KR102199680B1 - Method and apparatus for controlling drone for autonomic landing - Google Patents

Abstract

The present invention relates to a method for controlling a drone for an autonomous landing, which comprises the following steps of: obtaining target altitude information and landing allowable condition information of a destination; obtaining image information in a direction of the ground at a target altitude of the destination in accordance with the target altitude information; determining a landing area based on the landing allowable condition information and the image information in the direction of the ground; moving the drone to a position where a line of sight (LOI) to the landing area is secured; generating a flight path based on the LOI; and controlling the landing of the drone based on the flight path. Therefore, the method for controlling a drone for an autonomous landing enables the drone to land on the determined landing area.

Description

Drone control method and device for autonomous landing {METHOD AND APPARATUS FOR CONTROLLING DRONE FOR AUTONOMIC LANDING}

The present invention relates to a drone control method and apparatus for autonomous landing, and more particularly, to a drone control method and apparatus for autonomously performing landing to a landing area by determining a landing area based on image information.

Unmanned aerial vehicles or'drones' are operated autonomously or semi-automatically according to a pre-programmed route, remotely controlled from the ground without a pilot directly boarding the vehicle, or equipped with artificial intelligence to perform tasks according to their own environmental judgment. It refers to the vehicle that performs. In addition to this, the drone system can collectively refer to the entire system such as ground control equipment (GCS), communication equipment, and support equipment.

However, in the case of a drone that performs autonomous flight, there is an inconvenience that a pilot must assist or manually control a landing flight due to various ground conditions that can change in real time.

An object of the present invention for solving the above problems is to provide a drone control method for autonomous landing.

Another object of the present invention for solving the above problems is to provide a drone control device for autonomous landing.

A drone control method for autonomous landing according to an embodiment of the present invention for achieving the above object includes: acquiring target altitude information and landing permit condition information of a destination, at a target altitude of the destination according to the target altitude information Acquiring image information of the ground direction, determining a landing area based on the landing allowable condition information and the image information of the ground direction, and moving the drone to a location where a line of sight (LOI) to the landing area is secured. It may include moving, generating a flight path based on the LOI, and controlling the landing of the drone based on the flight path.

A drone control apparatus for autonomous landing according to an embodiment of the present invention for achieving the other object includes a vision sensor, a processor, and a memory in which at least one command executed through the processor is stored. And, the at least one command is executed to obtain target altitude information and landing allowable condition information of the destination, and acquires ground direction image information using the vision sensor at the target altitude of the destination according to the target altitude information It is executed to determine the landing area based on the landing allowable condition information and the image information of the ground direction, and is executed to move the drone to a position where the LOI (Line Of Sight) to the landing area is secured. , It is executed to generate a flight path based on the LOI, and may be executed to control the landing of the drone based on the flight path.

According to the present invention, a drone can autonomously determine a landing area by determining a real-time state of a destination and perform landing to the determined landing area.

According to the present invention, an obstacle may be detected based on image information, and an evasion flight path may be generated to perform an evasion flight.

According to the present invention, it is possible to safely land a drone regardless of the user's control skill.

1 is a conceptual diagram of a drone control method for autonomous landing according to an embodiment of the present invention.
2 schematically shows each step of a method for controlling a drone for autonomous landing according to an embodiment of the present invention.
3 is a block diagram of a drone control device for autonomous landing according to an embodiment of the present invention.
4 is a flowchart of a drone control method for autonomous landing according to an embodiment of the present invention.

In the present invention, various modifications may be made and various embodiments may be provided, and specific embodiments will be illustrated in the drawings and described in detail in the detailed description. However, this is not intended to limit the present invention to a specific embodiment, it is to be understood to include all changes, equivalents, and substitutes included in the spirit and scope of the present invention. In describing each drawing, similar reference numerals have been used for similar elements.

