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

Risk assessment device, risk assessment method, and recording medium

[0001] The present disclosure relates to assessing risks associated with flying an air vehicle.

[0002] In recent years, the use of drones for various purposes has been considered. However, when flying a drone, various risks are expected, such as the risk of the drone itself crashing or 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 risk of an unmanned aerial vehicle such as a drone crashing.

[0003] Japanese Patent Application Laid-Open No. 2020-112574

[0004] Typically, operators plan drone flights by looking at maps such as mapping apps, but it is important to confirm the safety of the flight plan before actually flying the drone.

[0005] One object of the present disclosure is to provide a risk assessment device that can assess in advance the risks involved in flying an aerial vehicle such as a drone.

[0006] In one aspect of the present disclosure, a risk assessment device includes: an acquisition means for acquiring input information including location information indicating the location of an aircraft, aircraft information about the aircraft, weather information, and environmental information; and a risk assessment means for evaluating the risk when the aircraft is at the location using a trained risk assessment model based on the input information, and outputting a risk assessment result.

[0007] In another aspect of the present disclosure, a risk assessment method includes acquiring input information including location information indicating the location of an aircraft, aircraft information of the aircraft, weather information, and environmental information, and using a trained risk assessment model based on the input information, assessing the risk when the aircraft is at the location, and outputting a risk assessment result.

[0008] In yet another aspect of the present disclosure, a recording medium records a program that causes a computer to execute a process of acquiring input information including location information indicating the location of an aircraft, aircraft information of the aircraft, weather information, and environmental information, and, based on the input information, using a trained risk assessment model, assessing the risk when the aircraft is at the location, and outputting the risk assessment result.

[0009] According to the present disclosure, it is possible to evaluate in advance the risks involved in flying an aircraft such as a drone.

[0010] 1 shows a risk assessment device according to a first embodiment; FIG. 2 is a block diagram showing the hardware configuration of the risk assessment device; FIG. 3 is a block diagram showing the functional configuration for model training of the risk assessment device according to the first embodiment; FIG. 4 shows an example of simulating the behavior of a drone; FIG. 5 shows an example of a simulation result of a drone crashing; FIG. 6 shows an example of a risk assessment unit assessing risk; FIG. 7 shows an example of a risk assessment model; FIG. 8 is a flowchart of a training process for the risk assessment model; FIG. 9 is a block diagram showing the functional configuration for risk assessment of the risk assessment device according to the first embodiment; FIG. 10 is a flowchart of a risk assessment process; FIG. 11 is a block diagram showing the functional configuration of a risk assessment device according to a second embodiment; FIG. 12 is a flowchart of processing by the risk assessment device according to the second embodiment.

[0011] Preferred embodiments of the present disclosure will be described below with reference to the drawings. <First Embodiment> [Overall Configuration] Fig. 1 shows a risk assessment device according to a first embodiment. The risk assessment device 100 is configured by a computer such as a personal computer (PC). The risk assessment device 100 evaluates risks that may occur when an air vehicle such as a drone is flown along a planned route. Note that, although the following description will use a drone as an example of an air vehicle, the air vehicle in this disclosure is not limited to air vehicles generally referred to as drones, but includes various unmanned air vehicles that fly under external control.

[0012] The risk assessment device 100 receives input information such as location information, aircraft information, weather information, and environmental information. The risk assessment device 100 is equipped with a pre-trained risk assessment model. The risk assessment device 100 uses the risk assessment model to assess risk based on the input information and outputs a risk assessment value as the risk assessment result. By assessing 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 along a planned route.

[0013] 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] The I / F 11 inputs and outputs data to and from external devices. Specifically, input information such as location information and aircraft information is input to the risk assessment device 100 through the I / F 11. In addition, the risk assessment value generated by the risk assessment device 100 is output to the external device through the I / F 11 as necessary.

[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 be a GPU (Graphics Processing Unit), a TPU (Tensor Processing Unit), a quantum processor, or an FPGA (Field-Programmable Gate Array). As will be described later, the processor 12 executes a risk assessment model training process and a risk assessment process using the trained risk assessment model.

[0016] The memory 13 is configured by a ROM (Read Only Memory), a RAM (Random Access Memory), etc. The memory 13 is also used as a working memory while the processor 12 is executing various processes.

[0017] The recording medium 14 is a non-volatile, non-transitory 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 records various programs to be executed by the processor 12. When the risk assessment device 100 executes various processes, the programs recorded on the recording medium 14 are loaded into the memory 13 and executed by the processor 12.

