is determined to be the terrain priority control strategy. Exemplarily, when the first speed priority weight is greater than the first terrain priority weight, it indicates that the flatness of the terrain of the operation scene is greater than the ruggedness of the terrain, and its adaptability to the speed priority control strategy is higher, so the speed priority control strategy is preliminarily determined to be the real-time control strategy. When the first speed priority weight is less than the first terrain priority weight, it indicates that the flatness of the terrain of the operation scene is less than the ruggedness of the terrain, and its adaptability to the terrain priority control strategy is higher, so the speed priority control strategy is preliminarily determined to be the real-time control strategy. This embodiment determines a real-time control strategy that is more suitable for the terrain of the operation scene by comparing the first speed priority weight and the first terrain priority weight, which is conducive to reducing the adjustment frequency of the subsequent real-time control strategy and flight trajectory, and improving the control stability of the drone.

[0061] It should be noted that although the terrain types of the operation scene can be roughly divided into flat terrain and rugged terrain, in fact, some areas are transitional terrains between flat terrain and rugged terrain, and the ruggedness of the transitional terrain is less than that of the rugged terrain, and the flatness is less than that of the flat terrain. For the transitional terrain, both the speed priority control strategy and the terrain priority control strategy can be adopted, but the adaptability is not high. In this regard, for the transitional terrain, this embodiment proposes a combined control strategy to control the UAV to perform efficient terrain-imitating flight in the transitional terrain through the combined control strategy, so as to ensure the flight efficiency and flight safety of the UAV. Among them, the combined control strategy can be understood as a control strategy that integrates the speed priority control strategy and the terrain priority control strategy.

[0062] Optionally, when the first speed priority weight is greater than the first terrain priority weight and the difference between the two is greater than a preset difference threshold, the real-time control strategy is determined to be a speed priority control strategy; when the first terrain priority weight is greater than the first speed priority weight and the difference between the two is greater than a preset difference threshold, the real-time control strategy is determined to be a terrain priority control strategy; when the difference between the first terrain priority weight and the first speed priority weight is less than a preset difference threshold, the real-time control strategy is determined to be a combined control strategy. Exemplarily, if the first speed priority weight is greater than the first terrain priority weight, and the difference between the first speed priority weight and the first terrain priority weight is greater than a preset difference threshold, it indicates that the flatness of the terrain of the operation scene is much greater than the ruggedness of the terrain, so the operation scene can be determined to be a flat terrain, and the real-time control strategy is determined to be a speed priority control strategy. If the first speed priority weight is less than the first terrain priority weight, and the difference between the first terrain priority weight and the first speed priority weight is greater than the preset difference threshold, it indicates that the ruggedness of the terrain of the operation scene is much greater than the flatness of the terrain, so the operation scene can be determined to be a rugged terrain, and the real-time control strategy is determined to be a terrain priority control strategy. If the absolute value of the difference between the first terrain priority weight and the first speed priority weight is less than the preset difference threshold, it indicates that the ruggedness of the terrain of the operation scene is not much different from the flatness of the terrain. Therefore, the operation scene can be determined as a transitional terrain, and the real-time control strategy is determined to be a combined control strategy. This embodiment determines a real-time control strategy adapted to flat terrain, rugged terrain, or transitional terrain by comparing the first speed priority weight and the first terrain priority weight and comparing the difference between the two with the preset difference threshold, which is conducive to reducing the adjustment frequency of subsequent real-time control strategies and flight trajectories and improving the control stability of the drone.

[0063] S120, obtaining terrain information collected by the perception sensor in real time, and planning the flight trajectory according to the terrain information and the real-time control strategy.

[0064] Among them, the perception sensor is a sensor installed on the UAV for collecting terrain information of the operation scene, which can be a camera or radar, etc. When performing a flight, the UAV can control the perception sensor to collect terrain information of the operation scene in real time, plan a terrain-simulating flight trajectory according to the real-time control strategy and real-time terrain information, and fly in the operation scene based on the terrain-simulating flight trajectory.

[0065] When the real-time control strategy is a speed priority control strategy, the flight speed of the UAV can be given priority, that is, a straight line trajectory is first planned according to the preset flight speed, and then the straight line trajectory is adjusted to a terrain-mimicking flight trajectory according to the terrain information, so as to ensure the flight efficiency while taking into account the flight safety of the UAV, and realize the efficient and safe flight of the UAV in the operation scenario of flat terrain. For example, Figure 2 : is a flow chart of planning a flight trajectory based on a speed priority control strategy and terrain information provided by an embodiment of the present application. Figure 2 As shown, the steps of planning the flight trajectory based on the speed priority control strategy and terrain information specifically include S1201-S1202:

[0066] S1201, determining a trajectory starting point and a trajectory end point, and planning a horizontal straight line trajectory according to the trajectory starting point and the trajectory end point and a preset flight speed, wherein the horizontal straight line trajectory includes a plurality of first control points, and the first control point is used to control the UAV to arrive at a first planned arrival time corresponding to the first control point.

[0067] Exemplarily, the flight starting point of the UAV is determined as the trajectory starting point of the flight trajectory, and the trajectory end point is determined based on the trajectory starting point, the preset trajectory length, and the preset operating route. For example, due to the limited perception range of the perception sensor, the UAV cannot obtain terrain information of the operating scene beyond the perception range. Therefore, the trajectory length of the flight trajectory that can be planned in real time is limited. The preset trajectory length can be understood as the trajectory length set based on the perception range of the perception sensor, and the flight trajectory planned with the preset trajectory length will not exceed the perception range of the perception sensor. The preset operating route is the route that the UAV navigates when performing a flight sortie, that is, the UAV will fly in the operating scene along the preset operating route. The flight starting point can be determined as the trajectory starting point, and the waypoint on the operating route that is separated from the trajectory starting point by the preset trajectory length can be used as the trajectory end point, or the endpoint on the operating route that is less than the preset trajectory length from the trajectory starting point can be used as the trajectory end point. Exemplarily, Figure 3 Schematic diagram of the operation route provided in the embodiment of the present application. Figure 3As shown, an operation route 10 is planned in the operation scene 12. When the drone takes off at waypoint A of the operation route 10, waypoint A is determined as the starting point of the trajectory. If waypoint B is within the preset trajectory length of waypoint A, waypoint B can be used as the end point of the trajectory. Waypoint C is the end point of the straight line segment of the operation waypoint 10. If its distance from waypoint A is less than the preset trajectory length, waypoint C can also be used as the end point of the straight line trajectory. It should be noted that Figure 3 It can be seen from the shown content that the horizontal straight line trajectory and the horizontal straight line path are not the straight line trajectory and the straight line path in three-dimensional space, but the straight line trajectory and the straight line path in the horizontal direction, that is, the straight line trajectory and the straight line path are in a straight line shape when projected into a vertical plane.

[0068] Afterwards, the horizontal flight speed is assigned to the horizontal straight path between the trajectory starting point and the trajectory end point by presetting the flight speed, so as to calculate the planned arrival time of the UAV at each waypoint on the horizontal straight path, and the horizontal straight trajectory between the trajectory starting point and the trajectory end point is planned according to the planned arrival time of each waypoint and the first control point on the horizontal straight trajectory is obtained by sampling in each waypoint.

