Intelligent stopping method for unmanned aerial vehicle, undercarriage system and storage medium

Abstract

The invention relates to the technical field of unmanned aerial vehicle parking, and discloses an intelligent unmanned aerial vehicle parking method, an undercarriage system and a storage medium. The method comprises the steps of obtaining historical shutdown environment information and historical shutdown strategies with corresponding relations, generating a shutdown environment feature database, generating a shutdown strategy database, generating an unmanned aerial vehicle shutdown model, obtaining real-time shutdown environment information, calling a real-time shutdown strategy and controlling the unmanned aerial vehicle to stop. The undercarriage system and the storage medium both correspond to the method. According to the method and the device, the parking environment characteristic data and the parking strategy database are generated, and the unmanned aerial vehicle parking model is generated by utilizing the parking environment characteristic data and the parking strategy database, so that the real-time parking environment information is processed; the corresponding shutdown strategy is quickly called in the shutdown strategy database, so that the shutdown preparation time is shortened, the accuracy of quick calling of the shutdown strategy database is achieved through the generative adversarial network technology, and intelligent shutdown of the unmanned aerial vehicle is achieved.

Description

Technical Field

[0001] The present application relates to the technical field of drone shutdown, and specifically to a drone intelligent shutdown method, a landing gear system, and a storage medium. Background Art

[0002] With the rapid development of drone technology, its application scenarios are becoming increasingly extensive, but there are still some urgent problems to be solved in drone downtime.

[0003] In the prior art, drone parking mainly relies on manual control by operators or sensor-based parking adjustments, which require high technical skills of operators and are easily affected by human factors, making it difficult to ensure the accuracy and safety of parking. In addition, the requirements for sensors and parking adjustments are high, which leads to increased costs. In complex environments, such as mountainous areas with undulating terrain, urban areas with tall buildings, or in severe climatic conditions, it becomes extremely difficult to find a suitable parking location. Traditional parking methods often cannot accurately judge the flatness and slope of the terrain and the distribution of surrounding obstacles, which can easily cause the drone to tilt, collide, or even crash during landing, and the corresponding parking preparation time is relatively long, which affects the drone's ability to meet application requirements.

[0004] In summary, the prior art urgently needs a technical solution for intelligent drone shutdown that can reduce the drone shutdown preparation time. Summary of the invention

[0005] The purpose of this application is to provide a drone intelligent parking method, landing gear system and storage medium to solve the technical problems raised in the above background technology.

[0006] To achieve the above objectives, this application discloses the following technical solutions:

[0007] In a first aspect, the present application discloses a method for intelligently stopping a drone, the method comprising:

[0008] S1: Acquire historical parking environment information and corresponding historical parking strategies; wherein the parking environment information at least includes terrain data and climate data, and the parking strategy at least includes a braking strategy and a landing gear release strategy;

[0009] S2: extracting features from the historical shutdown environment information to generate a shutdown environment feature database; wherein the shutdown environment feature database stores different shutdown environment features;

[0010] S3: using the correspondence between the historical shutdown strategy and the historical shutdown environment information, generating a shutdown strategy database having a corresponding relationship with the shutdown environment feature database; wherein the shutdown strategy database stores different shutdown strategies corresponding to the shutdown environment features;

[0011] S4: training a preset UAV shutdown pre-model to execute the shutdown strategy corresponding to the shutdown environment information output, and generating a UAV shutdown model; wherein the preset and training of the UAV shutdown pre-model are both performed using generative adversarial network technology, and the UAV shutdown model is configured to be based on the shutdown strategy corresponding to the shutdown environment information output;

[0012] S5: using a preset sensor of the drone to obtain real-time shutdown environment information; wherein the preset sensor corresponds to the shutdown environment information;

[0013] S6: running the drone model, receiving the real-time shutdown environment information, and calling the corresponding real-time shutdown strategy;

[0014] S7: Based on the real-time shutdown strategy, the preset power system and landing gear of the UAV are controlled to shut down the UAV; wherein the power system is used to control the power output during the shutdown process of the UAV.

[0015] Preferably, the terrain data at least includes terrain height data and terrain slope and flatness data;

[0016] The climate data includes at least wind speed, wind direction, air pressure, temperature and humidity;

[0017] The braking strategy is used to control the operation of the power system;

[0018] The landing gear release strategy is used to control the release of the landing gear.

