Prediction device, prediction method, and prediction program

Abstract

Enables appropriate prediction of dangers on the road. [Solution] A prediction device 100 controls the flight of an aircraft flying ahead of a vehicle based on predetermined conditions. The prediction device 100 predicts risks related to vehicle traffic using information about the situation at a target location collected by the aircraft whose flight is being controlled.

Description

[Technical Field]

[0001] The present invention relates to a prediction device, a prediction method, and a prediction program. [Background technology]

[0002] Road hazard prediction is performed to avoid hazards on the roads on which the vehicles travel and ensure the safe passage of autonomous vehicles.Hazard prediction is performed by analyzing information about road abnormalities such as obstacles, construction work, and accidents.Therefore, in order to perform hazard prediction, it is necessary to collect information about road abnormalities in advance.

[0003] Therefore, as a conventional technology for collecting information on abnormalities on the road, for example, a technology for collecting external information of the vehicle using sensors, cameras, etc. mounted on the vehicle is known (see, for example, Patent Document 1). Also, a technology for acquiring wide-angle images used for roadside detection using wide-angle cameras installed on the roadside is known (see, for example, Patent Document 2). [Prior art documents] [Patent documents]

[0004] [Patent Document 1] International Publication No. 2019 / 082774 [Patent Document 2] Japanese Patent Publication No. 2022-048963 Summary of the Invention [Problem to be solved by the invention]

[0005] However, conventional technologies have issues in making appropriate hazard predictions on roads. For example, they cannot detect obstacles in the blind spots of sensors and cameras attached to vehicles, making it difficult to predict hazards in advance. In addition, because cameras and sensors must be installed on the target roads, it is currently difficult to install cameras and sensors on all roads that autonomous vehicles may travel on. [Means for solving the problem]

[0006] Therefore, in order to solve the above-mentioned problems and achieve the objectives, the prediction device of the present invention is characterized by having a flight control unit that controls the flight of an aircraft flying ahead of a vehicle based on predetermined conditions, and a prediction unit that predicts risks related to the passage of the vehicle using information regarding the situation of a target point collected by the aircraft controlled by the flight control unit. [Effects of the Invention]

[0007] The present invention has the effect of enabling appropriate prediction of dangers on the road. [Brief explanation of the drawings]

[0008] [Figure 1] FIG. 1 is a diagram illustrating an overall view of the processing of a prediction device according to an embodiment. [Figure 2] FIG. 2 is a diagram illustrating a configuration of a prediction device according to an embodiment. [Figure 3] FIG. 3 is a table illustrating an example of flight conditions according to the embodiment. [Figure 4] FIG. 4 is a diagram illustrating an example of flight control according to the embodiment. [Figure 5] FIG. 5 is a diagram illustrating an example of an output of a risk prediction result according to the embodiment. [Figure 6] FIG. 6 is a diagram illustrating a flowchart of processing by the prediction device according to the embodiment. [Figure 7] FIG. 7 is a diagram illustrating a flowchart of processing by the prediction device according to the embodiment. [Figure 8] FIG. 8 is a diagram illustrating an example of a computer that realizes the prediction device according to the embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0009] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, embodiments of the present invention (hereinafter referred to as "embodiments") will be described with reference to the drawings. Note that the embodiments are not limited to the following description.

[0010] <Overview> (background) To ensure the safe passage of autonomous vehicles, information on road abnormalities such as road obstacles, construction work, and accidents is analyzed to predict possible dangers on the road. In order to make the above-mentioned danger predictions, it is necessary to collect information on road abnormalities (hereinafter sometimes referred to as "road abnormality information") in advance.

[0011] Therefore, as a technology for collecting information regarding abnormalities on the road, there are known reference technologies, such as collecting external information about the vehicle using sensors and cameras mounted on the vehicle, and acquiring wide-angle images to be used for roadside detection using wide-angle cameras installed on the roadside.

[0012] However, with the above-mentioned reference technologies, it is difficult to predict dangers caused by obstacles in the blind spots of sensors and cameras attached to the vehicle. Also, in order to collect roadside information, it is necessary to install cameras and sensors on the target roads, but it is difficult to install cameras and sensors on all roads on which autonomous vehicles may travel.

[0013] (Processing by prediction device 100) Therefore, the prediction device 100 according to this embodiment performs risk prediction using information about the situation of a target point (hereinafter, sometimes simply referred to as "point information") collected by an air vehicle such as a drone or small airplane (hereinafter, sometimes simply referred to as "air vehicle") that flies ahead of the vehicle. Note that in this embodiment, the "target point" includes points where there are blind spots from the vehicle's perspective, points where accidents have occurred in the past, points where there is a possibility of danger to vehicle traffic due to bad weather, deteriorating road conditions, etc.