Terms such as first, second, A, and B may be used to describe various elements, but the elements should not be limited by the terms. These terms are used only for the purpose of distinguishing one component from another component. For example, without departing from the scope of the present invention, a first element may be referred to as a second element, and similarly, a second element may be referred to as a first element. The term "and/or" includes a combination of a plurality of related stated items or any of a plurality of related stated items.

When a component is referred to as being "connected" or "connected" to another component, it is understood that it may be directly connected or connected to the other component, but other components may exist in the middle. Should be. On the other hand, when a component is referred to as being "directly connected" or "directly connected" to another component, it should be understood that there is no other component in the middle.

The terms used in the present application are only used to describe specific embodiments, and are not intended to limit the present invention. Singular expressions include plural expressions unless the context clearly indicates otherwise. In the present application, terms such as "comprise" or "have" are intended to designate the presence of features, numbers, steps, actions, components, parts, or combinations thereof described in the specification, but one or more other features. It is to be understood that the presence or addition of elements or numbers, steps, actions, components, parts, or combinations thereof, does not preclude in advance.

Unless otherwise defined, all terms used herein, including technical or scientific terms, have the same meaning as commonly understood by one of ordinary skill in the art to which the present invention belongs. Terms as defined in a commonly used dictionary should be interpreted as having a meaning consistent with the meaning in the context of the related technology, and should not be interpreted as an ideal or excessively formal meaning unless explicitly defined in this application. Does not.

Hereinafter, preferred embodiments of the present invention will be described in more detail with reference to the accompanying drawings. In describing the present invention, in order to facilitate an overall understanding, the same reference numerals are used for the same elements in the drawings, and duplicate descriptions for the same elements are omitted.

1 is a conceptual diagram of a drone control method for autonomous landing according to an embodiment of the present invention.

Referring to FIG. 1, briefly explaining the operation of a drone performing autonomous landing according to an embodiment, the drone can reach the destination (or destination) by flying above, and obtain image information of the ground from above. In addition, by determining the landing area from the image information on the ground, the landing area may be landed.

That is, in an exemplary embodiment, image information in the direction of the ground may be photographed or acquired through a camera or a vision sensor at a specific altitude of the destination, and the state of the ground may be determined from the image information in the direction of the ground. In other words, in one embodiment, it is possible to determine whether some or all of the grounds in the image information are above the water surface, trees, obstacles, and whether the inclination angle of the ground is severe, and by determining the landable ground, the optimum landing is possible. It is possible to determine the area of , determine the flight path to the determined optimal area, and control the drone to land according to the flight path accordingly.

A detailed description of the above-described operations will be described later with reference to FIG. 2.

2 schematically shows each step of a method for controlling a drone for autonomous landing according to an embodiment of the present invention.

Referring to FIG. 2, a method of controlling a drone according to an embodiment may be performed through five steps in size. Here, the five steps may include setting an allowable landing condition, taking off/flying and arriving above the destination, determining the optimum landing location, creating a landing flight path, and landing flight and landing. Hereinafter, each step will be described in detail, but the name of each step may be changed for convenience of description, a plurality of steps may be performed as one step, and one step may be divided into a plurality of steps. May be performed, and some steps or some operations of a specific step may be omitted. Also, some operations within a step may be performed in other steps.

First, in the landing allowable condition setting step, landing allowable condition information and destination target altitude information may be obtained from the user. Here, the landing allowance condition information may include at least one of drone type information, landing area search range information, landing area condition condition information, priority information, search altitude information, and turning radius information.

Here, the shape information of the drone may be expressed as 3D shape information, and may include information about the size of the drone. An embodiment may use this information when determining or generating a flight path of a drone, an evasive flight path or a landing area to be described later.

