Low-altitude unmanned aerial vehicle early warning method

Abstract

The present application relates to unmanned aerial vehicle early warning technical field, specifically to a kind of low altitude unmanned aerial vehicle early warning method.The present application includes the safety distance of hierarchical, by the flight trajectory of each step of target bird, determine early warning obstacle avoidance strategy, and further adaptively adjust strategy according to the feedback of obstacle avoidance strategy and the trajectory of target bird, realize effective obstacle avoidance to target bird, improve the safety of unmanned aerial vehicle in low altitude, the present application also uses timing and real-time monitoring mode to save energy, and according to whether the hostility of obstacle bird, develop multiple strategies to ensure that unmanned aerial vehicle can effectively avoid obstacles to target bird.

Description

Technical Field

[0001] This invention relates to the field of unmanned aerial vehicle (UAV) early warning technology, specifically a method for early warning of low-altitude UAVs. Background Technology

[0002] With the widespread application of drone technology, low-altitude flight safety has become a significant issue. Especially in areas with frequent bird activity, the risk of drone collisions with birds is high. Existing warning methods are often insufficiently comprehensive; simple avoidance strategies fail to account for actual conditions, particularly when encountering biological obstacles. The unpredictable behavior of biological obstacles makes effective avoidance difficult. Summary of the Invention

[0003] This invention provides a low-altitude UAV early warning method to solve the problem that the early warning and obstacle avoidance effects in the prior art are not good and cannot effectively avoid obstacles for birds.

[0004] In a first aspect, embodiments of the present invention provide a low-altitude unmanned aerial vehicle (UAV) early warning method, the method comprising: periodically acquiring the timed distance between the UAV and a target bird; if the timed distance is less than a preset first safe distance and greater than a preset second safe distance, acquiring a first predicted target trajectory route; and acquiring a first shortest distance between the first predicted target trajectory route and the UAV trajectory route based on the first predicted target trajectory route and the UAV trajectory route.

[0005] If the timed distance is less than the preset second safety distance, the real-time distance between the drone and the target bird is monitored in real time. If the real-time distance is greater than the preset third safety distance, the second predicted target trajectory route is obtained. Based on the second predicted target trajectory route and the drone trajectory route, the second shortest distance between the second predicted target trajectory route and the drone trajectory route is obtained.

[0006] If the real-time distance is less than the preset third safe distance, the drone triggers an avoidance strategy, which includes adjusting the drone's vertical altitude and / or adjusting the drone's horizontal flight direction.

[0007] If the second shortest distance is less than the first shortest distance, the image recognition module determines whether the target bird is hostile. If hostile, the drone triggers a drive-away strategy. If not hostile, the drone triggers an avoidance strategy.

[0008] Optionally, the timing time T is 0.3 seconds, and the second safety distance L is a dynamically changing value. The second safety distance L = (V1 + V2) * T + V3 * T3, where V1 is the speed of the drone at that time; V2 is the speed of the target bird at that time; T is the timing time; V3 is the maximum ascent speed of the drone; and T3 is the safety time, which is set to 0.5 seconds.

[0009] Optionally, it is determined whether the target bird is a bird of prey. If the target bird is a bird of prey, the deterrent strategy is to release a bird repellent. If the target bird is not a bird of prey, the deterrent strategy is to play a sound, which is the sound made by a bird of prey when it catches its prey.

[0010] Optionally, the number of target birds is determined. If the number of target birds is three or more, the avoidance strategy is to adjust the vertical altitude of the drone. The adjustment of the vertical altitude of the drone is to increase the flight altitude of the drone, and the increase in the flight altitude of the drone is at least greater than the third safety distance. If the number of target birds is one or two, the avoidance strategy is to keep the drone hovering.

[0011] Optionally, the release of the bird repellent is performed by launching high-speed aerosol droplets toward the target birds.

[0012] Optionally, the method further includes: when the bird repellent is released and the real-time distance does not increase, activating the laser device, which will emit a laser horizontally toward the target bird.

[0013] Optionally, the method further includes: when the laser device emits a laser horizontally toward the target bird and the real-time distance does not increase, detecting whether there is sunlight; if there is sunlight, commanding the drone to fly toward the direction of sunlight.

[0014] Optionally, the method further includes: turning off all light-emitting devices of the drone when the ambient condition is nighttime.

[0015] Secondly, embodiments of the present invention provide a drone device, characterized in that it includes:

[0016] At least one processor; and

[0017] At least one memory communicatively connected to the processor, wherein:

[0018] The memory stores program instructions that can be executed by the processor, and the processor can invoke the program instructions to perform the method described in any of the first aspects.

