WO2022016534A1

WO2022016534A1 - Flight control method of unmanned aerial vehicle and unmanned aerial vehicle

Info

Publication number: WO2022016534A1
Application number: PCT/CN2020/104527
Authority: WO
Inventors: 许天野; 赵力尧
Original assignee: 深圳市大疆创新科技有限公司
Priority date: 2020-07-24
Filing date: 2020-07-24
Publication date: 2022-01-27
Also published as: CN113795805A; CN113795805B

Abstract

Provided are a flight control method of an unmanned aerial vehicle and the unmanned aerial vehicle. The flight control method of the unmanned aerial vehicle comprises: in a flight process of an unmanned aerial vehicle, if it is detected that communication connection between the unmanned aerial vehicle and a control device of the unmanned aerial vehicle is interrupted, controlling the unmanned aerial vehicle to fly back along a flight track before the interruption of the communication connection, and detecting whether the communication connection is restored (S301); determining, in the process of flying back, whether a return condition is satisfied (S302); if the return condition is not satisfied and it is detected that the communication connection is restored, controlling the unmanned aerial vehicle to fly in response to a control instruction of the control device (S303); and if the return condition is satisfied, controlling the unmanned aerial vehicle to fly to a return point (S304). The flight control method improves the autonomy of the unmanned aerial vehicle to solve problems in a missing scenario.

Description

UAV flight control method and UAV

technical field

The embodiments of the present application relate to the technical field of unmanned aerial vehicles, and in particular, to a flight control method of an unmanned aerial vehicle and an unmanned aerial vehicle.

Background technique

The drone may experience abnormal status during flight, for example, disconnecting from the remote control. Usually, the drone sits in place and waits for the user to adjust the angle of the remote control antenna to restore the connection. This solution leads to the lack of autonomy of the UAV, and the UAV is less effective in getting out of trouble when dealing with abnormal conditions.

SUMMARY OF THE INVENTION

The embodiments of the present application provide a flight control method for an unmanned aerial vehicle and an unmanned aerial vehicle, which improve the autonomy of the unmanned aerial vehicle to solve problems in a disconnected scenario.

In a first aspect, an embodiment of the present application provides a method for controlling the flight of an unmanned aerial vehicle, including:

During the flight of the UAV, if it is detected that the communication connection between the UAV and the control device of the UAV is interrupted, the UAV is controlled to fly back along the flight trajectory before the communication connection is interrupted, and detecting whether the communication connection is restored;

Judging whether the return-to-home condition is met during the retrospective flight;

If the return-to-home condition is not met and it is detected that the communication connection is restored, control the drone to fly in response to the control command of the control device;

If the return-to-home condition is satisfied, the drone is controlled to fly to the return point.

In a second aspect, an embodiment of the present application provides an unmanned aerial vehicle, including: a memory, a processor, and a transceiver;

the transceiver for communicating with other devices;

the memory for storing program codes;

The processor calls the program code, and when the program code is executed, is configured to perform the following operations:

In a third aspect, an embodiment of the present application provides a computer-readable storage medium, where a computer program is stored in the readable storage medium, and when the computer program is executed, the method provided in the first aspect is implemented.

Embodiments of the present application provide a flight control method for an unmanned aerial vehicle and an unmanned aerial vehicle, which are suitable for scenarios where the communication connection with the control device is interrupted during the flight of the unmanned aerial vehicle. By controlling the UAV to fly back along the flight trajectory before the communication connection was interrupted, detecting whether the communication connection is restored and whether the return-to-home condition is met, and controlling the flight of the UAV according to the detection result, the UAV in the UAV disconnection scenario is improved. Problem-solving autonomy.

Description of drawings

1 is a schematic architecture diagram of an unmanned aerial system according to an embodiment of the present application;

FIG. 2 is a schematic diagram of an application scenario provided by an embodiment of the present application;

3 is a flowchart of a method for controlling the flight of an unmanned aerial vehicle provided by an embodiment of the present application;

4 is a schematic diagram of a flight trajectory provided by an embodiment of the present application;

5 is another flowchart of a method for controlling the flight of an unmanned aerial vehicle provided by an embodiment of the present application;

6 is a schematic diagram of a UAV retrospective flight provided by an embodiment of the present application;

7 is another schematic diagram of the UAV retrospective flight provided by an embodiment of the present application;

8 is another flowchart of a method for controlling the flight of an unmanned aerial vehicle provided by an embodiment of the present application;

9A to 9C are schematic diagrams of drone flight provided by an embodiment of the present application;

FIG. 10 is a schematic structural diagram of an unmanned aerial vehicle provided by an embodiment of the present application.

detailed description

The embodiments of the present application are described below with reference to the accompanying drawings.

FIG. 1 is a schematic architectural diagram of an unmanned aerial system according to an embodiment of the present application. This embodiment is described by taking a rotor unmanned aerial vehicle as an example.

The unmanned aerial system 100 may include an unmanned aerial vehicle 110 , a display device 130 and a control terminal 140 . The unmanned aerial vehicle 110 may include a power system 150, a flight control system 160, a frame, and a gimbal 120 carried on the frame. The UAV 110 may wirelessly communicate with the control terminal 140 and the display device 130 . The unmanned aerial vehicle 110 further includes a battery (not shown in the figure), and the battery provides power for the power system 150 . The unmanned aerial vehicle 110 may be an agricultural drone or an industrial application drone, and there is a need for cyclic operation. Correspondingly, the battery also needs to be cycled.

The frame may include a fuselage and a foot stand (also known as a landing gear). The fuselage may include a center frame and one or more arms connected to the center frame, the one or more arms extending radially from the center frame. The tripod is connected with the fuselage, and is used for supporting when the UAV 110 is landed.

The power system 150 may include one or more electronic governors (referred to as ESCs for short) 151, one or more propellers 153, and one or more electric motors 152 corresponding to the one or more propellers 153, wherein the electric motors 152 are connected to the Between the electronic governor 151 and the propeller 153, the motor 152 and the propeller 153 are arranged on the arm of the unmanned aerial vehicle 110; the electronic governor 151 is used to receive the driving signal generated by the flight control system 160, and provide driving according to the driving signal Electric current is supplied to the motor 152 to control the rotational speed of the motor 152 . The motor 152 is used to drive the propeller to rotate, thereby providing power for the flight of the UAV 110, and the power enables the UAV 110 to achieve one or more degrees of freedom movement. In certain embodiments, UAV 110 may rotate about one or more axes of rotation. For example, the above-mentioned rotation axis may include a roll axis (Roll), a yaw axis (Yaw), and a pitch axis (pitch). It should be understood that the motor 152 may be a DC motor or an AC motor. In addition, the motor 152 may be a brushless motor or a brushed motor.

