A dynamic landing method and system for unmanned aerial vehicles (UAVs)

Abstract

This invention discloses a dynamic landing method and system for unmanned aerial vehicles (UAVs), relating to the field of UAV technology. Upon receiving a landing location, the system acquires the UAV's status and environmental information in real time, performs a safety assessment on the status and environmental information to obtain a safety status value, and determines whether the safety status value is greater than a preset safety threshold. If the safety status value is less than or equal to the safety threshold, the UAV is controlled to land at the landing location using a preset first control strategy based on the status and environmental information. If the safety status value is greater than the safety threshold, the UAV is controlled to land at the landing location using a preset second control strategy based on the status and environmental information. This invention solves the technical problem that most existing UAV landing control methods plan the UAV's landing path based on a global path planning algorithm, which cannot adjust the landing path in a timely manner when dynamic obstacles exist during landing, thus reducing the safety of UAV operation.

Description

Technical Field

[0001] This invention relates to the field of unmanned aerial vehicle (UAV) technology, and more particularly to a dynamic landing method and system for UAVs. Background Technology

[0002] With the rapid development of drone technology, drones are increasingly being used in logistics, agriculture, emergency rescue, military reconnaissance, and other fields. However, drones face many challenges during landing, especially in complex environments (such as cities, forests, and mountains). How to achieve safe landing of drones has become a critical issue that urgently needs to be addressed.

[0003] Currently, most existing UAV landing control methods are based on global path planning algorithms such as A* and Dijkstra's algorithm to plan the UAV's landing path. When there are dynamic obstacles during the landing process, the landing path cannot be adjusted in time, which reduces the safety of UAV operation. Summary of the Invention

[0004] This invention provides a dynamic landing method and system for unmanned aerial vehicles (UAVs), which solves the technical problem that most existing UAV landing control methods are based on global path planning algorithms such as A* algorithm and Dijkstra algorithm to plan the landing path of the UAV. When there are dynamic obstacles during the landing process, the landing path cannot be adjusted in time, which reduces the safety of UAV operation.

[0005] The first aspect of this invention provides a dynamic landing method for an unmanned aerial vehicle (UAV), comprising:

[0006] Upon receiving the landing location, the drone's status and environmental information are acquired in real time.

[0007] A security assessment is performed on the state information and the environmental information to obtain a security state value;

[0008] Determine whether the security status value is greater than a preset security threshold;

[0009] If the safety status value is less than or equal to the safety threshold, then the drone is controlled to land at the landing position according to the status information and the environmental information using a preset first control strategy.

[0010] If the safety status value is greater than the safety threshold, the drone is controlled to land at the landing location according to the status information and the environmental information using a preset second control strategy.

[0011] Optionally, the state information includes the UAV's position, flight speed, attitude angle deviation, and angular velocity; the environmental information includes the UAV's battery level and the positions of multiple obstacles; and the step of performing a safety assessment on the state information and the environmental information to obtain a safety state value includes:

[0012] Calculate the distance between the drone's position and each of the obstacle positions, and select the smallest distance value from all the distance values ​​as the target distance value;

[0013] The difference between the target distance value and the preset safety distance value is processed to obtain the first evaluation value;

[0014] The difference between the preset maximum permissible flight speed and the flight speed is processed to obtain the second evaluation value;

[0015] The third evaluation value is obtained by subtracting the preset maximum attitude angle deviation from the attitude angle deviation.

[0016] The difference between the preset maximum angular velocity and the angular velocity is processed to obtain the fourth evaluation value;

[0017] The difference between the preset power threshold and the drone's power level is calculated to obtain the fifth evaluation value;

[0018] The first evaluation value, the second evaluation value, the third evaluation value, the fourth evaluation value, and the fifth evaluation value are weighted according to the preset security evaluation weights to obtain the security status value.

[0019] Optionally, the step of controlling the UAV to land at the landing location according to the state information and the environmental information using a preset first control strategy includes:

[0020] Based on the drone's position and landing position, a first landing path is generated;

[0021] The first landing path is optimized based on a preset local path optimization algorithm, the state information, and the environmental information to obtain a first optimized path;

[0022] Control the drone to land at the landing position along the first optimized path, and obtain the flight distance of the drone in real time;

[0023] Determine whether the flight distance is greater than a preset flight threshold;

[0024] When the flight distance exceeds the flight threshold, the process jumps to the step of acquiring the real-time status and environmental information of the UAV.