[0014] Here, an overview of the processing performed by the prediction device 100 will be described. Fig. 1 is a diagram illustrating an overview of the processing performed by the prediction device 100 according to an embodiment. The prediction device 100 shown in Fig. 1 is an example of a computer that provides a technology for realizing information processing related to risk prediction, which will be described below.

[0015] First, the prediction device 100 controls the flight of the aircraft based on predetermined conditions ((1) in FIG. 1). Specifically, the prediction device 100 controls the aircraft 200 so that it flies over the target point 1 ahead of the vehicle 10 (e.g., an autonomous bus).

[0016] Next, the prediction device 100 causes the flying object 200 to collect point information at the target point. For example, the prediction device 100 causes the flying object 200 to collect point information including road abnormality information such as automobiles 11, pedestrians 12, and construction sites 13 that are in the blind spot as seen from the vehicle 10 at the target point 1 (intersection).

[0017] The prediction device 100 uses location information collected by an aircraft whose flight is controlled to predict dangers related to vehicle traffic ((2) in FIG. 1). The prediction device 100 then outputs the results of the danger prediction, such as information informing of danger (danger information) and information used to control the automatic driving of the vehicle based on the results of the danger prediction (automatic driving control information), to the user who drives the vehicle and to a control device that automatically drives the vehicle (hereinafter, sometimes referred to as an "automatic driving control device") ((3) and (3-1) in FIG. 1).

[0018] In this way, the prediction device 100 of this embodiment has the effect of enabling appropriate prediction of dangers on the road by predicting dangers that may occur in the future based on location information collected by an aircraft flying ahead of the vehicle.

[0019] <Explanation of Prediction Device 100> Next, the configuration of the prediction device 100 according to this embodiment will be described. Fig. 2 is a diagram showing the configuration of the prediction device 100 according to this embodiment. As shown in Fig. 2, the prediction device 100 includes a communication unit 110, a storage unit 120, and a control unit 130.

[0020] 2, the prediction device 100 may include an input unit such as a keyboard or a mouse for receiving input such as operations by an administrator, etc. The prediction device 100 may also include a display or the like for displaying to an administrator, etc., location information collected by the flying object 200 and information regarding the results of risk predictions made by the prediction unit 133 described below.

[0021] (Communication unit 110) The communication unit 110 performs data communication related to input of location information collected by the flying object 200, information about the situation around the vehicle collected by the automatic driving control device (hereinafter, may be simply referred to as "surrounding information"), etc. The communication unit 110 also performs data communication related to output of information about the prediction result of the risk prediction made by the prediction unit 133 described below.

[0022] The communication unit 110 is realized by a NIC (Network Interface Card) or the like, and controls communication via an electric communication line such as a LAN (Local Area Network) or the Internet. The communication unit 110 is connected to a network by wire or wirelessly as necessary, and can transmit and receive information bidirectionally with the flying object 200, other prediction devices, the automatic driving control device 300, etc.

[0023] (Storage unit 120) The storage unit 120 stores data and programs used for various processes by the control unit 130, and various data acquired by the operation of the control unit 130. The storage unit 120 is realized by a semiconductor memory element such as a random access memory (RAM) or a flash memory, or a storage device such as a hard disk or an optical disk. As shown in FIG. 2 , the storage unit 120 has a flight condition DB 121, a location information DB 122, a surrounding information DB 123, and a prediction model DB 124.

[0024] (Flight conditions DB121) Flight condition DB 121 is a database that stores flight conditions that are set in advance to control the flight of flying object 200. Specifically, flight condition DB 121 stores conditions that act as triggers for controlling the flight of flying object 200, in association with flight control that is executed by flight control unit 132 (described later) when the conditions are met.

[0025] An example of flight conditions stored in the flight condition DB 121 will now be described with reference to Fig. 3. Fig. 3 is a table diagram showing an example of flight conditions according to an embodiment. As shown in Fig. 3, the flight condition DB 121 stores "No.", which is information identifying individual data included in the flight conditions, in association with "conditions" and "flight control" in a table format or the like. In the following sections, each of the individual conditions shown in the table shown in Fig. 3 will be described.

[0026] As shown in No. "1," the flight condition DB 121 stores the conditions "driving is performed by navigation" and "flying ahead along a planned course based on navigation" in association with each other. Under the condition of No. "1," the flight control unit 132 controls the flying object 200 to fly ahead of the vehicle and collect location information based on the future course of the vehicle.

[0027] As shown in No. "2," flight condition DB121 stores the condition "vehicle speed is equal to or greater than (or less than) XX km / h" in association with "control the distance between the vehicle and the aircraft to '●● m', and control the flight altitude of the aircraft to 'XX m'." Under the condition of No. "2," the aircraft 200 is controlled by the flight control unit 132 to change the distance ahead of the vehicle and the flight altitude when the vehicle is equal to or greater than a predetermined speed or less than a predetermined speed.