[0018] DB15 stores data used and generated by the risk assessment device 100. Specifically, DB15 stores location information, aircraft information, weather information, environmental information, and the like that are input as input information. DB15 also stores data used in training of the risk assessment model described below, such as risk definition data and simulation results of drone behavior. Information related to the risk assessment model obtained through training is also stored in DB15. Note that if the capacity of memory 13 is sufficient, the above data may be stored in memory 13.

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

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

[0021] The simulation unit 31 simulates the behavior of the drone based on the input information and outputs a simulation result indicating the predicted behavior of the drone. Specifically, the input information to the simulation unit 31 includes location information, aircraft information, weather information, and environmental information. The input information is used as conditions for the simulation.

[0022] The location information indicates the three-dimensional position of the drone, and may be, for example, latitude, longitude, altitude, etc. in a real geographical space. Note that in a simulation of drone behavior, a virtual geographical space may be used instead of a real geographical space. In this case, the location information indicates the three-dimensional position in the virtual geographical space.

[0023] The aircraft information is information about the drone itself, and includes various information about the drone, such as its size, shape, type, engine type, number of wings, etc. Drone movement information, such as the direction of movement, speed, and acceleration of the drone, may also be used as the aircraft information.

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

[0025] Environmental information is information that indicates the geographical environment in the area where the drone flies, and includes topographical information on the ground. Typically, so-called map information can be used as the topographical information. The topographical information includes information that indicates the state of the ground, such as classifications of sea, river, land, mountainous area, road, and urban area. In particular, in order to evaluate the risk of a drone crash, the environmental information preferably includes information such as whether the area is crowded with buildings or whether the area is crowded with people.

[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 occurs with the drone (hereinafter simply referred to as "trouble").

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

[0028] For example, when engine trouble occurs in drone D, the simulation unit 31 performs a simulation of drone D crashing based on the drone D's aircraft information, weather information at that time, and environmental information. FIG. 5A shows an example of a simulation result of drone D crashing. In the example of FIG. 5A, simulation result S1 indicates that drone D will crash to the ground along the trajectory indicated by the symbol S1. The simulation unit 31 performs multiple simulations while keeping the position and aircraft information of drone D the same and changing the movement information and weather information of drone D. As a result, as shown in FIG. 5B, simulation results S2 to S5 that differ from simulation result S1 are obtained.

[0029] The simulation unit 31 performs multiple simulations for the planned drone flight area while changing the location information, aircraft information, weather information, and environmental information. The simulation unit 31 also performs multiple simulations while changing the type of drone trouble. Examples of drone trouble include engine trouble, communication equipment trouble, propeller trouble, being blown by strong winds, and contact with birds or other drones. This allows for obtaining simulation results of the behavior of various drones when various troubles occur under various weather conditions in the planned drone flight area. The simulation unit 31 outputs the obtained simulation results to the risk assessment unit 32. Note that various methods, such as Monte Carlo simulation using random numbers, can be used for the simulation.

[0030] The risk assessment unit 32 assesses the risks corresponding to the drone's behavior obtained as a result of the simulation using risk definition data. The risk definition data defines risks that primarily result from a drone crash, depending on the ground conditions indicated by the map information. There are multiple possible risks that could occur if a drone crashes, such as the risk of the drone hitting a person or the risk of environmental pollution. The risk definition data specifies a risk value for each risk.

[0031] FIG. 6 shows an example of the risk assessment unit 32 assessing risk using risk definition data. Consider risk A as the risk of a crashed drone hitting a person. The risk definition data for risk A defines a risk value of "0" if the drone crashes into the ocean and a risk value of "1" if the drone crashes onto land. Furthermore, as shown in FIG. 6, assume that simulation results S1 to S5 are obtained for drone behavior. In simulation results S1 and S2, drone D crashes onto land, resulting in a risk value of "1." Meanwhile, in simulation results S3 to S5, drone D crashes into the ocean, resulting in a risk value of "0." Therefore, the average risk of simulations S1 to S5 for risk A is "0.4." In this way, the risk assessment unit 32 can calculate the risk value when drone D is at a certain location.

[0032] In the above example, the risk definition data for Risk A sets the risk value to "1" if the drone crashes on land. However, for example, land can be divided into densely populated areas such as urban areas and sparsely populated areas, and the risk value can be set to "2" in densely populated areas and "1" in sparsely populated areas.

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

[0034] In formula (1), "tranjectory i " indicates the trajectory of the drone obtained as a result of the simulation by the simulation unit 31. As described above, the simulation unit 31 simulates the behavior of the drone when multiple troubles t occur. The trajectory of one simulation result obtained is called "tranjectory i "i" is the identifier of each simulation, and "S ｔ " indicates the number of simulations.

