KR20160103353A - Apparatus for controlling unmanned aerial vehicle based on learning and method for setting path the same - Google Patents

Abstract

The present invention relates to a learning based unmanned aerial vehicle controller and a method for setting a path using the same. The unmanned aerial vehicle controller in accordance with the present invention, comprises: a motor control learning part which measures a motor control signal or a propeller rotation speed of an unmanned aerial vehicle in accordance with the height or movement direction of the unmanned aerial vehicle; a calculation part which calculates a representative value in respect of the motor control signal or the propeller rotation speed of the unmanned aerial vehicle in accordance with the height or movement direction of the unmanned aerial vehicle; a path learning part which measures a movement path where the unmanned aerial vehicle is automatically operated; a storage part which stores the representative value in respect of the motor control signal or the propeller rotation speed of the unmanned aerial vehicle in accordance with the height or movement direction of the unmanned aerial vehicle, and information about the movement path where the unmanned aerial vehicle is automatically operated; and a control part which controls the motor control signal or the propeller rotation speed of the unmanned aerial vehicle using the representative value in respect of the motor control signal or the propeller rotation speed of the unmanned aerial vehicle in accordance with the height or movement direction of the unmanned aerial vehicle and the information about the movement path where the unmanned aerial vehicle is automatically operated, which are received from the storage part. According to the present invention, the unmanned aerial vehicle is automatically operated using information about the motor control signal or the propeller rotation speed, and the information about the movement path, so is accurately moved along a designated movement path, thereby preventing a collision with an unexpected obstacle.

Description

BACKGROUND OF THE INVENTION 1. Field of the Invention [0001] The present invention relates to a learning-based unmanned aerial vehicle control apparatus,

The present invention relates to a learning-based unmanned aerial vehicle control device and a route setting method using the same, and more particularly, to a control device and a route setting method using the unmanned airplane control device for setting a travel route according to the position of an unmanned airplane.

UAV (Unmanned Aerial Vehicle) has advantages that it is easier to control than conventional aviation, and therefore many studies are being carried out to utilize it in various fields in recent years. Automatically controlling the aircraft can be used in various fields such as disaster relief, disaster prevention, security, and military purposes. In recent years, quadrotor type UAV has been actively studied, and it is required to control not only basic flight control but also autonomous flight in various environments.

In recent years, there has been studied a method of pre-learning quadrotor UAV by applying demo-based learning. This method has an advantage that it can be easily re-learned when the operating environment is changed as compared with other learning algorithms and planning algorithms. However, the existing demo-based learning is problematic in that it can not cope with the dynamic changes in the structure of the motor primitive, In addition, there is a problem that errors may occur as the movement path becomes longer when the movement path is learned by the demo-based learning.

Especially, the control method using the unmanned airplane by applying the demonstration based learning has been studied, but the accuracy of the monitoring or monitoring is low at the current technology level.

Also, according to the conventional automatic unmanned aerial vehicle operation system, the unmanned airplane can have an unexpected risk of collision with the obstacle because it is operated only by the GPS system. Especially, in case of urban landforms, there are many obstacles such as buildings, overpasses, and electric poles, so that the risk of unmanned airplanes colliding with obstacles becomes bigger in automatic operation.

BACKGROUND ART [0002] Techniques that serve as a background of the present invention are disclosed in Korean Patent Registration No. 10-0324581 (published on Feb. 16, 2002).

SUMMARY OF THE INVENTION It is an object of the present invention to provide a control apparatus for a learning-based unmanned aerial vehicle for controlling automatic operation of an unmanned airplane by setting a travel route according to the position of the unmanned airplane and a route setting method using the same.