The landing area search range information may be referred to as a landing allowable range, and may indicate information on a range or area for searching another landing area when landing is not appropriate due to poor ground conditions. For example, the landing area search range information may be determined in a circle or in another form according to a setting, and in the case of a circle, it may be expressed as a radius of 50 m based on the destination. For example, the landing area search range information may be divided and set for each step. That is, a radius of 25m is first searched based on the destination, and if there is no suitable landing area within this range, it may be expanded to a radius of 50m to further search. However, this may provide the same or similar function by expanding the landing area search range and determining an optimal landing area according to priority information to be described later when there are a plurality of landable areas.

Here, the state condition information of the landing area may be referred to as landing disallow condition information, and may include basic condition information related to the safety of the drone and/or special condition information related to a specific mission of the drone. For example, the basic condition information may include information on whether it is on the surface of the water, whether it is on a tree, whether there is an obstacle moving around, or an inclination angle of the destination. In addition, the special condition information may include information on whether the destination is a lower/higher position (altitude) than the surroundings or whether concealment/coverage is impossible.

Here, the priority information may indicate information on priority for deriving an optimal landing area from among a plurality of landable areas within the search range according to the landing area search range information. For example, the priority information may include information that prioritizes the location at the nearest distance from the location information of the destination, or information that prioritizes the region with the gentlest slope, but this may vary according to the description, so limited to this. It does not become.

The search altitude information may indicate information used to change the altitude in the process of securing a light of sight (LOI) to be described later, and the turning radius information may also indicate information used to turn in the process of securing an LOI, which will be described later. . That is, the drone may change the altitude based on the top color altitude information in the process of securing the LOI, which will be described later, and secure the LOI or perform a turning flight based on the turning radius information to secure the LOI. However, the LOI can also be secured through other methods.

For example, the user may represent a drone system administrator or a drone pilot, and the landing allowance condition information and destination target altitude information may be input or set before the flight of the drone begins. However, this is not limited to being set before the start of the flight, since additionally acquired or acquired information may be changed during the flight of the drone.

In the take-off/flight and arrival stage above the destination, the drone can fly to the destination altitude according to the destination altitude information. Here, the drone can fly through various methods such as satellite navigation, inertial navigation, vision-based navigation, or adjustment by a pilot. In addition, for this purpose, the drone may be equipped with a Global Navigation Satellite System (GNSS) module, a Global Positioning System (GPS) module, and an Inertial Measurement Unit (IMU).

In the step of determining the optimum landing location, image information of the ground direction may be photographed or acquired at the target altitude of arrival, and the landing area may be determined based on this. Here, in one embodiment, a camera or a vision sensor may be used to acquire image information, and a ground state is determined from the acquired image information based on a ground state determination model that has been learned through machine learning in advance, and Can determine the landing area.

In other words, according to an exemplary embodiment, the state of the ground may be determined by directly acquiring image information in the direction of the ground from above. This is to adaptively determine the state of the ground because the state of the ground may be different from the predicted state as the state of the ground may change in real time. For example, on the ground, surrounding trees may grow in summer, the surface may get wet due to rainfall, and animals may stand. In addition, snow may accumulate on the ground in winter, and the inclination angle of the surface may change due to ice. In addition, the ground may change due to various factors, such as a floating population may exist in addition to such seasonal changes, and electric wires may be installed.

In addition, since the ground state determination model according to an embodiment may be pre-trained through machine learning and various machine learning techniques may be used, the type of machine learning technique is not limited. That is, the ground state determination model may be pre-trained based on the learning image information about the ground, and the ground state may be determined from the image information of the ground based on this model. Here, the ground state determination model may be trained by altitude. In this case, a plurality of ground state determination models may exist according to a preset altitude, and a ground state determination model corresponding to the current altitude of the drone may be used to determine the state of the ground. In other words, a plurality of ground condition discrimination models corresponding to a plurality of preset altitudes (for example, 150m, 100m, 50m, etc.) are learned based on the learning image information according to each altitude, and the ground corresponding to the altitude of the drone A state determination model can be used to determine the state of the ground.

Alternatively, in one embodiment, image information of the same ground may be obtained at different points through a turning flight of a drone, etc., and depth information of the image may be derived based on such image information, and through this You can also judge the status.