[0025] Optionally, the step of controlling the UAV to land at the landing location according to the state information and the environmental information using a preset second control strategy includes:

[0026] Based on the drone's position and landing position, a second landing path is generated;

[0027] Based on the UAV detection distance and the second landing path, the local endpoint position of the UAV is determined;

[0028] The state information, the environmental information, and the local endpoint position are input into a pre-trained landing path planning model to obtain a second optimized path;

[0029] Determine whether the local endpoint location is the landing location;

[0030] If the local endpoint is the landing position, then control the UAV to land at the landing position along the second optimized path;

[0031] If the local endpoint position is not the landing position, then control the UAV to fly along the second optimized path to the local endpoint position;

[0032] When the drone reaches the local endpoint, the process jumps to the step of acquiring the drone's status information and environmental information in real time.

[0033] Optionally, the training process of the landing path planning model is as follows:

[0034] Acquire landing training data and use the landing training data to train a preset initial landing path planning model to obtain training landing path data;

[0035] Calculate the training loss function value and reward function value of the landing training data based on the training landing path data;

[0036] The training loss function value and the reward function value are weighted according to preset training weights to obtain the target loss value;

[0037] When the target loss value is greater than or equal to the preset standard loss value, the gradient descent method is used to adjust the network parameters of the initial landing path planning model, and the process jumps to the step of training the preset initial landing path planning model with the landing training data to obtain training landing path data, until the target loss value is less than the standard loss value.

[0038] When the target loss value is less than the standard loss value, a landing path planning model is generated.

[0039] Optionally, the landing path planning model is an RNN neural network model.

[0040] A second aspect of the present invention provides a dynamic landing system for an unmanned aerial vehicle (UAV), comprising:

[0041] The response module is used to obtain the drone's status and environmental information in real time when the landing location is received;

[0042] The evaluation module is used to perform a security evaluation on the status information and the environmental information to obtain a security status value;

[0043] The analysis module is used to determine whether the security status value is greater than a preset security threshold.

[0044] The first control module is used to control the UAV to land at the landing position according to the state information and the environmental information if the safety status value is less than or equal to the safety threshold.

[0045] The second control module is used to control the UAV to land at the landing location according to the status information and the environmental information based on the safety status value and the safety threshold if the safety status value is greater than the safety threshold.

[0046] A third aspect of the present invention provides an electronic device, including a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor causes the processor to perform the steps of the dynamic landing method for a drone as described in any of the preceding claims.

[0047] The fourth aspect of the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed, implements the dynamic landing method for a drone as described in any of the preceding claims.

[0048] The fifth aspect of the present invention provides a computer program product comprising a computer program stored on a non-transitory computer-readable storage medium, the computer program comprising program instructions, wherein when the program instructions are executed by a computer, the computer performs the dynamic landing method of the UAV as described in any of the preceding claims.

[0049] As can be seen from the above technical solutions, the present invention has the following advantages:

[0050] This invention improves the efficiency of UAV landing path planning by acquiring real-time UAV status and environmental information, performing safety assessments on this information to obtain a safety state value, and then selecting an appropriate control strategy based on the magnitude of the safety state value. It overcomes the technical problem that most existing UAV landing control methods rely on global path planning algorithms such as A* and Dijkstra's algorithm, which cannot adjust the landing path in time when dynamic obstacles exist during landing, thus reducing the safety of UAV operation. Compared with traditional landing control methods, this invention improves the safety of UAV operation by calculating the UAV's safety state value in real time and dynamically selecting an appropriate control strategy based on this value. Attached Figure Description

[0051] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0052] Figure 1 A flowchart illustrating the steps of a dynamic landing method for an unmanned aerial vehicle (UAV) according to Embodiment 1 of the present invention;

[0053] Figure 2 This is a flowchart illustrating the steps of a dynamic landing method for an unmanned aerial vehicle (UAV) according to Embodiment 2 of the present invention.

[0054] Figure 3 This is a structural block diagram of a dynamic landing system for an unmanned aerial vehicle (UAV) provided in Embodiment 3 of the present invention;

[0055] Figure 4 This is a structural block diagram of an electronic device provided in Embodiment 4 of the present invention. Detailed Implementation

[0056] This invention provides a dynamic landing method and system for unmanned aerial vehicles (UAVs), addressing the technical problem that most existing UAV landing control methods are based on global path planning algorithms such as A* and Dijkstra's algorithm to plan the UAV's landing path. When dynamic obstacles exist during the landing process, the landing path cannot be adjusted in time, reducing the safety of UAV operation.

