Apparatus and method for generating path for unmanned aerial vehicle

Abstract

An apparatus for generating a path for an unmanned aerial vehicle, the apparatus comprising: a data collection unit that collects flight data in real time via an integrated sensor module; a flight plan setting unit that analyzes a current location, altitude, speed, battery status, and obstacle information of the unmanned aerial vehicle on the basis of the collected data and establishes a flight plan; a flight path generation unit that generates a predefined flight path data file on the basis of data from the flight plan setting unit; a communication unit that transmits the flight path data file to a flight control device of the unmanned aerial vehicle; a flight path modification unit that dynamically modifies the flight path data in response to real-time dynamic environmental changes or variables occurring during flight to establish a new flight path; and a landing control unit that, when the battery level of the unmanned aerial vehicle drops below a preset threshold level, modifies the flight path to search for a nearest priority landing zone and controls landing at the priority landing zone.

Description

Path generation device and method for unmanned aerial vehicles

[0001] The present invention relates to a path generation device and method for an unmanned aerial vehicle (UAV), and more specifically, to a path generation device and method for an unmanned aerial vehicle that acquires real-time location information using RTK (Real-Time Kinematic) and GPS (Global Positioning System) and generates an optimized path through artificial intelligence learning.

[0002] The commercialization of unmanned aerial vehicles, particularly drones, is rapidly expanding across various fields such as logistics, rescue, surveillance, and agriculture. This proliferation of drones, coupled with advancements in autonomous flight technology, is enabling safe and efficient utilization in a wider range of areas. For instance, in the logistics sector, they allow for rapid delivery that avoids traffic congestion, while in rescue operations, they can support real-time monitoring and life-saving operations even in hazardous environments.

[0003] However, several technical challenges remain to be addressed for the commercialization of autonomous flight technology. In particular, due to limited battery capacity, path optimization is essential to enhance energy efficiency during flight. Currently, unmanned aerial vehicles rely heavily on GPS and inertial measurement units, but accuracy can be degraded in urban areas or mountainous terrain due to signal reflection and blockage. Therefore, these technical limitations must be overcome to ensure stable flight.

[0004] In addition, the existing system illustrated in Fig. 1 is designed to follow only a preset path, making it difficult to flexibly respond to unexpected obstacles or weather changes. This necessitates the development of an autonomous flight system capable of real-time environmental monitoring and path adjustment.

[0005] The present invention aims to provide an unmanned aerial vehicle capable of setting an optimal path to respond quickly to unexpected obstacles or sudden weather changes.

[0006] In addition, the present invention aims to provide an unmanned aerial vehicle capable of setting an optimal path to minimize battery consumption.

[0007] A path generation device for an unmanned aerial vehicle according to one embodiment of the present invention may include: a data collection unit that collects flight data in real time through an integrated sensor module comprising at least one of RTK, GPS, LiDAR sensor, ultrasonic sensor, inertial measurement unit (IMU), and thermal imaging camera; a flight plan setting unit that sets a flight plan by analyzing the current position, altitude, speed, battery status, and obstacle information of the unmanned aerial vehicle based on the data collected by the data collection unit; a flight path generation unit that generates a predefined flight path data file based on the data generated by the flight plan setting unit; a communication unit that transmits the flight path data file generated by the flight path generation unit to a flight control unit of the unmanned aerial vehicle; a flight path modification unit that sets a new path by dynamically modifying the flight path data according to dynamic environmental changes or variables occurring in real time during flight; and a landing control unit that modifies the flight path to search for the nearest priority landing zone and controls the unmanned aerial vehicle to land in the priority landing zone when the battery status of the unmanned aerial vehicle decreases below a preset threshold level.

[0008] According to one embodiment, the flight plan setting unit can modify the flight path to reduce battery consumption when the battery temperature of the unmanned aerial vehicle exceeds a preset threshold.

[0009] According to one embodiment, the flight plan setting unit can set the flight plan of an unmanned aerial vehicle using an Adaptive Fuzzy Logic System.

[0010] According to one embodiment, the flight plan setting unit can predict obstacle-dense areas in advance by integrating three-dimensional map data and LiDAR scan data that are stored in advance or acquired from a server, and dynamically generate flight path data based on the data regarding the predicted obstacle-dense areas.

[0011] According to one embodiment, the flight path generation unit generates path data that minimizes flight time and battery consumption according to the flight environment of the unmanned aerial vehicle, and can set weight-based priorities according to the mission execution goals of the unmanned aerial vehicle.

[0012] According to one embodiment, the communication unit can automatically switch the data transmission protocol when a data transmission delay or communication failure occurs between the unmanned aerial vehicle and the flight control module.