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

[0036] "weight j " indicates the weight assigned to each risk. When assessing the risk arising from a drone crash, multiple risks have different levels of importance. For example, the importance of the risk of a drone hitting a person should be set higher than the importance of the risk of the drone falling into the sea. For this reason, a weight is assigned to each risk, and the total risk R is calculated taking into account the importance of each risk. The second half of formula (1) (1 / S ｔ (hereafter) multiple simulation results tranjectory i The weighted sum of the risk values ​​for each simulation is calculated by the number of simulations S ｔ The average risk value across multiple simulations is calculated by averaging the risk values ​​by .

[0037] "p(happen t ) indicates the probability of trouble t occurring, and "t" indicates the type of trouble. Therefore, the total risk R is calculated for multiple assumed troubles t, taking into account the probability of each trouble occurring. In this way, using equation (1), the total risk R when a drone is at a certain location is calculated based on the results of multiple simulations, taking into account multiple risks, the weight of each risk, multiple troubles, and the probability of each trouble occurring. The risk assessment unit 32 outputs the total risk R calculated in this way to the model training unit 33.

[0038] The model training unit 33 trains the 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 uses input information including location information, aircraft information, etc. as input data and performs supervised learning using the total risk as correct answer data to train the risk assessment model. When location information, aircraft information, weather information, and environmental information regarding a drone present at a certain location are input, the risk assessment model obtained by training outputs an assessment value of the risk posed by the drone under those conditions. The output assessment value is a value indicating the total risk taking into account multiple troubles and multiple risks that may occur under those conditions.

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

[0040] [Model Training Process] Next, the risk assessment model training process will be described. Fig. 8 is a flowchart of the risk assessment model training process. This process is realized by the processor 12 shown in Fig. 2 executing a pre-prepared program and operating as the elements shown in Fig. 3.

[0041] First, the simulation unit 31 receives location information, aircraft information, weather information, and environmental information as input information (step S10) and simulates the drone's behavior for multiple troubles (step S11). Next, the risk assessment unit 32 refers to the risk definition data and calculates a total risk taking into account multiple risks based on the drone's trajectory indicated by the multiple simulation results (step S12). Specifically, the risk assessment unit 32 calculates the total risk R using the aforementioned formula (1) based on the multiple simulation results. Next, the model training unit 33 trains the risk assessment model using the input information input in step S10 and the total risk R obtained in step S12 (step S13). Then, the model training process ends.

[0042] [Functional Configuration for Risk Assessment] Fig. 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 components 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 location on the planned flight path of the drone that is the subject of risk assessment. The aircraft information input unit 42 receives aircraft information about the drone that is the subject of risk assessment. The weather information input unit 43 receives weather information indicating the weather conditions that are the subject of risk assessment. The environmental information input unit 44 receives information about the environment that is the subject of risk assessment, specifically, topographical information about the area corresponding to the drone's location.

[0044] The risk assessment unit 45 performs risk assessment using the trained risk assessment model obtained by the above-described 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 the 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 types of trouble occur with the drone under the conditions specified by the information entered in each of the above input sections. Therefore, anyone planning to fly a drone can assess the risks in advance by entering the location where the drone will be flown, drone information, weather conditions at the time, environmental information about the flight area, etc.

[0046] [Risk Assessment Processing] Next, a description will be given of the risk assessment processing performed by the risk assessment device 100. Fig. 10 is a flowchart of the risk assessment processing. This processing is realized by the processor 12 shown in Fig. 2 executing a program prepared in advance and operating as the elements shown in Fig. 9.

[0047] First, the location information input unit 41, the aircraft information input unit 42, the weather information input unit 43, and the 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 processing ends.

[0048] The risk assessment value indicates the total risk when the drone is at the location indicated by the input location information. Therefore, by performing risk assessment processing for multiple locations on the planned drone flight route or within the area, the user can confirm the risk of the planned flight route or the entire area.

[0049] [Variation] During risk assessment, when displaying the obtained risk value on the display unit 16, the risk assessment device 100 may display the risk value on a map indicating the drone's position. For example, the risk assessment device 100 displays a map on the display unit 16. The position information input unit 41 acquires position information of a point specified by the user on the displayed map using a mouse or the like. The risk output unit 46 then superimposes the calculated risk value on the map, for example, near that point. This allows the user to associate the point specified as the drone's position with the risk value at that point.

[0050] 11 is a block diagram showing the functional configuration of a risk assessment device 70 according to the second embodiment. The risk assessment device 70 includes an acquisition unit 71 and a risk assessment unit 72.

