KR102352881B1 - Methods for setting up dangerous air space for unmanned aerial vehicles - Google Patents

Abstract

An objective of the present invention is to provide a hazard weather airspace setting method for an unmanned aerial vehicle, wherein by determining the weather data value step-by-step and using a decision-making tree to determine whether or not to set a hazard weather airspace, a hazard caused by the weather factors of the unmanned aerial vehicle is minimized by quickly determining the hazard weather airspace that variously changes according to a weather condition in a flight airspace of the unmanned aerial vehicle. The hazard weather airspace setting method comprises: an origin and destination setting step; a generating step; a weather data receiving step; a topographic data receiving step; a writing step; and a hazard weather airspace setting step.

Description

Hazardous weather airspace setting method for unmanned aerial vehicles {METHODS FOR SETTING UP DANGEROUS AIR SPACE FOR UNMANNED AERIAL VEHICLES}

The present invention relates to a method for setting a dangerous weather area for an unmanned aerial vehicle, and more particularly, by judging the weather data value step by step and using a decision tree to determine whether to set the dangerous weather airspace, to set the dangerous weather area It relates to a method of setting up a dangerous weather area for an unmanned aerial vehicle for an unmanned aerial vehicle.

An unmanned aerial vehicle (UAV) is a vehicle that flies autonomously or remotely without a passenger on board. At first, it was mainly used for military purposes, but now it is being used in various industries such as sports broadcasting, disaster site shooting, investigative reporting, and delivery service, and the commercial unmanned aerial vehicle market is growing very rapidly.

As the spread and use of unmanned aerial vehicles increases, accidents in which unmanned aerial vehicles fall are increasing. The causes of the crash of unmanned aerial vehicles are human error, equipment defects, and environmental factors, and research is being conducted on the development of high-quality flight equipment to increase the stability of the unmanned aerial vehicle, flight education and development of unmanned navigation technology.

The prior art (Patent Document 1) relates to a system for setting a path for a drone and a method for setting a path thereof, and sets a path based on weather information collected by the drone, and sets the path by avoiding areas with problems in the flight of the drone How to do it is disclosed.

However, since the prior art utilizes only the wind strength and direction as weather information, there is a problem in that it cannot quickly respond to various weather phenomena.

Republic of Korea Patent Publication No. 10-2062661 (Title of the invention: Drone route setting system and route setting method thereof, announcement date: 2020.01.06.)

Accordingly, the present invention is to solve the problems of the prior art as described above, and by judging meteorological data values step by step and utilizing a decision tree to determine whether to set a dangerous weather area, the weather conditions within the flight airspace of the unmanned aerial vehicle The purpose of this is to provide a method for setting up a dangerous weather area for an unmanned aerial vehicle that minimizes the risk caused by the weather factors of the unmanned aerial vehicle by quickly determining the dangerous weather airspace that varies according to the weather conditions.

In order to solve the above problems, the dangerous weather airspace setting method for an unmanned aerial vehicle according to the present invention is a starting point and destination setting step of setting the locations of the departure point and the destination in the dangerous weather airspace setting method for the unmanned aerial vehicle And, a grid point generating step of generating a grid point in the flight airspace between the departure point and the destination, a meteorological data receiving step of receiving weather data including at least one or more weather elements; a topographic data receiving step of receiving topographic data including at least one of height, type, and area; A decision tree creation step of creating a decision tree to determine whether to set the dangerous weather airspace of the grid points by alternately determining the data values step by step, and whether to set the dangerous weather airspace determined by the decision tree and a dangerous weather airspace setting step of setting the dangerous weather airspace at the grid point, wherein in the decision tree preparation step, the weather data is actually measured up to the grid point within the time for the unmanned aerial vehicle to reach the corresponding grid point Using data, grid points over time are characterized by corresponding prediction data.

delete

delete

delete

According to the method for setting a dangerous weather area for an unmanned aerial vehicle of the present invention, there are one or more of the following effects.

First, by using a decision tree that determines whether or not to set up a dangerous weather zone by judging the weather data value step by step, there is an advantage in that it can quickly determine the dangerous weather zone even in the case of various weather phenomena caused by complex factors.

Second, there is an advantage in that it is possible to minimize the risk due to the weather factors of the unmanned aerial vehicle by setting the dangerous weather airspace within the flight area of the unmanned aerial vehicle and flying by avoiding it.

Third, when creating a decision tree, it is possible to effectively identify weather phenomena that appear differently depending on the terrain by considering not only meteorological data but also topographical data to determine whether or not to set up a dangerous meteorological airspace.