[0013] According to one embodiment, the flight path correction unit monitors the surrounding environment in real time during the flight of the unmanned aerial vehicle and can correct the flight path in response to unexpected obstacles or weather changes using a model learned through a Deep Reinforcement Learning (DQN) algorithm.

[0014] According to one embodiment, the landing control unit analyzes three-dimensional terrain data of a potential landing zone on the flight path of an unmanned aerial vehicle and can predict a landing point in real time in the event of an emergency.

[0015] According to one embodiment, when the battery status decreases below a preset threshold level, the landing control unit analyzes the energy consumption pattern of the unmanned aerial vehicle, disables the integrated sensor module and the communication unit, and sets a path to land within the remaining battery capacity.

[0016] A method for generating a path for an unmanned aerial vehicle according to another embodiment of the present invention may include: collecting flight data in real time through an integrated sensor module comprising at least one of RTK, GPS, LiDAR sensor, ultrasonic sensor, inertial measurement unit (IMU), and thermal imaging camera; setting a flight plan by analyzing the current position, altitude, speed, battery status, and obstacle information of the unmanned aerial vehicle based on the collected data; generating a predefined flight path data file by a flight path generation unit mounted on the unmanned aerial vehicle; generating a flight path based on the flight path data file; setting a new path by dynamically modifying the flight path data according to dynamic environmental changes or variables occurring in real time during flight; and modifying the flight path to search for the nearest priority landing zone and landing in the said landing zone when the battery status decreases below a preset threshold level.

[0017] According to one embodiment, if the battery temperature of the unmanned aerial vehicle exceeds a preset threshold, the flight path may further include a step of modifying the flight path to reduce battery consumption.

[0018] According to one embodiment, the step of setting a flight plan may include the step of setting a flight plan of an unmanned aerial vehicle using an Adaptive Fuzzy Logic System.

[0019] According to one embodiment, the step of setting a flight plan may include integrating three-dimensional map data and LiDAR scan data that are stored in advance or acquired from a server to predict obstacle-dense areas in advance, and dynamically generating flight path data based on the predicted obstacle-dense area data.

[0020] According to one embodiment, the step of generating a flight path data file may include generating path data that minimizes flight time and battery consumption according to the flight environment of the unmanned aerial vehicle, and setting weight-based priorities according to mission execution objectives.

[0021] According to one embodiment, the step of transmitting a flight path data file to a flight path control module may include a step of automatically switching the data transmission protocol when a data transmission delay or communication failure occurs between the unmanned aerial vehicle and the flight control module.

[0022] According to one embodiment, the step of landing in a landing zone first may include analyzing three-dimensional terrain data of a possible landing zone on a flight path and predicting a landing point in real time in the event of an emergency.

[0023] According to one embodiment, when the battery status decreases below a preset threshold level, the method may include the step of analyzing the energy consumption pattern of the unmanned aerial vehicle to disable the integrated sensor module and communication unit, and setting a landing path within the remaining battery capacity.

[0024] According to the present invention, an unmanned aerial vehicle capable of setting an optimal path to respond quickly to unexpected obstacles or sudden weather changes can be provided.

[0025] In addition, according to the present invention, an unmanned aerial vehicle capable of setting an optimal path to minimize battery consumption can be provided.

[0026] Figure 1 is a diagram showing a preset path of a conventional unmanned aerial vehicle.

[0027] FIG. 2 is a block diagram showing a path setting device for an unmanned aerial vehicle according to one embodiment of the present invention.

[0028] FIG. 3 is a flowchart illustrating a method for setting a path of an unmanned aerial vehicle according to another embodiment of the present invention.

[0029] Embodiments of the present invention are described in detail below with reference to the attached drawings so that those skilled in the art can easily implement the invention. Since the present invention is susceptible to various modifications and may have various embodiments, specific embodiments are illustrated in the drawings and described in detail in the description. However, this is not intended to limit the present invention to specific embodiments, and it should be understood that it includes all modifications, equivalents, and substitutions that fall within the spirit and scope of the invention.

[0030] To clearly explain the present invention, parts unrelated to the description have been omitted from the drawings, and similar parts throughout the specification have been given similar reference numerals. Furthermore, while describing with reference to the drawings, even components indicated by the same name may have different drawing numbers depending on the drawing, and drawing numbers are provided merely for the convenience of explanation; the concept, feature, function, or effect of each component is not to be interpreted restrictively by the corresponding drawing number.

[0031] Similar reference numerals are used for similar components when describing each drawing. Terms such as "first," "second," etc., may be used to describe various components, but said components should not be limited by said terms. These terms are used solely for the purpose of distinguishing one component from another. For example, without departing from the scope of the present invention, the first component may be named the second component, and similarly, the second component may be named the first component.