[0069] In addition, multiple first control points can be sampled on the horizontal straight path between the starting point and the end point of the trajectory, and the multiple first control points divide the horizontal straight path into multiple first path segments; a speed is assigned to each first path segment according to a preset flight speed to obtain an assigned speed corresponding to each first path segment; and the first planned arrival time of the UAV flying to the first control point corresponding to the first path segment at the assigned speed corresponding to the first path segment is determined. Exemplarily, multiple first control points can be collected on the horizontal straight path between the starting point and the end point of the trajectory by a preset equidistant sampling rule. The horizontal speed of the UAV navigating the first path segment between two adjacent first control points is assigned according to the preset flight speed, and the planned arrival time of the UAV arriving at each first control point is determined. A smooth horizontal straight trajectory is generated by fitting based on multiple first control points and the corresponding first planned arrival times. Exemplarily, Figure 4 and Figure 5 Schematic diagrams of horizontal straight line paths and horizontal straight line trajectories provided in the embodiments of the present application. Figure 4 and Figure 5 As shown, the horizontal straight path 11 is a straight route segment between waypoint A and waypoint C, and below the horizontal straight path 11 is the operation scene 12. The position of the horizontal straight track 13 is the same as that of the straight path 11, that is, the operation scene 12 below it is also the same as the operation scene 12 below the straight path 11. The horizontal straight track 13 includes a plurality of first control points 14, each of which corresponds to a first planned arrival time of a UAV flying to the first control point.

[0070] S1202: Adjust the heights of multiple first control points according to terrain information, and generate a flight trajectory.

[0071] For example, the first terrain height at each first control point can be determined according to the terrain information, and the height of the corresponding first control point can be adjusted according to the first terrain height, wherein the first terrain height is the terrain height at a position point in the operation scene having the same horizontal coordinate as the first control point. Figure 6 Schematic diagram of the adjustment trend of the first control point provided in the embodiment of the present application. Figure 6 As shown, when the height difference between the height of the first control point and the height of the first terrain at the corresponding position is less than the safe height, the height of the first control point is adjusted up so that the difference between the height of the first control point and the height of the corresponding first terrain is maintained at the safe height. When the height difference between the height of the first control point and the height of the first terrain at the corresponding position is greater than the safe height, the height of the first control point is adjusted down so that the difference between the height of the first control point and the height of the corresponding first terrain is maintained at the safe height. It should be noted that the height adjustment range of the first control point is limited, otherwise the drone cannot fly to the first control point at the corresponding arrival time. Therefore, after determining the height difference between the height of the first control point and the height of the first terrain at the corresponding position, if the difference between the height difference and the safe height exceeds the height adjustment range, the height of the first control point can be adjusted according to the height adjustment range to ensure that the drone can fly to the first control point at the arrival time, that is, give priority to the flight speed of the drone. In addition, when the difference between the height difference and the safe height exceeds the height adjustment range, it can be determined that the actual terrain type of the operation scene does not match the estimated terrain type, and then adjust the real-time control strategy, that is, switch the speed priority control strategy to the combined control strategy or the terrain priority control strategy to ensure the flight safety of the drone.

[0072] Figure 7 Schematic diagram of the flight trajectory provided by the embodiment of the present application. Figure 7 As shown, the adjusted first control point 14 maintains a safe height with the working scene at the corresponding position, and a smooth flight trajectory 15 is fitted according to the multiple first control points 14 with adjusted heights and the corresponding arrival times, and the flight trajectory 15 adapts to the terrain of the working scene 12 below.

[0073] In order to improve the terrain simulation accuracy of the flight trajectory, a first height adjustment operation can be performed on multiple first control points of the horizontal straight line trajectory according to the terrain information to obtain a first trajectory; the first trajectory is sampled, and a second height adjustment operation is performed on the sampled trajectory points, and a flight trajectory is generated. Exemplarily, a smooth first trajectory is fitted based on the first control point after the height adjustment and the corresponding arrival time, the first trajectory is sampled to obtain a new first control point and a corresponding arrival time, the first terrain height at the new first control point is determined according to the terrain information, the height of the new first control point is adjusted according to the first terrain height, and a smooth first trajectory is refitted according to the new first control point after the height adjustment and the corresponding arrival time. Repeat the above sampling and height adjustment process for the new first trajectory to continuously iterate a new first trajectory. Since each iteration adjusts the height of the corresponding first control point according to the terrain information, a first trajectory that is highly adapted to the terrain of the operation scene can be generated after multiple iterations. When the number of iterations reaches the upper limit, the iteration is stopped and the latest fitted first trajectory is used as the flight trajectory. This embodiment continuously improves the adaptability of the first trajectory to the terrain of the operation scene by performing iterative operations of repeated sampling and height adjustment on the first trajectory, thereby improving the planning accuracy of the flight trajectory and achieving precise control of the UAV.

[0074] In this embodiment, when the real-time control strategy is a speed priority control strategy, the flight speed can be allocated to the horizontal straight line path between the trajectory starting point and the trajectory end point according to the preset flight speed, so as to determine a plurality of first control points for controlling the UAV to reach the first planned arrival time at the corresponding position, so as to prioritize the flight speed of the UAV through the first control point, and then adjust the height of the first control point according to the terrain information to generate a terrain-simulating flight trajectory, so as to ensure the flight efficiency while taking into account the flight safety of the UAV, and realize the efficient and safe flight of the UAV in the operation scenario of flat terrain.

[0075] When the real-time control strategy is the terrain priority control strategy, the terrain of the operation scene can be given priority, that is, the terrain-imitating path is first planned according to the terrain information, and then the terrain-imitating flight trajectory is generated according to the terrain-imitating path and the preset flight speed, so as to ensure the flight safety while taking into account the flight efficiency of the UAV, so as to achieve efficient and safe flight of the UAV in the operation scene of rough terrain. For example, Figure 8 1 is a flow chart of planning a flight trajectory based on a terrain priority control strategy and terrain information provided by an embodiment of the present application. Figure 8 As shown, the step of planning the flight trajectory based on the terrain priority control strategy and terrain information specifically includes S1203-S1204:

[0076] S1203: determining a starting point and an end point of the trajectory, and planning a first terrain-imitating path according to the starting point and the end point of the trajectory and terrain information, wherein the first terrain-imitating path includes a plurality of second control points, and the second control points are used to control the flight altitude of the UAV corresponding to the second control points, and the plurality of second control points divide the first terrain-imitating path into a plurality of second path segments.

[0077] Exemplarily, the flight starting point of the drone is determined as the trajectory starting point of the flight trajectory, and the trajectory end point is determined according to the trajectory starting point, the preset trajectory length, and the preset operation route. For details, please refer to the step of determining the trajectory starting point and the trajectory end point in step S1201.

[0078] Afterwards, a horizontal straight line path between the trajectory start point and the trajectory end point is adjusted according to the terrain information to obtain a first terrain-simulating path adapted to the terrain of the operation scene, and the first terrain-simulating path is sampled to obtain a plurality of second control points.

[0079] Optionally, multiple third control points can be sampled on the horizontal straight path between the starting point and the end point of the trajectory, and the heights of the multiple third control points can be adjusted according to the terrain information to obtain multiple third control points with adjusted heights; the multiple third control points with adjusted heights can be thinned out to obtain multiple second control points. After that, the multiple second control points are fitted to obtain a smooth first terrain-simulating path. Exemplarily, multiple third control points are collected on the horizontal straight path between the starting point and the end point of the trajectory by using an equidistant sampling rule. The second terrain height at each third control point is determined according to the terrain information, and the height of the corresponding third control point is adjusted according to the second terrain height. The second terrain height is the terrain height at a position in the operating scene that has the same horizontal coordinate as the third control point. Since the real-time control strategy is a terrain priority control strategy, there is no limit on the adjustable height range of the third control point, that is, the terrain of the operating scene is given priority. Exemplarily, Fig. 9 is a schematic diagram of the third control point before adjusting the height provided in the embodiment of the present application, Fig.10 Schematic diagram of the third control point after adjusting the height provided in the embodiment of the present application. Fig. 9 and Fig.10 As shown, the horizontal straight path 13 is a straight route segment between waypoint A and waypoint C, and the horizontal straight path 13 is the work scene 12. A plurality of third control points 16 are sampled on the straight path 13, and the height of the third control point 16 is adjusted according to the terrain height at the third control point 16 in the terrain information, so that the plurality of third control points 16 after the height adjustment can be connected to form a terrain-simulating path 17 adapted to the terrain of the work scene 12.