Fourth, by combining the measured data of the weather data and the predicted data, it is possible to predict future weather conditions in advance to improve the accuracy of setting dangerous weather airspace and to maximize the stability of the unmanned aerial vehicle.

Effects of the present invention are not limited to the effects mentioned above, and other effects not mentioned will be clearly understood by those skilled in the art from the description of the claims.

1 is a flowchart of a method for setting dangerous weather airspace for an unmanned aerial vehicle according to an embodiment of the present invention.
2A and 2B are diagrams schematically illustrating grid points according to an embodiment of the present invention.
3 is a diagram schematically illustrating a decision tree according to an embodiment of the present invention.
4A and 4B are diagrams for explaining a method for setting a dangerous weather airspace for an unmanned aerial vehicle according to an embodiment of the present invention.

Advantages and features of the present invention and methods of achieving them will become apparent with reference to the embodiments described below in detail in conjunction with the accompanying drawings. However, the present invention is not limited to the embodiments disclosed below, but may be implemented in various different forms, and only these embodiments allow the disclosure of the present invention to be complete, and common knowledge in the art to which the present invention pertains It is provided to fully inform those who have the scope of the invention, and the present invention is only defined by the scope of the claims. Like reference numerals refer to like elements throughout.

The terminology used herein is used to describe specific embodiments, not to limit the present invention. As used herein, the singular form may include the plural form unless the context clearly dictates otherwise. In addition, when a part "includes" a certain component throughout the present specification, it means that other components may be further included unless otherwise stated.

Hereinafter, the present invention will be described with reference to the drawings in order to explain a method for setting a dangerous weather area for an unmanned aerial vehicle according to embodiments of the present invention.

1 is a flowchart of a method for setting a dangerous weather area for an unmanned aerial vehicle according to an embodiment of the present invention.

Referring to Figure 1, the dangerous weather airspace setting method for an unmanned aerial vehicle according to the present invention includes a departure point and destination setting step (S10), a grid point generation step (S20), a weather data reception step (S30), a terrain data reception step (S40), a decision tree writing step (S50), including a dangerous weather airspace setting step (S60).

First, in the departure point and destination setting step (S10), location information of the departure point and the destination of the unmanned aerial vehicle 1 is set. In this case, the location information of the departure point and the destination may be coordinates in which latitude, longitude, and altitude are x, y, and z values. The starting point may be a place where the unmanned aerial vehicle 1 is currently located, and the destination may be an area where there are buildings, people, etc. for the unmanned aerial vehicle 1 to perform a specific mission.

Referring to FIG. 2A , in the grid point generation step S20 , grid points 3 are generated in the flight airspace between the departure point and the destination. The grid points 3 may be formed in the airspace between the departure and destination, including the departure and destination, while maintaining a constant horizontal distance with a predetermined size, and may be formed in a three-dimensional cylindrical shape upward from the ground. The size of the grid points 3 may be set and changed by a user, such as 1 meter, 2 meters, or 10 meters, and the horizontal spacing between grid points 3 may also be set and changed. At this time, according to the method for setting the dangerous weather airspace for the unmanned aerial vehicle according to the present embodiment, the height formed in the form of a three-dimensional cylinder from the ground is preferably formed up to a maximum of 2 km.

In addition, although the flight airspace between the departure point and the destination is shown in a rectangular shape in FIG. 2A , a method for determining the airspace between the departure point and the destination may be formed in various ways regardless of what is shown in the drawing.

In addition, referring to FIG. 2B , the lattice points 3 formed in a three-dimensional cylindrical shape may be formed by being vertically divided at regular intervals, and the vertical spacing of the lattice points 3 may be set by the user, such as 1 meter, 10 meters, and the like. can be changed.

Referring back to FIG. 1 , in the meteorological data receiving step S30 , meteorological data may be received from a meteorological service provider such as the Korea Meteorological Administration in real time or at regular intervals. Meteorological data is composed of measured data and predicted data. Actual data can be prepared based on data observed every minute from ground observation systems AWS, ASOS, etc., and forecast data are prepared from digital forecast data that are quantitatively forecasted for 48 hours at 3-hour intervals from meteorological service providers such as the Korea Meteorological Administration can be By combining the predicted data with the measured data, the accuracy of setting the dangerous weather zone 5 can be improved.

In addition, the meteorological data includes at least one or more meteorological elements. Meteorological factors can be various, such as air pressure, temperature, humidity, wind direction, wind speed, cloud amount, cloud shape, precipitation, thunderstorm, fog, and the like.

In the topographic data receiving step S40 , topographic data including at least one of a height, a type, and an area of a topographical feature existing at the grid point 3 is received. Here, the type of the feature may be a building, a mountain, the sea, or the like.