[0019] Preferably, the generation process of the shutdown environment feature database includes:

[0020] Extracting features from the terrain data and climate data using feature extraction technology to obtain corresponding terrain features and climate features;

[0021] The database technology is used to build a database in combination with the terrain characteristics and the climate characteristics to obtain the shutdown environment characteristics database.

[0022] Preferably, the generation process of the shutdown strategy database includes:

[0023] The correspondence between the historical shutdown strategy and the historical shutdown environment information is obtained, and the calling relationship between the terrain characteristics and the climate characteristics and the shutdown strategy is constructed using the correspondence. The calling relationship and the shutdown strategy are built into a database using database technology to obtain the shutdown strategy database.

[0024] Preferably, the generation process of the drone shutdown model includes:

[0025] Obtain a drone shutdown prediction model preset using generative adversarial network technology;

[0026] The preset feature extraction tool, the shutdown environment feature database and the shutdown strategy database are stored in the UAV shutdown pre-model; wherein the feature extraction tool is used to extract features of the shutdown environment information;

[0027] The UAV shutdown prediction model is trained using historical shutdown environment information and generative adversarial network technology to execute steps A1 to A3:

[0028] A1: calling the feature extraction tool to extract features from the historical downtime environment information to obtain corresponding historical downtime environment features;

[0029] A2: using the historical shutdown environment features obtained in step A1 to perform similarity matching in the shutdown environment feature database, and judging whether the historical shutdown strategy corresponding to the outputted maximum similarity meets a preset similarity threshold, if yes, output and call the historical shutdown strategy corresponding to the maximum similarity, otherwise, execute step A3;

[0030] A3: Generate predicted shutdown ring features by using generative adversarial network technology and combining the historical shutdown environment features, and use the predicted shutdown features to perform similarity matching in the shutdown environment feature database, and determine whether the historical shutdown strategy corresponding to the outputted maximum similarity meets a preset similarity threshold. If yes, output and call the historical shutdown strategy corresponding to the maximum similarity, otherwise repeat step A3 until the similarity threshold is met;

[0031] A drone shutdown pre-model that meets preset model training conditions is output and defined as the drone shutdown model.

[0032] Preferably, the process of acquiring the real-time shutdown environment information includes:

[0033] Enable corresponding sensors to collect real-time terrain data and real-time environmental data; the sensors include at least laser radar, ultrasonic sensor and meteorological sensor;

[0034] The real-time terrain data and the real-time environment data are used to generate corresponding real-time shutdown environment information.

[0035] Preferably, the calling process of the real-time shutdown strategy includes:

[0036] Run the drone shutdown model to perform the following steps B1 to B3:

[0037] B1: calling a preset feature extraction tool to extract features from the real-time shutdown environment information to obtain corresponding real-time shutdown environment features;

[0038] B2: using the real-time shutdown environment features obtained in step B1 to perform similarity matching in the shutdown environment feature database, and judging whether the shutdown strategy corresponding to the outputted maximum similarity meets a preset similarity threshold, if yes, output and call the shutdown strategy corresponding to the maximum similarity as the real-time shutdown strategy, otherwise, execute step B3;

[0039] B3: Generate predicted shutdown loop features by using generative adversarial network technology in combination with the real-time shutdown environment features, and use the predicted shutdown features to perform similarity matching in the shutdown environment feature database to determine whether the shutdown strategy corresponding to the outputted maximum similarity meets a preset similarity threshold. If so, output and call the shutdown strategy corresponding to the maximum similarity as the real-time shutdown strategy. Otherwise, repeat step B3 until the similarity threshold is met.

[0040] Preferably, step S7 specifically includes:

[0041] S71: Acquire and analyze the called real-time parking strategy to obtain a real-time braking strategy and a real-time landing gear release strategy;

[0042] S72: Using the real-time braking strategy to control the power system to brake;

[0043] S73: Using the real-time landing gear release strategy to control the landing gear to be released.

[0044] In a second aspect, the present application discloses a drone intelligent parking landing gear system, which is applicable to the drone intelligent parking method as described above, and the system includes:

[0045] A first data acquisition module, wherein the data acquisition module is configured to: acquire historical shutdown environment information and historical shutdown strategies having a corresponding relationship; wherein the shutdown environment information at least includes terrain data and climate data, and the shutdown strategy at least includes a braking strategy and a landing gear release strategy;

[0046] A shutdown environment feature database generation module, wherein the shutdown environment feature database generation module is configured to: extract features from the historical shutdown environment information to generate a shutdown environment feature database; wherein the shutdown environment feature database stores different shutdown environment features;