Flight control system 160 may include flight controller 161 and sensing system 162 . The sensing system 162 is used to measure the attitude information of the UAV, that is, the position information and state information of the UAV 110 in space, such as three-dimensional position, three-dimensional angle, three-dimensional velocity, three-dimensional acceleration and three-dimensional angular velocity. The sensing system 162 may include, for example, at least one of sensors such as a gyroscope, an ultrasonic sensor, an electronic compass, an inertial measurement unit (IMU), a vision sensor, a global navigation satellite system, and a barometer. For example, the global navigation satellite system may be the Global Positioning System (GPS). The flight controller 161 is used to control the flight of the UAV 110 , for example, the flight of the UAV 110 can be controlled according to the attitude information measured by the sensing system 162 . It should be understood that the flight controller 161 can control the UAV 110 according to pre-programmed instructions, and can also control the UAV 110 by responding to one or more remote control signals from the control terminal 140.

The pan/tilt head 120 may include a motor 122 . The PTZ is used to carry a payload, and the payload can be, for example, a photographing device 123 . The flight controller 161 can control the movement of the gimbal 120 through the motor 122 . Optionally, as another embodiment, the pan/tilt 120 may further include a controller for controlling the movement of the pan/tilt 120 by controlling the motor 122 . It should be understood that the gimbal 120 may be independent of the UAV 110 , or may be a part of the UAV 110 . It should be understood that the motor 122 may be a DC motor or an AC motor. In addition, the motor 122 may be a brushless motor or a brushed motor. It should also be understood that the gimbal may be located on the top of the UAV, or may be located on the bottom of the UAV.

The photographing device 123 may be, for example, a device for capturing images such as a camera or a video camera, and the photographing device 123 may communicate with the flight controller and perform photography under the control of the flight controller. The photographing device 123 in this embodiment at least includes a photosensitive element, such as a complementary metal oxide semiconductor (Complementary Metal Oxide Semiconductor, CMOS) sensor or a charge-coupled device (Charge-coupled Device, CCD) sensor. It can be understood that the photographing device 123 can also be directly fixed on the unmanned aerial vehicle 110, so that the gimbal 120 can be omitted.

The display device 130 is located at the ground end of the unmanned aerial vehicle 100 , can communicate with the unmanned aerial vehicle 110 in a wireless manner, and can be used to display the attitude information of the unmanned aerial vehicle 110 . In addition, the image captured by the capturing device 123 may also be displayed on the display device 130 . It should be understood that the display device 130 may be an independent device, or may be integrated into the control terminal 140 .

The control terminal 140 is located at the ground end of the unmanned aerial vehicle system 100 , and can communicate with the unmanned aerial vehicle 110 in a wireless manner, so as to remotely control the unmanned aerial vehicle 110 .

It should be understood that the above naming of the components of the unmanned aerial system is only for the purpose of identification, and should not be construed as a limitation on the embodiments of the present application.

FIG. 2 is a schematic diagram of an application scenario provided by an embodiment of the present application. As shown in FIG. 2 , FIG. 2 shows an unmanned aerial vehicle 201 and a control terminal 202 of the unmanned aerial vehicle. The control terminal 202 of the UAV 201 may be one or more of a remote controller, a smart phone, a desktop computer, a laptop computer, and a wearable device (watch, wristband). The embodiments of the present application take that the control terminal 202 is a remote controller 2021 and a terminal device 2022 as an example for schematic illustration. The terminal device 2022 is, for example, a smart phone, a wearable device, a tablet computer, etc., but the embodiment of the present application is not limited thereto.

The remote controller 2021 can communicate with the unmanned aerial vehicle 201, and the user can control the flight state of the unmanned aerial vehicle 201 by manipulating the joystick on the remote controller. The control stick and the throttle control stick respectively control the aircraft to fly forward and backward, turn the heading, fly left and right, and fly up and down, and the stick amounts in each direction are independent of each other, and the control is decoupled. Four physical control sticks can be set on the remote control 2021, namely the pitch control stick, the yaw control stick, the roll control stick and the throttle control stick are four physically independent control sticks; or, on the remote control 2021 Two physical joysticks can be set, and each physical joystick can implement the functions of two joysticks. The remote controller 2021 is specifically provided with several solid joysticks, which is not limited in this embodiment.

The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are 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 those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present application.

FIG. 3 is a flowchart of a flight control method for an unmanned aerial vehicle provided by an embodiment of the present application. In the flight control method for an unmanned aerial vehicle provided by this embodiment, the execution subject may be an unmanned aerial vehicle. As shown in FIG. 3 , the flight control method of the UAV provided by this embodiment may include:

S301. During the flight of the UAV, if it is detected that the communication connection between the UAV and the control device of the UAV is interrupted, control the UAV to fly back along the flight trajectory before the communication connection is interrupted, and detect whether the communication connection is recover.

Specifically, the drone needs to detect whether the communication connection with the control device of the drone is interrupted during the flight. If it is interrupted, it means that the communication environment of the current position of the drone is poor, such as the signal is blocked, or the distance between the drone and the control device is far, etc. At this time, control the flight of the drone along the flight before the communication connection is interrupted. The trajectory is backtracked, and during the backtracking flight, it is detected whether the communication connection with the control device is restored.

By flying back along the flight trajectory, compared with the existing technology in which the UAV waits in place, the success rate of restoring the communication connection between the UAV and the control device is improved, and the failure of the UAV to be interrupted in communication with the control device is improved. The autonomy of solving problems in the scene improves the effect of getting out of trouble.

The method for detecting whether the communication connection is interrupted is not limited in this embodiment. Optionally, the drone may periodically send detection signals to the control device, and correspondingly, periodically receive response signals sent by the control device. If the response signal sent by the control device is not continuously received within the time period T1, it can be determined that the communication connection between the drone and the control device is interrupted. The detection period is not limited in this embodiment, and can be set according to the type of the drone and the flight environment of the drone. For example, in a scene with many occlusions in the woods, a smaller detection period can be set. In a scene with few occluders, a larger detection period can be set. Optionally, the control device may periodically send a detection signal to the drone, and correspondingly, the drone periodically sends a response signal to the control device.

The method for detecting whether the communication connection is restored is not limited in this embodiment. Optionally, the drone can periodically send detection signals to the control device. If the response signal sent by the control device is continuously received within the time period T2, it can be determined that the communication connection between the drone and the control device is restored.