[0032] Unless otherwise defined, all terms used herein, including technical or scientific terms, have the same meaning as generally understood by those skilled in the art to which this invention pertains.

[0033] Terms such as those defined in commonly used dictionaries should be interpreted as having meanings consistent with their meanings in the context of the relevant technology, and should not be interpreted in an ideal or overly formal sense unless explicitly defined in this application.

[0034] Throughout the specification, when a part is described as being "connected" to another part, this includes not only cases where they are "directly connected" but also cases where they are "electrically connected" with other elements interposed between them. Furthermore, when a part is described as "comprising" a certain component, this means that, unless specifically stated otherwise, it does not exclude other components but rather allows for the inclusion of additional components; it should be understood that this does not preclude the existence or addition of one or more other features, numbers, steps, actions, components, parts, or combinations thereof.

[0035] Hereinafter, a path generation device and method for an unmanned aerial vehicle according to various embodiments of the present invention will be described with reference to the attached drawings.

[0036] FIG. 2 is a block diagram showing a path setting device for an unmanned aerial vehicle according to one embodiment of the present invention.

[0037] Referring to FIG. 2, a path setting device (10) for an unmanned aerial vehicle according to one embodiment of the present invention may include a data collection unit (110), a flight plan setting unit (120), a flight path generation unit (130), a communication unit (140), a flight path modification unit (150), and a landing control unit (160).

[0038] The data collection unit (110) is a module that collects real-time data during the flight of an unmanned aerial vehicle, and can be configured by integrating various sensors so that the unmanned aerial vehicle can recognize the surrounding environment and collect necessary information during flight. The data collection unit (110) can be configured as an integrated sensor module (111) including sensors such as RTK (112), GPS (113), LiDAR (114), ultrasonic sensor (115), inertial measurement unit (IMU, 116), and thermal imaging camera (117).

[0039] Conventional GPS can have an error margin of several meters, which can limit obstacle avoidance and the performance of precise tasks, particularly in complex urban environments or mountainous terrain. For instance, when flying between buildings or landing precisely at a specific point, relying solely on existing GPS signals can lead to limitations in position control. To address this, RTK systems are introduced. RTK systems can correct GPS signal errors in real time through phase correction technology between a base station and a rover station mounted on the unmanned aerial vehicle (UAV). During this process, the UAV receives differential correction data from the base station, enabling it to track its position with an accuracy of within a few centimeters.

[0040] By utilizing RTK technology, unmanned aerial vehicles (UAVs) can perform precise path tracking and accurate landings during autonomous flight. For example, when agricultural UAVs perform tasks such as harvesting specific crops or spreading fertilizer, using an RTK system allows them to approach specific points with precision, thereby increasing operational accuracy. Furthermore, RTK systems are essential for urban logistics UAVs to accurately reach designated delivery points to deliver packages. Such high-precision positioning is crucial for performing high-precision tasks in confined spaces.

[0041] The operating principles of RTK systems are broadly divided into two methods. First, by utilizing the Carrier Phase Measurement method to analyze phase changes in GPS signals, it can detect even minute errors. RTK systems leverage carrier wave information from GPS signals to precisely calculate changes in distance between the unmanned aerial vehicle (UAV) and the ground station. For example, based on phase changes, the distance traveled by the UAV can be accurately determined down to the centimeter. Second, RTK systems can modify location data in real time through a dynamic correction function. This allows the UAV to continuously receive correction data from the ground station even while in motion, thereby maintaining positional accuracy in response to environmental changes. Through this, the UAV can correct unexpected errors in real time during flight and maintain safe flight.

[0042] In an unmanned aerial vehicle system, the fusion of RTK, IMU, and LiDAR sensors is not limited to simply precise position measurement, but can simultaneously ensure the optimization of the autonomous flight path and safety. For example, in a situation where the unmanned aerial vehicle needs to detect an obstacle and correct its path during flight, RTK provides accurate position data, the IMU (116) stabilizes the attitude of the unmanned aerial vehicle, and the LiDAR (114) scans the surrounding environment to detect obstacles in real time. Through this, the unmanned aerial vehicle can perform safe, autonomous flight in complex environments.

[0043] Network-based RTK (N-RTK) systems can transmit correction data over the Internet without a ground station, enabling high-precision position control over large areas. For example, when an agricultural unmanned aerial vehicle (UAV) needs to track its exact location while flying over a wide farmland, utilizing an N-RTK system allows for precise position control without a ground station. This can be particularly useful in areas with limited communication or for remote operations.

