Risk assessment device, risk assessment method, and program

Abstract

This risk assessment device comprises an acquisition means and a risk assessment means. The acquisition means acquires input information including position information indicating the position of an aircraft, body information on the aircraft, weather information, and environment information. The risk assessment means uses a trained risk assessment model to assess the risk when the aircraft is at the position, on the basis of the input information, and outputs the risk assessment result.

Description

[Technical Field]

[0001] This disclosure relates to the assessment of risks associated with the flight of an aircraft. [Background technology]

[0002] In recent years, the use of drones for various purposes has been explored. However, when flying a drone, various risks can be anticipated, such as the risk of the drone itself crashing and the risk of the cargo being carried by the drone falling. Patent Document 1 proposes a device for collecting information that can be used to calculate the risks in the event of a crash of an unmanned flying object such as a drone. [Prior art documents] [Patent Documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2020-112574 [Overview of the project] [Problems that the invention aims to solve]

[0004] Typically, operators plan drone flights by looking at maps such as those provided by map apps, but it is crucial to verify the safety of that flight plan before actually flying the drone.

[0005] One of the purposes of this disclosure is to provide a risk assessment device that can evaluate in advance the risks involved when flying an aircraft such as a drone. [Means for solving the problem]

[0006] In one aspect of the present invention, the risk assessment device is An acquisition means for acquiring input information including position information indicating the position of an aircraft, aircraft information of the aircraft, weather information, and environmental information. Based on the aforementioned input information, a risk assessment means evaluates the risk when the aircraft is in the aforementioned position using a trained risk assessment model and outputs the risk assessment result. Equipped with 、 The risk assessment model is a model trained using the input information and risk values ​​corresponding to the behavior of the aircraft obtained by simulation based on the input information. .

[0007] In another aspect of the present invention, the risk assessment method is: Computers The system acquires input information including position information indicating the location of the aircraft, aircraft information of the aircraft, weather information, and environmental information. Based on the input information, the risk when the aircraft is in the aforementioned position is evaluated using a trained risk assessment model, and the risk assessment results are output. 、 The risk assessment model is a model trained using the input information and risk values ​​corresponding to the behavior of the aircraft obtained by simulation based on the input information. .

[0008] In yet another aspect of the present invention, the program is The system acquires input information including position information indicating the location of the aircraft, aircraft information of the aircraft, weather information, and environmental information. Based on the input information, the computer is instructed to use a trained risk assessment model to evaluate the risk when the aircraft is in the aforementioned position and to output the risk assessment results. 、 The risk assessment model is a model trained using the input information and risk values ​​corresponding to the behavior of the aircraft obtained by simulation based on the input information. . [Effects of the Invention]

[0009] According to this disclosure, it will be possible to assess the risks involved in flying drones and other aerial vehicles in advance. [Brief explanation of the drawing]

[0010] [Figure 1] A risk assessment device according to the first embodiment is shown. [Figure 2] This is a block diagram showing the hardware configuration of a risk assessment device. [Figure 3]It is a block diagram showing the functional configuration for model training of the risk assessment device according to the first embodiment. [Figure 4] An example showing the simulation of the behavior of a drone is shown. [Figure 5] An example of the simulation result of the drone falling is shown. [Figure 6] An example showing the risk assessment by the risk assessment unit is shown. [Figure 7] An example of a risk assessment model is shown. [Figure 8] It is a flowchart of the training process of the risk assessment model. [Figure 9] It is a block diagram showing the functional configuration for risk assessment of the risk assessment device according to the first embodiment. [Figure 10] It is a flowchart of the risk assessment process. [Figure 11] It is a block diagram showing the functional configuration of the risk assessment device of the second embodiment. [Figure 12] It is a flowchart of the process by the risk assessment device of the second embodiment.