[0080] Afterwards, a thinning algorithm such as a distance thinning algorithm or an angle thinning algorithm is used to thin out the multiple third control points after adjusting the height, so as to eliminate the third control points that do not have a significant impact on the shape of the terrain-simulating path, and the remaining third control points are used as second control points. For example, the angle formed by any three consecutive third control points can be determined. When the angle is greater than a preset angle threshold, it indicates that the connection formed by the corresponding three consecutive third control points is approximately a straight line, and the middle third control point has no significant impact on the shape of the terrain-simulating path. Therefore, the middle third control point can be eliminated. Among them, the order of the third control points is their order on the straight path, and the third control point used to calculate the angle is the third control point after adjusting the height. According to the order of each third control point on the straight path, the three consecutive control points are divided into a group. When the angle of the group is greater than the preset angle threshold, the third control point in the middle of the group is eliminated. Exemplarily, Fig.11 is a schematic diagram of a second control point provided in an embodiment of the present application. Fig.10 and Fig.11 After thinning out the third control points after adjusting the height, some of the third control points that do not have much influence on the shape of the terrain-imitating path 17 can be eliminated to obtain the second control points 18. The second control points 18 can be connected to form a terrain-imitating path 19. Compared with the terrain-imitating path 17, the terrain-imitating path 19 is simpler, so that the UAV does not need to frequently adjust the vertical direction during flight, which is conducive to maintaining the speed in the horizontal direction, thereby improving the flight efficiency of the UAV. This embodiment thins out the third control points after adjusting the height to reduce the waypoints used to plan the flight trajectory, simplify the route complexity of the flight trajectory, and help improve the flight efficiency of the UAV.

[0081] S1204. Allocate a speed to each second path segment according to a preset flight speed, obtain an allocated speed corresponding to each second path segment, and determine a second planned arrival time for the UAV to arrive at a second control point corresponding to the second path segment at the allocated speed corresponding to the second path segment.

[0082] Exemplarily, a horizontal speed is allocated to a second path segment between two adjacent second control points according to a preset flight speed, and then the second planned arrival time of the UAV at each second control point is determined according to the horizontal speed and path length corresponding to the second path segment.

[0083] S1205: Generate a flight trajectory according to the plurality of second control points and the corresponding second planned arrival times.

[0084] Exemplarily, a smooth flight trajectory is fitted through multiple second control points and corresponding arrival times. Fig.12 Schematic diagram of the flight trajectory provided by the embodiment of the present application. Fig.12As shown, the flight trajectory 20 fitted based on the second control point 18 is adapted to the terrain of the working scene 12 below, and the route of the flight trajectory 20 is simple, which ensures the flight safety of the UAV and takes into account the flight efficiency.

[0085] In this embodiment, when the real-time control strategy is the terrain priority control strategy, the height of each waypoint can be adjusted for the horizontal straight path between the trajectory starting point and the trajectory end point according to the terrain information, so as to determine multiple second control points for controlling the UAV to reach the flight height at the corresponding position, so as to prioritize the flight safety of the UAV through the second control points, and then determine the arrival time of the UAV at the second control point by presetting the flight speed to generate a terrain-simulating flight trajectory, so as to ensure the flight safety while taking into account the flight efficiency of the UAV, and realize efficient and safe flight of the UAV in the operation scenario of rugged terrain.

[0086] When the real-time control strategy is a combined control strategy, the terrain-simulating path can be planned first, and then the terrain-simulating trajectory can be generated according to the terrain-simulating path and the preset flight speed. Finally, the height of the sampling points in the terrain-simulating trajectory is adjusted iteratively to obtain a flight trajectory that better fits the terrain, so as to take into account the flight efficiency and flight safety of the UAV at the same time, and realize the efficient and safe flight of the UAV in the operation scenario of transitional terrain. For example, Fig.13 This is a flow chart of planning a flight trajectory based on combining control strategy and terrain information provided by an embodiment of the present application. Fig.13 As shown, the steps of planning the flight trajectory based on the terrain priority control strategy and terrain information specifically include S1206-S1208:

[0087] S1205: Determine a trajectory start point and a trajectory end point, and plan a second terrain-imitating path according to the trajectory start point and the trajectory end point and terrain information. The second terrain-imitating path includes a plurality of fourth control points. The fourth control points are used to control the flight altitude of the UAV at the corresponding fourth control points.

[0088] Exemplarily, the flight starting point of the drone is determined as the trajectory starting point of the flight trajectory, and the trajectory end point is determined according to the trajectory starting point, the preset trajectory length, and the preset operation route. For details, please refer to the step of determining the trajectory starting point and the trajectory end point in step S1201.

[0089] Afterwards, multiple fourth control points are collected on the horizontal straight path between the path starting point and the path starting point by using the equidistant sampling rule. The third terrain height at each fourth control point is determined according to the terrain information, and the height of the corresponding fourth control point is adjusted according to the third terrain height. The third terrain height is the terrain height at the position point in the operation scene with the same horizontal coordinate as the fourth control point.

[0090] S1206, performing thinning processing on the plurality of fourth control points to obtain a plurality of fifth control points, determining a third planned arrival time for the UAV to reach the fifth control point according to a preset flight speed, and generating a second trajectory according to the fifth control point and the corresponding arrival time.

[0091] Exemplarily, the plurality of fourth control points after the height adjustment are thinned out by a thinning algorithm such as a distance thinning algorithm or an angle thinning algorithm to eliminate fourth control points that have no significant impact on the shape of the terrain-simulating path, and the remaining fourth control points are used as fifth control points.

[0092] Optionally, the angle formed by any three consecutive fourth control points can be determined; when the angle is greater than a preset angle threshold, the fourth control point among any three consecutive fourth control points is removed, and the remaining fourth control point is determined as the fifth control point.

[0093] Among them, the preset angle threshold is positively correlated with the first terrain priority weight. The order of the fourth control points is their order on the straight path, and the fourth control point used to calculate the angle is the fourth control point after the height is adjusted. According to the order of each fourth control point on the straight path, four consecutive control points are divided into a group. When the angle of the group is greater than the preset angle threshold, the fourth control point in the middle of the group is removed. This embodiment performs a thinning process on the fourth control point after the height is adjusted to reduce the waypoints used to plan the second trajectory, simplify the route complexity of the second trajectory, and then reduce the route complexity of the subsequently generated flight trajectory, which is beneficial to improving the flight efficiency of the UAV.