[0044] The LiDAR (114) sensor operates by emitting laser pulses and receiving reflected signals to calculate distance and position, which allows the unmanned aerial vehicle to generate a three-dimensional map of the surrounding environment in real time. The ultrasonic sensor (115) is effective for detecting nearby obstacles and can help the unmanned aerial vehicle fly safely in a narrow space indoors.

[0045] The flight plan setting unit (120) enables autonomous flight of the unmanned aerial vehicle and can set the optimal flight path of the unmanned aerial vehicle based on data collected from the data collection unit (110). The flight plan setting unit (120) supports the unmanned aerial vehicle to fly safely and efficiently in various environments and can dynamically establish an appropriate flight plan by analyzing real-time flight conditions. Specifically, the information collected from the data collection unit (110) may include the unmanned aerial vehicle's current location, altitude, speed, battery status, and surrounding obstacle information, and through this, the unmanned aerial vehicle can set the optimal flight path by responding in real-time to environmental changes during flight.

[0046] The flight plan setting unit (120) can operate by integrating various algorithms for the autonomous flight of the unmanned aerial vehicle, and in particular, can set a flight path by utilizing an Adaptive Fuzzy Logic System. Unlike traditional binary logic, the Fuzzy Logic System is an algorithm that can make flexible decisions by considering various conditions simultaneously. While traditional binary logic systems can make decisions only when a specific condition is true or false, the Fuzzy Logic System enables more sophisticated decision-making by introducing the concept that a condition can be partially true. Through this, the unmanned aerial vehicle can simultaneously analyze various variables such as weather changes, wind speed, density of obstacles, and battery level, and set an optimal flight path based on this. For example, assuming the case where the unmanned aerial vehicle performs a rescue mission in a mountainous area, the Fuzzy Logic System can generate a safe flight path by comprehensively considering the slope of the terrain, the direction and speed of the wind, and the density of obstacles appearing in the field of view.

[0047] When an unmanned aerial vehicle performs a mission to monitor a specific area or the condition of crops in a wide area, the flight plan setting unit (120) can analyze the remaining battery level in real time and optimize the flight path based on this. This minimizes unnecessary flights and allows for the efficient use of energy. For example, when an agricultural unmanned aerial vehicle sprays fertilizer on a large farm, a fuzzy logic system can be utilized to adjust the speed and altitude of the unmanned aerial vehicle and consider the direction of the wind to maximize the efficiency of fertilizer spraying.

[0048] The flight plan setting unit (120) can also integrate an obstacle avoidance function to enhance the safety of the unmanned aerial vehicle. By analyzing the current location and surrounding environment of the unmanned aerial vehicle based on obstacle information collected through sensors such as LiDAR (114), ultrasonic sensor (115), and IMU (116) in the data collection unit (110), the path can be modified in real time and obstacles can be avoided. For example, when an unmanned aerial vehicle performing logistics delivery in an urban area suddenly detects an obstacle such as a building or power line, the flight plan setting unit (120) can utilize a fuzzy logic system to quickly set a safe detour path and adjust the flight path so that the unmanned aerial vehicle can avoid a collision.

[0049] The flight path generation unit (130) can generate a specific flight path based on the flight plan established by the flight plan setting unit (120) so that the unmanned aerial vehicle can fly autonomously. The flight path generation unit (130) is designed not merely to follow a fixed path set in advance, but to dynamically generate and adjust an optimal flight path based on data collected in real time during flight. In particular, by utilizing deep learning algorithms, it can provide the ability for the unmanned aerial vehicle to generate a path on its own and avoid obstacles in complex environments. The technology primarily used for this purpose is a Convolutional Neural Network (CNN) model, and since the CNN model possesses excellent performance in image recognition and pattern analysis, it is suitable for the unmanned aerial vehicle to recognize and analyze the surrounding environment in real time during flight.

[0050] The CNN model can analyze input data through a multilayer neural network structure and combine features extracted from each layer to ultimately recognize a specific pattern. The input data may include 3D distance information provided by the LiDAR (114), infrared images collected from the thermal imaging camera (117), and attitude data collected from the IMU (116). These data reflect various environmental variables that the unmanned aerial vehicle may encounter during flight in real time and can be utilized to generate a safe flight path for the unmanned aerial vehicle through the CNN model. For example, an unmanned aerial vehicle flying autonomously in an urban area can detect various obstacles such as buildings, power lines, and trees in real time through the LiDAR (114) and analyze this data through the CNN model to set an optimal flight path.