According to another aspect of the present invention, there is provided an apparatus for controlling an unmanned airplane, comprising: a motor control signal learning unit for measuring a motor control signal or a propeller speed according to a height or a moving direction of an unmanned airplane; A calculation unit for calculating a representative value of a motor control signal or a propeller number of the unmanned airplane according to a height of the unmanned airplane or a moving direction of the unmanned airplane, A storage unit for storing a representative value of a motor control signal or a propeller number of the unmanned airplane according to a height or a moving direction of the unmanned airplane and learned travel path information of the unmanned airplane, In addition, according to the height of the stored unmanned aerial vehicle or the direction of movement, Or by using a central value as a learned travel path information of the UAV for the propeller rotational speed and a motor control signal or a control unit for controlling the number of revolutions of the propeller UAV.

The motor control signal learning unit may measure the motor control signal or the number of revolutions of the propeller according to the height or the moving direction of the unmanned airplane while making the unmanned airplane take off and land a plurality of times, turn left or right or turn right.

The motor control signal learning unit may measure the height of the UAV using at least one of an infrared sensor, an altitude sensor and an ultrasonic sensor, and sense the moving direction of the UAV by using a tilt sensor.

The path learning unit may move the user in a state that the user holds the unmanned airplane or move the unmanned airplane with the height measurement sensor and the GPS system connected to the moving means, And the GPS system mounted on the mobile terminal, thereby learning the route information of the unmanned aerial vehicle.

The path learning unit may acquire vertical path information of the movement path of the UAV through the height measurement sensor and obtain horizontal path information of the unmanned airplane through the GPS system.

According to another aspect of the present invention, there is provided a method of routing an unmanned aerial vehicle control device, comprising: measuring a motor control signal or a propeller speed according to a height or a moving direction of an unmanned airplane; Calculating a representative value of a motor control signal or a propeller rotational speed of the UAV according to a direction of the UAV; measuring three-dimensional coordinates of the learned route information in a course of learning the UAV travel path; Storing the representative value of the motor control signal or the propeller speed of the unmanned airplane according to the height of the aircraft or the moving direction and the learned travel route information of the unmanned airplane, A representative value of the motor control signal or the number of revolutions of the propeller, Using the learned travel path information of the unmanned aerial vehicle comprises the steps of controlling the motor control signal, or the number of revolutions of the propeller UAV.

According to the unmanned airplane control apparatus and method of the present invention, since the unmanned airplane automatically travels using the propeller rotation number information and the movement route information acquired through learning, the designated movement route is moved accurately, and thus collision with an unexpected obstacle Can be prevented.

FIG. 1 is a block diagram showing a configuration of an unmanned aerial vehicle control apparatus according to an embodiment of the present invention.
FIG. 2 is a diagram illustrating a path setting method of an unmanned aerial vehicle according to an embodiment of the present invention. Referring to FIG.
3 is a flowchart illustrating a route setting method of an unmanned aerial vehicle according to an embodiment of the present invention.
FIG. 4 is a diagram illustrating a rotation amount and a rotation direction of a propeller of a UAV according to the direction of movement of a UAV in the case of a quadrotor type UAV according to an embodiment of the present invention.

Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings so that those skilled in the art can easily carry out the present invention. The present invention may, however, be embodied in many different forms and should not be construed as limited to the embodiments set forth herein. In order to clearly illustrate the present invention, parts not related to the description are omitted, and similar parts are denoted by like reference characters throughout the specification.

First, a configuration of an unmanned airplane control device 100 according to an embodiment of the present invention will be described with reference to FIG. 1 is a block diagram showing a configuration of a control unit for an unmanned aerial vehicle.

1, the UAV controller 100 according to an embodiment of the present invention includes a motor control signal learning unit 110, an operation unit 120, a path learning unit 130, a storage unit 140, a control unit 150), and the unmanned airplane control device 100 can be installed inside the unmanned airplane.

More specifically, the motor control signal learning unit 110 measures the motor control signal or the propeller speed of the unmanned aerial vehicle according to the elevation or movement direction of the unmanned aerial vehicle.

Here, the motor control signal includes at least one of a transmission (ESC) signal (transmission speed signal), a PWM control signal, and a motor strength signal, and the number of revolutions of the propeller is determined according to the change of the motor control signal.