Optionally, the flight trajectory may include multiple waypoints, and the multiple waypoints are the waypoints that the UAV traverses within a preset time period before the communication connection is interrupted. This embodiment does not limit the specific value of the preset time period. Optionally, the preset time period may be related to the way the drone records the waypoint.

The flight trajectory is exemplarily described below with reference to FIG. 4 , but FIG. 4 does not limit the flight trajectory.

As shown in Figure 4, the vertical line on the left represents the take-off position of the UAV, and the vertical line on the right represents the current position where the UAV detects that the communication connection with the control device is interrupted, which can be called the lost contact position. Black solid circles represent waypoints recorded by the drone. In example 1, the drone records the waypoints from the take-off position. Therefore, the flight trajectory before the communication connection is interrupted can be trajectory 1. The flight trajectory includes 9 waypoints, and the preset time period is from the disconnected position to the The entire time period during which the drone is flown between takeoff positions. In Example 2, the UAV updates and records a preset number of waypoints, such as 5, that the UAV traverses before the current moment during the flight. Therefore, the flight trajectory before the communication connection is interrupted can be trajectory 2, and the flight trajectory includes 5 waypoints. In Example 3, the UAV can record the traversed waypoints in segments to form different trajectories. Therefore, the flight trajectory before the communication connection is interrupted can be trajectory 4, and the flight trajectory includes 4 waypoints.

It should be noted that this embodiment does not limit the interval between two waypoints. Optionally, the time interval between two adjacent waypoints is the same. Optionally, the distance between two adjacent waypoints is the same. Optionally, the interval between two adjacent waypoints can be adjusted according to the flying environment of the drone. For example, when flying in flat terrain, the time interval or distance interval between two waypoints may be larger. In scenes with many occlusions or obstacles, such as mountains, canyons, and woods, the time interval or distance interval between two waypoints may be small.

Optionally, the waypoints may correspond to identification information, and the identification information may uniquely distinguish different waypoints. For example, in Example 1 of FIG. 4 , the identification information of the nine waypoints may be 1 to 9, respectively. In Example 3 of FIG. 4 , the track 3 includes 5 waypoints, and the identification information may be 1 to 5, respectively, and the track 4 includes 4 waypoints, and the identification information may be 6 to 9, respectively.

S302. Determine whether the return-to-home condition is satisfied during the retrospective flight.

S303 or S304 is subsequently executed according to the judgment result.

S303 , when the return-to-home condition is not met and it is detected that the communication connection is restored, control the drone to fly in response to the control command of the control device.

S304 , if the return-to-home condition is satisfied, control the drone to fly to the return point.

Specifically, during the retrospective flight of the UAV along the flight trajectory before the communication connection was interrupted, it is also possible to detect whether the return-to-home condition is met, and according to whether the return-to-home condition is met and whether the communication connection between the UAV and the control device is restored, Control the flight of the drone. This embodiment does not limit the execution sequence of detecting whether the return-to-home condition is satisfied and detecting whether the communication connection is restored. For example, they can be executed simultaneously. For another example, period detection is performed according to respective detection periods, and the detection period is not limited in this embodiment.

Among them, in one scenario, if the communication connection between the drone and the control device is not restored, the drone is still in a disconnected state. If the return conditions are met, control the drone to return and fly to the return point.

In another scenario, if it is detected that the communication connection between the UAV and the control device is restored, the UAV can then fly according to the control instructions sent by the control device. Moreover, if the return-to-home condition has not been met, the drone is controlled to fly in response to the control command of the control device.

Based on the solution of the above embodiment, the uncertain factors during the in-situ waiting period after the unmanned aerial vehicle is disconnected from the control device can be reduced, and the autonomy of the unmanned aerial vehicle to get out of trouble can be improved.

In one solution, it is determined to return to the home point directly after the disconnection. Although the UAV is returning to the home point and re-establishes communication with the remote control device, if the flight mission needs to be continued, the pre-flight segment needs to be re-flyed. This invisibly increases the cost of completing the mission.

In addition, when the drone is flying at a long distance, the communication between the drone and the control device is often blocked by obstacles, resulting in poor signal quality and even frequent disconnection, but if the disconnection directly returns to the home point, it is equivalent to the end After this flight mission, if you are performing an aerial photography mission, you may not be able to allow the user to complete the aerial photography mission to the fullest. If you are performing a flight experience mission (for example, through the FPV screen of the UAV, let the user experience the flight from the FPV perspective) , it may not allow users to fully experience the fun of playing drones.

Based on the solution of the above embodiment, after the disconnection, the drone is first controlled to fly backwards, and it is detected whether the communication connection is re-established, which can improve the possibility of retrieving the communication signal to a certain extent. Establishing a communication connection can reduce the cost of continuing to complete the flight mission, thereby ensuring flight safety and balancing the cost of flight.

In an optional embodiment, the step of judging power can be added after disconnection. The communication connection of the drone is interrupted, and it is detected whether the power of the drone is lower than the preset power threshold,

If the power is not lower than the preset power threshold, control the UAV to fly back along the flight trajectory before the communication connection was interrupted, and detect whether the communication connection is restored; if the return-to-home condition is met, the communication connection is not detected recovery, control the drone to fly to the return point; if it is detected that the communication connection is restored when the return-to-home condition is not met, control the drone to fly in response to the control command of the control device;

If the power is lower than the preset power threshold, the drone is controlled to fly to the home point.

In this way, when the power of the drone is still sufficient, we can focus on letting the drone get out of trouble autonomously, and give a certain tolerance to the abnormal state, so that the flight mission can be better completed. When the power of the drone is insufficient, controlling the drone to fly to the home point can ensure the flight safety of the drone. Compared with simply executing a single return-to-home control strategy, this embodiment can not improve the flexibility of the UAV in autonomously handling complex abnormal states.

Optionally, the method for controlling the flight of an unmanned aerial vehicle provided in this embodiment may further include:

If it is detected that the communication connection is restored and the return-to-home condition is met, the drone will be controlled to fly in response to the control command of the control device.

In this scenario, since it is detected that the communication connection between the UAV and the control device has been restored, the UAV can then fly according to the control instructions sent by the control device. Even if the return-to-home condition is also met, the reliability of the drone flight is improved by controlling the drone to fly in response to the control command of the control device.

Wherein, this embodiment does not limit the home point. For example, the home point can be a preset position point. For another example, the home point may be the take-off point of the drone.