[0094] It should be noted that when the first terrain priority weight is larger, it indicates that the roughness of the transition terrain is greater. In order to ensure that the terrain-imitating path can track the terrain, the corresponding preset angle threshold is set to be larger to avoid eliminating the important fourth control point. When the first terrain priority weight is smaller, it indicates that the roughness of the transition terrain is smaller. In order to simplify the route of the terrain-imitating path, the corresponding preset angle threshold is set to be smaller to avoid retaining the insignificant fourth control point. In addition, the preset angle threshold used by the thinning algorithm in the combined control strategy will be smaller than the preset angle threshold used by the thinning algorithm in the terrain priority control strategy, that is, the flight trajectory planned by the terrain priority control strategy will be more in line with the terrain of the operation scene than the combined control strategy, and it also meets the requirement of the terrain priority control strategy to give priority to the terrain.

[0095] Afterwards, a horizontal speed is assigned to the path between two adjacent fifth control points according to the preset flight speed, and then the third planned arrival time of the UAV at the fifth control point is determined according to the horizontal speed and the path length. A smooth second trajectory is fitted through multiple fifth control points and the corresponding third planned arrival times.

[0096] S1207, sampling the second trajectory to obtain multiple sixth control points and the fourth planned arrival time of the UAV to reach the sixth control point, adjusting the heights of the multiple sixth control points according to the terrain information, and generating a flight trajectory according to the sixth control points with adjusted heights and the corresponding fourth planned arrival time.

[0097] Exemplarily, the second trajectory is sampled to obtain multiple sixth control points and corresponding arrival times, the fourth terrain height at the sixth control point is determined according to the terrain information, the height of the sixth control point is adjusted according to the fourth terrain height, and a smooth second trajectory is refitted according to the sixth control point after the height adjustment and the corresponding arrival time. The above-mentioned adoption and height adjustment process is repeated for the new second trajectory to continuously iterate a new second trajectory. Since the height of the corresponding sixth control point is adjusted according to the terrain information in each iteration, a second trajectory that is highly adapted to the terrain of the operating scene can be generated after multiple iterations. When the number of iterations reaches the upper limit, the iteration is stopped and the second trajectory obtained by the latest fitting is used as the flight trajectory.

[0098] S130: When the UAV is flying based on the flight trajectory, second scene information is determined according to the terrain information, and the real-time control strategy is adjusted according to the second scene information.

[0099] Exemplarily, the drone flies based on the flight trajectory planned in real time. During the flight, the drone's flight speed and flight direction are adjusted according to the arrival time and position of each control point in the flight trajectory, so as to ensure that the drone flies to the control point at the arrival time and maintains a safe altitude with the operation scene, so as to achieve safe and efficient flight of the drone in various terrains. During the flight, the perception sensor continuously collects terrain information, and the drone continuously updates the flight trajectory based on the terrain information. At the same time, the drone can also determine the second scene information in real time based on the terrain information, compare the real-time second scene information with the first scene information or the second scene information at the previous moment, and determine that the current real-time control strategy is not suitable for the terrain type of the operation scene when the gap is large, so as to adjust the real-time control strategy. Among them, the second scene information is information that characterizes the real-time terrain type of the operation scene.

[0100] Optionally, the second scene information may be determined based on the terrain information collected historically and in real time by the perception sensor. Exemplarily, a topographic map of the operation scene may be drawn based on the terrain information collected historically and in real time, and the height variance may be calculated based on the terrain heights of each location point in the topographic map. When the height variance is greater than a preset variance threshold, the second scene information is determined to be rugged terrain, and when the height variance is less than a preset variance threshold, the second scene information is determined to be flat terrain. Alternatively, the fourth terrain priority weight and the fourth speed priority weight in the second scene information may be determined based on the size and difference between the height variance and the preset variance threshold.

[0101] It should be noted that during the actual flight of the drone, the actual flight speed of the drone has a greater impact on the collection results of the perception sensor. When flying at high speed, more attention should be paid to the front information, while when flying at low speed, the terrain integrity can be taken into account. Therefore, when the flight speed of the drone is greater than the preset speed threshold, the perception sensor collects the terrain information in front of and below the drone; when the flight speed of the drone is less than the preset speed threshold, the perception sensor collects the terrain information in front of, above and below the drone. Among them, if the actual flight speed of the drone is greater than the preset speed threshold, it means that the drone is flying at high speed, then the perception sensor is controlled to collect the terrain information in front and below, so as to avoid collecting too much invalid data and save the energy consumption of the perception sensor. If the actual flight speed of the drone is less than the preset speed threshold, it means that the drone is flying at low speed, then the perception sensor is controlled to collect the terrain information in front, below and above, so as to collect detailed terrain information to plan a high-precision flight trajectory and improve the control accuracy of the drone.

[0102] After determining the fourth terrain priority weight and the fourth speed priority weight based on the terrain information, the fourth terrain priority weight and the fourth speed priority weight and the difference between the two and the preset difference threshold can be compared, and the real-time control strategy for current terrain adaptation can be determined according to the comparison result. When the real-time control strategy for current terrain adaptation is different from the real-time control strategy actually adopted by the drone, the real-time control strategy adopted by the drone can be adjusted to the real-time control strategy for current terrain adaptation. For example, if the real-time control strategy for current terrain adaptation is the speed priority control strategy and the real-time control strategy actually adopted by the drone is the terrain priority control strategy, the real-time control strategy adopted by the drone is adjusted to the speed priority control strategy. In this embodiment, the real-time second scene information is determined based on the terrain information collected in real time by the perception sensor during the flight process, so as to adaptively adjust the real-time control strategy of the drone according to the second scene information to adapt to the terrain type of the current operation scene, so as to plan the flight trajectory adapted to the second scene information according to the adjusted real-time control strategy and the real-time terrain information, so as to ensure that the flight trajectory of the drone can accurately track the terrain of the scene and take into account the flight speed, so as to realize the autonomous flight of the drone in any terrain scene, without the user having to worry about the terrain type and the adaptive terrain imitation mode of the scene where the drone is located.

[0103] S140: re-plan the flight trajectory according to the adjusted real-time control strategy and terrain information.

[0104] Exemplarily, the step of re-planning the flight trajectory is similar to the step of planning the flight trajectory in S120, but the starting point of the flight trajectory is the real-time posture of the UAV, and the process of planning the flight trajectory in S120 can be referred to, which will not be repeated here. After re-planning the flight trajectory, the UAV can be controlled to fly based on the re-planned flight trajectory.

[0105] In one embodiment, the drone is provided with a scene prediction system, a real-time control system, and a scene adaptation system. The scene prediction system is used to obtain first scene information before the drone performs a flight sortie, and provide the first scene information to the real-time control system. The real-time control system is used to determine the real-time control strategy according to the first scene information, plan the flight trajectory according to the real-time control strategy and the terrain information collected by the perception sensor, and control the flight of the drone according to the flight trajectory. The scene adaptation system is used to determine whether the current terrain matches the real-time control strategy according to the terrain information, and notify the real-time control system to adjust the real-time control strategy when it does not match, and then re-plan the flight trajectory.

[0106] Fig.14 : is a system framework diagram of the drone provided in the embodiment of the present application. Fig.14 As shown, the scene prediction system can determine the first scene information according to the third scene information of the previous flight and / or the preset flight speed before the UAV takes off, and send the first scene information to the real-time control system. The real-time control system includes a speed priority control system and a terrain priority control system. When the real-time control system determines that the real-time control strategy is the speed priority control strategy based on the first scene information, the speed priority control system plans the flight trajectory according to the terrain information and the preset flight speed; when the real-time control system determines that the real-time control strategy is the terrain priority control strategy based on the first scene information, the terrain priority control system plans the flight trajectory according to the terrain information and the preset flight speed. Afterwards, the control amount of the UAV is determined according to the flight trajectory, and the control amount is sent to the controller, and the controller controls the UAV to fly along the flight trajectory according to the control amount. The real-time control system sends the real-time control strategy to the scene adaptive system, and the scene adaptive system determines the real-time second scene information according to the terrain information, determines the real-time control system adapted to the current terrain according to the second scene information, and notifies the real-time control system to adjust the real-time control strategy when the real-time control system adapted to the current terrain does not match the real-time control strategy adopted by the UAV.