The motor control signal learning unit 110 may use a height measurement sensor to acquire information about the height of the UAV, and the height measurement sensor may include an infrared sensor, an altitude detection sensor, and an ultrasonic sensor. In addition, the motor control signal learning unit 110 may use a tilt sensor to acquire movement direction information of the unmanned airplane such as forward, backward, left turn, and right turn.

The motor control signal learning unit 110 transmits the motor control signal or the propeller rotation number of the unmanned airplane to the operation unit 120 according to the height or movement direction of the unmanned airplane.

The calculating unit 120 calculates an average value of the motor control signal or the propeller speed according to the height or the moving direction of the unmanned aerial vehicle received from the motor control signal learning unit 110. The calculation unit 120 transmits the average value of the motor control signal or the number of revolutions of the propeller to the storage unit 140 according to the height of the UAV or the movement direction of the UAV.

The path learning unit 130 measures three-dimensional coordinate information of the learned route information in the process of learning the route of the UAV. That is, the path learning unit 130 measures information about the learned travel route to be operated by the UAV, and the information about the route to be operated by the UAV is information about the vertical route and the horizontal route of the UAV .

The information on the vertical path among the information on the route on which the UAV will be automatically operated means information on the height from the landmarks of the UAV. The path learning unit 130 measures height information And the height measurement sensor may include an infrared sensor, an altitude detection sensor, and an ultrasonic sensor.

In addition, the information on the horizontal path among the information on the movement route on which the unmanned airplane will be automatically operated means information on the direction of the unmanned airplane of the unmanned airplane, and the path learning unit 130 uses the GPS system And an acceleration sensor can be used.

The path learning unit 130 transmits the information about the movement path of the measured unmanned airplane to the storage unit 140.

The storage unit 140 receives and stores the average value of the motor control signal or the propeller rotation number of the unmanned airplane according to the height of the unmanned airplane or the moving direction from the operation unit 120. In addition, the storage unit 140 receives information on the route to be automatically traveled by the unmanned airplane from the route learning unit 130 and stores the received information.

The storage unit 140 transmits the information received from the operation unit 120 and the path learning unit 130 to the controller 150.

The control unit 150 uses the average value of the motor control signal or the propeller speed of the unmanned airplane according to the height of the unmanned airplane stored in the storage unit 140 or the moving direction of the unmanned airplane, Controls the motor control signal or propeller speed of unmanned aerial vehicles.

When the unmanned airplane is automatically operated, the control unit 150 receives the information about the movement route to be automatically operated by the unmanned airplane from the storage unit 140, and sets the movement path of the unmanned airplane.

The control unit 150 receives the motor control signal or the propeller of the unmanned airplane according to the height of the unmanned airplane or the moving direction of the unmanned airplane from the storage unit 140 according to the information about the movement path of the unmanned airplane, And receives the average value of the number of revolutions to control the motor control signal or the number of revolutions of the propeller of the unmanned airplane.

Next, an unmanned aerial vehicle path setting method according to an embodiment of the present invention will be described with reference to FIG. 2 to FIG. FIG. 2 is a diagram illustrating a path setting method of an unmanned aerial vehicle according to an embodiment of the present invention. Referring to FIG.

As shown in FIG. 2, in the first learning step, the user of the UAV can operate the UAV by using the controller to obtain information on the motor control signal or the number of revolutions of the UAV according to the height or movement direction of the UAV.

Generally, as the altitude of the UAV increases, the rotation speed increases. Therefore, the UAV controller 100 calculates the average value of the motor control signal or the propeller rotation number of the UAV according to the height or movement direction of the acquired UAV And then stores it.

In the second learning step, the user moves the unmanned airplane along the movement path by holding the unmanned airplane in order to obtain the information about the movement route to be automatically operated. In this case, the unmanned airplane can be connected to other means of transportation such as automobiles.

During the movement of the UAV, the UAV controller 100 stores the position information (x, y coordinates) of the UAV by GPS information and the height information (z coordinate) .

Next, in the test step, using the motor control signal or the propeller rotational speed information according to the travel path and the height stored in the first learning step and the second learning step, the controller 150 controls the propeller so that the unmanned airplane travels through the learned path. To rotate automatically.