Mode for Carrying Out the Invention

[0011] Hereinafter, preferred embodiments of the present disclosure will be described with reference to the drawings. <First Embodiment> [Overall Configuration] FIG. 1 shows a risk assessment device according to the first embodiment. The risk assessment device 100 is configured by a computer such as a personal computer (PC). The risk assessment device 100 assesses the risks that may occur when a flying object such as a drone flies along a planned route. Hereinafter, a drone will be used as an example of the flying object for description, but the flying object in the present disclosure is not limited to a flying object generally called a drone, and includes various unmanned flying objects that fly under external control.

[0012] The risk assessment device 100 receives location information, aircraft information, weather information, and environmental information as input information. The risk assessment device 100 is equipped with a pre-trained risk assessment model. Using the risk assessment model, the risk assessment device 100 assesses the risk based on the input information and outputs a risk assessment value as the risk assessment result. By assessing the risk in advance using the risk assessment device 100, it is possible to predict in advance the risks that may occur when flying a drone according to a planned route.

[0013] [Hardware configuration] Figure 2 is a block diagram showing the hardware configuration of the risk assessment device 100. As shown in the figure, the risk assessment device 100 includes an interface (I / F) 11, a processor 12, a memory 13, a recording medium 14, a database (DB) 15, a display unit 16, and an input unit 17.

[0014] I / F11 performs data input and output with external devices. Specifically, input information such as location information and aircraft information is input to the risk assessment device 100 via I / F11. In addition, the risk assessment value generated by the risk assessment device 100 is output to the external device via I / F11 as needed.

[0015] The processor 12 is a computer such as a CPU (Central Processing Unit) and controls the entire risk assessment device 100 by executing a pre-prepared program. The processor 12 may also be a GPU (Graphics Processing Unit), TPU (Tensor Processing Unit), quantum processor, or FPGA (Field-Programmable Gate Array). As described later, the processor 12 performs the training process of the risk assessment model and the risk assessment process using the trained risk assessment model.

[0016] Memory 13 consists of ROM (Read Only Memory), RAM (Random Access Memory), and other components. Memory 13 is also used as working memory while the processor 12 is executing various processes.

[0017] The recording medium 14 is a non-volatile, non-temporary recording medium such as a disk-shaped recording medium or semiconductor memory, and is configured to be detachable from the risk assessment device 100. The recording medium 14 stores various programs that the processor 12 executes. When the risk assessment device 100 performs various processes, the programs stored on the recording medium 14 are loaded into the memory 13 and executed by the processor 12.

[0018] DB15 stores data used by the risk assessment device 100 and data generated by it. Specifically, DB15 stores input information such as location information, aircraft information, weather information, and environmental information. DB15 also stores data used in training the risk assessment model, which will be described later, such as risk definition data and simulation results of drone behavior. In addition, information about the risk assessment model obtained through training is stored in DB15. If the capacity of memory 13 is sufficient, the above data may be stored in memory 13 instead.

[0019] The display unit 16 is, for example, a liquid crystal display device, and displays the risk assessment values ​​generated by the risk assessment device 100. The input unit 17 is, for example, a mouse or keyboard, and is used by the user to give instructions and inputs necessary during risk assessment training and risk assessment processing using the risk assessment model.

[0020] [Functional configuration for model training] Figure 3 is a block diagram showing the functional configuration of the risk assessment device 100 for model training according to the first embodiment. The risk assessment device 100 comprises a simulation unit 31, a risk assessment unit 32, and a model training unit 33 as its configuration for model training.

[0021] The simulation unit 31 simulates the behavior of the drone based on the input information and outputs simulation results showing the predicted behavior of the drone. Specifically, the simulation unit 31 receives location information, aircraft information, weather information, and environmental information as input information. The input information is used as the conditions for the simulation.

[0022] The location information indicates the drone's three-dimensional position and can use, for example, latitude, longitude, and altitude in real-world geographical space. However, in the simulation of the drone's behavior, a virtual geographical space may be used instead of real-world geographical space. In this case, the location information will indicate the three-dimensional position within that virtual geographical space.

[0023] Aircraft information refers to information about the drone itself, including various information such as the drone's size, shape, type, engine type, and number of wings. Alternatively, drone movement information, such as the drone's direction of movement, speed, and acceleration, may also be used as aircraft information.