[0057] To make the objectives, features, and advantages of this invention more apparent and understandable, the technical solutions of the embodiments of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the embodiments described below are only some embodiments of this invention, and not all embodiments. Based on the embodiments of this invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this invention.

[0058] Please see Figure 1 , Figure 1 This is a flowchart illustrating the steps of a dynamic landing method for an unmanned aerial vehicle (UAV) according to Embodiment 1 of the present invention.

[0059] This invention provides a dynamic landing method for a drone, comprising:

[0060] Step 101: Upon receiving the landing location, acquire the drone's status and environmental information in real time;

[0061] In this embodiment of the invention, when the UAV receives the landing location, it obtains the UAV's status information and environmental information through the multimodal perception system on the UAV.

[0062] It should be noted that the status information includes the drone's position, flight speed, attitude angle deviation, and angular velocity, while the environmental information includes the drone's battery level and the positions of multiple obstacles.

[0063] Step 102: Perform a security assessment on the status information and environmental information to obtain a security status value;

[0064] In this embodiment of the invention, the state information and environmental information are input into a preset safety assessment function to obtain a safety state value.

[0065] It should be noted that the security assessment function is as follows:

[0066]

[0067] in, This is a safe state value. The target distance value. This is a safe distance value. For the maximum permissible flight speed, For flight speed, For the maximum attitude angle deviation, For attitude angle deviation, For the maximum angular velocity, Angular velocity, This is the battery threshold. For drone battery, This is the first safety assessment weighting coefficient. This is the second safety assessment weighting coefficient. This is the third safety assessment weighting coefficient. This is the fourth safety assessment weighting coefficient. This is the fifth safety assessment weighting coefficient.

[0068] Step 103: Determine whether the safety status value is greater than the preset safety threshold;

[0069] In this embodiment of the invention, it is determined whether the safety status value is greater than a preset safety threshold.

[0070] Step 104: If the safety status value is less than or equal to the safety threshold, then control the drone to land at the landing position according to the status information and environmental information using the preset first control strategy.

[0071] In this embodiment of the invention, when the safety status value is less than or equal to the safety threshold, a first landing path is determined based on the drone's position and landing position in the status information. The first landing path is then optimized based on a preset local path optimization algorithm, status information, and environmental information to obtain a first optimized path. The drone is controlled to land along the first optimized path to the landing position, and the drone's flight distance is obtained in real time. When the flight distance is greater than the flight threshold, the process jumps to step 101.

[0072] Step 105: If the safety status value is greater than the safety threshold, then control the drone to land at the landing position according to the status information and environmental information using the preset second control strategy.

[0073] In this embodiment of the invention, when the safety status value is greater than the safety threshold, a second landing path is determined based on the UAV position and landing position of the status information. The local endpoint position of the UAV is determined based on the UAV detection distance of the status information and the second landing path. The status information, environmental information and local endpoint position are input into the pre-trained landing path planning model to obtain the second optimized path. It is determined whether the local endpoint position is the landing position. If the local endpoint position is the landing position, the UAV is controlled to land along the second optimized path to the landing position. If the local endpoint position is not the landing position, the UAV is controlled to fly along the second optimized path to the local endpoint position, and the process jumps to step 101.

[0074] In this embodiment of the invention, by acquiring the UAV's status and environmental information in real time and performing a safety assessment on the status and environmental information to obtain a safety status value, an appropriate control strategy is selected based on the magnitude of the safety status value to plan the UAV's landing path, thereby improving the efficiency of UAV landing path planning. This overcomes the technical problem that most existing UAV landing control methods rely on global path planning algorithms such as A* and Dijkstra's algorithm, which cannot adjust the landing path in time when dynamic obstacles exist during landing, thus reducing the safety of UAV operation. Compared with traditional landing control methods, this invention improves the safety of UAV operation by calculating the UAV's safety status value in real time and dynamically selecting an appropriate control strategy to plan the UAV path based on the safety status value.

[0075] Please see Figure 2 , Figure 2 This is a flowchart illustrating the steps of a dynamic landing method for an unmanned aerial vehicle (UAV) according to Embodiment 2 of the present invention.

[0076] This invention provides a dynamic landing method for a drone, comprising:

[0077] Step 201: Upon receiving the landing location, acquire the drone's status and environmental information in real time;

[0078] In this embodiment of the invention, when the landing location is received, the status information and environmental information of the UAV are obtained in real time through a multimodal perception system.