Hereinafter, a route setting method of the UAV will be described in detail with reference to FIG. 3 is a flowchart illustrating a route setting method of an unmanned aerial vehicle according to an embodiment of the present invention.

First, in the first learning step, the user of the unmanned airplane manages the unmanned airplane and measures the motor control signal or the number of revolutions of the unmanned airplane according to the height or the moving direction of the unmanned airplane (S310).

Unmanned aerial vehicles may vary in their equipment depending on their mission, so the weight of the unmanned aerial vehicle may vary according to each mission. Therefore, even if the unmanned airplane is driven by the same propeller speed, the height and the direction may be changed according to each mission.

For this reason, in order for an unmanned airplane to operate correctly according to a predetermined route, the unmanned airplane needs to acquire the propeller rotation information of the unmanned airplane in advance according to the height or movement direction in a state in which equipment necessary for a unique mission is mounted .

In this case, the height of the UAV means the vertical distance from the ground or the floor of the UAV to the UAV, and the direction of the UAV's horizontal movement means that the UAV is forward, backward, leftward or rightward.

FIG. 4 is a diagram showing the rotation amount and the rotation direction of the propeller of the UAV according to the direction of movement of the UAV in the case of a quadrotor type UAV.

In FIG. 4, each circle represents a propeller of a quadrotor-type unmanned aerial vehicle, and an arrow direction in a circle represents a rotation direction of a propeller of a quadrotor-type UAV. The thicker the arrow in the circle means the more revolutions of the propeller of the quad rotor type UAV, and the smaller the thickness of the arrow, the less the rotation speed of the propeller of the quad rotor type UAV. Thus, the UAV controls the direction of movement by controlling the number of revolutions of each propeller.

In order to obtain information about the propeller speed of the UAV according to the elevation or movement direction of the UAV, the user of the UAV uses the UAV of the UAV to move the UAV to and from the takeoff and landing direction at least once.

For example, a user of an unmanned airplane uses an unmanned airplane's manipulator to take off the unmanned airplane at a height of 10 meters. The user of the unmanned airplane then measures the motor control signal or the propeller speed of the unmanned airplane by moving the unmanned airplane at least once in each direction such as forward, backward, left turn, and right turn using the pilot of the unmanned airplane. The user of the unmanned airplane measures the propeller speed of the unmanned airplane at a height of 10 meters, and then measures the motor control signal or the propeller speed of the unmanned airplane more than once at another height.

At this time, the motor control signal learning unit 110 may use a height measurement sensor to obtain height information of the UAV, and the height measurement sensor may include an infrared sensor, an altitude detection sensor, and an ultrasonic sensor. In addition, the motor control signal learning unit 110 may use a tilt sensor to acquire movement direction information of the unmanned aerial vehicle.

The motor control signal learning unit 110 transmits the motor control signal or the propeller rotation number information of the unmanned airplane to the operation unit 120 according to the measured height or movement direction of the unmanned airplane.

The calculation unit 120 calculates the number of revolutions of the unmanned airplane using the motor control signal of the unmanned airplane or the number of revolutions of the propeller according to the height or movement direction of the unmanned airplane, The average value of the control signal or the number of revolutions of the propeller is calculated and stored in the storage unit 140 (S320).

For example, when the unmanned airplane makes a left turn at a height of 10M, which is received by the operation unit 120, it is assumed that the propeller rotation number of the unmanned airplane is 1900RPM and 2100RPM. At this time, the calculation unit 120 calculates 2000 RPM which is an average value of 1900 RPM and 2100 RPM.

The operation unit 120 transmits the average value of the motor control signal or the propeller rotation number of the unmanned airplane to the storage unit 140 according to the height or movement direction of the calculated unmanned airplane, The average value of the motor control signal or the propeller speed of the unmanned aerial vehicle transmitted is stored by height or movement direction.

Meanwhile, in the embodiment of the present invention, the average value of the motor control signal or the propeller speed is stored for the sake of convenience of explanation, but it is also possible to store the representative value except for the large standard deviation.