According to an embodiment of the present disclosure, when the state of the ground is determined as described above, the landing area may be determined based on the landing allowable condition information and the state of the ground. That is, a landing area that satisfies the landing allowance condition according to the landing allowance condition information may be determined based on the state of the ground. Here, the landing area may indicate an area in which the drone can land according to the size information of the drone within the image information in the ground direction.

For example, in an embodiment, when there are a plurality of areas in which the drone can land within the image information in the ground direction, the plurality of areas may be respectively represented as landing area candidates, and the optimal landing area among the plurality of landing area candidates You can decide. Here, the optimal landing area may be determined based on the above-described priority information.

Or, for example, in one embodiment, when there is no landing area within the image information of the ground direction, the range of searching the landing area is increased by increasing the altitude of the drone or moving the drone according to a preset method. The image information may be obtained again, and the landing area may be determined.

Thereafter, in the step of creating a landing flight path, an embodiment may move the drone to a position where a line of sight (LOI) to the landing area determined as described above is secured. Here, the LOI may mean field-of-sight information in consideration of the size information of the drone from the location of the current drone to the landing area, and may be a process for a straight flight path capable of moving the shortest.

Here, in an embodiment, when the LOI is secured from the current position of the drone to the landing area, the drone is not moved, and a flight path may be immediately generated based on this.

However, in an embodiment, when the LOI is not secured from the current drone position to the landing area, the drone may be moved to secure the LOI through altitude change or sea flight. Here, the altitude change may be performed based on the above-described search altitude information, and the turning flight may be performed based on the above-described turning radius information.

Or, for example, if the LOI is not secured even when the altitude change or turning flight is performed, the landing area may be determined again. That is, when there are a plurality of landing region candidates, another landing region candidate may be determined as the landing region. Alternatively, if there is no other landing area candidate, the drone may be moved to derive the landing area candidate again based on a wider range of image information.

Or, for example, even if the LOI considering the size information of the drone is not secured, if the avoidance flight path can be generated in consideration of location information such as obstacles in the image information, it may be generated and used for landing flight.

Or, for example, it is possible to gradually lower the altitude of the drone and create an evasive flight path based on image information to the ground in real time. In this case, since it is possible to continuously generate a new avoidance flight path as the altitude changes, a more diverse or efficient flight path may be created.

Finally, in the landing flight and landing phase, the landing of the drone may be controlled according to the flight path or the avoidance flight path created as described above. For example, one embodiment may acquire image information according to the flight path in real time through a vision sensor while controlling the landing flight of the drone according to the flight path, through which obstacles that may be changed or generated in real time ( For example, tree branches, birds, etc.) can be detected and avoided. That is, based on the image information acquired in real time, it is possible to continuously determine whether an obstacle exists in the flight path, and if an obstacle occurs, an evasive flight path can be immediately generated based on the image information, and based on this, the drone You can control the landing flight. Here, the avoidance flight path may be generated based on position information of an obstacle in the image information.

For example, an obstacle detection model learned in advance using machine learning may be used to detect an obstacle for securing an LOI or detect an obstacle in image information during a landing flight, and the obstacle detection model uses image information for learning about an obstacle. Thus, learning can be carried out.

For example, a ground condition determination model or an obstacle detection model may be provided through a chip or processor mounted on a drone, but may be provided by a separate server, etc., in this case, through a communication module mounted on the drone. Image information may be transmitted to a separate server, and result information derived from a separate server may be transmitted to a drone. However, this may vary depending on the implementation method as an example, but is not limited thereto.

3 is a block diagram of a drone control device for autonomous landing according to an embodiment of the present invention.

Referring to FIG. 3, the drone control apparatus 300 according to an embodiment of the present invention may include at least one processor 310, a memory 320, and a storage device 330. In addition, although not shown in FIG. 3, the drone control device 300 may include a vision sensor module, and at least one of a Global Navigation Satellite System (GNSS) module, a Global Positioning System (GPS) module, and an Inertial Measurement Unit (IMU) It may further include.