[0079] It should be noted that the multimodal perception system includes a four-spectral polarization imaging unit and an electromagnetic field compensation module. The four-spectral polarization imaging unit acquires the initial UAV position, flight speed, attitude angle deviation, angular velocity, UAV battery level, electromagnetic field change rate, and the positions of multiple obstacles. The electromagnetic field compensation module is used to input the initial UAV position and electromagnetic field change rate into a preset electromagnetic field compensation function to obtain the UAV position.

[0080] The electromagnetic field compensation function is as follows:

[0081]

[0082] in, Location of the drone. The initial drone position, For the current time, The initial time, For compensation amount, This is the electromagnetic compensation gain coefficient. The rate of change of the electromagnetic field, It is an electromagnetic field.

[0083] Step 202: Perform a security assessment on the status information and environmental information to obtain a security status value;

[0084] Furthermore, the status information includes the drone's position, flight speed, attitude angle deviation, and angular velocity; the environmental information includes the drone's battery level and the positions of multiple obstacles. Step 202 includes the following sub-steps:

[0085] S11. Calculate the distance between the UAV's position and the positions of each obstacle, and select the smallest distance value from all the distance values ​​as the target distance value;

[0086] In this embodiment of the invention, the distance values ​​between the drone's position and the positions of each obstacle are calculated, and the smallest distance value is selected from all the distance values ​​as the target distance value.

[0087] S12. Perform difference processing between the target distance value and the preset safety distance value to obtain the first evaluation value;

[0088] In this embodiment of the invention, the difference between the target distance value and the preset safe distance value is calculated to obtain a first evaluation value.

[0089] It should be noted that the preset safe distance value is determined based on the size of the drone, its flight speed, and the complexity of the operating environment.

[0090] S13. The difference between the preset maximum allowable flight speed and the flight speed is processed to obtain the second evaluation value;

[0091] In this embodiment of the invention, the difference between the preset maximum permissible flight speed and the actual flight speed is calculated to obtain a second evaluation value. The maximum permissible flight speed is determined by the hardware performance and design requirements of the UAV.

[0092] S14. The difference between the preset maximum attitude angle deviation and the attitude angle deviation is processed to obtain the third evaluation value;

[0093] In this embodiment of the invention, the difference between the preset maximum attitude angle deviation and the attitude angle deviation is calculated to obtain the third evaluation value.

[0094] S15. The difference between the preset maximum angular velocity and the angular velocity is processed to obtain the fourth evaluation value;

[0095] In this embodiment of the invention, the difference between the preset maximum angular velocity and the angular velocity is calculated to obtain the fourth evaluation value.

[0096] S16. The difference between the preset power threshold and the drone's power level is processed to obtain the fifth evaluation value;

[0097] In this embodiment of the invention, the difference between a preset power threshold and the drone's power level is calculated to obtain a fifth evaluation value.

[0098] It should be noted that the battery threshold refers to the minimum safe battery level for the drone.

[0099] S17. The first evaluation value, the second evaluation value, the third evaluation value, the fourth evaluation value and the fifth evaluation value are weighted according to the preset safety evaluation weights to obtain the safety status value.

[0100] In this embodiment of the invention, the first evaluation value, the second evaluation value, the third evaluation value, the fourth evaluation value, and the fifth evaluation value are weighted according to a preset full evaluation weight to obtain a safety status value. The safety evaluation weight includes a first safety evaluation weight coefficient, a second safety evaluation weight coefficient, a third safety evaluation weight coefficient, a fourth safety evaluation weight coefficient, and a fifth safety evaluation weight coefficient.

[0101] Step 203: Determine whether the safety status value is greater than the preset safety threshold;

[0102] In this embodiment of the invention, it is determined whether the safety status value is greater than a preset safety threshold.

[0103] Step 204: If the safety status value is less than or equal to the safety threshold, then generate the first landing path based on the drone's position and landing position in the status information;

[0104] In this embodiment of the invention, when the safety status value is less than or equal to the safety threshold, a first landing path is generated based on the drone's position and landing position in the status information. The first landing path is a straight line from the drone's position to the landing position (regardless of whether it will pass through obstacles).