Next, in the second learning step, the path learning unit 130 measures information about the learned travel route to be automatically traveled by the UAV, and the storage unit 140 stores the information of the unmanned airplane measured by the path learning unit 130 And stores information about the learned travel route (S330).

That is, the user of the UAV can measure the movement path of the UAV by hanging the UAV on the movement path along which the UAV is to be automatically operated, or by hanging on the other means such as a car.

In addition, it is also possible to learn the route information of the unmanned aerial vehicle by suspending and moving the height measuring sensor to the moving means equipped with the GPS system without mounting the unmanned airplane to the other moving means.

The movement path where the unmanned aerial vehicle is to be automatically operated includes a vertical path and a horizontal path. Here, the vertical path means the distance from the bottom of the land or building to the position of the UAV, and the horizontal path means the direction of horizontal movement of the UAV.

The path learning unit 130 may use a height measurement sensor to acquire information on the vertical path (Z coordinate) of the movement path of the UAV. At this time, the height measurement sensor may include an infrared sensor, an altitude detection sensor, an ultrasonic sensor,

The path learning unit 130 may use a GPS system to acquire information on the horizontal path (XY coordinate) of the movement path of the UAV. In addition, the path learning unit 130 may use an acceleration sensor to acquire information on the horizontal path in the movement path of the UAV.

The path learning unit 130 transmits information about the learned travel path to the storage unit 140 in step S330, and the storage unit 140 stores information about the learned travel path.

Next, in the test step, the control unit 150 controls the motor control signal of the unmanned aerial vehicle according to the height of the unmanned airplane or the moving direction of the unmanned airplane, The motor control signal or the number of revolutions of the propeller of the unmanned airplane is controlled by using the number average value and information on the learned travel route (S340).

That is, when the unmanned airplane is automatically operated, the control unit 150 sets the movement path of the unmanned airplane according to the learned information about the unmanned aircraft received from the storage unit 140. The control unit 150 receives the motor control signal or the average value of the propeller rotation number of the unmanned airplane according to the height of the unmanned airplane or the moving direction from the storage unit 140 according to the set movement path, .

For example, it is assumed that the control unit 150 receives information about the vertical path from the learned path of the unmanned aerial vehicle received from the storage unit 140, and the horizontal path is the left turn. The control unit 150 receives the average value of the propeller rotation number of the unmanned airplane when the left turn at a height of 10 meters from the storage unit 140. [ At this time, assuming that the average value of the propeller rotation speed of the unmanned airplane at the time of the left turn at the height of 10M is 2000 RPM, the control unit 150 controls the propeller rotation speed of the unmanned airplane to 2000 RPM.

As described above, the controller 150 controls the motor control signal or the propeller rotation number of the unmanned airplane when the automatic unmanned airplane travels on the measured movement path of the unmanned airplane, and the unmanned airplane manages the unmanned airplane in the first learning step and the second learning step The learned movement path is moved.

Unmanned aircraft may have an unexpected risk of collision with an obstacle if it is operated only by the GPS system as in the case of the conventional automatic unmanned aerial vehicle operation. Especially, in the case of urban landforms, since there are many obstacles such as buildings, overpasses and electric poles, the risk of unmanned aircraft colliding with obstacles becomes larger when the vehicle is automatically operated.

However, according to the controller and the method for controlling the unmanned airplane according to the embodiment of the present invention, since the unmanned airplane automatically runs using the motor control signal or the propeller rotation number information and the movement route information acquired through learning, The collision with an unexpected obstacle can be prevented.

The present invention has been described above with reference to the embodiments. It will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the invention as defined by the appended claims. Therefore, the disclosed embodiments should be considered in an illustrative rather than a restrictive sense. Therefore, the scope of the present invention is not limited to the above-described embodiments, but should be construed to include various embodiments within the scope of the claims and equivalents thereof.