[0047] A shutdown strategy database generation module, wherein the shutdown strategy database generation module is configured to: utilize the correspondence between the historical shutdown strategy and the historical shutdown environment information to generate a shutdown strategy database having a corresponding relationship with the shutdown environment feature database; wherein the shutdown strategy database stores different shutdown strategies corresponding to the shutdown environment features;

[0048] A drone shutdown model generation module, wherein the drone shutdown model generation module is configured to: train a preset drone shutdown pre-model to execute the shutdown strategy corresponding to the shutdown environment information output, and generate a drone shutdown model; wherein the preset and training of the drone shutdown pre-model are both performed using generative adversarial network technology, and the drone shutdown model is configured to output the shutdown strategy corresponding to the shutdown environment information;

[0049] A second data acquisition module, wherein the second data acquisition module is configured to: acquire real-time shutdown environment information using a sensor preset on the drone; wherein the preset sensor corresponds to the shutdown environment information;

[0050] A drone shutdown model operation module, wherein the drone shutdown model operation module is configured to: run the drone model, receive the real-time shutdown environment information, and call a corresponding real-time shutdown strategy;

[0051] A shutdown control module, wherein the shutdown control module is configured to: control a preset power system and landing gear of the drone to shut down the drone based on the real-time shutdown strategy; wherein the power system is used to control the power output of the drone shutdown process.

[0052] In a third aspect, the present application discloses a storage medium having a computer program stored thereon. When the computer program is executed by a processor, the intelligent shutdown method of the drone as described above is implemented.

[0053] Beneficial effects: The UAV intelligent shutdown method, landing gear system and storage medium of the present application utilize historical shutdown environment information and corresponding historical shutdown strategies to realize the generation of shutdown environment characteristic data and a corresponding shutdown strategy database, and utilize the shutdown environment characteristic data and the corresponding shutdown strategy database to realize the generation of a UAV shutdown model, utilize the UAV shutdown model to realize the processing of real-time shutdown environment information, and reduce the shutdown preparation time by quickly calling the corresponding shutdown strategy in the shutdown strategy database, and realize the accuracy of the rapid calling of the shutdown strategy database through the generation of adversarial network technology, thereby realizing intelligent shutdown of the UAV. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For those skilled in the art, other drawings can be obtained based on these drawings without paying any creative work.

[0055] Figure 1 A flowchart of the intelligent shutdown method for a drone provided in an embodiment of the present application;

[0056] Figure 2 This is a structural block diagram of the UAV intelligent parking landing gear system provided in an embodiment of the present application. DETAILED DESCRIPTION

[0057] The technical solutions in the embodiments of the present application are described clearly and completely below. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present application.

[0058] In this article, the term "comprising" is intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of more restrictions, the elements defined by the sentence "comprising..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0059] In a first aspect, this embodiment discloses Figure 1 A method for intelligently stopping a drone is shown, the method comprising:

[0060] S1: Acquire historical parking environment information and corresponding historical parking strategies; wherein the parking environment information at least includes terrain data and climate data, and the parking strategy at least includes a braking strategy and a landing gear release strategy;

[0061] S2: extracting features from historical shutdown environment information to generate a shutdown environment feature database; wherein the shutdown environment feature database stores different shutdown environment features;

[0062] S3: using the correspondence between historical shutdown strategies and historical shutdown environment information, generating a shutdown strategy database that has a corresponding relationship with the shutdown environment feature database; wherein the shutdown strategy database stores different shutdown strategies corresponding to the shutdown environment features;

[0063] S4: training a preset UAV shutdown pre-model to execute a shutdown strategy corresponding to the shutdown environment information output, and generating a UAV shutdown model; wherein the preset and training of the UAV shutdown pre-model are both performed using generative adversarial network technology, and the UAV shutdown model is configured as a shutdown strategy corresponding to the shutdown environment information output;

[0064] S5: using the preset sensors of the drone to obtain real-time parking environment information; wherein the preset sensors correspond to the parking environment information;

[0065] S6: Run the drone model, receive real-time shutdown environment information, and call the corresponding real-time shutdown strategy;

[0066] S7: Based on the real-time shutdown strategy, the preset power system and landing gear of the UAV are controlled to shut down the UAV; wherein the power system is used to control the power output of the UAV shutdown process.