It can be seen that the flight control method of the UAV provided in this embodiment is suitable for the scenario where the communication connection with the control device is interrupted during the flight of the UAV. By controlling the UAV to fly back along the flight trajectory before the communication connection was interrupted, detecting whether the communication connection is restored and whether the return-to-home condition is met, and controlling the flight of the UAV according to the detection result, the UAV in the UAV disconnection scenario is improved. The autonomy of solving problems improves the reliability of UAV flight and the effect of getting out of trouble.

Optionally, the return-to-home condition may include at least one of the following:

The distance between the current position of the UAV and the waypoint initially recorded in the flight trajectory is less than or equal to the first distance threshold.

The remaining power of the drone's battery is less than or equal to the preset power.

The cumulative flight time of the drone after takeoff is equal to or greater than the preset time.

The cumulative flight distance of the drone after takeoff is equal to or greater than the second distance threshold.

Wherein, this embodiment does not limit the specific values of the first distance threshold, the preset power, the preset duration, and the second distance threshold.

The distance between the current position of the UAV and the waypoint initially recorded in the flight trajectory will be exemplarily described below with reference to FIG. 4 . In Example 1, the initial recorded waypoint in the flight trajectory is waypoint 1, and the distance between the current position of the drone and the initial recorded waypoint in the flight trajectory is the distance between the disconnected position and waypoint 1. distance. In example 2, the initial recorded waypoint in the flight trajectory is the waypoint 1 in trajectory 2, and the distance between the current position of the drone and the initial recorded waypoint in the flight trajectory is the disconnected position and trajectory 2 The distance between waypoints 1. In Example 3, the distance between the current position of the UAV and the waypoint in the flight trajectory that was initially recorded is the distance between the lost contact position and the waypoint 6 in the trajectory 4.

Optionally, in S303, controlling the drone to fly in response to the control command of the control device may include:

Control the drone to hover and wait to receive the control command sent by the control device.

By controlling the drone to wait in place to receive the control command sent by the control device, the drone can then fly according to the control command, which improves the reliability of the drone flight.

Optionally, in S304, controlling the drone to fly to the home point may include:

Acquire the first environment image above the drone.

Determine whether the target space area above the UAV includes obstacles according to the first environment image.

If the target space area does not include obstacles, control the drone to fly up to the first height, and then fly horizontally above the home point at the first height.

Specifically, during the flight of the drone, the camera device configured by itself can capture the environmental image in the flight environment where the drone is located. When the drone returns to home, the drone can hover at the current position, and the first environment image above the drone is captured by the camera device. Wherein, this embodiment does not limit the type and installation position of the imaging device. For example, the camera device may include at least one of the following: a monocular camera, a binocular camera, or an infrared camera. Optionally, the camera device may be installed on the pan/tilt, and at this time, the upward viewing function of the camera device may be realized by the pan/tilt. After acquiring the first environment image, it is determined whether the target space area above the UAV includes obstacles according to the first environment image. If no obstacle is included, it means that the drone can fly straight and return to home smoothly, then control the drone to fly up to the first altitude, and then fly horizontally above the return point at the first altitude.

The specific value of the first height is not limited in this embodiment.

Optionally, acquiring the first environment image above the drone may include:

Control the rotation of the gimbal configured by the UAV, so that the observation range of the sensing device mounted on the gimbal includes the area above the UAV.

A first environment image captured by the sensing device is acquired.

Optionally, determining whether the target space area above the UAV includes obstacles according to the first environment image may include:

Semantic recognition processing is performed on the first environment image to obtain semantic categories corresponding to the pixel regions in the first environment image.

It is determined whether there is a pixel region whose semantic category belongs to a preset obstacle category in the first environment image.

If there is no pixel area whose semantic category belongs to the preset obstacle category, it is determined that the target space area does not include obstacles.

Wherein, this embodiment does not limit the preset obstacle type. For example, it can be set based on the class of objects in the drone flight area.

Optionally, performing semantic recognition processing on the first environment image to obtain the semantic category corresponding to the pixel area in the first environment image may be accomplished by means of a neural network model.

Specifically, the neural network model may specifically be a Convolutional Neural Networks (CNN) model. The neural network model can include multiple computing nodes, and each computing node can include a convolution (Conv) layer, batch normalization (BN) and activation function ReLU, and skip connections can be used between computing nodes. ) connection.

The input data of K×H×W can be input into the neural network model, and after being processed by the neural network model, the output data of C×H×W can be obtained. Among them, K can represent the number of input channels, and K can be equal to 4, corresponding to four channels of red (R, red), green (G, green), blue (B, blue) and depth (D, deep) respectively; H may represent the height of the input image (ie, the first environment image), W may represent the width of the input image, and C may represent the number of categories.

It should be noted that when the input image is too large, an input image can be cut into N sub-images, correspondingly, the input data can be N×K×H'×W', and the output data can be N×C×H' ×W', where H' may represent the height of the sub-image, and W' may represent the width of the sub-image. Of course, in other embodiments, the feature map may also be obtained in other manners, which is not limited in this embodiment.

Using the above-mentioned pre-trained neural network model to process the first environmental image to obtain a feature map, specifically, the following steps may be included:

Step 1: Input the first environment image into the neural network model to obtain the model output result of the neural network model.

The model output result of the neural network model may include confidence feature maps output by multiple output channels respectively, and the multiple output channels may be in one-to-one correspondence with multiple object categories, and the pixel values of the confidence feature map of a single object category are to characterize the probability that a pixel is an object class.

In step 2, a feature map containing semantic information is obtained according to the model output result of the neural network model.

The feature map can be obtained by taking the object category corresponding to the confidence feature map with the largest pixel value at the same pixel position in the confidence feature maps corresponding to the multiple output channels one-to-one as the object category of the pixel position.

It is assumed that the number of output channels of the neural network model is 4, and the output result of each channel is a confidence feature map, that is, the 4 confidence feature maps are respectively the confidence feature map 1 to the confidence feature map 4, and the confidence Confidence feature map 1 corresponds to the sky, confidence feature map 2 corresponds to buildings, confidence feature map 3 corresponds to trees, and confidence feature map 4 corresponds to "other". In these categories, except for the sky, the rest can be considered as obstacles.

For example, when the pixel value of the pixel position (100, 100) in the confidence feature map 1 is 70, the pixel value of the pixel position (100, 100) in the confidence feature map 2 is 50, and the pixel value of the pixel position (100, 100) in the confidence feature map 3 The value is 20, and when the pixel value of the pixel position (100, 100) in the confidence feature map 4 is 20, it can be determined that the pixel position (100, 100) is the sky.