[0105] Step 205: Optimize the first landing path based on the preset local path optimization algorithm, state information and environmental information to obtain the first optimized path;

[0106] In this embodiment of the invention, a first landing path is optimized based on a preset local path optimization algorithm, taking into account state information and environmental information, to obtain a first optimized path. The local path optimization algorithm includes Dynamic Window (DWA), Artificial Potential Field (APF), Rapid Exploratory Random Tree (RRT) series, Probabilistic Roadmap (PRM), Model Predictive Control (MPC), APF+RRT / MPC* method, and DRL+Traditional Planning.

[0107] Step 206: Control the drone to land at the landing position along the first optimized path and obtain the drone's flight distance in real time;

[0108] In this embodiment of the invention, the drone is controlled to land at the landing position according to the first optimized path, and the flight distance of the drone is obtained in real time.

[0109] Step 207: Determine whether the flight distance is greater than the preset flight threshold;

[0110] In this embodiment of the invention, it is determined whether the flight distance is greater than a preset flight threshold.

[0111] Step 208: When the flight distance is greater than the flight threshold, proceed to the step of obtaining the drone's status information and environmental information in real time.

[0112] In this embodiment of the invention, when the flight distance is greater than the flight threshold, the process jumps to step 201.

[0113] Step 209: If the safety status value is greater than the safety threshold, then control the drone to land at the landing position according to the status information and environmental information using the preset second control strategy.

[0114] Furthermore, step 209 includes the following sub-steps:

[0115] S21. Generate a second landing path based on the drone's position and landing location in the status information;

[0116] In this embodiment of the invention, a second landing path is generated based on the drone's position and landing position, according to the status information. The second landing path is a straight line from the drone's position to the landing position (regardless of whether it will pass through obstacles).

[0117] S22. Based on the state information, the UAV detects the distance and the second landing path to determine the local endpoint position of the UAV.

[0118] In this embodiment of the invention: 1. The drone detection distance based on the status information is used as the target selection distance. 2. Based on the target selection distance, the point on the second landing path that is furthest from the drone's current distance is selected as the local endpoint position. 3. If the local endpoint position coincides with the obstacle position, the target selection distance is reduced by half as the new target selection distance. 4. Step 2 is repeated until the selected local endpoint position does not coincide with the obstacle position.

[0119] It should be noted that the local endpoints are all located on the second landing path.

[0120] S23. Input the state information, environmental information, and local endpoint position into the pre-trained landing path planning model to obtain the second optimized path;

[0121] In this embodiment of the invention, state information, environmental information, and local endpoint location are used as inputs to a pre-trained landing path planning model to obtain a second optimized path.

[0122] It should be noted that the landing path planning model is an RNN neural network model.

[0123] It should be noted that the training process of the landing path planning model is as follows:

[0124] A1. Obtain landing training data and use the landing training data to train the preset initial landing path planning model to obtain training landing path data.

[0125] Landing training data refers to the historical trajectory data of drone landings.

[0126] In this embodiment of the invention, historical trajectory data of UAV landing is obtained, and the historical trajectory data is used to train a preset initial landing path planning model to obtain training landing path data.

[0127] A2. Calculate the training loss function value and reward function value of the landing training data based on the training landing path data;

[0128] In this embodiment of the invention, training landing path data and landing training data are input into a preset loss function to obtain a training loss function value. The training landing path data and landing training data are then input into a preset reward function to obtain a reward function value. The reward function value is the sum of the reward values ​​at each time step.

[0129] It should be noted that the loss function is as follows:

[0130]

[0131] in, To train the loss function values, For the sample size, For the action of the i-th expert, For the i-th predicted action, Let i be the state of the i-th expert. Let i be the predicted state of the i-th sample, where i is the sample number.

[0132] It should be noted that the reward function is as follows:

[0133]

[0134] in, Let be the reward value at time t. Let t be the position of the drone. The target landing location, This represents the distance between the drone and the obstacle.

[0135] A3. The training loss function value and reward function value are weighted according to the preset training weights to obtain the target loss value;

[0136] In this embodiment of the invention, the training loss function value and the reward function value are weighted according to preset training weights to obtain the target loss value, wherein the training weights include loss weight coefficients and reward weight coefficients.

[0137] A4. When the target loss value is greater than or equal to the preset standard loss value, the gradient descent method is used to adjust the network parameters of the initial landing path planning model, and the process jumps to the step of training the preset initial landing path planning model with landing training data to obtain training landing path data, until the target loss value is less than the standard loss value.

[0138] In this embodiment of the invention, when the target loss value is greater than or equal to the preset standard loss value, the gradient descent method is used to adjust the network parameters of the initial landing path planning model, and the execution jumps to A1 until the target loss value is less than the standard loss value.