[0107] Of course, the real-time control system can be divided not only into speed priority control system and terrain priority control system, but also into multi-level control system or stepless control system. Under the multi-level control system, the speed priority control system belongs to the first level, the terrain priority control system belongs to the first level, and the combined control system can be the first level or divided into multiple levels. Under the stepless control system, the stepless control system is the real-time control system, that is, the flight trajectory is planned directly according to the real-time control strategy and terrain information, without distinguishing the control systems corresponding to various real-time control strategies.

[0108] In summary, the full-scenario adaptive flight method provided by the embodiment of the present application preliminarily determines the real-time control strategy through the first scene information, and plans a flight trajectory adapted to the first scene information according to the real-time control strategy and the terrain information collected in real time by the perception sensor during the initial flight. During the flight, the real-time second scene information can be determined according to the terrain information, and the real-time control strategy is adaptively adjusted according to the second scene information, so as to plan a flight trajectory adapted to the second scene information according to the adjusted real-time control strategy and the real-time terrain information, ensuring that the flight trajectory of the drone can accurately track the terrain of the scene and take into account the flight speed, thereby improving the flight safety and efficiency of the drone. The real-time control strategy and flight trajectory can be adaptively adjusted during the entire flight process, realizing the autonomous flight of the drone in any terrain scene, without the user having to worry about the terrain type and the adaptive terrain imitation mode of the scene where the drone is located, solving the problem in the prior art that the user needs to judge the terrain characteristics and control the drone to switch the terrain imitation mode, greatly simplifying the user's operating difficulty, and avoiding safety hazards caused by misoperation.

[0109] Based on the above embodiments, Fig.15 This is a schematic diagram of the structure of a full-scenario adaptive flight device provided in an embodiment of the present application. Fig.15 The full-scenario adaptive flight device provided in this embodiment specifically includes: a strategy determination module 21, a trajectory planning module 22, a strategy adjustment module 23 and a trajectory adjustment module 24.

[0110] Wherein, the strategy determination module 21 is configured to determine a real-time control strategy according to the first scene information, and the real-time control strategy includes a speed priority control strategy and a terrain priority control strategy;

[0111] The trajectory planning module 22 is configured to obtain terrain information collected by the perception sensor in real time and plan the flight trajectory according to the terrain information and the real-time control strategy;

[0112] The strategy adjustment module 23 is configured to determine the second scene information according to the terrain information when the UAV is flying based on the flight trajectory, and adjust the real-time control strategy according to the second scene information;

[0113] The trajectory adjustment module 24 is configured to re-plan the flight trajectory according to the adjusted real-time control strategy and terrain information.

[0114] Based on the above embodiments, the full-scenario adaptive flight device includes a first scene determination module, and the first scene determination module includes: a first scene determination unit, configured to determine the first scene information according to the third scene information of the previous flight before determining the real-time control strategy according to the first scene information; or, a second scene determination unit, configured to determine the first scene information according to the operation task information; or, a third scene determination unit, configured to determine the first scene information according to the third scene information and the operation task information of the previous flight.

[0115] On the basis of the above embodiment, the first scene determination unit includes: a first scene determination subunit configured to determine the third scene information of the previous flight as the first scene information of the current flight.

[0116] On the basis of the above embodiment, the second scene determination unit includes: a second scene determination subunit, which is configured to obtain a preset flight speed in the operation task information when the current flight sortie is the first flight sortie, and if the preset flight speed is greater than the first speed threshold, the first scene information is determined to be the first scene; if the preset flight speed is not greater than the first speed threshold, the first scene information is determined to be the second scene; or, a third scene determination subunit, which is configured to obtain an operation area parameter in the operation task information when the current flight sortie is the first flight sortie, and if the operation area parameter is greater than the first area parameter threshold, the first scene information is determined to be the second scene; if the operation area parameter is not greater than the first area parameter threshold, the first scene information is determined to be the first scene.

[0117] On the basis of the above embodiment, the first scene information includes a first terrain priority weight and a first speed priority weight, and the sum of the first terrain priority weight and the first speed priority weight is equal to one; accordingly, the second scene determination unit includes: a first speed acquisition subunit, configured to obtain a preset flight speed and a preset maximum speed in the operation task information when this flight sortie is the first flight sortie; a first ratio determination subunit, configured to determine the speed ratio of the preset flight speed and the preset maximum speed; wherein the preset maximum speed is the maximum flight speed allowed for the drone, and the preset flight speed is the planned flight speed of the drone in this flight sortie; a fourth scene determination subunit, configured to determine the first terrain priority weight and the first speed priority weight according to the speed ratio and the preset second terrain priority weight and the second speed priority weight, the second terrain priority weight and the second speed priority weight are equal and the sum is equal to one.

[0118] Based on the above embodiment, the fourth scene determination subunit is specifically configured as: adding the product of the second terrain priority weight and the preset weight coefficient plus the product of the speed ratio and the second speed priority weight to obtain the first speed priority weight, and determining the first terrain priority weight according to the first speed priority weight; wherein the preset weight coefficient is equal to 0.5.

[0119] On the basis of the above embodiment, the first scene information includes a first terrain priority weight and a first speed priority weight; accordingly, the third scene determination unit includes: a weight acquisition subunit, configured to obtain the third terrain priority weight and the third speed priority weight in the third scene information of the previous flight; a second ratio determination subunit, configured to obtain the preset flight speed and the preset maximum speed in the operation task information, and determine the speed ratio between the preset flight speed and the preset maximum speed; a fifth scene determination subunit, configured to determine the first terrain priority weight and the first speed priority weight according to the speed ratio and the third terrain priority weight and the third speed priority weight.

[0120] On the basis of the above embodiments, the fifth scenario determination subunit is specifically configured to, when the third terrain priority weight is greater than the third speed priority weight, determine the product of the third speed priority weight and the speed ratio as the first speed priority weight, and determine the first terrain priority weight according to the first speed priority weight; when the third terrain priority weight is less than the third speed priority weight, add the product of the third speed priority weight and the speed ratio to the third terrain priority weight to obtain the first speed priority weight, and determine the first terrain priority weight according to the first speed priority weight.

[0121] Based on the above embodiment, the strategy determination module 21 includes: a first strategy determination unit, configured to determine that the corresponding real-time control strategy is a speed priority control strategy according to the first scenario; or, a second strategy determination unit, configured to determine that the corresponding real-time control strategy is a terrain priority control strategy according to the second scenario.

[0122] Based on the above embodiment, the first scene information includes a first terrain priority weight and a first speed priority weight; the strategy determination module 21 includes: a third strategy determination unit, configured to determine that the real-time control strategy is a speed priority control strategy when the first speed priority weight is greater than the first terrain priority weight; a fourth strategy determination unit, configured to determine that the real-time control strategy is a terrain priority control strategy when the first speed priority weight is less than the first terrain priority weight.