[0067] Based on the above, this embodiment realizes the generation of shutdown environment feature data and a corresponding shutdown strategy database through historical shutdown environment information and corresponding historical shutdown strategies, and uses the shutdown environment feature data and the corresponding shutdown strategy database to realize the generation of a drone shutdown model, and uses the drone shutdown model to realize the processing of real-time shutdown environment information, and reduces the shutdown preparation time by quickly calling the corresponding shutdown strategy in the shutdown strategy database, and realizes the accuracy of the rapid call of the shutdown strategy database through the generation of adversarial network technology, thereby realizing intelligent shutdown of the drone.

[0068] Specifically, the terrain data includes at least terrain height data and terrain slope and flatness data;

[0069] Climate data include at least wind speed, wind direction, air pressure, temperature and humidity;

[0070] Braking strategies are used to control the operation of the powertrain;

[0071] The landing gear release strategy is used to control the release of the landing gear.

[0072] It should be noted that in the specific application of this embodiment, the terrain data may also include the distribution and height of obstacles and the frequency of terrain undulations, and the climate data may also include precipitation data and atmospheric visibility, thereby obtaining comprehensive parking environment information; the braking strategy and landing gear release strategy of this embodiment are both extracted based on the actual UAV parking process.

[0073] Based on the above, this embodiment achieves a comprehensive description of the parking environment information through terrain data and climate data, provides accurate data reference for calling the parking strategy, and provides a data basis for calling the parking strategy through the braking strategy and landing gear release strategy.

[0074] Specifically, the generation process of the shutdown environment feature database includes:

[0075] The feature extraction technology is used to extract the features of the terrain data and climate data to obtain the corresponding terrain features and climate features;

[0076] By using database technology and combining terrain characteristics and climate characteristics, a shutdown environment characteristics database is obtained.

[0077] It should be noted that this embodiment uses existing feature extraction technology to extract corresponding terrain features and climate features, and uses existing database technology to build a database. In a simple example, terrain features can be terrain type, slope, and obstacle distribution, and climate features can be average wind speed, precipitation type, and average visibility.

[0078] Based on the above, this embodiment provides a data basis for the drone shutdown model to process real-time shutdown environment information by constructing a shutdown environment feature database, and provides technical support for reducing shutdown preparation time.

[0079] Specifically, the process of generating the shutdown strategy database includes:

[0080] The correspondence between historical shutdown strategies and historical shutdown environment information is obtained, and the calling relationship between terrain characteristics and climate characteristics and shutdown strategies is constructed using the correspondence. The calling relationship and shutdown strategies are built into a database using database technology to obtain a shutdown strategy database.

[0081] It should be noted that the correspondence between the historical parking strategy and the historical parking environment information of the present embodiment is extracted and solidified based on the time series relationship between the parking strategy and the parking environment information of the actual UAV parking process. For example, if the terrain height changes little, the surface material is grass, the wind speed is low, the weather is clear and cloudless, the temperature is moderate, and the humidity is normal, a more direct landing path can be selected to descend at a normal speed. Since the terrain is flat, the landing gear does not need special adjustment and maintains a stable flight attitude until a smooth landing. For example, if the terrain has certain undulations, the slope is gentle, the surface may be grass or bushes, the wind speed is moderate, the weather is cloudy, and the temperature and humidity are relatively stable, choose to land in an area with a smaller slope, plan the landing path according to the direction of the hills, try to avoid parking in places with too large slopes, and during the landing process, pay close attention to terrain changes, adjust the flight attitude at any time, and the landing gear can adjust the angle appropriately to ensure stable parking on inclined ground.

[0082] Based on the above, this embodiment provides a data basis for calling the shutdown strategy by constructing a shutdown strategy database, thereby providing a technical guarantee for reducing the shutdown preparation time.

[0083] Specifically, the generation process of the drone shutdown model includes:

[0084] Obtain a drone shutdown prediction model preset using generative adversarial network technology;

[0085] The preset feature extraction tool, the shutdown environment feature database and the shutdown strategy database are stored in the UAV shutdown pre-model; wherein the feature extraction tool is used to extract the features of the shutdown environment information;

[0086] Use historical downtime environment information and generative adversarial network technology to train the drone downtime prediction model to execute steps A1 to A3:

[0087] A1: Call the feature extraction tool to extract features from the historical downtime environment information to obtain the corresponding historical downtime environment features;

[0088] A2: Use the historical shutdown environment features obtained in step A1 to perform similarity matching in the shutdown environment feature database, and determine whether the historical shutdown strategy corresponding to the outputted maximum similarity meets the preset similarity threshold. If yes, output and call the historical shutdown strategy corresponding to the maximum similarity, otherwise execute step A3;

[0089] A3: Generate predicted shutdown ring features by using generative adversarial network technology and combining historical shutdown environment features, and use the predicted shutdown features to perform similarity matching in the shutdown environment feature database to determine whether the historical shutdown strategy corresponding to the maximum similarity output meets the preset similarity threshold. If yes, output and call the historical shutdown strategy corresponding to the maximum similarity, otherwise repeat step A3 until the similarity threshold is met;

[0090] The drone shutdown pre-model that meets the preset model training conditions is output and defined as the drone shutdown model.