[0139] A5. When the target loss value is less than the standard loss value, a landing path planning model is generated.

[0140] In this embodiment of the invention, when the target loss value is less than the standard loss value, a landing path planning model is generated.

[0141] S24. Determine whether the local endpoint position is the landing position;

[0142] In this embodiment of the invention, it is determined whether the local endpoint position coincides with the landing position.

[0143] S25. If the local endpoint is the landing position, then control the UAV to land along the second optimized path to the landing position;

[0144] In this embodiment of the invention, if the local endpoint position coincides with the landing position, the drone is controlled to land at the landing position along the second optimized path.

[0145] S26. If the local endpoint position is not the landing position, control the UAV to fly along the second optimized path to the local endpoint position.

[0146] In this embodiment of the invention, if the local endpoint position does not coincide with the landing position, the UAV is controlled to fly along the second optimized path to the local endpoint position.

[0147] S27. When the drone reaches the local endpoint, proceed to the step of acquiring the drone's status information and environmental information in real time.

[0148] In this embodiment of the invention, when the drone flies to the local endpoint position, it jumps to step 201.

[0149] In this embodiment of the invention, by acquiring the UAV's status and environmental information in real time and performing a safety assessment on the status and environmental information to obtain a safety status value, an appropriate control strategy is selected based on the magnitude of the safety status value to plan the UAV's landing path, thereby improving the efficiency of UAV landing path planning. This overcomes the technical problem that most existing UAV landing control methods rely on global path planning algorithms such as A* and Dijkstra's algorithm, which cannot adjust the landing path in time when dynamic obstacles exist during landing, thus reducing the safety of UAV operation. Compared with traditional landing control methods, this invention improves the safety of UAV operation by calculating the UAV's safety status value in real time and dynamically selecting an appropriate control strategy to plan the UAV path based on the safety status value.

[0150] Please see Figure 3 , Figure 3 This is a structural block diagram of a dynamic landing system for an unmanned aerial vehicle (UAV) provided in Embodiment 3 of the present invention.

[0151] This invention provides a dynamic landing system for unmanned aerial vehicles (UAVs), comprising:

[0152] The response module 301 is used to acquire the drone's status and environmental information in real time when the landing location is received.

[0153] The assessment module 302 is used to perform a safety assessment on the status information and environmental information to obtain a safety status value.

[0154] Analysis module 303 is used to determine whether the safety status value is greater than a preset safety threshold;

[0155] The first control module 304 is used to control the drone to land at the landing position according to the status information and environmental information based on the safety status value and the safety threshold if the safety status value is less than or equal to the safety threshold.

[0156] The second control module 305 is used to control the UAV to land at the landing position according to the status information and environmental information based on the safety status value and the safety threshold.

[0157] Furthermore, the status information includes the drone's position, flight speed, attitude angle deviation, and angular velocity; the environmental information includes the drone's battery level and the positions of multiple obstacles; and the evaluation module 302 includes:

[0158] The ranging submodule is used to calculate the distance between the UAV's position and the positions of each obstacle, and select the smallest distance value from all the distance values ​​as the target distance value.

[0159] The evaluation submodule is used to perform difference processing between the target distance value and the preset safety distance value to obtain the first evaluation value;

[0160] The second evaluation value is obtained by taking the difference between the preset maximum allowable flight speed and the actual flight speed.

[0161] The third evaluation value is obtained by subtracting the preset maximum attitude angle deviation from the attitude angle deviation.

[0162] The fourth evaluation value is obtained by processing the difference between the preset maximum angular velocity and the angular velocity;

[0163] The difference between the preset battery threshold and the drone's battery level is calculated to obtain the fifth evaluation value;

[0164] The first weighted submodule is used to perform weighted calculations on the first evaluation value, the second evaluation value, the third evaluation value, the fourth evaluation value, and the fifth evaluation value according to the preset security evaluation weights, so as to obtain the security status value.

[0165] Furthermore, the first control module 304 includes:

[0166] The first landing path submodule is used to generate the first landing path based on the UAV's position and landing position in the status information;

[0167] The first optimization submodule is used to optimize the first landing path based on a preset local path optimization algorithm, state information and environmental information to obtain the first optimized path;

[0168] The first control submodule is used to control the UAV to land along the first optimized path to the landing position and to obtain the flight distance of the UAV in real time.

[0169] The first analysis submodule is used to determine whether the flight distance is greater than the preset flight threshold.