[0051] When an unmanned aerial vehicle needs to perform rescue operations inside a complex building, the flight path generation unit (130) can generate a three-dimensional map of the space the unmanned aerial vehicle explores using LiDAR (114) and a thermal imaging camera (117), and set a path optimized for rescue operations through a CNN model. The CNN model can analyze the input three-dimensional map data to identify locations requiring rescue operations and the distribution of obstacles, and generate an optimal path that allows the unmanned aerial vehicle to approach safely. At a fire scene, the unmanned aerial vehicle can use the thermal imaging camera (117) to identify areas where high temperatures are detected and generate a path that bypasses those areas through the CNN model, thereby supporting rescue workers to approach safely. In this way, the flight path generation unit (130) helps the unmanned aerial vehicle to autonomously fly in a complex environment and generate and adjust a path suitable for the situation in real time.

[0052] In addition, the flight path generation unit (130) can be utilized to optimize the energy efficiency of the unmanned aerial vehicle beyond simple obstacle avoidance. By using a CNN model to set the optimal altitude and speed when the unmanned aerial vehicle flies, a path that minimizes battery consumption can be generated. That is, by analyzing the battery status and weather data of the unmanned aerial vehicle in real time, an optimal path can be set to reduce battery consumption during flight. For example, by considering the direction and speed of the wind and adjusting the path so that the unmanned aerial vehicle flies with a tailwind, energy efficiency can be maximized.

[0053] The flight path correction unit (160) can dynamically modify the flight path according to the environment that changes in real time while the unmanned aircraft is flying autonomously. Deep Reinforcement Learning (DQN) algorithms can be utilized to take advantage of the autonomy of the unmanned aircraft. The unmanned aircraft may encounter unexpected obstacles, sudden weather changes, or unexpected situations while flying, and in such situations, it may be difficult to guarantee safe flight using only pre-defined flight paths. To solve these problems, the flight path correction unit (160) can provide the ability for the unmanned aircraft to learn autonomously and make optimal decisions in real time through the DQN algorithm. The DQN algorithm supports the unmanned aircraft in selecting the most efficient and safe action in the current situation by analyzing data collected in real time while the unmanned aircraft continuously monitors the surrounding environment during flight. At this time, the DQN algorithm is a form of reinforcement learning designed to enable the unmanned aircraft to learn the optimal action on its own in a given environment, and in particular, can provide the ability to respond quickly to unexpected situations during flight.

[0054] By applying the DQN algorithm to the flight path correction unit (160), the unmanned aerial vehicle can acquire the ability to explore the environment on its own and select an optimal flight path based on past experiences. In the DQN algorithm, the unmanned aerial vehicle acts as an agent in reinforcement learning, and the environment in which the unmanned aerial vehicle flies can be defined as a state. The unmanned aerial vehicle selects a specific action based on its current state and receives a reward according to the result. For example, one can assume a situation where the unmanned aerial vehicle detects an obstacle that suddenly appears while flying. In this case, if the unmanned aerial vehicle can quickly generate an avoidance path and safely avoid the obstacle, that action can lead to a high reward; conversely, if it fails to avoid the obstacle and collides or is in danger, that action can be evaluated as a low reward or penalty. The DQN algorithm can help the unmanned aerial vehicle generate a more sophisticated and safe flight path through iterative learning by continuously accumulating such experiences.

[0055] The flight path correction unit (160) can significantly improve the flight safety of the unmanned aerial vehicle, especially in unpredictable environments such as complex urban areas or mountainous terrain. For example, when an unmanned aerial vehicle performing a rescue mission faces situations such as suddenly changing weather conditions, such as strong gusts of wind or the sudden appearance of rain, a new flight path can be generated in real time through the DQN algorithm. In such cases, the unmanned aerial vehicle can analyze the surrounding environment in real time based on data collected from various sensors, such as LiDAR (114), ultrasonic sensors (115), and an inertial measurement unit (IMU, 160). For example, the LiDAR (114) sensor can help the unmanned aerial vehicle accurately determine the distance and shape of obstacles while flying, thereby enabling the unmanned aerial vehicle to generate a safe path to avoid in real time. The IMU (116) can continuously monitor the attitude and acceleration of the unmanned aerial vehicle to allow for immediate adjustment of shaking or unstable conditions during flight.

[0056] Additionally, the flight path modification unit (160) can adjust the flight path by considering the energy efficiency of the unmanned aerial vehicle. For example, if the battery level of the unmanned aerial vehicle decreases below a certain level during flight, the optimal path to safely reach the nearest landing point can be calculated using the DQN algorithm. At this time, a new path reflecting the current flight situation and battery status can be generated by referring to the pre-established path in the flight path generation unit (130).