[0019] Thirdly, embodiments of the present invention provide a storage medium including a stored program, wherein, when the program is executed, it controls the device where the storage medium is located to perform the method described in any of the first aspects.

[0020] This invention determines an early warning and obstacle avoidance strategy by analyzing each step of the target bird's flight trajectory, and further adaptively adjusts the strategy based on the obstacle avoidance strategy and the target bird's trajectory feedback, thereby effectively avoiding obstacles for the target bird and improving the safety of the UAV at low altitudes.

[0021] To more clearly illustrate the technical solutions of the embodiments of this application, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0022] Figure 1 The diagram shown is a schematic representation of a low-altitude unmanned aerial vehicle (UAV) early warning method provided in an embodiment of this application.

[0023] Figure 2 The diagram shown is a schematic representation of a low-altitude UAV target bird avoidance strategy provided in an embodiment of this application.

[0024] Figure 3 The diagram shown is a schematic representation of a low-altitude UAV raptor avoidance strategy provided in an embodiment of this application. Detailed Implementation

[0025] To better understand the technical solution of this application, the embodiments of this application will be described in detail below with reference to the accompanying drawings.

[0026] It should be understood that the described embodiments are merely some, not all, of the embodiments in this application. All other embodiments obtained by those skilled in the art based on the embodiments in this application without inventive effort are within the scope of protection of this application.

[0027] like Figure 1 The diagram shown is a schematic diagram of a low-altitude drone early warning method provided by an embodiment of the present invention. Specifically, S1 timed acquisition of the timed distance between the drone and the target bird, that is, the acquisition of distance data between the drone and the target bird at intervals.

[0028] S2 determines the timing distance. If it is less than the first safe distance but greater than the second safe distance, proceed to S3 to obtain the first shortest distance. The first pair of shortest distances is obtained from the predicted trajectory of the target bird and the trajectory of the drone.

[0029] S4 determines the timed distance. If the timed distance is less than the second safe distance, then proceed to S5 to determine the real-time distance, that is, start real-time distance detection and simultaneously obtain the second shortest distance in S5. The second shortest distance is obtained by combining the predicted trajectory of the target bird and the trajectory of the drone. If the real-time distance is less than the third safe distance, then directly trigger the avoidance strategy in S10.

[0030] S7 determines whether the second shortest distance is less than the first shortest distance. If so, proceed to S8 to determine whether the birds are hostile. Otherwise, proceed to S9 to continue implementation and monitoring.

[0031] The more detailed implementation plan is as follows: The drone will prioritize acquiring information in a timed manner, which effectively reduces energy consumption. Specifically, the timed distance between the drone and the target bird will be acquired at regular intervals. If the timed distance is less than a preset first safety distance but greater than a preset second safety distance, the first predicted target trajectory will be acquired. Based on the first predicted target trajectory and the drone trajectory, the first shortest distance between the two will be acquired. This first shortest distance is used to determine whether the target bird will ultimately affect the drone. If the first shortest distance is 0 or lower than the set safety distance (which can be 10 meters and can be adjusted according to actual needs), the drone needs to issue a warning notification to the end user or server. In one implementation, the second safety distance is dynamically changing: the second safety distance L is a dynamically changing value, calculated as L = (V1 + V2) * T + V3 * T3, where the specific timing T is 0.3 seconds, V1 is the drone's current speed, V2 is the target bird's current speed, T is the timing time, V3 is the drone's maximum ascent speed, and T3 is the safety time, set to 0.5 seconds. This formula is derived by combining horizontal and vertical avoidance distances. The timing time T is set to 0.3 seconds and the safety time to 0.5 seconds, based on actual tests showing that the drone does not face a collision risk within this time, and this value ensures sufficient safety for the drone.

[0032] If the timed distance is less than the preset second safety distance, the real-time distance between the drone and the target bird is monitored. At this point, the target bird is already below the second safety distance, which is relatively dangerous. Therefore, more resources need to be allocated to monitor the real-time distance between the target bird and the drone, giving the drone time to make appropriate avoidance strategies. Based on the above, if the real-time distance is greater than the preset third safety distance, the second predicted target trajectory is obtained. Based on the second predicted target trajectory and the drone trajectory, the second shortest distance between the second predicted target trajectory and the drone trajectory is obtained. Similarly, if the first shortest distance is 0 or lower than the set safety distance (the set safety distance can be 10 meters, which can be adjusted according to actual needs), the drone needs to issue a warning notification to the end user or server.