The processor 310 may execute a program command stored in the memory 320 and/or the storage device 330. The processor 310 may mean a central processing unit (CPU), a graphics processing unit (GPU), or a dedicated processor in which the methods according to the present invention are performed. The memory 320 and the storage device 330 may be formed of a volatile storage medium and/or a nonvolatile storage medium. For example, the memory 320 may be composed of read only memory (ROM) and/or random access memory (RAM).

The memory 320 may store at least one instruction executed through the processor 310. The at least one command is a command for acquiring target altitude information and landing allowable condition information of the destination, a command for acquiring image information of the ground direction at the target altitude of the destination according to the target altitude information, the landing allowable condition information and the ground A command to determine a landing area based on image information of a direction, a command to move the drone to a position where a line of sight (LOI) to the landing area is secured, a command to create a flight path based on the LOI, and the flight It may include a command to control the landing of the drone based on the path.

For example, the landing allowance condition information may include at least one of three-dimensional shape information of the drone, information about the landing area search range, and condition condition information of the landing area, and the state condition information of the landing area is the It may include basic condition information related to the safety of the drone and special condition information related to a specific mission of the drone.

Alternatively, the command for determining a landing area based on the landing allowable condition information and the image information of the ground direction is a command for deriving a state of the ground based on the image information of the ground direction and the landing based on the state of the ground. It may include a command for determining the landing area that satisfies the landing allowable condition according to the allowable condition information.

Alternatively, the command for determining the landing area that satisfies the landing allowance condition according to the landing allowance condition information based on the state of the ground, satisfies the landing allowance condition according to the landing allowance condition information based on the state of the ground. A command for deriving a plurality of landing area candidates and a command for determining one of the plurality of landing area candidates as the landing area based on priority information. Here, the priority information may be included in the landing permit condition information.

For example, the command for deriving the state of the ground based on the image information of the ground direction is an image of the ground direction using a pre-learned ground state determination model based on the learning image information about the ground through machine learning. It may include an instruction to derive the state of the ground from the information.

Or, for example, the ground state determination model includes a plurality of ground state determination models corresponding to a plurality of preset altitudes, and the plurality of ground state determination models are each based on training image information according to the plurality of elevations. It is learned, and the state of the ground may be derived based on a specific ground state determination model corresponding to the altitude of the drone among the plurality of ground state determination models.

Alternatively, the command for moving the drone to a location where the LOI to the landing area is secured may include a command to move the drone to a location where the LOI is secured through altitude change or turning flight. Here, the altitude change may be performed based on search altitude information, and the turning flight may be performed based on the turning radius information. In addition, the search altitude information and the turning radius information may be included in the landing allowance condition information.

For example, the landing area may be determined as a specific landing area candidate among a plurality of landing area candidates, and, for example, the command to move the drone to a position where the LOI to the landing area is secured may include changing the altitude or When the LOI is not secured through the turning flight, the landing area may include a command that is determined again as a landing area candidate different from the specific landing area candidate among the plurality of landing area candidates.

Or, for example, the command for controlling the landing of the drone based on the flight path is a command for obtaining image information according to the flight path, the presence of an obstacle in the flight path based on the image information according to the flight path A command for determining whether or not there is an obstacle in the flight path, generating an avoidance flight path, and a command for controlling the landing of the drone based on the avoidance flight path.

For example, the avoidance flight path may be generated based on location information of the obstacle in image information according to the flight path.

4 is a flowchart of a drone control method for autonomous landing according to an embodiment of the present invention.