[0024] Weather information refers to information that indicates the weather conditions in the area where the drone is flying, and includes, for example, weather, temperature, humidity, wind direction, and wind speed.

[0025] Environmental information refers to information describing the geographical environment in the area where the drone will fly, and includes ground topography information. Typically, so-called map information can be used as topography information. Furthermore, topography information includes classifications of ground conditions, such as sea, river, land, mountainous areas, roads, and urban areas. In particular, to assess the risks arising from drone crashes, it is preferable that environmental information include information such as whether the area has many buildings or is densely populated.

[0026] The simulation unit 31 uses the input location information, aircraft information, weather information, and environmental information to simulate the behavior of the drone when a problem or malfunction (hereinafter simply referred to as "problem") occurs in the drone.

[0027] Figure 4 shows an example of simulating the behavior of a drone. The simulation unit 31 sets up a simulation space 50 with the drone D's position as the origin, based on the input position information. The simulation space 50 is a geographical space within a predetermined range from the drone D's position. The simulation unit 31 then uses the aircraft information and weather and environmental information in the simulation space 50 to simulate the behavior of the drone D in the event of a problem occurring. The simulation unit 31 sets the probability of the problem occurring based on the input information and performs the simulation.

[0028] For example, if a problem occurs with the engine of drone D, the simulation unit 31 performs a simulation of drone D crashing based on the drone D's aircraft information, the weather information at that time, and the environmental information. Figure 5(A) shows an example of a simulation result of drone D crashing. In the example in Figure 5(A), simulation result S1 shows that drone D crashes to the ground along the trajectory indicated by symbol S1. The simulation unit 31 performs multiple simulations, keeping the position and aircraft information of drone D the same, and changing the drone D's movement information, weather information, etc. As a result, simulation results S2 to S5, which are different from simulation result S1, are obtained, as shown in Figure 5(B).

[0029] The simulation unit 31 performs numerous simulations for the drone's planned flight area, changing the location information, aircraft information, weather information, and environmental information. The simulation unit 31 also performs numerous simulations, changing the types of problems that may occur to the drone. Examples of drone problems include engine problems, communication equipment problems, propeller problems, being buffeted by strong winds, and contact with birds or other drones. This allows the system to obtain simulation results of how various drones behave when various problems occur under various weather conditions in the drone's planned flight area. The simulation unit 31 outputs the obtained simulation results to the risk assessment unit 32. Various methods, such as Monte Carlo simulation using random numbers, can be used for the simulation.

[0030] The risk assessment unit 32 evaluates the risks corresponding to the drone's behavior obtained as a simulation result using risk definition data. The risk definition data defines risks mainly arising from drone crashes, depending on the ground conditions indicated by the map information. Potential risks that may arise from a drone crash include the risk of the drone hitting a person and the risk of environmental pollution. The risk definition data specifies a risk value for each risk.

[0031] Figure 6 shows an example of the risk assessment unit 32 evaluating risk using risk definition data. Let's consider the risk A, which is the risk of a crashed drone hitting a person. For risk A, the risk definition data defines the risk value when the drone crashes into the sea as "0" and the risk value when the drone crashes onto land as "1". Also, as shown in Figure 6, let's assume that simulation results S1 to S5 have been obtained for the drone's behavior. In simulation results S1 and S2, the drone D crashes onto land, so the risk value is "1". On the other hand, in simulation results S3 to S5, the drone D crashes into the sea, so the risk value is "0". Therefore, the average risk for risk A from simulations S1 to S5 is "0.4". In this way, the risk assessment unit 32 can calculate the risk value when the drone D is at a certain location.

[0032] In the example above, the risk definition data for Risk A sets the risk value for the case where the drone crashes onto land to "1". However, for example, the land could be divided into densely populated areas such as urban areas and areas without dense populations, and the risk value in densely populated areas could be set to "2" and the risk value in areas without dense populations to "1".

[0033] Next, we will explain the specific method for calculating the risk value. The risk assessment unit 32 calculates the total risk R when the drone is at a certain location using the following formula (1).