[0033] If the real-time distance is less than the preset third safe distance, reaching the highest risk level, the drone will directly trigger an avoidance strategy. This strategy includes adjusting the drone's vertical altitude and / or adjusting its horizontal flight direction. Firstly, by adjusting the horizontal flight direction, the drone can change its relative trajectory to the target bird. It can change its horizontal flight direction to one side, causing their relative trajectories to diverge, much like two ships changing course to avoid a collision. Secondly, the drone can ascend to a certain altitude, maintaining a safe vertical distance from the target bird, similar to a car changing lanes to avoid vehicles or obstacles ahead.

[0034] If the second shortest distance is less than the first shortest distance, it indicates that the target bird is changing its original path and flying towards the drone. In this case, the drone needs to use its image recognition module to determine if the bird is hostile. If hostile, the drone triggers a deterrent strategy; if not, it triggers an avoidance strategy. The image recognition module uses deep learning algorithms to analyze the bird's posture in real time. For example, when a bird tilts its head forward and faces the drone, these posture features are captured by the algorithm and compared with samples in the database already marked as "hostile postures." Through learning from a large number of samples, the algorithm can identify the hostile signals represented by these posture combinations, thereby determining whether the target bird has aggressive intentions.

[0035] If the second shortest distance is greater than the first shortest distance, it means that the target bird's trajectory and the drone's trajectory have moved away. At this point, you only need to monitor the distance between the target bird and the drone normally until the distance between them is greater than the first safe distance, then cancel the monitoring, or if the distance between them is less than the third safe distance, execute the avoidance strategy.

[0036] This solution initially uses timed distance measurement to save energy. If the distance is relatively close, it will be switched to real-time measurement to ensure safety. The first and second shortest distances can not only provide notifications and warnings, but also determine further avoidance strategies by combining the relationship between the two.

[0037] according to Figure 2 To further explain, when it is determined that a deterrent strategy is needed, it is determined whether the target bird is a bird of prey. If the target bird is a bird of prey, the deterrent strategy is to release a bird repellent, specifically by launching high-speed aerosol droplets toward the target bird. If the target bird is not a bird of prey, the deterrent strategy is to play a sound, which is the sound made by birds of prey when they catch their prey.

[0038] Furthermore, the number of target birds can be determined. If there are three or more target birds, the avoidance strategy is to adjust the vertical altitude of the drone, which means increasing the drone's flight altitude to a height at least greater than the third safe distance. If there are only one or two target birds, the strategy is to keep the drone hovering. Because the flock of birds is relatively large, the drone should actively avoid them. If there are only one or two lone birds, the drone can hover until the target birds move away.

[0039] according to Figure 3 The flowchart further illustrates that in some embodiments, after releasing the bird repellent in step S01, the real-time distance is determined. If the real-time distance increases, step S05 stops releasing the bird repellent. If the real-time distance does not increase, step S02 activates the laser device, which emits a laser horizontally toward the target bird and combines it with ultrasonic waves and voice (such as eagle calls or firecracker sounds) to enhance the deterrent effect. This way, the calls of similar birds of prey will also have a certain deterrent effect. After the laser device emits the laser horizontally toward the target bird, step S03 determines the real-time distance. If the real-time distance increases, step S06 stops releasing the bird repellent and the laser device. If the real-time distance does not increase, the presence of sunlight is detected. If sunlight is present, the drone is commanded to fly in the direction of sunlight in step S04. At this time, if the hostile target bird continues to chase the drone, it will also be dazzled by the sunlight, creating an uncomfortable environmental condition for the target bird, and the bird will give up the chase. Furthermore, the flight direction of the drone can be adjusted according to the intensity and direction of the sunlight.

[0040] Optionally, in some embodiments, the method further includes: when the environment is nighttime, turning off all light-emitting devices of the drone. Some birds of interest (interested in the drone) or hostile birds are largely attracted or hostile because of the light-emitting devices on the drone. Turning off the light-emitting devices can not only eliminate the interest or hostility, but also, at night, can cause the target birds to lose sight of the drone they are chasing, thus causing the birds to give up the chase.

[0041] The aforementioned non-transitory computer-readable storage medium may be any combination of one or more computer-readable media. A computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium. A computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of computer-readable storage media (a non-exhaustive list) include: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), or flash memory, optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this document, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in connection with an instruction execution system, apparatus, or device.

[0042] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, capable of sending, propagating, or transmitting programs for use by or in connection with an instruction execution system, apparatus, or device.

[0043] Program code contained on a computer-readable medium may be transmitted using any suitable medium, including but not limited to wireless, wire, optical fiber, RF, etc., or any suitable combination thereof.