[0057] The landing control unit (170) can control the unmanned aircraft to land safely by monitoring the battery status in real time during flight. In particular, the landing control unit (170) can set a path to land safely by immediately searching for the nearest priority landing zone when the remaining battery level drops below a critical level. To this end, it can evaluate a safe landing point for the unmanned aircraft by utilizing data collected from various sensors such as LiDAR (114), ultrasonic sensors (115), and IMU (116). For example, if the unmanned aircraft detects a situation where the remaining battery level rapidly decreases during flight, the landing control unit (170) can scan the surrounding terrain to find a flat and obstacle-free landing point in real time.

[0058] Additionally, the landing control unit (170) can automatically disable high-power consuming devices, such as high-resolution cameras and communication modules, when an emergency landing is required to optimize the energy consumption of the unmanned aerial vehicle. This allows for the maximum conservation of the remaining battery, thereby facilitating a safe landing. For example, when a logistics delivery unmanned aerial vehicle faces a situation where the battery rapidly decreases in an urban area, the communication module can be temporarily disabled to conserve battery power, and the route can be adjusted to safely avoid the buildings in the city and land in the nearest open space.

[0059] FIG. 3 is a flowchart illustrating a method for setting a path of an unmanned aerial vehicle according to another embodiment of the present invention.

[0060] Referring to FIG. 3, in the flight data collection step (S310), flight data can be collected in real time using an integrated sensor module. The integrated sensor module may consist of various sensors such as RTK, GPS, LiDAR sensors, ultrasonic sensors, inertial measurement units (IMUs), and thermal imaging cameras. RTK technology can provide position data with much higher precision than conventional GPS, thereby enabling the unmanned aerial vehicle to maintain an accurate position in urban areas or complex environments. LiDAR sensors can support the unmanned aerial vehicle in avoiding obstacles and flying safely by generating a 3D map through lasers to measure the distance to objects. Similarly, ultrasonic sensors are specialized for detecting near-field obstacles and are useful in indoor environments or areas with many obstacles. IMUs can contribute to ensuring flight stability by measuring the attitude of the unmanned aerial vehicle based on accelerometers and gyroscopes, while thermal imaging cameras can be usefully utilized for night flights or rescue operations in disaster areas.

[0061] In the flight plan setting stage (S320), various data collected by the data collection unit is analyzed to determine the current status of the unmanned aerial vehicle, and an optimal flight plan is established based on this. In the flight plan setting stage (S320), the unmanned aerial vehicle's current location, altitude, speed, battery status, and information on surrounding obstacles are analyzed. This information is essential for planning the flight so that the unmanned aerial vehicle can fly efficiently and safely. In particular, real-time monitoring of the battery status is essential because it significantly affects the flight time of the unmanned aerial vehicle. For example, if the remaining battery level drops below a critical threshold, the unmanned aerial vehicle must search for the nearest landing site and land safely, even while in the middle of a mission.

[0062] In the flight path data file generation step (S330), a predefined flight path data file can be generated based on information determined by the flight plan setting unit. This data file may include information such as the departure location, arrival point, waypoint, flight altitude, and speed of the unmanned aerial vehicle.

[0063] The flight path generation step (S340) is a process of generating an actual flight path based on the generated flight path data file and applying it to the unmanned aerial vehicle. In the flight path generation step (S340), the unmanned aerial vehicle begins flying according to a pre-set plan and moves along the path via a flight control device. An important aspect of this step is that, considering the possibility that the flight environment may change unexpectedly, the system is designed to allow the unmanned aerial vehicle to continuously monitor data and adjust its flight path.

[0064] The step of establishing a new path (S350) includes a function to dynamically modify the path in response to unexpected environmental changes or variables during flight. In the S350 step, a Deep Reinforcement Learning (DQN) algorithm may be used. Through this algorithm, the unmanned aerial vehicle learns and adapts to environmental changes in real time, enabling it to respond quickly to sudden situations such as obstacles or weather changes. For example, if the unmanned aerial vehicle encounters a sudden obstacle during a rescue mission, it can immediately generate a new avoidance path by utilizing the DQN algorithm.

[0065] The landing control step (S360) is a step for performing an emergency landing when the battery status of the unmanned aerial vehicle decreases below a preset threshold level. In step S360, the unmanned aerial vehicle can be controlled to search for the nearest available landing site and land safely at that site. The landing control unit can use LiDAR, ultrasonic sensors, and an IMU to analyze the landing site in real time and ensure a safe landing. For example, if the unmanned aerial vehicle faces a low battery condition during a rescue mission, it can locate the nearest available landing area and land immediately.