In the decision tree creation step (S50), the received weather data value is matched according to the location of the grid point (3), and the weather data value is determined step by step to determine whether the dangerous weather airspace (5) of the grid point (3) is set. Write a decision tree to make a decision. In addition, it is possible to determine whether to set the dangerous weather airspace 5 by further considering the topographic data. Here, the dangerous weather area 5 means an area in which the unmanned aerial vehicle 1 cannot fly due to weather factors.

Dangerous weather caused by wind can change due to various causes, such as the direction and strength of the wind, and the presence and size of obstacles. When the wind blows into the mountains, the windward side, the downwind side, tends to have a greater intensity of turbulence than the upwind side, the windward side. Therefore, it is possible to effectively predict dangerous weather conditions such as turbulence by considering topographical information. Accordingly, by judging the weather data and the terrain data together through the decision tree step by step, it is possible to effectively set the dangerous weather area 5 within the flight area of the unmanned aerial vehicle 1 .

Here, when the received weather data value corresponds to the grid point 3 , the measured data value and the predicted data value may be appropriately matched according to the time taken from the departure point to the corresponding grid point 3 . For example, if there is a prediction data value that predicts one hour later, the actual data value corresponds to the grid points 3 that can be reached within one hour, and the grid points 3 that exceed one hour correspond to the prediction data can be matched. Through this, even if the flight time of the unmanned aerial vehicle 1 lasts for a long time, by setting the dangerous weather area 5 by predicting the weather conditions that will occur later in advance, the prediction accuracy is improved and the stability of the unmanned aerial vehicle 1 is improved. can be maximized.

3 is a diagram schematically illustrating a decision tree according to an embodiment of the present invention.

Referring to FIG. 3 , the decision tree is composed of nodes, branches, and leaves. Each node represents a feature or attribute, each branch represents a decision or rule, and each leaf represents a result. Each node can be a height, type, or area of a meteorological element or feature. In addition, each branch may be determined by factors, and a factor determining a branch may be determined according to a node in which the branch is formed. For example, as shown in FIG. 3 , when the node where the branch is formed is the strength of the wind, the factor may be set to a specific value for the strength of the wind, such as a wind speed of 5 m/s or less and 5 m/s or more. . In addition, the leaf value derived by the node and branch can be a dangerous weather case for determining whether to set the dangerous weather area (5), and accordingly, a decision is finally made to determine whether to set the dangerous weather area (5) can do.

In FIG. 3, the wind direction, wind strength, and hourly precipitation can be nodes, and east and west winds, 5 m/s, and 5 mm/s can be factors that determine branching, and all airspaces can be used, downwind side A ban on low-altitude flying, a ban on flying under the wind, and a ban on the use of all airspace can be a leaf.

Here, the dangerous weather case is dangerous weather for weather conditions that are complexly caused by each meteorological phenomenon and topographical factors, such as all flights available, no low-altitude flight under the wind, no flight under the wind, no use of all airspace, etc. It means a case divided to determine whether to set the airspace (5). For example, if there is a building or mountain in the flight airspace, even if the wind strength is the same, the unmanned aerial vehicle 1 can fly normally on the upwind side, but turbulence occurs on the downwind side, making flight impossible. A hazardous weather case may be established to prohibit use of the downwind airspace.

In addition, the dangerous weather case may be determined in various ways. It can be arbitrarily determined by users such as airspace designers and controllers, and airspace usability can be set based on the results of analyzing the building style using numerical analysis techniques.

As shown in FIG. 3 , the decision tree can set the dangerous weather airspace 5 by dividing the dangerous weather cases by considering several factors in a complex way based on the input value. Although only the wind direction, strength, and hourly precipitation are considered in FIG. 3 , FIG. 4 is only schematically illustrated for explanation, and in reality, a dangerous weather case may be determined by a wide variety of factors.

In addition, weights are determined for the weather elements and terrain data set in each node, so that an optimal decision tree for determining whether to set the dangerous weather airspace 5 can be made.

The weight of each item in the decision tree can be obtained by using a machine learning algorithm. Available machine learning algorithms include Python, R, Gradient Boosting Classifier, Support Vector Machines, Random Forest, and KNN, and they can be used overlapping each other. Using these machine learning algorithms, an optimal decision tree can be created.

In addition, as the physical quantity input to the decision tree, observation values such as temperature, humidity, wind speed, wind direction, and atmospheric pressure can be used. A composite value of basic physical quantities such as heating temperature, temperature, vortex, etc. may be used. Factors and weights that determine branching of a decision tree can be variously determined by multivariate analysis, and which value to use as a branching condition to determine a tree can be determined through data-based calculations.