[0170] When the flight distance exceeds the flight threshold, the process will jump to the step of acquiring the drone's status and environmental information in real time.

[0171] Furthermore, the second control module 305 includes:

[0172] The second landing path submodule is used to generate a second landing path based on the UAV's position and landing position in the status information.

[0173] The local endpoint submodule is used to determine the local endpoint position of the UAV based on the UAV's detection range and second landing path, using state information.

[0174] The second optimization submodule is used to input state information, environmental information, and local endpoint position into a pre-trained landing path planning model to obtain the second optimized path;

[0175] The second analysis submodule is used to determine whether the local endpoint location is the landing location;

[0176] If the local endpoint is the landing position, then control the drone to land along the second optimized path to the landing position;

[0177] If the local endpoint is not the landing position, then control the UAV to fly along the second optimized path to the local endpoint.

[0178] When the drone reaches the local endpoint, the process jumps to the step of acquiring the drone's status and environmental information in real time.

[0179] Furthermore, the training process of the landing path planning model is as follows:

[0180] Acquire landing training data and use the landing training data to train the preset initial landing path planning model to obtain training landing path data;

[0181] Calculate the training loss function value and reward function value of the landing training data based on the training landing path data;

[0182] The training loss function value and reward function value are weighted according to the preset training weights to obtain the target loss value;

[0183] When the target loss value is greater than or equal to the preset standard loss value, the gradient descent method is used to adjust the network parameters of the initial landing path planning model, and the process jumps to the step of training the preset initial landing path planning model with landing training data to obtain training landing path data, until the target loss value is less than the standard loss value.

[0184] When the target loss value is less than the standard loss value, a landing path planning model is generated.

[0185] Furthermore, the landing path planning model is an RNN neural network model.

[0186] Please see Figure 4 , Figure 4 This is a structural block diagram of an electronic device provided in Embodiment 4 of the present invention.

[0187] An electronic device according to an embodiment of the present invention includes: a memory 401 and a processor 402. The memory 402 stores a computer program. When the computer program is executed by the processor 402, the processor 402 executes the dynamic landing method of the UAV as described in any of the above embodiments.

[0188] Memory 401 may be an electronic memory such as flash memory, EEPROM (Electrically Erasable Programmable Read-Only Memory), EPROM, hard disk, or ROM. Memory 401 has storage space 403 for program code 413 for performing any of the method steps described above. For example, storage space 403 for program code may include individual program codes 413 for implementing the various steps in the methods described above. This program code may be read from or written to one or more computer program products. These computer program products include program code carriers such as hard disks, compact discs (CDs), memory cards, or floppy disks. The program code may be compressed, for example, in a suitable form. When run by a computing processing device, this code causes the computing processing device to perform the various steps in the methods described above.

[0189] Embodiment 5 of the present invention also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the dynamic landing method of the UAV as described in any of the above embodiments.

[0190] Embodiment 6 of the present invention also provides a computer program product, which includes a computer program stored on a non-transitory computer-readable storage medium. The computer program includes program instructions, wherein when the program instructions are executed by a computer, the computer performs the dynamic landing method of the UAV as described in any of the above embodiments.

[0191] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0192] In the several embodiments provided in this application, 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, or indirect coupling or communication connection between apparatuses or units, and may be electrical, mechanical, or other forms.

[0193] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0194] Furthermore, the functional units in the various embodiments of the present invention 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 as a software functional unit.