For another example, when the pixel value of the pixel position (100, 80) in the confidence feature map 1 is 20, the pixel value of the pixel position (100, 80) in the confidence feature map 2 is 30, and the pixel position in the confidence feature map 3 When the pixel value of (100,80) is 20, and the pixel value of the pixel position (100,80) in the confidence feature map 4 is 70, it can be determined that the pixel position (100,80) is other, that is, not trees, buildings and any of the trees.

It can be seen that the above recognition is actually at the pixel level, that is, to identify the category to which each pixel in the first environmental image belongs, that is, to identify the category to which each object in the first environmental image belongs, which is also indirect. The position of each object in the first environment image is determined.

If it is recognized that there are no obstacles in the first environment image, the drone can fly upwards and fly horizontally above the home point.

If there is a pixel area whose semantic category belongs to the preset obstacle category, the distance between the real object corresponding to the pixel area and the drone is obtained.

If the distance is greater than the preset distance, it is determined that the target space area does not include obstacles.

Specifically, if it is identified that there is a pixel area belonging to a preset obstacle category in the first environmental image, the distance between the real object corresponding to the pixel area and the drone is further obtained, and whether the obstacle affects the unmanned aerial vehicle is determined according to the distance. Return of the man-machine. If the distance is greater than the preset distance, it means that the obstacle does not affect the return flight of the drone, and it can be determined that the target space area does not include obstacles.

The specific value of the preset distance is not limited in this embodiment.

If the distance is less than or equal to the preset distance, control the drone to fly horizontally from the current position to the target position, and re-execute the steps of acquiring the environment image above the drone and determining whether the target space area above the drone includes obstacles .

Specifically, if it is identified that there is a pixel area belonging to a preset obstacle category in the first environmental image, the distance between the real object corresponding to the pixel area and the drone is further obtained, and whether the obstacle affects the unmanned aerial vehicle is determined according to the distance. Return of the man-machine. If the distance is less than or equal to the preset distance, it means that the obstacle affects the return of the drone, and it can be determined that the target space area includes obstacles, and the drone is controlled to fly horizontally from the current position to the target position, and execute again after the position moves. Steps to obtain imagery of the environment above the drone and determine whether the target space area above the drone includes obstacles.

Optionally, in an implementation manner, the distance between the current position of the drone and the target position may be a fixed distance, and the specific value of the fixed distance is not limited in this embodiment.

Optionally, in another implementation manner, the distance between the current position of the UAV and the target position is determined according to the physical size information of the obstacle. The distance that the UAV can fly horizontally is determined by the physical size information of the obstacles, which can better avoid obstacles, reduce the probability of obstacles above the target position, and improve the return flight efficiency.

Get the flight status information of the drone.

Determine whether the return-to-air condition is met according to the flight status information.

If the return conditions are met, the drone will be directly controlled to fly to the return point.

Specifically, at any time during the flight of the UAV, the flight status information of the UAV can be obtained, and it is determined whether the return-to-home condition is satisfied according to the flight status information. When the return conditions are met, the drone can be directly controlled to fly to the return point to ensure the drone returns safely.

Optionally, this embodiment does not limit the specific content included in the flight status information. For example, the flight status information may include, but is not limited to, at least one of the following: the remaining power of the UAV's battery, the UAV's accumulated flight time, the UAV's accumulated flight distance, or the UAV's alarm information.

FIG. 5 is another flowchart of the method for controlling the flight of an unmanned aerial vehicle according to an embodiment of the present application. On the basis of the above-mentioned embodiment shown in FIG. 3 , this embodiment provides an implementation manner of controlling the UAV to fly back along the flight trajectory before the communication connection is interrupted in S301 . As shown in Figure 5, controlling the UAV to fly back along the flight trajectory before the communication connection is interrupted can include:

S501. Acquire a second environment image obtained by the UAV during the retrospective flight.

S502. If it is determined according to the second environment image that there is an obstacle on the flight trajectory, control the drone to avoid the obstacle to fly, and after avoiding the obstacle, return to the flight trajectory and continue to fly backwards.

An exemplary description will be given below with reference to FIG. 6 . FIG. 6 is a schematic diagram of a UAV retrospective flight provided by an embodiment of the present application. As shown in FIG. 6 , when the drone 60 flies back along the flight trajectory 61 , the second environment image can be acquired. For the acquisition of the second environmental image by the drone, reference may be made to the above description of the acquisition of the first environmental image by the drone. The principles are similar and will not be repeated here. The position of the drone during the retrospective flight is different, and the obtained second environment image is different. After acquiring the second environment image, determine whether there are obstacles on the flight trajectory according to the second environment image. For details, please refer to the above description about determining whether the target space area above the UAV includes obstacles according to the first environment image. The principle similar, and will not be repeated here. If it is determined that there is an obstacle on the flight path according to the second environment image, the UAV is controlled to avoid the obstacle to fly, and after avoiding the obstacle, it returns to the flight path and continues to fly backwards. For example, in FIG. 6 , when the UAV 60 is at position 1, it is determined that there is an obstacle 62 on the flight trajectory according to the obtained second environment image, then it avoids the obstacle 62 to fly, and then returns to fly after avoiding the obstacle 62 Trajectory 61 continues to fly backwards. The UAV 60 continues to fly back along the flight trajectory 61. When the UAV 60 is in position 2, it is determined that there is an obstacle 64 on the flight trajectory according to the obtained second environment image, and then the UAV 64 is avoided to fly and avoid the obstacle 64. After the obstacle 64, it returns to the flight path 61 and continues to fly backwards.

Optionally, in S502, the drone is controlled to avoid obstacles to fly, and after avoiding the obstacles, it returns to the flight track to continue the backtracking flight, which may include:

Get the obstacle information of the obstacle.

Determine the target waypoint on the flight trajectory according to the obstacle information and flight trajectory, and the target waypoint is the waypoint where the drone returns to the flight trajectory and continues to fly after avoiding the obstacle.

Generate obstacle avoidance routes based on obstacle information and target waypoints.

Control the drone to fly along the obstacle avoidance route, and control the drone to continue to fly back along the flight trajectory after flying along the obstacle avoidance route.

An exemplary description will be given below with reference to FIG. 7 . FIG. 7 is another schematic diagram of the retrospective flight of the UAV provided by the embodiment of the present application. As shown in FIG. 7 , when the UAV 70 is flying backwards along the flight trajectory 71, it is determined according to the obtained second environment image that there is an obstacle 73 on the flight trajectory 71, then it needs to avoid the obstacle 73 to fly, and when avoiding the obstacle 73 After the obstacle 73, it returns to the flight path 71 and continues to fly backwards. The flight trajectory 71 may include multiple waypoints 72 . By acquiring the obstacle information of the obstacle 73, the target waypoint 75 on the flight trajectory is determined according to the obstacle information and the flight trajectory 71, so as to generate the obstacle avoidance route 74 according to the obstacle information and the target waypoint 75, and along the obstacle avoidance route After 74 flight, control the drone to continue to fly back along the flight path 71.