[0044] Computer program code for performing the operations described herein can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, and conventional procedural programming languages ​​such as C or similar languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or it can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0045] The foregoing has described specific embodiments of this specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in a different order than that shown in the embodiments and may still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily require the specific or sequential order shown to achieve the desired result. In some embodiments, multitasking and parallel processing are possible or may be advantageous.

[0046] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this specification, "a plurality of" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0047] Any process or method described in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or more executable instructions for implementing custom logic functions or processes, and the scope of the preferred embodiments of this specification includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as will be understood by those skilled in the art to which the embodiments of this specification pertain.

[0048] Depending on the context, the word "if" as used here can be interpreted as "when," "when," "in response to determination," or "in response to detection." Similarly, depending on the context, the phrase "if determination" or "if detection (of the stated condition or event)" can be interpreted as "when determination," "in response to determination," "when detection (of the stated condition or event)," or "in response to detection (of the stated condition or event)."

[0049] It should be noted that the terminals involved in the embodiments of this specification may include, but are not limited to, personal computers (hereinafter referred to as PCs), personal digital assistants (hereinafter referred to as PDAs), wireless handheld devices, tablet computers, mobile phones, MP3 players, MP4 players, etc.

[0050] In the embodiments provided in this specification, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0051] Furthermore, the functional units in the various embodiments of this specification can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or in a combination of hardware and software functional units.

[0052] The integrated units implemented as software functional units described above can be stored in a computer-readable storage medium. These software functional units, stored in a storage medium, include several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) or processor to execute some steps of the methods described in the various embodiments of this specification.

[0053] The above description is merely a preferred embodiment of this specification and is not intended to limit this specification. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this specification should be included within the scope of protection of this specification.

Claims

1. A method for early warning of low-altitude unmanned aerial vehicles (UAVs), characterized in that, The method includes: periodically acquiring the timed distance between the drone and the target bird; if the timed distance is less than a preset first safety distance and greater than a preset second safety distance, acquiring a first predicted target trajectory route; and acquiring a first shortest distance between the first predicted target trajectory route and the drone trajectory route based on the first predicted target trajectory route and the drone trajectory route. If the timed distance is less than the preset second safety distance, the real-time distance between the drone and the target bird is monitored in real time. If the real-time distance is greater than the preset third safety distance, the second predicted target trajectory route is obtained. Based on the second predicted target trajectory route and the drone trajectory route, the second shortest distance between the second predicted target trajectory route and the drone trajectory route is obtained. If the real-time distance is less than the preset third safe distance, the drone triggers an avoidance strategy, which includes adjusting the drone's vertical altitude and / or adjusting the drone's horizontal flight direction. If the second shortest distance is less than the first shortest distance, the image recognition module determines whether the target bird is hostile. If hostile, the drone triggers a deterrent strategy, determining whether the target bird is a bird of prey. If the target bird is a bird of prey, the deterrent strategy involves releasing a bird repellent. After the bird repellent is released and the real-time distance does not increase, a laser device is activated, emitting a laser horizontally toward the target bird. After the laser device emits a laser horizontally toward the target bird and the real-time distance does not increase, the presence of sunlight is detected. If sunlight is present, the drone is commanded to fly in the direction of sunlight. If the target bird is not a bird of prey, the deterrent strategy involves playing a sound, specifically the sound made by birds of prey when hunting. If there is no hostility, the drone triggers an avoidance strategy.

2. The method according to claim 1, characterized in that, The timing time T is 0.3 seconds, and the second safety distance L is a dynamically changing value. The second safety distance L = (V1 + V2) * T + V3 * T3, where V1 is the speed of the drone at that time; V2 is the speed of the target bird at that time; T is the timing time; V3 is the maximum altitude speed of the drone; and T3 is the safety time, which is set to 0.5 seconds.

3. The method according to claim 1, characterized in that, If the number of target birds is three or more, the avoidance strategy is to adjust the vertical altitude of the drone, which means increasing the drone's flight altitude, and the increased flight altitude is at least greater than the third safety distance; if the number of target birds is one or two, the avoidance strategy is to keep the drone hovering.

4. The method according to claim 1, characterized in that, The release of the bird repellent involves launching high-speed aerosol droplets toward the target birds.

5. The method according to claim 2, characterized in that, The method also includes turning off all light-emitting devices of the drone when the ambient condition is nighttime.

6. A drone device, characterized in that, include: At least one processor; And at least one memory communicatively connected to the processor, wherein: the memory stores program instructions executable by the processor, and the processor invokes the program instructions to perform the method as described in any one of claims 1 to 5.

7. A storage medium, characterized in that, The storage medium includes a stored program, wherein, when the program is executed, it controls the device on which the storage medium is located to perform the method according to any one of claims 1 to 5.

Images