[0034]

number

[0035] "risk j ()" is a function indicating the risk value. As described above, the risk definition data defines the risk values for multiple risks. "j" indicates the type of risk. Therefore, "risk j (trajectory i )" indicates the risk value of risk j caused by the trajectory i obtained as the simulation result.

[0036] "weight j " indicates the weight set for each risk. When evaluating the risk caused by the drone crashing, there are differences in importance among multiple risks. For example, the importance of the risk that the drone hits a person should be set higher than the importance of the risk that the drone falls into the sea. For this reason, weights are set for each risk, and the total risk R is calculated taking into account the importance of each risk. In the latter half of formula (1) (starting from 1 / S t onward), the weighted sum of the risk values for each of the multiple simulation results trajectory i is averaged by the number of simulation times S t to calculate the average of the risk values over the entire multiple simulations.

[0037] "p(happen t )" indicates the probability that trouble t occurs, and "t" indicates the type of trouble. Therefore, the total risk R is calculated considering the occurrence probability of each of the assumed multiple troubles t. Thus, according to formula (1), the total risk R when the drone is at a certain location is calculated based on the multiple simulation results, considering multiple risks, the weight of each risk, multiple troubles, and the occurrence probability of each trouble. The risk evaluation unit 32 outputs the thus calculated total risk R to the model training unit 33.

[0038] The model training unit 33 trains a risk assessment model using the input information input to the simulation unit 31 and the total risk output from the risk assessment unit 32. Specifically, the model training unit 33 trains the risk assessment model by performing supervised learning using input information including location information and aircraft information as input data, and the total risk as the ground truth data. When location information, aircraft information, weather information, and environmental information about a drone located at a certain point are input to the training risk assessment model, it outputs an assessment value of the risk that the drone will generate under those conditions. The output assessment value is a value that represents the total risk considering multiple troubles and multiple risks that may occur under those conditions.

[0039] Figure 7 shows an example of a risk assessment model. In this example, the risk assessment model is constructed using a neural network. The inputs to the risk assessment model include aircraft information, the drone's direction of movement and acceleration, weather information (wind speed), and risk values ​​at the relative position to the drone. The drone's direction of movement and acceleration are part of the aircraft information. Wind speed is given for each cell (voxel) when the X, Y, and Z directions in the simulation space 50 shown in Figure 4 are each divided into multiple cells. The risk value at the relative position to the drone is also given for each cell in the simulation space 50 and for each type of risk. This risk value is obtained based on environmental information and risk definition data.

[0040] [Model training process] Next, we will explain the training process for the risk assessment model. Figure 8 is a flowchart of the training process for the risk assessment model. This process is realized when the processor 12 shown in Figure 2 executes a pre-prepared program and operates as the elements shown in Figure 3.

[0041] First, the simulation unit 31 receives location information, aircraft information, weather information, and environmental information as input information (step S10), and performs simulations of the drone's behavior for multiple problems (step S11). Next, the risk assessment unit 32 refers to the risk definition data and calculates the total risk considering multiple risks based on the drone's trajectory shown by the multiple simulation results (step S12). Specifically, the risk assessment unit 32 calculates the total risk R using the aforementioned equation (1) based on the multiple simulation results. Next, the model training unit 33 trains the risk assessment model using the input information entered in step S10 and the total risk R obtained in step S12 (step S13). Then, the model training process is completed.

[0042] [Functional configuration for risk assessment] Figure 9 is a block diagram showing the functional configuration for risk assessment of the risk assessment device 100 according to the first embodiment. The risk assessment device 100 includes, as a configuration for risk assessment, a location information input unit 41, an aircraft information input unit 42, a weather information input unit 43, an environmental information input unit 44, a risk assessment unit 45, and a risk output unit 46.

[0043] The location information input unit 41 receives location information indicating the drone's position on its planned flight path, which is the subject of the risk assessment. The aircraft information input unit 42 receives aircraft information related to the drone being assessed. The weather information input unit 43 receives weather information indicating the weather conditions subject to the risk assessment. The environmental information input unit 44 receives environmental information subject to the risk assessment, specifically topographic information of the region corresponding to the drone's location.