Optionally, this embodiment does not limit the specific content included in the obstacle information. For example, the obstacle information may include, but is not limited to, at least one of the following: physical size information of the obstacle information and category of the obstacle information.

By generating an obstacle avoidance route, the flight trajectory correction during the UAV's retrospective flight is realized, and the safety and reliability of the UAV retrospective flight are improved by slightly correcting the flight trajectory.

It should be noted that this embodiment does not limit the obstacle avoidance method used when generating the obstacle avoidance route, and an existing obstacle avoidance method may be used.

FIG. 8 is another flowchart of the flight control method of the unmanned aerial vehicle provided by the embodiment of the present application. In the flight control method for an unmanned aerial vehicle provided by this embodiment, the execution subject may be an unmanned aerial vehicle. As shown in FIG. 8 , the flight control method of the UAV provided by this embodiment may include:

S801. During the flight of the UAV, if it is detected that the communication connection between the UAV and the control device of the UAV is interrupted, obtain the flight status information of the UAV.

S802. Determine whether the return-to-home condition is satisfied according to the flight status information.

S803 , if the return-to-home condition is met, directly control the drone to fly to the return point.

The difference between this embodiment and the embodiment shown in FIG. 3 is that in the embodiment shown in FIG. 3 , after the UAV detects that the communication connection with the control device is interrupted, the UAV is controlled to fly back along the flight trajectory before the communication connection is interrupted. , and check whether the communication connection is restored and whether the return-to-home condition is satisfied during the retrospective flight. However, in this embodiment, after detecting that the communication connection with the control device is interrupted, the drone determines whether the return-to-home condition is satisfied according to the flight status information. If it is judged that the return-to-home condition is satisfied according to the flight status information, the UAV will be directly controlled to fly to the return point. At this time, there is no need to control the UAV to fly back along the flight trajectory before the communication connection is interrupted.

It can be seen that the flight control method of the drone provided in this embodiment is suitable for the scenario where the communication connection between the drone and the control device is interrupted during the flight of the drone. By judging whether the return-to-home condition is met, the drone is controlled to fly according to the judgment result. When it is determined that the return conditions are met, the drone is directly controlled to return and fly to the return point. Compared with the UAV waiting in place in the prior art, the autonomy of the UAV to solve the problem in the unconnected scenario of the UAV is improved, and the reliability of the UAV flight and the effect of getting out of trouble are improved.

If the return-to-home condition is not met, control the UAV to fly back along the flight trajectory before the communication connection was interrupted, and detect whether the communication connection is restored.

If the return-to-home condition is met, the communication connection is not detected, and the drone is controlled to fly to the home point.

If it is detected that the communication connection is restored when the return-to-home condition is not met, the drone will be controlled to fly in response to the control command of the control device.

In this implementation, if the drone does not meet the return-to-home condition when the drone loses contact, the drone can be controlled to fly back along the flight trajectory before the communication connection was interrupted. Reference may be made to the relevant descriptions of S301 to S304 in the embodiment shown in FIG. 3 , and the subsequent flight process may also refer to the embodiment shown in FIG. 3 , the principles are similar, and will not be repeated here.

Below, on the basis of the embodiments shown in the above-mentioned FIGS. 3 to 8 , the flying effect of the unmanned aerial vehicle will be exemplarily described with reference to FIGS. 9A to 9C . FIGS. 9A to 9C are schematic diagrams of drone flight according to an embodiment of the present application.

Optionally, in an example, as shown in FIG. 9A , when the UAV 90 detects that the communication connection with the control device is interrupted, the UAV 90 is controlled to fly back along the flight trajectory 91 before the communication connection is interrupted, And check whether the communication connection is restored. In this example, the recovery of the communication connection has not been detected. When the drone flies back to the position 92, it is determined that the return-to-home condition is satisfied, and the drone is controlled to return to the home and fly above the return point 93.

Optionally, in another example, as shown in FIG. 9B , when the UAV 90 detects that the communication connection with the control device is interrupted, the UAV 90 is controlled to fly back along the flight trajectory 91 before the communication connection is interrupted. , and check whether the communication connection is restored. In this example, the return-to-home condition has not been met. When the drone flies back to the position 94, it is detected that the communication connection between the drone and the control device is restored, and the drone 90 is controlled to hover and wait for receiving the control device. control command sent.

Optionally, in another example, as shown in FIG. 9C , when the drone 90 detects that the communication connection with the control device is interrupted, it is determined whether the return-to-home condition is satisfied. In this example, if it is determined that the return-to-home condition is satisfied, the drone is controlled to return to the home and fly to the top of the return point 93 .

FIG. 10 is a schematic structural diagram of an unmanned aerial vehicle provided by an embodiment of the present application. As shown in FIG. 10 , the drone provided in this embodiment may include: a memory 1002, a processor 1001, and a transceiver 1003;

The transceiver 1003 is used to communicate with other devices;

The memory 1002 is used to store program codes;

The processor 1001 calls the program code, and when the program code is executed, is configured to perform the following operations:

If the return-to-home condition is not met and it is detected that the communication connection is restored, the drone is controlled to fly in response to the control command of the control device;

Optionally, the processor 1001 is specifically used for:

Control the drone to hover, and control the transceiver 1003 to wait for receiving the control instruction sent by the control device.

Optionally, the processor 1001 is specifically used for:

acquiring a first environment image above the drone;

Determine whether the target space area above the UAV includes obstacles according to the first environment image;

If the target space area does not include obstacles, the UAV is controlled to fly upward to a first height, and horizontally fly above the home point at the first height.

Optionally, the processor 1001 is specifically used for:

Perform semantic recognition processing on the first environment image to obtain the semantic category corresponding to the pixel area in the first environment image;

judging whether there is a pixel region whose semantic category belongs to a preset obstacle category in the first environment image;

If there is no pixel region whose semantic category belongs to the preset obstacle category, it is determined that the target space region does not include obstacles.

Optionally, the processor 1001 is further configured to:

If there is a pixel area whose semantic category belongs to the preset obstacle category, obtain the distance between the real object corresponding to the pixel area and the drone;

If the distance is greater than a preset distance, it is determined that the target space area does not include obstacles.

Optionally, the processor 1001 is further configured to:

If the distance is less than or equal to the preset distance, control the drone to fly horizontally from the current position to the target position, and re-execute the acquisition of the environmental image above the drone and the determination of the unmanned aerial vehicle. Steps to check if the target space area above the aircraft includes obstacles.