[0091] Generative adversarial network technology is a deep learning model composed of a generator and a discriminator. It can predict shutdown environment information through data enhancement, thereby achieving accurate rapid call of the shutdown strategy database.

[0092] It should be noted that the feature extraction tool of this embodiment is any one of the existing feature extraction technologies, which can realize the extraction of shutdown environment features; the similarity matching of this embodiment is realized by using the existing data similarity matching technology, which can realize the matching of real-time shutdown environment information with the shutdown environment information in the shutdown environment feature database; the predicted shutdown ring feature of this embodiment is based on the generation of the generator and discriminator of the existing generative adversarial network technology, which provides a technical basis for improving the accuracy of rapid calling of the shutdown strategy database.

[0093] Based on the above, this embodiment realizes the processing of real-time shutdown environment information by generating a drone shutdown pre-model, providing a technical basis for realizing drone intelligent shutdown.

[0094] Specifically, the process of obtaining real-time shutdown environment information includes:

[0095] Enable corresponding sensors to collect real-time terrain data and real-time environmental data; the sensors include at least laser radar, ultrasonic sensor and meteorological sensor;

[0096] The real-time terrain data and the real-time environment data are used to generate corresponding real-time shutdown environment information.

[0097] It should be noted that the sensor of this embodiment may also include a proximity sensor in a specific application, which is installed around the landing gear or fuselage of the drone to detect the distance between the drone and surrounding objects. During landing, the proximity sensor can help the drone avoid collision with the ground or other obstacles to ensure safe shutdown.

[0098] It should be noted that this embodiment realizes the collection of comprehensive real-time shutdown environment information through corresponding sensors, providing a comprehensive and real-time data basis for the shutdown strategy database to quickly call the corresponding shutdown strategy.

[0099] Based on the above, this embodiment realizes the collection of real-time shutdown environment information through sensors, thereby providing a data basis for calling the shutdown strategy.

[0100] Specifically, the calling process of the real-time shutdown strategy includes:

[0101] Run the drone parking model and perform the following steps B1 to B3:

[0102] B1: calling a preset feature extraction tool to extract features from the real-time shutdown environment information to obtain corresponding real-time shutdown environment features;

[0103] B2: Use the real-time shutdown environment features obtained in step B1 to perform similarity matching in the shutdown environment feature database, and determine whether the shutdown strategy corresponding to the maximum similarity output meets the preset similarity threshold. If yes, output and call the shutdown strategy corresponding to the maximum similarity as the real-time shutdown strategy, otherwise execute step B3;

[0104] B3: Generate predicted shutdown loop features by using generative adversarial network technology and combining them with real-time shutdown environment features. Use the predicted shutdown features to perform similarity matching in the shutdown environment feature database to determine whether the shutdown strategy corresponding to the output with the greatest similarity meets the preset similarity threshold. If so, output and call the shutdown strategy corresponding to the greatest similarity as the real-time shutdown strategy. Otherwise, repeat step B3 until the similarity threshold is met.

[0105] It should be noted that the drone parking model of this embodiment corresponds to the drone parking pre-model mentioned above, and the preset similarity threshold therein is an empirical value obtained based on the experience known to those skilled in the art. For example, if the similarity threshold is 90%, that is, the similarity of the parking environment information to the matched parking environment features in the parking environment feature database is greater than or equal to 90%, the preset similarity threshold is met, and the parking strategy corresponding to the maximum similarity is used as the real-time parking strategy.

[0106] Based on the above, this embodiment realizes the processing of real-time shutdown environment information through the UAV shutdown model, and realizes the generation of predicted shutdown ring features through generative adversarial network technology, which provides an accurate data basis for calling the shutdown strategy based on the shutdown strategy database, and reduces the shutdown preparation time through the called real-time shutdown strategy, and provides a data basis for the intelligent shutdown of the UAV.