In addition, in making a decision based on the weather data and the terrain data value, only the weather data value or the terrain data value may be set in each node, or both the weather data and the terrain data may be set to process the decision. When both the weather data and the terrain data are set, the order in which the nodes are set is not determined and can be determined by using an algorithm as described above, so that the weather data and the terrain data can be determined step by step alternately.

4A and 4B are diagrams for explaining a method for setting a dangerous weather airspace for the unmanned aerial vehicle 1 according to an embodiment of the present invention.

Referring to FIG. 4 , in the dangerous weather airspace setting step S60 , the obtained meteorological data is input to the decision tree to set the dangerous weather airspace 5 at the grid point 3 .

As shown in FIG. 4A , in the case of a westerly wind, A and B, which are the windward sides, correspond to the windward side, and C, D, E, and F, which are the windward sides, correspond to the downwind side with respect to the terrain. At this time, it is possible to set the dangerous weather airspace (5) according to the wind speed. For example, when the input value is 3 m/s or less, all grid points (3) are airspace in which the air can fly, and when the wind speed exceeds 3 m/s and less than 5 m/s, C2, C3, and C4 are set as dangerous weather airspace (5). , When the wind speed exceeds 5m/s and below 10m/s, C2, C3, C4, D2, D3, and D4 are set as dangerous weather airspace (5), and when the wind speed exceeds 10m/s, all grid points (3) are set as dangerous weather Can be set to airspace (5).

In addition, as shown in FIG. 4B , in the case of the east wind, C, D, E, and F, which are the windward sides, correspond to the windward side, and the windward sides, A and B, correspond to the windward side. Therefore, in this case, when the wind speed is 3 m/s or less, all grid points (3) are flightable airspace, and when the wind speed exceeds 3 m/s and 5 m/s or less, B2, B3, and B4 are set as dangerous weather airspace (5), and the wind speed When it exceeds 5 m/s and below 10 m/s, B2, B3, B4, A2, A3, A4 is set as the dangerous weather airspace (5), and when the wind speed exceeds 10 m/s, all grid points (3) 5) can be set.

As such, the degree of risk of the grid point (3) varies according to the direction and strength of the wind, and based on the dangerous weather case determined through the decision tree, finally the hazardous weather area (5) for each grid point (3) can be set.

In addition, in the above, the dangerous meteorological airspace 5 was set only according to the direction and strength of the wind, but since the meteorological phenomenon appears as a combination of complex factors, it is a decision tree that determines whether each of the weather elements satisfies a specific value step by step By writing , the dangerous weather airspace 5 can be set in consideration of all elements of the entered meteorological data, and as shown in FIG. (5) can be set.

For example, in the case of FIG. 4, when the wind speed is 3 m/s or less, all grid points 3 are in flightable airspace, but when the wind speed is 3 m/s or less but the precipitation is very high as 60 mm/h The grid point (3) can be set as the dangerous weather airspace (5) according to the step-by-step determination of the decision tree.

As described above, although preferred embodiments of the present invention have been illustrated and described with reference to the drawings, the present invention is not limited to the specific embodiments described above, and the present invention is not limited to the scope of the present invention as claimed in the claims. Various modifications may be made by those of ordinary skill in the art to which the invention pertains, and these modifications should not be individually understood from the technical spirit or prospect of the present invention.

1: Unmanned aerial vehicle
3: grid points
5: Dangerous weather airspace

Claims (4)

In the method for setting a dangerous weather area for an unmanned aerial vehicle,
A source and destination setting step of setting the location of the source and destination;
a grid point generation step of generating grid points in the flight airspace between the departure point and the destination;
a meteorological data receiving step of receiving meteorological data including at least one meteorological element;
a topographic data receiving step of receiving topographic data including at least one of a height, a type, and an area of a feature existing at the grid point;
Decision-making in which the weather data value and the terrain data value are matched according to the location of the grid point, and the weather data value and the terrain data value are determined alternately step by step to determine whether to set the dangerous weather airspace of the grid point Decision tree creation step of creating a tree;
Dangerous weather airspace setting step of setting the dangerous weather airspace at the grid points according to whether the dangerous weather airspace is set determined by the decision tree;
In the decision tree writing step,
The weather data is dangerous weather for the unmanned aerial vehicle, characterized in that the actual data is used up to the grid point within the time for the unmanned aerial vehicle to reach the corresponding grid point, and the grid point exceeding the time corresponds to the predicted data How to set up airspace. delete delete delete

Images