[0066] At least some of the configurations of the embodiments described above may be implemented as hardware components, software components, and / or a combination of hardware components and software components. For example, the devices, methods, and components described in the embodiments may be implemented using one or more general-purpose computers or special-purpose computers, such as, for example, a processor, a controller, an Arithmetic Logic Unit (ALU), a Digital Signal Processor, a microcomputer, a Field Programmable Gate Array (FPGA), a Programmable Logic Unit (PLU), a microprocessor, or any other device capable of executing and responding to instructions.

[0067] The processing unit may execute an operating system and one or more software applications executed on said operating system. Additionally, the processing unit may access, store, manipulate, process, and generate data in response to the execution of the software. For convenience of understanding, the processing unit may be described as being used as a single unit, but a person of ordinary skill in the art will understand that the processing unit may include multiple processing elements and / or multiple types of processing elements.

[0068] For example, the processing unit may include multiple processors or one processor and one controller. Additionally, other processing configurations, such as a parallel processor, are also possible. Software may include a computer program, code, instructions, or a combination of one or more of these, and may configure the processing unit to operate as desired or instruct the processing unit independently or collectively.

[0069] Software and / or data may be embodied in any type of machine, component, physical device, virtual equipment, computer storage medium, or device so as to be interpreted by a processing device or to provide instructions or data to a processing device. Software may be distributed over networked computer systems and stored or executed in a distributed manner. Software and data may be stored on one or more computer-readable recording media.

[0070] The method according to the embodiment may be implemented in the form of program instructions that can be executed through various computer means and recorded on a computer-readable medium. The computer-readable medium may include program instructions, data files, data structures, etc., either alone or in combination. The program instructions recorded on the medium may be those specifically designed and configured for the embodiment, or they may be those known and available to those skilled in the art of computer software.

[0071] Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks, and magnetic tapes; optical recording media such as CD-ROMs and DVDs; and hardware devices specifically configured to store and execute program instructions, such as ROM, RAM, and flash memory. Examples of program instructions include machine code, such as that generated by a compiler, as well as high-level language code that can be executed by a computer using an interpreter, etc. The hardware devices described above may be configured to operate as one or more software modules to perform the operation of the embodiments, and vice versa.

[0072] Although embodiments of the present invention have been described above with reference to the attached drawings, those skilled in the art will understand that the present invention may be implemented in other specific forms without altering its technical concept or essential features. Therefore, the embodiments described above should be understood as illustrative in all respects and not restrictive, and the scope of the present invention is defined by the claims set forth below. Furthermore, all modifications or variations derived from the meaning and scope of the claims and their equivalents should be interpreted as being included within the scope of the present invention.

[0073] (Explanation of symbols)

[0074] 10: Path generation device

[0075] 110: Data Collection Unit

[0076] 111: Integrated sensor module

[0077] 112: RTK

[0078] 113: GPS

[0079] 114: LiDAR

[0080] 115: Ultrasonic sensor

[0081] 116: IMU

[0082] 117: Thermal imaging camera

[0083] 120: Flight Plan Settings

[0084] 130: Flight path generation unit

[0085] 140: Communications Department

[0086] 150: Flight Path Correction Unit

[0087] 160: Landing Control Unit

Claims

1. In a path generation device for an unmanned aerial vehicle, A data acquisition unit that collects flight data in real time through an integrated sensor module comprising at least one of RTK (Real-Time Kinematic), GPS (Global Positioning System), LiDAR sensor, ultrasonic sensor, inertial measurement unit (IMU), and thermal imaging camera; A flight plan setting unit that sets a flight plan by analyzing the current location, altitude, speed, battery status, and obstacle information of the unmanned aerial vehicle based on data collected by the data collection unit; A flight path generation unit that generates a predefined flight path data file based on data generated by the flight plan setting unit above; A communication unit that transmits a flight path data file generated by the flight path generation unit to the flight control device of the unmanned aerial vehicle; A flight path modification unit that sets a new path by dynamically modifying the flight path data according to dynamic environmental changes or variables occurring in real time during flight; and A landing control unit that, when the battery status of the above-mentioned unmanned aerial vehicle decreases below a preset threshold level, modifies the flight path to search for the nearest priority landing zone and controls the landing to take place in the priority landing zone; A path generation device for an unmanned aerial vehicle, comprising 2. In Paragraph 1, The above flight plan setting unit, A path generation device for an unmanned aerial vehicle that modifies the flight path to reduce battery consumption when the battery temperature of the unmanned aerial vehicle exceeds a preset threshold.

3. In Paragraph 1, The above flight plan setting unit, A path generation device for an unmanned aerial vehicle that sets a flight plan for the unmanned aerial vehicle using an Adaptive Fuzzy Logic System.