[0044] The risk assessment unit 45 performs a risk assessment using the trained risk assessment model obtained through the aforementioned model training process. Specifically, the risk assessment unit 45 inputs the above input information into the risk assessment model and obtains a risk assessment value as its output. The risk assessment unit 45 then outputs the obtained risk assessment value to the risk output unit 46. The risk output unit 46 presents the risk value to the user as a risk assessment result. For example, the risk output unit 46 displays the input risk value on the display unit 16.

[0045] The risk assessment value presented to the user in this way is a comprehensive risk value that takes into account multiple risks that may occur if various problems occur with the drone under the conditions defined by the information entered in each of the above input fields. Therefore, those planning to fly a drone can assess the risks in advance by entering information such as the location where the drone will be flown, the drone's aircraft information, the weather conditions at the time, and the environmental information of the area where the drone will be flown.

[0046] [Risk assessment process] Next, the risk assessment process performed by the risk assessment device 100 will be described. Figure 10 is a flowchart of the risk assessment process. This process is realized when the processor 12 shown in Figure 2 executes a pre-prepared program and operates as the elements shown in Figure 9.

[0047] First, the location information input unit 41, aircraft information input unit 42, weather information input unit 43, and environmental information input unit 44 receive location information, aircraft information, weather information, and environmental information, respectively (step S21). Next, the risk assessment unit 45 uses a trained risk assessment model to perform a risk assessment based on the input information (step S22) and outputs a risk assessment value as the assessment result (step S23). For example, the risk assessment unit 45 displays the risk assessment value on the display unit 16. Then, the process ends.

[0048] The risk assessment value mentioned above represents the total risk when the drone is located at the point indicated by the input location information. Therefore, users can check the risk along the planned flight path or in the entire area by performing risk assessment processing on multiple points along the planned flight path or within the area.

[0049] [Differentiation] During risk assessment, the risk assessment device 100 may display the obtained risk values ​​on a map showing the drone's location when displaying them on the display unit 16. For example, the risk assessment device 100 displays a map on the display unit 16. The location information input unit 41 acquires location information of a point specified by the user using a mouse or the like on the displayed map. The risk output unit 46 then overlays the calculated risk value on the map near that point. This allows the user to see the correspondence between the location specified as the drone's location and the risk value at that location.

[0050] <Second Embodiment> Figure 11 is a block diagram showing the functional configuration of the risk assessment device 70 of the second embodiment. The risk assessment device 70 comprises an acquisition means 71 and a risk assessment means 72.

[0051] Figure 12 is a flowchart of the processing performed by the risk assessment device 70 of the second embodiment. The acquisition means 71 acquires input information including position information indicating the position of the aircraft, aircraft information of the aircraft, weather information, and environmental information (step S71). Based on the input information, the risk assessment means 72 uses a trained risk assessment model to evaluate the risk when the aircraft is at that position and outputs the risk assessment result (step S72).

[0052] According to the risk assessment device 70 of the second embodiment, it is possible to assess in advance the risks that may arise from the flight of an aircraft.

[0053] Some or all of the above embodiments may also be described as follows, but are not limited to the following:

[0054] (Note 1) An acquisition means for acquiring input information including position information indicating the position of an aircraft, aircraft information of the aircraft, weather information, and environmental information. Based on the aforementioned input information, a risk assessment means evaluates the risk when the aircraft is in the aforementioned position using a trained risk assessment model and outputs the risk assessment result. A risk assessment device equipped with the following features.

[0055] (Note 2) The risk assessment device described in Appendix 1 is a model trained using the input information and risk values ​​corresponding to the behavior of the aircraft obtained by simulation based on the input information.

[0056] (Note 3) The risk value corresponding to the behavior of the aforementioned flying object is calculated based on a plurality of risks associated with the aforementioned flying object using the risk assessment device described in Appendix 2.