[0107] Specifically, step S7 specifically includes:

[0108] S71: Acquire and parse the called real-time parking strategy to obtain a real-time braking strategy and a real-time landing gear release strategy;

[0109] S72: Control the power system to brake using a real-time braking strategy;

[0110] S73: Control the landing gear to release using the real-time landing gear release strategy.

[0111] Based on the above, this embodiment realizes adaptive intelligent parking through the execution of real-time braking strategy and real-time landing gear release strategy, and reduces the parking preparation time based on the parking environment characteristic data and the corresponding parking strategy database, and realizes the accuracy of rapid calling of the parking strategy database through generative adversarial network technology, thereby optimizing the quality of drone parking.

[0112] In a second aspect, this embodiment discloses Figure 2 A UAV intelligent parking landing gear system is shown, and the system is applicable to the UAV intelligent parking method as described above, and the system includes:

[0113] A first data acquisition module, the data acquisition module is configured to: acquire historical parking environment information and historical parking strategies with corresponding relationships; wherein the parking environment information at least includes terrain data and climate data, and the parking strategies at least include braking strategies and landing gear release strategies;

[0114] A shutdown environment feature database generation module, wherein the shutdown environment feature database generation module is configured to: extract features from historical shutdown environment information to generate a shutdown environment feature database; wherein the shutdown environment feature database stores different shutdown environment features;

[0115] A shutdown strategy database generation module, the shutdown strategy database generation module is configured to: generate a shutdown strategy database having a corresponding relationship with the shutdown environment feature database by using the corresponding relationship between the historical shutdown strategy and the historical shutdown environment information; wherein the shutdown strategy database stores different shutdown strategies corresponding to the shutdown environment features;

[0116] The UAV shutdown model generation module is configured to: train a preset UAV shutdown pre-model to execute a shutdown strategy corresponding to the shutdown environment information output, and generate a UAV shutdown model; wherein the preset and training of the UAV shutdown pre-model are both performed using the generative adversarial network technology, and the UAV shutdown model is configured to be a shutdown strategy corresponding to the shutdown environment information output;

[0117] A second data acquisition module, the second data acquisition module is configured to: use a preset sensor of the drone to acquire real-time shutdown environment information; wherein the preset sensor corresponds to the shutdown environment information;

[0118] The UAV shutdown model operation module is configured to: run the UAV model, receive real-time shutdown environment information, and call the corresponding real-time shutdown strategy;

[0119] The shutdown control module is configured to: control the preset power system and landing gear of the UAV to shut down the UAV based on the real-time shutdown strategy; wherein the power system is used to control the power output of the UAV shutdown process.

[0120] It should be noted that the UAV intelligent parking landing gear system of this embodiment corresponds to the UAV intelligent parking method mentioned above. Therefore, the contents not specifically described in the UAV intelligent parking landing gear system of this embodiment may include but are not limited to the function definition, working principle and technical effect, etc., which are the same as the UAV intelligent parking method mentioned above and will not be elaborated in this text.

[0121] In a third aspect, this embodiment discloses a storage medium on which a computer program is stored. When the computer program is executed by a processor, the intelligent shutdown method for the drone as described above is implemented.

[0122] Similarly, it should be noted that the storage medium of this embodiment corresponds to the drone intelligent shutdown method mentioned above. Therefore, the content not specifically described in the storage medium of this embodiment may include but is not limited to function definition, working principle and technical effect, etc., which are the same as the drone intelligent shutdown method mentioned above and will not be elaborated in this text.

[0123] In summary, the UAV intelligent shutdown method, landing gear system and storage medium of this embodiment use historical shutdown environment information and corresponding historical shutdown strategies to realize the generation of shutdown environment characteristic data and a corresponding shutdown strategy database, and use the shutdown environment characteristic data and the corresponding shutdown strategy database to realize the generation of a UAV shutdown model, and use the UAV shutdown model to realize the processing of real-time shutdown environment information, and reduce the shutdown preparation time by quickly calling the corresponding shutdown strategy in the shutdown strategy database, and realize the accuracy of the rapid call of the shutdown strategy database through the generative adversarial network technology, thereby realizing the intelligent shutdown of the UAV.