[0123] On the basis of the above embodiments, when the real-time control strategy is a speed priority control strategy, the trajectory planning module 22 includes: a straight line trajectory planning unit, configured to determine the trajectory starting point and the trajectory end point, and plan a horizontal straight line trajectory according to the trajectory starting point and the trajectory end point and a preset flight speed, the horizontal straight line trajectory including a plurality of first control points, and the first control point is used to control the UAV to arrive at the first planned arrival time of the corresponding first control point; a first flight trajectory planning unit, configured to adjust the height of the plurality of first control points according to the terrain information, and generate a flight trajectory.

[0124] Based on the above embodiments, the straight line trajectory planning unit includes: a first sampling subunit, configured to sample a plurality of first control points on a horizontal straight line path between a trajectory starting point and a trajectory end point, and the plurality of first control points divide the horizontal straight line path into a plurality of first path segments; a first speed allocation subunit, configured to allocate a speed to each first path segment according to a preset flight speed, and obtain an allocated speed corresponding to each first path segment; a first arrival time determination subunit, configured to determine a first planned arrival time when the UAV flies to a first control point corresponding to the first path segment at the allocated speed corresponding to the first path segment.

[0125] Based on the above embodiment, the first flight trajectory planning unit includes: a first trajectory generating subunit, configured to perform a first height adjustment operation on multiple first control points of the horizontal straight line trajectory according to terrain information to obtain a first trajectory; a first flight trajectory planning subunit, configured to sample the first trajectory, perform a second height adjustment operation on the sampled trajectory points, and generate a flight trajectory.

[0126] On the basis of the above embodiments, when the real-time control strategy is a terrain priority control strategy, the trajectory planning module 22 includes: a first terrain-imitating path planning unit, configured to determine a trajectory starting point and a trajectory end point, and plan a first terrain-imitating path according to the trajectory starting point and the trajectory end point and terrain information, the first terrain-imitating path including a plurality of second control points, the second control points being used to control the flight altitude of the UAV at the corresponding second control points, and the plurality of second control points dividing the first terrain-imitating path into a plurality of second path segments; a second speed allocating unit, configured to allocate a speed to each second path segment according to a preset flight speed, obtain an allocated speed corresponding to each second path segment, and determine a second planned arrival time when the UAV arrives at the second control point corresponding to the second path segment at the allocated speed corresponding to the second path segment; and a second flight trajectory planning unit, configured to generate a flight trajectory according to the plurality of second control points and the corresponding second planned arrival times.

[0127] On the basis of the above embodiment, the first terrain-imitating path planning unit includes: a second sampling subunit, configured to sample a plurality of third control points on a horizontal straight path between a trajectory start point and a trajectory end point, and adjust the heights of the plurality of third control points according to terrain information to obtain a plurality of third control points after the heights are adjusted; and a first thinning subunit, configured to thin out the plurality of third control points after the heights are adjusted to obtain a plurality of second control points.

[0128] Based on the above embodiment, the straight line trajectory planning unit or the first terrain-imitation path planning unit includes: a starting point determination subunit, which is configured to determine the flight starting point of the drone as the trajectory starting point, and determine the trajectory end point according to the trajectory starting point, the preset trajectory length and the preset operation route.

[0129] On the basis of the above embodiment, the real-time control strategy also includes a combined control strategy, and the first scene information includes a first terrain priority weight and a first speed priority weight; accordingly, the strategy determination module 21 includes: a fifth strategy determination unit, configured to determine that the real-time control strategy is a speed priority control strategy when the first speed priority weight is greater than the first terrain priority weight and the difference between the two is greater than a preset difference threshold; a sixth strategy determination unit, configured to determine that the real-time control strategy is a terrain priority control strategy when the first terrain priority weight is greater than the first speed priority weight and the difference between the two is greater than a preset difference threshold; a seventh strategy determination unit, configured to determine that the real-time control strategy is a combined control strategy when the difference between the first terrain priority weight and the first speed priority weight is less than a preset difference threshold.

[0130] On the basis of the above embodiment, when the real-time control strategy is a combined control strategy; the trajectory planning module 22 includes: a second terrain-imitating path planning unit, configured to determine the trajectory starting point and the trajectory end point, and plan a second terrain-imitating path according to the trajectory starting point and the trajectory end point and the terrain information, the second terrain-imitating path includes a plurality of fourth control points, and the fourth control point is used to control the flight height of the UAV at the corresponding fourth control point; the second trajectory planning unit is configured to perform a thinning process on the plurality of fourth control points to obtain a plurality of fifth control points, determine the third planned arrival time of the UAV reaching the fifth control point according to a preset flight speed, and generate a second trajectory according to the fifth control point and the corresponding arrival time; the third flight trajectory planning unit is configured to sample the second trajectory to obtain a plurality of sixth control points and the fourth planned arrival time of the UAV reaching the sixth control point, adjust the height of the plurality of sixth control points according to the terrain information, and generate a flight trajectory according to the sixth control points after the height adjustment and the corresponding fourth planned arrival time.

[0131] Based on the above embodiment, the second trajectory planning unit includes: an angle determination subunit, configured to determine the angle formed by any three consecutive fourth control points; a second thinning subunit, configured to eliminate the fourth control points in the middle of any three consecutive fourth control points when the angle is greater than a preset angle threshold, and determine the remaining fourth control points as fifth control points.

[0132] Based on the above embodiment, the full-scenario adaptive flight device includes a second scene determination module, which is configured to determine the second scene information based on the terrain information collected historically and in real time by the perception sensor; wherein, when the current flight speed of the UAV is greater than a preset speed threshold, the perception sensor collects the terrain information in front of and below the UAV; when the current flight speed of the UAV is less than the preset speed threshold, the perception sensor collects the terrain information in front of, above and below the UAV.

[0133] As mentioned above, the full-scenario adaptive flight device provided by the embodiment of the present application, the first scene information preliminarily determines the real-time control strategy, and in the initial flight, the flight trajectory adapted to the first scene information is planned according to the real-time control strategy and the terrain information collected in real time by the perception sensor, and the real-time second scene information can be determined according to the terrain information during the flight, and the real-time control strategy is adaptively adjusted according to the second scene information, so as to plan the flight trajectory adapted to the second scene information according to the adjusted real-time control strategy and the real-time terrain information, so as to ensure that the flight trajectory of the drone can accurately track the terrain of the scene and take into account the flight speed, thereby improving the flight safety and flight efficiency of the drone. The real-time control strategy and flight trajectory can be adaptively adjusted during the entire flight process, and the autonomous flight of the drone in any terrain scene is realized, without the user having to worry about the terrain type and the adaptive terrain imitation mode of the scene where the drone is located, which solves the problem in the prior art that the user needs to judge the terrain characteristics and control the drone to switch the terrain imitation mode, greatly simplifies the user's operation difficulty, and avoids safety hazards caused by misoperation.

[0134] The full-scenario adaptive flight device provided in the embodiment of the present application can be used to execute the full-scenario adaptive flight method provided in the above embodiment, and has corresponding functions and beneficial effects.

[0135] Fig.16 is a schematic diagram of the structure of a drone provided in an embodiment of the present application, with reference to Fig.16The UAV includes: a processor 31, a memory 32, a communication device 33, an input device 34 and an output device 35. The number of processors 31 in the full-scenario adaptive flight device can be one or more, and the number of memories 32 in the full-scenario adaptive flight device can be one or more. The processor 31, memory 32, communication device 33, input device 34 and output device 35 of the full-scenario adaptive flight device can be connected through a bus or other methods.