[0057] (Note 4) The risk value corresponding to the behavior of the aforementioned flying object is calculated using weights set for each of the multiple risks, as described in Appendix 3 of the risk assessment device.

[0058] (Note 5) The risk value corresponding to the behavior of the aforementioned aircraft is calculated based on a plurality of troubles related to the aforementioned aircraft using the risk assessment device described in Appendix 2.

[0059] (Note 6) The risk value corresponding to the behavior of the aforementioned aircraft is calculated using the probability of occurrence of multiple troubles related to the aforementioned aircraft, as described in Appendix 5 of the risk assessment device.

[0060] (Note 7) The risk assessment device described in Appendix 2 calculates the risk value corresponding to the behavior of the aforementioned flying object using a pre-set risk value based on the topographic information of the region corresponding to the position of the aforementioned flying object.

[0061] (Note 8) The system acquires input information including position information indicating the location of the aircraft, aircraft information of the aircraft, weather information, and environmental information. A risk assessment method that evaluates the risk when the aircraft is in the aforementioned position, using a trained risk assessment model based on the aforementioned input information, and outputs a risk assessment result.

[0062] (Note 9) The system acquires input information including position information indicating the location of the aircraft, aircraft information of the aircraft, weather information, and environmental information. A recording medium containing a program that causes a computer to perform a process of evaluating the risk when the aircraft is in the aforementioned position, using a trained risk assessment model based on the aforementioned input information, and outputting the risk assessment results.

[0063] Although the present disclosure has been described above with reference to embodiments and examples, the present disclosure is not limited to the above embodiments and examples. Various modifications to the structure and details of the present disclosure can be understood by those skilled in the art within the scope of the present disclosure. [Explanation of symbols]

[0064] 12 processors 31 Simulation Department 32 Risk Assessment Department 33 Model Training Department 41 Location information input section 42. Aircraft Information Input Unit 43 Weather Information Input Section 44 Environmental Information Input Section 45 Risk Assessment Department 46. ​​Risk Output Section 100 Risk Assessment Device

Claims

1. An acquisition means for acquiring input information including position information indicating the position of an aircraft, aircraft information of the aircraft, weather information, and environmental information. Based on the aforementioned input information, a risk assessment means evaluates the risk when the aircraft is in the aforementioned position using a trained risk assessment model and outputs the risk assessment result. Equipped with, The risk assessment model is a risk assessment device that is a model trained using the input information and risk values ​​corresponding to the behavior of the aircraft obtained by simulation based on the input information.

2. The risk evaluation device according to claim 1, wherein the risk value corresponding to the behavior of the aircraft is calculated based on a plurality of risks associated with the aircraft.

3. The risk evaluation device according to claim 2, wherein the risk value corresponding to the behavior of the aircraft is calculated using weights set for each of the plurality of risks.

4. The risk evaluation device according to claim 1, wherein the risk value corresponding to the behavior of the aircraft is calculated based on a plurality of troubles related to the aircraft.

5. The risk evaluation device according to claim 4, wherein the risk value corresponding to the behavior of the aircraft is calculated using the probability of occurrence of a plurality of troubles related to the aircraft.

6. The risk evaluation device according to claim 1, wherein the risk value corresponding to the behavior of the aircraft is calculated using a pre-set risk value based on the terrain information of the region corresponding to the position of the aircraft.

7. Computers The system acquires input information including position information indicating the location of the aircraft, aircraft information of the aircraft, weather information, and environmental information. Based on the input information, the risk of the aircraft being in the aforementioned position is evaluated using a trained risk assessment model, and the risk assessment results are output. The risk assessment method is a model trained using the input information and a risk value corresponding to the behavior of the aircraft obtained by a simulation based on the input information.

8. The system acquires input information including position information indicating the location of the aircraft, aircraft information of the aircraft, weather information, and environmental information. Based on the input information, the computer is instructed to use a trained risk assessment model to evaluate the risk when the aircraft is in the aforementioned position and to output the risk assessment results. The risk assessment model is a program that is trained using the input information and the risk values ​​corresponding to the behavior of the aircraft obtained by simulation based on the input information.

Images