[0124] In the embodiments provided in the present application, it should be understood that the embodiments described herein can be implemented in hardware, software, firmware, middleware, code or any appropriate combination thereof. For hardware implementation, the processor can be implemented in one or more of the following units: application specific integrated circuit (ASIC), digital signal processor (DSP), digital signal processing device (DSPD), programmable logic device (PLD), field programmable gate array (FPGA), processor, controller, microcontroller, microprocessor, other electronic units designed to implement the functions described herein or their combination. For software implementation, part or all of the flow of the embodiment can be completed by instructing the relevant hardware through a computer program. When implemented, the above program can be stored in a computer-readable storage medium or transmitted as one or more instructions or codes on a computer-readable storage medium. Computer-readable storage media include computer storage media and communication media, wherein the communication medium includes any medium that is convenient for transmitting a computer program from one place to another. The storage medium can be any available medium that a computer can access. The computer-readable storage medium can include but is not limited to RAM, ROM, EEPROM, CD-ROM or other optical disk storage, disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of an instruction or data structure and can be accessed by a computer.

[0125] Finally, it should be noted that the above is only a preferred embodiment of the present application and is not intended to limit the present application. Although the present application has been described in detail with reference to the aforementioned embodiments, it is still possible for those skilled in the art to modify the technical solutions described in the aforementioned embodiments or to make equivalent substitutions for some of the technical features therein. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.

Claims

1. A drone intelligent shutdown method, characterized in that: The method includes: S1: Acquire historical parking environment information and corresponding historical parking strategies; wherein the parking environment information at least includes terrain data and climate data, and the parking strategy at least includes a braking strategy and a landing gear release strategy; S2: extracting features from the historical shutdown environment information to generate a shutdown environment feature database; wherein the shutdown environment feature database stores different shutdown environment features; S3: using the correspondence between the historical shutdown strategy and the historical shutdown environment information, generating a shutdown strategy database having a corresponding relationship with the shutdown environment feature database; wherein the shutdown strategy database stores different shutdown strategies corresponding to the shutdown environment features; S4: training a preset UAV shutdown pre-model to execute the shutdown strategy corresponding to the shutdown environment information output, and generating a UAV shutdown model; wherein the preset and training of the UAV shutdown pre-model are both performed using generative adversarial network technology, and the UAV shutdown model is configured to be based on the shutdown strategy corresponding to the shutdown environment information output; S5: using a preset sensor of the drone to obtain real-time shutdown environment information; wherein the preset sensor corresponds to the shutdown environment information; S6: running the drone model, receiving the real-time shutdown environment information, and calling the corresponding real-time shutdown strategy; S7: Based on the real-time shutdown strategy, the preset power system and landing gear of the UAV are controlled to shut down the UAV; wherein the power system is used to control the power output during the shutdown process of the UAV.

2. The intelligent shutdown method for unmanned aerial vehicles according to claim 1, characterized in that: The terrain data at least includes terrain height data and terrain slope and flatness data; The climate data includes at least wind speed, wind direction, air pressure, temperature and humidity; The braking strategy is used to control the operation of the power system; The landing gear release strategy is used to control the release of the landing gear.

3. The intelligent shutdown method for unmanned aerial vehicles according to claim 1, characterized in that: The generation process of the shutdown environment feature database includes: Extracting features from the terrain data and climate data using feature extraction technology to obtain corresponding terrain features and climate features; The database technology is used to build a database in combination with the terrain characteristics and the climate characteristics to obtain the shutdown environment characteristics database.

4. The intelligent shutdown method for unmanned aerial vehicle according to claim 3, characterized in that: The generation process of the shutdown strategy database includes: The correspondence between the historical shutdown strategy and the historical shutdown environment information is obtained, and the calling relationship between the terrain characteristics and the climate characteristics and the shutdown strategy is constructed using the correspondence. The calling relationship and the shutdown strategy are built into a database using database technology to obtain the shutdown strategy database.

5. The intelligent shutdown method for unmanned aerial vehicle according to claim 1, characterized in that: The generation process of the UAV shutdown model includes: Obtain a drone shutdown prediction model preset using generative adversarial network technology; The preset feature extraction tool, the shutdown environment feature database and the shutdown strategy database are stored in the UAV shutdown pre-model; wherein the feature extraction tool is used to extract features of the shutdown environment information; The UAV shutdown prediction model is trained using historical shutdown environment information and generative adversarial network technology to execute steps A1 to A3: A1: calling the feature extraction tool to extract features from the historical downtime environment information to obtain corresponding historical downtime environment features; A2: using the historical shutdown environment features obtained in step A1 to perform similarity matching in the shutdown environment feature database, and judging whether the historical shutdown strategy corresponding to the outputted maximum similarity meets a preset similarity threshold, if yes, output and call the historical shutdown strategy corresponding to the maximum similarity, otherwise, execute step A3; A3: Generate predicted shutdown ring features by using generative adversarial network technology and combining the historical shutdown environment features, and use the predicted shutdown features to perform similarity matching in the shutdown environment feature database, and determine whether the historical shutdown strategy corresponding to the outputted maximum similarity meets a preset similarity threshold. If yes, output and call the historical shutdown strategy corresponding to the maximum similarity, otherwise repeat step A3 until the similarity threshold is met; A drone shutdown pre-model that meets preset model training conditions is output and defined as the drone shutdown model.