[0136] The memory 32, as a computer-readable storage medium, can be used to store software programs, computer executable programs and modules, such as program instructions / modules corresponding to the full-scenario adaptive flight method of any embodiment of the present application (for example, the strategy determination module 21, trajectory planning module 22, strategy adjustment module 23 and trajectory adjustment module 24 in the full-scenario adaptive flight device). The memory 32 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created according to the use of the device, etc. In addition, the memory 32 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some instances, the memory may further include a memory remotely arranged relative to the processor, and these remote memories may be connected to the device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network and a combination thereof.

[0137] The communication device 33 is used for data transmission.

[0138] The processor 31 executes various functional applications and data processing of the device by running the software programs, instructions and modules stored in the memory 32, thereby realizing the above-mentioned full-scenario adaptive flight method.

[0139] The input device 34 may be used to receive input digital or character information and generate key signal input related to user settings and function control of the device. The output device 35 may include a display device such as a display screen.

[0140] The drone provided above can be used to execute the full-scenario adaptive flight method provided in the above embodiment, and has corresponding functions and beneficial effects.

[0141] An embodiment of the present application also provides a storage medium containing computer executable instructions, which, when executed by a computer processor, are used to execute a full-scenario adaptive flight method, the full-scenario adaptive flight method comprising: determining a real-time control strategy based on first scene information, the real-time control strategy comprising a speed priority control strategy and a terrain priority control strategy; acquiring terrain information collected in real time by a perception sensor, and planning a flight trajectory based on the terrain information and the real-time control strategy; when the UAV is flying based on the flight trajectory, determining second scene information based on the terrain information, and adjusting the real-time control strategy based on the second scene information; and replanning the flight trajectory based on the adjusted real-time control strategy and terrain information.

[0142] Storage medium - any of various types of memory devices or storage devices. The term "storage medium" is intended to include: installation media, such as CD-ROM, floppy disk or tape device; computer system memory or random access memory, such as DRAM, DDR RAM, SRAM, EDO RAM, Rambus RAM, etc.; non-volatile memory, such as flash memory, magnetic media (such as hard disk or optical storage); registers or other similar types of memory elements, etc. Storage media may also include other types of memory or combinations thereof. In addition, the storage medium may be located in the first computer system in which the program is executed, or may be located in a different second computer system, which is connected to the first computer system via a network (such as the Internet). The second computer system can provide program instructions to the first computer for execution. The term "storage medium" may include two or more storage media residing in different locations (for example, in different computer systems connected by a network). The storage medium may store program instructions (for example, embodied as a computer program) that can be executed by one or more processors.

[0143] Of course, the storage medium containing computer executable instructions provided in an embodiment of the present application, whose computer executable instructions are not limited to the above-mentioned full-scenario adaptive flight method, can also execute related operations in the full-scenario adaptive flight method provided in any embodiment of the present application.

[0144] The full-scenario adaptive flight device, storage medium and drone provided in the above embodiments can execute the full-scenario adaptive flight method provided in any embodiment of the present application. For technical details not described in detail in the above embodiments, please refer to the full-scenario adaptive flight method provided in any embodiment of the present application.

[0145] The above are only preferred embodiments of the present application and the technical principles used. The present application is not limited to the specific embodiments herein, and various obvious changes, readjustments and substitutions that can be made by those skilled in the art will not deviate from the protection scope of the present application. Therefore, although the present application is described in more detail through the above embodiments, the present application is not limited to the above embodiments, and may include more other equivalent embodiments without departing from the concept of the present application, and the scope of the present application is determined by the scope of the claims.

Claims

1. A full-scenario adaptive flight method, characterized in that: include: Determine a real-time control strategy according to the first scene information, wherein the real-time control strategy includes a speed priority control strategy and a terrain priority control strategy; Acquire terrain information collected by the perception sensor in real time, and plan a flight trajectory according to the terrain information and the real-time control strategy; When the UAV is flying based on the flight trajectory, second scene information is determined according to the terrain information, and the real-time control strategy is adjusted according to the second scene information; The flight trajectory is replanned according to the adjusted real-time control strategy and the terrain information.

2. The full-scenario adaptive flight method according to claim 1, characterized in that: Before determining the real-time control strategy according to the first scene information, the method further includes: Determine the first scene information according to the third scene information of the last flight; or, Determine the first scene information according to the operation task information; or, The first scene information is determined based on the third scene information and the operation task information of the previous flight.

3. The full-scenario adaptive flight method according to claim 2, characterized in that: The determining the first scene information according to the third scene information of the previous flight comprises: The third scene information of the previous flight is determined as the first scene information of the current flight.

4. The full-scenario adaptive flight method according to claim 2, characterized in that: The determining the first scene information according to the operation task information includes: In the case where this flight is the first flight, a preset flight speed in the operation task information is obtained, and if the preset flight speed is greater than a first speed threshold, the first scene information is determined to be a first scene; if the preset flight speed is not greater than the first speed threshold, the first scene information is determined to be a second scene; or, When this flight is the first flight, the operation area parameter in the operation task information is obtained. If the operation area parameter is greater than the first area parameter threshold, the first scene information is determined to be the second scene; if the operation area parameter is not greater than the first area parameter threshold, the first scene information is determined to be the first scene.

5. The full-scenario adaptive flight method according to claim 2, characterized in that: The first scene information includes a first terrain priority weight and a first speed priority weight, and a sum of the first terrain priority weight and the first speed priority weight is equal to one; The determining the first scene information according to the operation task information includes: When the current flight is the first flight, obtaining a preset flight speed and a preset maximum speed in the operation task information; Determine a speed ratio between a preset flight speed and a preset maximum speed; wherein the preset maximum speed is the maximum flight speed allowed for the UAV, and the preset flight speed is the planned flight speed of the UAV in this flight; The first terrain priority weight and the first speed priority weight are determined according to the speed ratio and the preset second terrain priority weight and the second speed priority weight, wherein the second terrain priority weight and the second speed priority weight are equal and the sum is equal to one.

6. The full-scenario adaptive flight method according to claim 5, characterized in that: The determining of the first terrain priority weight and the first speed priority weight according to the speed ratio and the preset second terrain priority weight and the second speed priority weight comprises: The first speed priority weight is obtained by adding the product of the second terrain priority weight and the preset weight coefficient to the product of the speed ratio and the second speed priority weight, and the first terrain priority weight is determined according to the first speed priority weight; wherein the preset weight coefficient is equal to 0.

5.

7. The full-scenario adaptive flight method according to claim 2, characterized in that: The first scene information includes a first terrain priority weight and a first speed priority weight, and a sum of the first terrain priority weight and the first speed priority weight is equal to one; The determining of the first scene information according to the third scene information and the operation task information of the last flight includes: Obtaining the third terrain priority weight and the third speed priority weight in the third scene information of the last flight; Obtaining a preset flight speed and a preset maximum speed in the operation task information, and determining a speed ratio between the preset flight speed and the preset maximum speed; A first terrain priority weight and a first speed priority weight are determined according to the speed ratio and the third terrain priority weight and the third speed priority weight.

8. The full-scenario adaptive flight method according to claim 7, characterized in that: The determining the first terrain priority weight and the first speed priority weight according to the speed ratio and the third terrain priority weight and the third speed priority weight comprises: In the case where the third terrain priority weight is greater than the third speed priority weight, the product of the third speed priority weight and the speed ratio is determined as the first speed priority weight, and the first terrain priority weight is determined according to the first speed priority weight; When the third terrain priority weight is less than the third speed priority weight, the product of the third speed priority weight and the speed ratio is added to the third terrain priority weight to obtain the first speed priority weight, and the first terrain priority weight is determined according to the first speed priority weight.