[0051] 12 is a flowchart of processing by the risk assessment device 70 of the second embodiment. The acquisition means 71 acquires input information including location information indicating the location of the aircraft, aircraft information of the aircraft, weather information, and environmental information (step S71). The risk assessment means 72 evaluates the risk when the aircraft is at that location using a trained risk assessment model based on the input information 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 occur due to the flight of an aircraft.

[0053] A part or all of the above-described embodiments can be described as, but not limited to, the following supplementary notes.

[0054] (Supplementary Note 1) A risk assessment device comprising: an acquisition means for acquiring input information including location information indicating the location of an aircraft, aircraft information of the aircraft, weather information, and environmental information; and a risk assessment means for assessing the risk when the aircraft is at the location using a trained risk assessment model based on the input information, and outputting a risk assessment result.

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

[0056] (Supplementary Note 3) The risk assessment device according to Supplementary Note 2, wherein the risk value corresponding to the behavior of the aircraft is calculated based on a plurality of risks associated with the aircraft.

[0057] (Supplementary Note 4) The risk assessment device according to Supplementary Note 3, wherein the risk value corresponding to the behavior of the aircraft is calculated using weights set for each of the plurality of risks.

[0058] (Supplementary Note 5) The risk assessment device according to Supplementary Note 2, wherein the risk value corresponding to the behavior of the aircraft is calculated based on a plurality of troubles related to the aircraft.

[0059] (Supplementary Note 6) The risk assessment device according to Supplementary Note 5, wherein the risk value corresponding to the behavior of the aircraft is calculated using the occurrence probabilities of multiple troubles related to the aircraft.

[0060] (Appendix 7) A risk assessment device as described in Appendix 2, in which the risk value corresponding to the behavior of the aircraft is calculated using a predetermined risk value based on topographical information of the area corresponding to the location of the aircraft.

[0061] (Supplementary Note 8) A risk assessment method that acquires input information including location information indicating the location of an aircraft, aircraft information of the aircraft, weather information, and environmental information, and, based on the input information, uses a trained risk assessment model to assess the risk when the aircraft is at the location, and outputs a risk assessment result.

[0062] (Supplementary Note 9) A recording medium having recorded thereon a program that causes a computer to execute a process of acquiring input information including location information indicating the location of an aircraft, aircraft information of the aircraft, weather information, and environmental information, and, based on the input information, using a trained risk assessment model, assessing the risk when the aircraft is at the location, and outputting the risk assessment results.

[0063] Although the present disclosure has been described above with reference to the embodiments and examples, the present disclosure is not limited to the above-described embodiments and examples. Various modifications that can be understood by a person skilled in the art can be made to the configuration and details of the present disclosure within the scope of the present disclosure.

[0064] 12 Processor 31 Simulation unit 32 Risk assessment unit 33 Model training unit 41 Position information input unit 42 Aircraft information input unit 43 Weather information input unit 44 Environmental information input unit 45 Risk assessment unit 46 Risk output unit 100 Risk assessment device

Claims

1. An acquisition means for acquiring input information including location information indicating a location of an aircraft, aircraft information of the aircraft, weather information, and environmental information; a risk assessment means for assessing a risk when the aircraft is at the position using a trained risk assessment model based on the input information, and outputting a risk assessment result; A risk assessment device comprising:

2. A risk assessment device as described in claim 1, wherein the risk assessment model is a model trained using the input information and a risk value corresponding to the behavior of the aircraft obtained by simulation based on the input information.

3. The risk assessment device according to claim 2 , wherein the risk value corresponding to the behavior of the flying object is calculated based on a plurality of risks associated with the flying object.

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

5. The risk assessment device according to claim 2 , wherein the risk value corresponding to the behavior of the aircraft is calculated based on a plurality of troubles related to the aircraft.

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

7. 3. The risk assessment device according to claim 2, wherein the risk value corresponding to the behavior of the aircraft is calculated using a preset risk value based on topographical information of the area corresponding to the position of the aircraft.

8. A computer comprising: Acquire input information including location information indicating a location of an aircraft, aircraft information of the aircraft, weather information, and environmental information; A risk assessment method that uses a trained risk assessment model to assess the risk when the aircraft is at the location based on the input information and outputs a risk assessment result.

9. Acquire input information including location information indicating a location of an aircraft, aircraft information of the aircraft, weather information, and environmental information; A program that causes a computer to execute a process of evaluating the risk when the aircraft is at the position using a trained risk assessment model based on the input information, and outputting the risk assessment results.