100: Unmanned aerial vehicle control device,
110: motor control signal learning unit, 120:
130: path learning unit, 140: storage unit,
150:

Claims (10)

A motor control signal learning unit for measuring a motor control signal or a propeller speed according to the height or movement direction of the UAV,
A calculating unit for calculating a representative value of the motor control signal or the number of revolutions of the propeller of the unmanned airplane according to the height or movement direction of the unmanned airplane,
A path learning unit for measuring three-dimensional coordinates of the learned travel path information in the process of learning the travel path of the UAV,
A storage unit for storing a representative value of the motor control signal or the number of revolutions of the propeller of the unmanned airplane and the learned travel path information of the unmanned airplane according to the height or movement direction of the unmanned airplane,
Controlling the motor control signal or the number of revolutions of the propeller of the unmanned airplane using the representative value of the motor control signal or the propeller speed according to the height or the moving direction of the stored unmanned airplane and the learned travel route information of the unmanned airplane And a control unit. The method according to claim 1,
Wherein the motor control signal learning unit comprises:
And measures the motor control signal or the number of revolutions of the propeller according to the height or the moving direction of the unmanned airplane while making the unmanned airplane take off and land a plurality of times, left turn or right turn. 3. The method of claim 2,
Wherein the motor control signal learning unit comprises:
Wherein the height of the unmanned airplane is measured using at least one of an infrared sensor, an altitude detection sensor and an ultrasonic sensor, and the moving direction of the unmanned airplane is detected using a tilt sensor. The method according to claim 1,
Wherein the path learning unit comprises:
The user moves the unmanned airplane while holding the unmanned airplane or moves the unmanned airplane attached with the height measurement sensor and the GPS system to the moving means while the height measurement sensor and the GPS system are mounted on the moving means And acquires travel route information of the unmanned airplane. 5. The method of claim 4,
Wherein the path learning unit comprises:
Acquiring vertical path information of the movement path of the UAV through the height measurement sensor and obtaining horizontal path information of the movement path of the UAV through the GPS system. A method for setting an unmanned aerial vehicle path of a control device for an unmanned airplane,
Measuring a motor control signal or a propeller speed according to a height or a moving direction of the unmanned aerial vehicle,
Calculating a representative value of the motor control signal or the number of revolutions of the propeller of the unmanned airplane according to the height or movement direction of the unmanned airplane,
Measuring three-dimensional coordinates of the learned route information in the process of learning the movement route of the UAV;
Storing the representative value of the motor control signal or the number of revolutions of the propeller of the unmanned airplane and the learned travel path information of the unmanned airplane according to the height or movement direction of the unmanned airplane,
Controlling the motor control signal or the number of revolutions of the propeller of the unmanned airplane using the representative value of the motor control signal or the propeller speed according to the height or the moving direction of the stored unmanned airplane and the learned travel route information of the unmanned airplane Wherein the unmanned airplane route setting method comprises the steps of: The method according to claim 6,
In the step of measuring the motor control signal or the propeller speed,
And measuring the motor control signal or the number of revolutions of the propeller according to the height or the moving direction of the unmanned airplane while making the unmanned airplane take off and land a plurality of times, take a left or right turn or make a right turn. 8. The method of claim 7,
In the step of measuring the motor control signal or the propeller speed,
Measuring a height of the unmanned air vehicle using at least one of an infrared sensor, an altitude sensor and an ultrasonic sensor, and detecting a moving direction of the unmanned air vehicle using a tilt sensor. The method according to claim 6,
The step of learning and measuring the route information of the unmanned aerial vehicle includes:
The user moves the unmanned airplane while holding the unmanned airplane or moves the unmanned airplane attached with the height measurement sensor and the GPS system to the moving means while the height measurement sensor and the GPS system are mounted on the moving means And learning the route information of the unmanned airplane. 10. The method of claim 9,
The step of learning and measuring the route information of the unmanned aerial vehicle includes:
Acquiring vertical path information of a route of the unmanned airplane through a height measuring sensor and acquiring horizontal path information of the unmanned airplane through a GPS system installed on the unmanned airplane.

Images