Optionally, the distance between the current position and the target position is determined according to the physical size information of the obstacle.

Optionally, the processor 1001 is specifically used for:

Controlling the rotation of the gimbal configured by the unmanned aerial vehicle, so that the observation range of the sensing device mounted on the gimbal includes the upper area of the unmanned aerial vehicle;

Acquiring the first environment image captured by the sensing device.

Optionally, the return-to-home condition includes at least one of the following:

The distance between the current position of the drone and the waypoint initially recorded in the flight trajectory is less than or equal to a first distance threshold;

The remaining power of the battery of the drone is less than or equal to the preset power;

The cumulative flight time of the drone after take-off is equal to or greater than the preset time;

Optionally, the processor 1001 is specifically used for:

acquiring the second environment image obtained by the UAV during the retrospective flight;

If it is determined that there is an obstacle on the flight path according to the second environment image, the UAV is controlled to avoid the obstacle to fly, and after avoiding the obstacle, it returns to the flight path and continues to fly backwards.

Optionally, the processor 1001 is specifically used for:

obtain the obstacle information of the obstacle;

A target waypoint on the flight trajectory is determined according to the obstacle information and the flight trajectory, and the target waypoint is the flight path where the drone returns to the flight trajectory and continues to fly after avoiding the obstacle. point;

generating an obstacle avoidance route according to the obstacle information and the target waypoint;

The UAV is controlled to fly along the obstacle avoidance route, and after flying along the obstacle avoidance route, the UAV is controlled to continue to fly back along the flight trajectory.

Optionally, the flight trajectory includes multiple waypoints, and the multiple waypoints are the waypoints that the UAV traverses within a preset time period before the communication connection is interrupted.

Optionally, the processor 1001 is further configured to:

Obtain the flight status information of the UAV;

Judging whether the return-to-home condition is met according to the flight status information;

If the return-to-home condition is satisfied, the UAV is directly controlled to fly to the return point.

Optionally, the step of judging whether the return-to-home condition is met according to the flight status information is performed before the control of the UAV to fly back along the flight trajectory before the communication connection is interrupted, and the return-to-home condition is met. , the step that satisfies the return-to-home condition is not performed.

The unmanned aerial vehicle provided by this embodiment can implement the flight control method of the unmanned aerial vehicle provided by the embodiment of the present application, and the technical principle and technical effect are similar, and will not be repeated here.

It should be understood that the processor may be a general-purpose processor, a digital signal processor, an application-specific integrated circuit, a field programmable gate array or other programmable logic device, a discrete gate or transistor logic device, or a discrete hardware component, which can implement or execute the implementation of the present application. The methods, steps, and logical block diagrams disclosed in the examples. A general purpose processor may be a microprocessor or any conventional processor or the like. The steps of the methods disclosed in conjunction with the embodiments of the present application may be directly embodied as executed by a hardware processor, or executed by a combination of hardware and software modules in the processor.

In this embodiment of the present application, the memory may be a non-volatile memory, such as a hard disk drive (HDD) or a solid-state drive (SSD), etc., or may also be a volatile memory (volatile memory), for example Random access memory (RAM). Memory is, but is not limited to, any medium that can be used to carry or store desired program code in the form of instructions or data structures and that can be accessed by a computer. The memory in this embodiment of the present application may also be a circuit or any other device capable of implementing a storage function, for storing program instructions and/or data.

Those of ordinary skill in the art can understand that all or part of the steps of implementing the above method embodiments may be completed by program instructions related to hardware. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, the steps including the above method embodiments are executed; and the foregoing storage medium includes: ROM, RAM, magnetic disk or optical disk and other media that can store program codes.

Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the embodiments of the present application, but not to limit them; It should be understood that: it is still possible to modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements to some or all of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the embodiments of the present application Scope of technical solutions.

Claims

A flight control method for an unmanned aerial vehicle, comprising:

During the flight of the UAV, if it is detected that the communication connection between the UAV and the control device of the UAV is interrupted, the UAV is controlled to fly back along the flight trajectory before the communication connection is interrupted, and detecting whether the communication connection is restored;

Judging whether the return-to-home condition is met during the retrospective flight;

If the return-to-home condition is not met and it is detected that the communication connection is restored, control the drone to fly in response to the control command of the control device;

If the return-to-home condition is satisfied, the drone is controlled to fly to the return point.
The method according to claim 1, wherein the controlling the drone to fly in response to a control command of the control device comprises:

Control the drone to hover, and wait to receive the control instruction sent by the control device.
The method according to claim 1, wherein the controlling the drone to fly to a home point comprises:

acquiring a first environment image above the drone;

Determine whether the target space area above the UAV includes obstacles according to the first environment image;

If the target space area does not include obstacles, the UAV is controlled to fly upward to a first height, and horizontally fly above the home point at the first height.
The method according to claim 3, wherein the determining whether the target space area above the UAV includes obstacles according to the first environment image comprises:

Perform semantic recognition processing on the first environment image to obtain the semantic category corresponding to the pixel area in the first environment image;

judging whether there is a pixel region whose semantic category belongs to a preset obstacle category in the first environment image;

If there is no pixel region whose semantic category belongs to the preset obstacle category, it is determined that the target space region does not include obstacles.
The method of claim 4, further comprising:

If there is a pixel area whose semantic category belongs to the preset obstacle category, obtain the distance between the real object corresponding to the pixel area and the drone;

If the distance is greater than a preset distance, it is determined that the target space area does not include obstacles.
The method of claim 5, further comprising:

If the distance is less than or equal to the preset distance, control the drone to fly horizontally from the current position to the target position, and re-execute the acquisition of the environment image above the drone and the determination of the unmanned aerial vehicle. Steps to check if the target space area above the aircraft includes obstacles.
The method according to claim 6, wherein the distance between the current position and the target position is determined according to the physical size information of the obstacle.
The method according to any one of claims 3-7, wherein the acquiring the first environment image above the drone comprises:

Controlling the rotation of the gimbal configured by the unmanned aerial vehicle, so that the observation range of the sensing device mounted on the gimbal includes the area above the unmanned aerial vehicle;

Acquiring the first environment image captured by the sensing device.
The method according to any one of claims 1-7, wherein the return-to-home condition includes at least one of the following:

The distance between the current position of the drone and the waypoint initially recorded in the flight trajectory is less than or equal to a first distance threshold;

The remaining power of the battery of the drone is less than or equal to the preset power;