Referring to FIG. 4, the drone control apparatus according to an embodiment of the present invention may acquire target altitude information and landing permission condition information of a destination (S410). For example, the landing allowance condition information may include at least one of three-dimensional shape information of the drone, information about the landing area search range, and condition condition information of the landing area, and the state condition information of the landing area is the It may include basic condition information related to the safety of the drone and special condition information related to a specific mission of the drone. That is, the user can set the basic condition information and the special condition information separately.

The drone control apparatus according to an embodiment may acquire image information in the direction of the ground at the target altitude of the destination according to the target altitude information (S420). Here, the image information may be acquired through a camera or a vision sensor mounted on a drone.

The drone control apparatus according to an embodiment may determine a landing area based on the landing permit condition information and the image information of the ground direction (S430). For example, in one embodiment, the state of the ground may be derived based on the image information of the ground direction, and the landing area that satisfies the landing allowance condition according to the landing allowance condition information may be determined based on the state of the ground. May be. Here, one embodiment may derive a plurality of landing area candidates that satisfy the landing allowance condition according to the landing allowance condition information based on the state of the ground, and when priority information is included in the landing allowance condition information, One of the plurality of landing area candidates may be determined as the landing area based on priority information.

For example, the state of the ground may be derived from the image information in the direction of the ground using a ground state determination model that has been learned in advance based on the learning image information about the ground through machine learning. Here, the ground state determination model may include a plurality of ground state determination models corresponding to a plurality of preset altitudes, and the plurality of ground state determination models are each trained based on the learning image information according to the plurality of altitudes. In this case, the state of the ground may be derived based on a specific ground state determination model corresponding to the altitude of the drone among the plurality of ground state determination models. However, since the state of the ground may be derived through another method described with reference to FIG. 2, it is not limited thereto.

The drone control apparatus according to an embodiment may move the drone to a position where a line of sight (LOI) to the landing area is secured (S440). For example, an embodiment may perform altitude change or turning flight to secure LOI. Here, the altitude change may be performed based on search altitude information in the landing allowance condition information, and the turning flight may be performed based on the turning radius information in the landing allowance condition information.

For example, when the landing area is determined as a specific landing area candidate among a plurality of landing area candidates, in one embodiment, when the LOI is not secured through the altitude change or the turning flight, the landing area is the plurality of Among the landing area candidates, the specific landing area candidate may be determined again as a different landing area candidate.

The drone control apparatus according to an embodiment may generate a flight path based on the LOI (S450), and control landing of the drone based on the flight path (S460). For example, in an embodiment, in a landing control process, image information according to the flight path may be obtained, and the existence of an obstacle in the flight path may be determined based on the image information according to the flight path, and the When there is an obstacle in the flight path, an avoidance flight path may be generated, and landing of the drone may be controlled based on the avoidance flight path. Here, the avoidance flight path may be generated based on location information of the obstacle in the image information according to the flight path.

The operation, function, or structure described with reference to FIG. 4 may be some of the embodiments of the present invention as an example. That is, it is obvious that an embodiment of the present invention may further include at least some of the various operations, functions, or structures described with reference to FIGS. 1 to 3 even if not illustrated in FIG. 4.

The operation according to an embodiment of the present invention can be implemented as a computer-readable program or code on a computer-readable recording medium. The computer-readable recording medium includes all types of recording devices that store data that can be read by a computer system. In addition, the computer-readable recording medium may be distributed over a computer system connected through a network to store and execute a computer-readable program or code in a distributed manner.

In addition, the computer-readable recording medium may include a hardware device specially configured to store and execute program commands, such as ROM, RAM, and flash memory. The program instructions may include not only machine language codes such as those produced by a compiler, but also high-level language codes that can be executed by a computer using an interpreter or the like.

While some aspects of the invention have been described in the context of an apparatus, it may also represent a description according to a corresponding method, where a block or apparatus corresponds to a method step or characteristic of a method step. Similarly, aspects described in the context of a method can also be represented by a corresponding block or item or a feature of a corresponding device. Some or all of the method steps may be performed by (or using) a hardware device such as, for example, a microprocessor, a programmable computer or electronic circuit. In some embodiments, one or more of the most important method steps may be performed by such an apparatus.