6. The intelligent shutdown method for unmanned aerial vehicle according to claim 1, characterized in that: The process of acquiring the real-time shutdown environment information includes: Enable corresponding sensors to collect real-time terrain data and real-time environmental data; the sensors include at least laser radar, ultrasonic sensor and meteorological sensor; The real-time terrain data and the real-time environment data are used to generate corresponding real-time shutdown environment information.

7. The intelligent shutdown method for unmanned aerial vehicles according to claim 1, characterized in that: The calling process of the real-time shutdown strategy includes: Run the drone shutdown model to perform the following steps B1 to B3: B1: calling a preset feature extraction tool to extract features from the real-time shutdown environment information to obtain corresponding real-time shutdown environment features; B2: using the real-time shutdown environment features obtained in step B1 to perform similarity matching in the shutdown environment feature database, and judging whether the shutdown strategy corresponding to the outputted maximum similarity meets a preset similarity threshold, if yes, output and call the shutdown strategy corresponding to the maximum similarity as the real-time shutdown strategy, otherwise, execute step B3; B3: Generate predicted shutdown loop features by using generative adversarial network technology in combination with the real-time shutdown environment features, and use the predicted shutdown features to perform similarity matching in the shutdown environment feature database to determine whether the shutdown strategy corresponding to the outputted maximum similarity meets a preset similarity threshold. If so, output and call the shutdown strategy corresponding to the maximum similarity as the real-time shutdown strategy. Otherwise, repeat step B3 until the similarity threshold is met.

8. The intelligent shutdown method for unmanned aerial vehicles according to claim 1, characterized in that: Step S7 specifically includes: S71: Acquire and analyze the called real-time parking strategy to obtain a real-time braking strategy and a real-time landing gear release strategy; S72: Using the real-time braking strategy to control the power system to brake; S73: Using the real-time landing gear release strategy to control the landing gear to be released.

9. An intelligent parking landing gear system for a drone, the system being applicable to the intelligent parking method for a drone as claimed in any one of claims 1 to 8, characterized in that: The system includes: A first data acquisition module, wherein the data acquisition module is configured to: acquire historical shutdown environment information and historical shutdown strategies having a corresponding relationship; wherein the shutdown environment information at least includes terrain data and climate data, and the shutdown strategy at least includes a braking strategy and a landing gear release strategy; A shutdown environment feature database generation module, wherein the shutdown environment feature database generation module is configured to: extract features from the historical shutdown environment information to generate a shutdown environment feature database; wherein the shutdown environment feature database stores different shutdown environment features; A shutdown strategy database generation module, wherein the shutdown strategy database generation module is configured to: utilize the correspondence between the historical shutdown strategy and the historical shutdown environment information to generate a shutdown strategy database having a corresponding relationship with the shutdown environment feature database; wherein the shutdown strategy database stores different shutdown strategies corresponding to the shutdown environment features; A drone shutdown model generation module, wherein the drone shutdown model generation module is configured to: train a preset drone shutdown pre-model to execute the shutdown strategy corresponding to the shutdown environment information output, and generate a drone shutdown model; wherein the preset and training of the drone shutdown pre-model are both performed using generative adversarial network technology, and the drone shutdown model is configured to output the shutdown strategy corresponding to the shutdown environment information; A second data acquisition module, wherein the second data acquisition module is configured to: acquire real-time shutdown environment information using a sensor preset on the drone; wherein the preset sensor corresponds to the shutdown environment information; A drone shutdown model operation module, wherein the drone shutdown model operation module is configured to: run the drone model, receive the real-time shutdown environment information, and call a corresponding real-time shutdown strategy; A shutdown control module, wherein the shutdown control module is configured to: control a preset power system and landing gear of the drone to shut down the drone based on the real-time shutdown strategy; wherein the power system is used to control the power output of the drone shutdown process.

10. A storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the intelligent shutdown method for a drone as described in any one of claims 1 to 8 is implemented.

Images