[0195] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0196] The above embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A dynamic landing method of a UAV, characterized in that, The application relates to a method for controlling a UAV to land, comprising the following steps: acquiring state information and environment information of the UAV in real time when receiving a landing position; safety evaluating the state information and the environment information to obtain a safety state value; judging whether the safety state value is greater than a preset safety threshold value; if the safety state value is less than or equal to the safety threshold value, controlling the UAV to land to the landing position according to the state information and the environment information in a preset first control strategy; if the safety state value is greater than the safety threshold value, controlling the UAV to land to the landing position according to the state information and the environment information in a preset second control strategy; the state information comprises a UAV position, a flight speed, an attitude angle deviation and an angular velocity, and the environment information comprises a UAV power and a plurality of obstacle positions, the step of safety evaluating the state information and the environment information to obtain a safety state value comprises the following steps: respectively calculating distance values between the UAV position and each of the obstacle positions, and selecting a minimum distance value from the distance values as a target distance value; differentially processing the target distance value and a preset safety distance value to obtain a first evaluation value; differentially processing a preset maximum allowed flight speed and the flight speed to obtain a second evaluation value; differentially processing a preset maximum attitude angle deviation and the attitude angle deviation to obtain a third evaluation value; differentially processing a preset maximum angular velocity and the angular velocity to obtain a fourth evaluation value; differentially processing a preset power threshold value and the UAV power to obtain a fifth evaluation value; weighting the first evaluation value, the second evaluation value, the third evaluation value, the fourth evaluation value and the fifth evaluation value according to a preset safety evaluation weight to obtain a safety state value; the step of controlling the UAV to land to the landing position according to the state information and the environment information in a preset first control strategy comprises the following steps: generating a first landing path according to the UAV position in the state information and the landing position; optimizing the first landing path based on a preset local path optimization algorithm, the state information and the environment information to obtain a first optimized path; controlling the UAV to land to the landing position along the first optimized path and acquiring a flight distance of the UAV in real time; judging whether the flight distance is greater than a preset flight threshold value; when the flight distance is greater than the flight threshold value, jumping to the step of acquiring the state information and the environment information of the UAV in real time; the step of controlling the UAV to land to the landing position according to the state information and the environment information in a preset second control strategy comprises the following steps: generating a second landing path according to the UAV position in the state information and the landing position; determining a local terminal position of the UAV based on a UAV detection distance in the state information and the second landing path; the step of determining the local terminal position of the UAV based on the UAV detection distance in the state information and the second landing path comprises the following steps: The UAV detection distance of the state information is taken as a selected target distance; and a point farthest from the current distance of the UAV on the second landing path is taken as a local end position according to the selected target distance; When the local end position coincides with the obstacle position, the selected target distance is reduced by half as a new selected target distance, and the step of taking a point farthest from the current distance of the UAV on the second landing path as a local end position according to the selected target distance is executed again until the local end position does not coincide with the obstacle position; The state information, the environment information and the local end position are input into a pre-trained landing path planning model to obtain a second optimized path; It is judged whether the local end position is the landing position; If the local end position is the landing position, the UAV is controlled to land at the landing position along the second optimized path; If the local end position is not the landing position, the UAV is controlled to fly to the local end position along the second optimized path; When the UAV reaches the local end position, the step of acquiring the state information and the environment information of the UAV in real time is executed again. 2.The dynamic landing method of the UAV of claim 1, wherein, The training process of the landing path planning model is specifically as follows: Landing training data is acquired, and the landing training data is used to train a preset initial landing path planning model to obtain training landing path data; A training loss function value and a reward function value of the landing training data are calculated according to the training landing path data; A target loss value is obtained by performing weighted calculation on the training loss function value and the reward function value according to a preset training weight; When the target loss value is greater than or equal to a preset standard loss value, the network parameters of the initial landing path planning model are adjusted by using a gradient descent method, and the step of training the preset initial landing path planning model by using the landing training data to obtain the training landing path data is executed again until the target loss value is less than the standard loss value; When the target loss value is less than the standard loss value, a landing path planning model is generated. 3.The dynamic landing method of the UAV of claim 1, wherein, The landing path planning model is an RNN neural network model.

4. A dynamic landing system for a drone, the system comprising: The dynamic landing method of the UAV according to any one of claims 1-3 comprises: a response module configured to acquire state information and environment information of the UAV in real time when a landing position is received; an evaluation module configured to perform safety evaluation on the state information and the environment information to obtain a safety state value; an analysis module configured to judge whether the safety state value is greater than a preset safety threshold; a first control module configured to control the UAV to land at the landing position according to the state information and the environment information in a preset first control strategy if the safety state value is less than or equal to the safety threshold; a second control module configured to control the UAV to land at the landing position according to the state information and the environment information in a preset second control strategy if the safety state value is greater than the safety threshold.

5. An electronic device, comprising: An unmanned aerial vehicle comprising a memory having stored therein a computer program, and a processor, wherein the computer program is executed by the processor to cause the processor to perform the steps of the dynamic landing method of any one of claims 1-3.

6. A computer-readable storage medium having stored thereon a computer program, characterized in that, The computer program, when executed, implements the dynamic landing method of any one of claims 1-3.

7. A computer program product, characterised in that, The computer program product comprises a computer program stored on a non-transitory computer-readable storage medium, the computer program comprising program instructions, wherein the program instructions, when executed by a computer, cause the computer to perform the dynamic landing method of any one of claims 1-3.

Images