In embodiments, a programmable logic device (eg, a field programmable gate array) may be used to perform some or all of the functionality of the methods described herein. In embodiments, the field programmable gate array may work with a microprocessor to perform one of the methods described herein. In general, the methods are preferably performed by some hardware device.

Although the above has been described with reference to preferred embodiments of the present invention, those skilled in the art will variously modify and change the present invention within the scope not departing from the spirit and scope of the present invention described in the following claims. You will understand that you can do it.

Claims (10)

As a drone control method for autonomous landing,
Obtaining target altitude information and landing permit condition information of the destination;
Obtaining image information of a ground direction at a target altitude of the destination according to the target altitude information;
Determining a landing area based on the landing permit condition information and the image information of the ground direction;
Moving the drone to a position where a line of sight (LOI) to the landing area is secured;
Generating a flight path based on the LOI; And
Including the step of controlling the landing of the drone based on the flight path,
The landing allowance condition information includes at least one of three-dimensional shape information of the drone, search range information of the landing area, and state condition information of the landing area,
The state condition information of the landing area includes basic condition information related to the safety of the drone and special condition information related to a specific mission of the drone,
The basic condition information includes information about whether the landing area is above the water surface, information about whether the landing area is above a tree, information about the presence or absence of obstacles moving around, and information about the inclination angle of the destination,
The special condition information includes information on whether the landing area is lower in altitude than an area adjacent to the landing area and information on whether the landing area is higher in altitude than the adjacent area,
The step of moving the drone to a position where the LOI to the landing area is secured,
Including the step of moving the drone to a position where the LOI is secured through altitude change or turning flight,
The altitude change is performed based on search altitude information,
The turning flight is performed based on turning radius information,
The search altitude information and the turning radius information are further included in the landing allowance condition information. delete The method according to claim 1,
The step of determining a landing area based on the landing allowable condition information and the image information of the ground direction,
Deriving a state of the ground based on the image information in the direction of the ground; And
And determining the landing area that satisfies the landing allowance condition according to the landing allowance condition information based on the state of the ground. The method of claim 3,
The step of determining the landing area that satisfies the landing allowance condition according to the landing allowance condition information based on the state of the ground,
Deriving a plurality of landing area candidates satisfying a landing allowance condition according to the landing allowance condition information based on the state of the ground; And
And determining one of the plurality of landing area candidates as the landing area based on priority information,
The priority information is characterized in that included in the landing permit condition information, drone control method. The method of claim 3,
The step of deriving the state of the ground based on the image information in the direction of the ground,
And deriving the state of the ground from the image information in the direction of the ground using a pre-learned ground state determination model based on the training image information about the ground through machine learning. The method of claim 5,
The ground state determination model includes a plurality of ground state determination models corresponding to a plurality of preset altitudes,
Each of the plurality of ground state determination models is trained based on the learning image information according to the plurality of elevations,
The state of the ground is derived based on a specific ground state determination model corresponding to the altitude of the drone among the plurality of ground state determination models. delete The method according to claim 1,
The landing area is determined as a specific landing area candidate among a plurality of landing area candidates,
The step of moving the drone to a position where the LOI to the landing area is secured,
When the LOI is not secured through the altitude change or the turning flight, the landing area is re-determined as a landing area candidate different from the specific landing area candidate among the plurality of landing area candidates, How to control the drone. The method according to claim 1,
Controlling the landing of the drone based on the flight path,
Obtaining image information according to the flight path;
Determining whether or not an obstacle exists in the flight path based on image information according to the flight path; And
If there is an obstacle in the flight path, generating an avoidance flight path, characterized in that it comprises the step of controlling the landing of the drone based on the avoidance flight path, drone control method. The method of claim 9,
The avoided flight path is generated based on the position information of the obstacle in the image information according to the flight path.

Images