4. In Paragraph 1, The above flight plan setting unit, A path generation device for an unmanned aerial vehicle that integrates three-dimensional map data stored in advance or acquired from a server with the LiDAR scan data to predict obstacle-dense areas in advance, and dynamically generates flight path data based on the data regarding the predicted obstacle-dense areas.

5. In Paragraph 1, The above flight path generation unit is, A path generation device for an unmanned aerial vehicle that generates path data to minimize flight time and battery consumption according to the flight environment of the unmanned aerial vehicle, and sets weight-based priorities according to the mission execution objectives of the unmanned aerial vehicle.

6. In Paragraph 1, The above communication unit is, A path generation device for an unmanned aerial vehicle that automatically switches the data transmission protocol when a data transmission delay or communication failure occurs between the unmanned aerial vehicle and the flight control module.

7. In Paragraph 1, The above flight path correction unit is, The surrounding environment is monitored in real time during the flight of the above-mentioned unmanned aerial vehicle, and a model trained through the Deep Reinforcement Learning (DQN) algorithm is used, A path generation device for an unmanned aerial vehicle that modifies the flight path in response to unexpected obstacles or weather changes.

8. In Paragraph 1, The above landing control unit is, A path generation device for an unmanned aerial vehicle that analyzes three-dimensional terrain data of a potential landing zone on the flight path of the unmanned aerial vehicle and predicts a landing point in real time in the event of an emergency.

9. In Paragraph 1, The above landing control unit is, A path generation device for an unmanned aerial vehicle characterized by analyzing the energy consumption pattern of the unmanned aerial vehicle to deactivate the integrated sensor module and the communication unit and setting a path that allows landing within the remaining battery capacity when the battery status decreases below a preset threshold level.

10. In a method for generating a path for an unmanned aerial vehicle, A step of collecting flight data in real time through an integrated sensor module comprising at least one of RTK, GPS, LiDAR sensor, ultrasonic sensor, inertial measurement unit (IMU), and thermal imaging camera mounted on the above unmanned aerial vehicle; A step of establishing a flight plan by analyzing the current location, altitude, speed, battery status, and obstacle information of the unmanned aerial vehicle based on the collected data; A step of generating a predefined flight path data file by a flight path generation unit mounted on the above unmanned aerial vehicle; A step of generating a flight path based on the above flight path data file; A step of dynamically modifying the flight path data according to dynamic environmental changes or variables occurring in real time during flight to set a new path; A method for generating a path for an unmanned aerial vehicle, comprising the step of modifying the flight path to search for the nearest priority landing zone and landing in the priority landing zone when the battery status of the unmanned aerial vehicle decreases below a preset threshold level.

11. In Paragraph 10, A method for generating a path for an unmanned aerial vehicle, further comprising the step of modifying the flight path to reduce battery consumption when the battery temperature of the unmanned aerial vehicle exceeds a preset threshold.

12. In Paragraph 10, The step of establishing the above flight plan is, A method for generating a path for an unmanned aerial vehicle, comprising the step of setting a flight plan for the unmanned aerial vehicle using an Adaptive Fuzzy Logic System.

13. In Paragraph 10, The step of establishing the above flight plan is, A method for generating a path for an unmanned aerial vehicle, comprising the step of integrating three-dimensional map data that is stored in advance or acquired from a server with the LiDAR scan data to predict an obstacle-dense area in advance, and dynamically generating flight path data based on the data regarding the predicted obstacle-dense area.

14. In Paragraph 10, The step of generating the above flight path data file is, A method for generating a path for an unmanned aerial vehicle, comprising the steps of generating path data that minimizes flight time and battery consumption according to the flight environment of the unmanned aerial vehicle, and setting weight-based priorities according to the mission execution objectives of the unmanned aerial vehicle.

15. In Paragraph 10, The step of transmitting the above flight path data file to the above flight path control module is, A method for generating a path for an unmanned aerial vehicle, comprising the step of automatically switching the data transmission protocol when a data transmission delay or communication failure occurs between the unmanned aerial vehicle and the flight control module.

16. In Paragraph 10, The step of landing in the aforementioned priority landing zone is, A method for generating a path for an unmanned aerial vehicle, comprising the step of analyzing three-dimensional terrain data of a potential landing zone on the flight path of the unmanned aerial vehicle and predicting a landing point in real time in the event of an emergency.

17. In Paragraph 10, A method for generating a path for an unmanned aerial vehicle, further comprising the step of analyzing the energy consumption pattern of the unmanned aerial vehicle when the battery status decreases below a preset threshold level, deactivating the integrated sensor module and communication unit, and setting a path that allows landing within the remaining battery capacity.

Images