9. The full-scenario adaptive flight method according to claim 4, characterized in that: The determining of the real-time control strategy according to the first scene information includes: According to the first scenario, the corresponding real-time control strategy is determined to be a speed priority control strategy; or, according to the second scenario, the corresponding real-time control strategy is determined to be a terrain priority control strategy.

10. The full-scenario adaptive flight method according to claim 1, characterized in that: The first scene information includes a first terrain priority weight and a first speed priority weight; and determining the real-time control strategy according to the first scene information includes: When the first speed priority weight is greater than the first terrain priority weight, determining the real-time control strategy to be a speed priority control strategy; When the first speed priority weight is less than the first terrain priority weight, the real-time control strategy is determined to be a terrain priority control strategy.

11. The full-scenario adaptive flight method according to claim 1, characterized in that: In the case where the real-time control strategy is a speed priority control strategy, planning a flight trajectory according to the terrain information and the real-time control strategy includes: Determine a trajectory starting point and a trajectory end point, and plan a horizontal straight line trajectory according to the trajectory starting point and the trajectory end point and a preset flight speed, wherein the horizontal straight line trajectory includes a plurality of first control points, and the first control points are used to control the UAV to arrive at a first planned arrival time corresponding to the first control points; The multiple first control points are height-adjusted according to the terrain information, and the flight trajectory is generated.

12. The full-scenario adaptive flight method according to claim 11, characterized in that: The step of planning a horizontal straight line trajectory according to the trajectory starting point, the trajectory end point and a preset flight speed includes: Sampling a plurality of first control points on a horizontal straight line path between the starting point of the trajectory and the end point of the trajectory, wherein the plurality of first control points divide the horizontal straight line path into a plurality of first path segments; Allocate a speed to each of the first path segments according to the preset flight speed to obtain an allocated speed corresponding to each of the first path segments; Determine a first planned arrival time of the UAV flying at the assigned speed corresponding to the first path segment to the first control point corresponding to the first path segment.

13. The full-scenario adaptive flight method according to claim 11, characterized in that: The step of adjusting the heights of the plurality of first control points according to the terrain information and generating the flight trajectory includes: Performing a first height adjustment operation on a plurality of first control points of the horizontal straight line track according to the terrain information to obtain a first track; The first trajectory is sampled, a second height adjustment operation is performed on the sampled trajectory points, and a flight trajectory is generated.

14. The full-scenario adaptive flight method according to claim 1, characterized in that: In the case where the real-time control strategy is a terrain priority control strategy, planning a flight trajectory according to the terrain information and the real-time control strategy includes: Determine a trajectory start point and a trajectory end point, and plan a first terrain-imitating path according to the trajectory start point, the trajectory end point and the terrain information, wherein the first terrain-imitating path includes a plurality of second control points, the second control points are used to control the flight altitude of the UAV corresponding to the second control points, and the plurality of second control points divide the first terrain-imitating path into a plurality of second path segments; Allocate a speed to each of the second path segments according to a preset flight speed, obtain an allocated speed corresponding to each of the second path segments, and determine a second planned arrival time for the UAV to arrive at a second control point corresponding to the second path segment at the allocated speed corresponding to the second path segment; A flight trajectory is generated according to the plurality of second control points and the corresponding second planned arrival times.

15. The full-scenario adaptive flight method according to claim 14, characterized in that: The planning of a first terrain-simulating path according to the trajectory starting point, the trajectory end point and the terrain information includes: Sampling a plurality of third control points on a horizontal straight line path between the trajectory starting point and the trajectory end point, and adjusting the heights of the plurality of third control points according to the terrain information to obtain a plurality of third control points after the heights are adjusted; A plurality of second control points are obtained by thinning out the plurality of third control points after the height adjustment.

16. The full-scenario adaptive flight method according to claim 11 or 14, characterized in that: The step of determining the trajectory starting point and the trajectory end point comprises: The flight starting point of the UAV is determined as the trajectory starting point, and the trajectory end point is determined according to the trajectory starting point, a preset trajectory length, and a preset operation route.

17. The full-scenario adaptive flight method according to claim 1, characterized in that: The real-time control strategy also includes a combined control strategy, wherein the first scene information includes a first terrain priority weight and a first speed priority weight; and determining the real-time control strategy according to the first scene information includes: When the first speed priority weight is greater than the first terrain priority weight and the difference between the two is greater than a preset difference threshold, determining the real-time control strategy to be a speed priority control strategy; When the first terrain priority weight is greater than the first speed priority weight and the difference between the two is greater than a preset difference threshold, determining the real-time control strategy to be a terrain priority control strategy; When the difference between the first terrain priority weight and the first speed priority weight is less than a preset difference threshold, the real-time control strategy is determined to be a combined control strategy.

18. The full-scenario adaptive flight method according to claim 1, characterized in that: In the case where the real-time control strategy is a combined control strategy, planning a flight trajectory according to the terrain information and the real-time control strategy includes: Determine a trajectory starting point and a trajectory end point, and plan a second terrain-imitating path according to the trajectory starting point, the trajectory end point and the terrain information, wherein the second terrain-imitating path includes a plurality of fourth control points, and the fourth control points are used to control the flight height of the UAV at the corresponding fourth control points; performing thinning processing on the plurality of fourth control points to obtain a plurality of fifth control points, determining a third planned arrival time for the drone to reach the fifth control point according to a preset flight speed, and generating a second trajectory according to the fifth control point and the corresponding arrival time; The second trajectory is sampled to obtain multiple sixth control points and a fourth planned arrival time for the drone to reach the sixth control points, the altitudes of the multiple sixth control points are adjusted according to the terrain information, and a flight trajectory is generated according to the sixth control points with adjusted altitudes and the corresponding fourth planned arrival times.

19. The full-scenario adaptive flight method according to claim 18, characterized in that: The step of thinning out the plurality of fourth control points to obtain a plurality of fifth control points comprises: Determine the angle formed by any three consecutive fourth control points; When the included angle is greater than a preset angle threshold, the fourth control point among any three consecutive fourth control points is removed, and the remaining fourth control point is determined as the fifth control point.

20. The full-scenario adaptive flight method according to claim 1, characterized in that: The determining the second scene information according to the terrain information includes: Determining second scene information based on the terrain information collected historically and in real time by the perception sensor; Among them, when the current flight speed of the UAV is greater than a preset speed threshold, the perception sensor collects terrain information in front of and below the UAV; when the current flight speed of the UAV is less than the preset speed threshold, the perception sensor collects terrain information in front of, above and below the UAV.

21. A full-scenario adaptive flight device, characterized in that: include: a strategy determination module, configured to determine a real-time control strategy according to the first scene information, wherein the real-time control strategy includes a speed priority control strategy and a terrain priority control strategy; A trajectory planning module is configured to obtain terrain information collected by the perception sensor in real time, and plan a flight trajectory according to the terrain information and the real-time control strategy; a strategy adjustment module, configured to determine second scene information according to the terrain information when the UAV flies based on the flight trajectory, and adjust the real-time control strategy according to the second scene information; The trajectory adjustment module is configured to re-plan the flight trajectory according to the adjusted real-time control strategy and the terrain information.

22. A full-scenario adaptive flight device, characterized in that: include: one or more processors; A memory storing one or more programs, when the one or more programs are executed by the one or more processors, enables the one or more processors to implement the full-scenario adaptive flight method as described in any one of claims 1-20.

23. A storage medium containing computer executable instructions, characterized in that: The computer executable instructions, when executed by a computer processor, are used to execute the full-scenario adaptive flight method as described in any one of claims 1-20.

Images