The cumulative flight time of the drone after take-off is equal to or greater than the preset time;

The cumulative flight distance of the drone after takeoff is equal to or greater than the second distance threshold.
The method according to any one of claims 1-7, wherein the controlling the UAV to fly back along the flight trajectory before the communication connection is interrupted comprises:

acquiring the second environment image obtained by the UAV during the retrospective flight;

If it is determined that there is an obstacle on the flight trajectory according to the second environment image, the UAV is controlled to avoid the obstacle to fly, and after avoiding the obstacle, it returns to the flight trajectory to continue flying backwards.
The method according to claim 10, wherein the controlling the UAV to avoid obstacles to fly, and after avoiding the obstacles, return to the flight trajectory to continue flying backwards, comprising:

obtain the obstacle information of the obstacle;

A target waypoint on the flight trajectory is determined according to the obstacle information and the flight trajectory, and the target waypoint is the flight path where the drone returns to the flight trajectory and continues to fly after avoiding the obstacle. point;

generating an obstacle avoidance route according to the obstacle information and the target waypoint;

The UAV is controlled to fly along the obstacle avoidance route, and after flying along the obstacle avoidance route, the UAV is controlled to continue to fly back along the flight trajectory.
The method according to any one of claims 1-7, wherein the flight trajectory includes a plurality of waypoints, and the plurality of waypoints are a preset time period before the communication connection of the UAV is interrupted Waypoints traversed within.
The method according to any one of claims 1-7, further comprising:

Obtain the flight status information of the UAV;

Judging whether the return-to-home condition is met according to the flight status information;

If the return-to-home condition is satisfied, the UAV is directly controlled to fly to the return point.
The method according to claim 13, wherein the step of judging whether the return-to-home condition is satisfied according to the flight status information is before the control of the UAV to fly back along the flight trajectory before the communication connection is interrupted. is executed, and when the return-to-home condition is met, the step of meeting the return-to-home condition is not executed.
An unmanned aerial vehicle, comprising: a memory, a processor and a transceiver;

the transceiver for communicating with other devices;

the memory for storing program codes;

The processor calls the program code, and when the program code is executed, is configured to perform the following operations:

During the flight of the UAV, if it is detected that the communication connection between the UAV and the control device of the UAV is interrupted, the UAV is controlled to fly back along the flight trajectory before the communication connection is interrupted, and detecting whether the communication connection is restored;

Judging whether the return-to-home condition is met during the retrospective flight;

If the return-to-home condition is not met and it is detected that the communication connection is restored, control the drone to fly in response to the control command of the control device;

If the return-to-home condition is satisfied, the drone is controlled to fly to the return point.
The drone according to claim 15, wherein the processor is specifically used for:

The drone is controlled to hover, and the transceiver is controlled to wait for receiving the control instruction sent by the control device.
The drone according to claim 15, wherein the processor is specifically used for:

acquiring a first environment image above the drone;

Determine whether the target space area above the UAV includes obstacles according to the first environment image;

If the target space area does not include obstacles, the UAV is controlled to fly upward to a first height, and horizontally fly above the return point at the first height.
The drone according to claim 17, wherein the processor is specifically used for:

Perform semantic recognition processing on the first environment image to obtain the semantic category corresponding to the pixel area in the first environment image;

judging whether there is a pixel region whose semantic category belongs to a preset obstacle category in the first environment image;

If there is no pixel region whose semantic category belongs to the preset obstacle category, it is determined that the target space region does not include obstacles.
The drone of claim 18, wherein the processor is further configured to:

If there is a pixel area whose semantic category belongs to the preset obstacle category, obtain the distance between the real object corresponding to the pixel area and the drone;

If the distance is greater than a preset distance, it is determined that the target space area does not include obstacles.
The drone of claim 19, wherein the processor is further configured to:

If the distance is less than or equal to the preset distance, control the drone to fly horizontally from the current position to the target position, and re-execute the acquisition of the environment image above the drone and the determination of the unmanned aerial vehicle. Steps to check if the target space area above the aircraft includes obstacles.
The drone according to claim 20, wherein the distance between the current position and the target position is determined according to the physical size information of the obstacle.
The drone according to any one of claims 17-21, wherein the processor is specifically used for:

Controlling the rotation of the gimbal configured by the unmanned aerial vehicle, so that the observation range of the sensing device mounted on the gimbal includes the area above the unmanned aerial vehicle;

Acquiring the first environment image captured by the sensing device.
The drone according to any one of claims 15-21, wherein the return-to-home condition includes at least one of the following:

The distance between the current position of the drone and the waypoint initially recorded in the flight trajectory is less than or equal to a first distance threshold;

The remaining power of the battery of the drone is less than or equal to the preset power;

The cumulative flight time of the drone after take-off is equal to or greater than the preset time;

The cumulative flight distance of the drone after takeoff is equal to or greater than the second distance threshold.
The drone according to any one of claims 15-21, wherein the processor is specifically used for:

acquiring the second environment image obtained by the UAV during the retrospective flight;

If it is determined that there is an obstacle on the flight trajectory according to the second environment image, the UAV is controlled to avoid the obstacle to fly, and after avoiding the obstacle, it returns to the flight trajectory to continue flying backwards.
The drone according to claim 24, wherein the processor is specifically used for:

obtain the obstacle information of the obstacle;

A target waypoint on the flight trajectory is determined according to the obstacle information and the flight trajectory, and the target waypoint is the flight path where the drone returns to the flight trajectory and continues to fly after avoiding the obstacle. point;

generating an obstacle avoidance route according to the obstacle information and the target waypoint;

The UAV is controlled to fly along the obstacle avoidance route, and after flying along the obstacle avoidance route, the UAV is controlled to continue to fly back along the flight trajectory.
The drone according to any one of claims 15-21, wherein the flight trajectory includes a plurality of waypoints, and the plurality of waypoints are preset by the drone before the communication connection is interrupted Waypoints traversed during the time period.
The drone according to any one of claims 15-21, wherein the processor is further configured to:

Obtain the flight status information of the UAV;

Judging whether the return-to-home condition is met according to the flight status information;

If the return-to-home condition is satisfied, the UAV is directly controlled to fly to the return point.
The drone according to claim 27, wherein the step of judging whether the return-to-home condition is satisfied according to the flight status information is controlled to backtrack the drone along the flight trajectory before the communication connection is interrupted. It is performed before the flight, and when the return-to-home condition is satisfied, the step of meeting the return-to-home condition is not performed.
A computer-readable storage medium, characterized in that a computer program is stored on the readable storage medium; when the computer program is executed, the method according to any one of claims 1-14 is implemented.