[0028] For example, if the vehicle speed is high (e.g., 80 km / h or higher), the flight control unit 132 can set the distance ahead of the vehicle to "50 m" and the flight altitude to "10 m." On the other hand, if the vehicle speed is low (e.g., less than 80 km / h), the flight control unit 132 can set the distance ahead of the vehicle to "25 m" and the flight altitude to "5 m." Note that the values ​​of the vehicle speed, distance ahead of the vehicle, and flight altitude described above are merely examples.

[0029] As shown in No. "3," flight condition DB121 stores the condition "the planned route has either a blind spot, an intersection, or an accident-prone location" in association with "fly ahead to the target location." Under condition No. "3," if there is a target location on the planned route of the vehicle where there is a possibility of danger occurring, the flying object 200 is controlled by the flight control unit 132 to fly ahead to the target location and collect location information.

[0030] As shown in Nos. "4 to 6," flight condition DB 121 stores the conditions "worsening weather," "no-fly zone," and "flight restricted area (tunnel, etc.)" in association with "cancel flight." Under the conditions of Nos. "4 to 6," if a situation that interferes with flight occurs or has occurred, flying object 200 is controlled by flight control unit 132 to cancel flight and return to a waiting position installed on the vehicle.

[0031] As shown in No. "7," flight condition DB 121 stores the condition "the same or similar other flying object exists" in association with "execute a predetermined linked operation." Under the condition of No. "7," if another flying object exists within a predetermined range of flying object 200 in the airspace in which flying object 200 flies, flight control unit 132 controls flying object 200 to fly in conjunction with the other flying object, collect location information, and so on.

[0032] The above-mentioned predetermined linked operations include, for example, controls such as acquiring location information acquired by other aircraft, and evacuating from the target airspace to avoid contact with other aircraft.

[0033] (Location information DB122) The point information DB 122 is a database that stores information (point information) about the status of a target point that is collected by the flying object 200 and acquired from the flying object 200 by an acquisition unit 131 described below.

[0034] Specifically, the location information DB122 stores still image data or video image data captured at the target location, the presence or absence of obstacles detected by the sensor, weather information (temperature, humidity, amount of precipitation / snowfall, fog occurrence, etc.), etc. as location information.

[0035] (Nearby information DB123) The surrounding information DB 123 is a database that stores information (surrounding information) about the situation around the vehicle, which is collected by an automatic driving control device or the like and acquired from the automatic driving control device by an acquisition unit 131, which will be described later.

[0036] Specifically, the surrounding information DB123 stores still image data or video image data captured around the autonomously driving vehicle, the presence or absence of obstacles detected by sensors, weather information (temperature, humidity, amount of precipitation / snowfall, fog occurrence, etc.), etc. as surrounding information.

[0037] (Prediction model DB124) The prediction model DB 124 is a database that stores predetermined prediction models used for risk prediction by the prediction unit 133, which will be described later. For example, the prediction model DB 124 can store, as prediction models, predetermined models based on publicly known techniques, such as generative models such as large-scale language models, supervised machine learning models, unsupervised machine learning models, and reinforcement learning models.

[0038] (control unit 130) Here, the explanation will be continued by returning to Fig. 2. The control unit 130 has an internal memory for temporarily storing programs that define various processing procedures and the like of the prediction device 100 and processing data, and is realized by electronic circuits such as a CPU (Central Processing Unit) and an MPU (Micro Processing Unit), and integrated circuits such as an ASIC (Application Specific Integrated Circuit) and an FPGA (Field Programmable Gate Array). As shown in Fig. 2, the control unit 130 has an acquisition unit 131, a flight control unit 132, a prediction unit 133, and an output unit 134.

[0039] (Acquisition part 131) The acquisition unit 131 acquires location information from the flying object 200 via the communication unit 110, and stores the acquired location information in the location information DB 122. The acquisition unit 131 also acquires surrounding area information from the vehicle's automatic driving control device 300 via the communication unit 110, and stores the acquired surrounding area information in the surrounding area information DB 123.

[0040] (Flight control unit 132) The flight control unit 132 controls the flight of the flying object 200, such as a drone or a small airplane, based on predetermined conditions. Specifically, the flight control unit 132 causes the flying object 200 to fly ahead of a vehicle. Then, the flight control unit 132 causes the flying object 200 to collect location information.

[0041] An example of flight control of the flying object 200 by the flight control unit 132 will now be described with reference to Fig. 4. Fig. 4 is a diagram showing an example of flight control according to an embodiment. Fig. 4 shows an example of the flying object 200 flying and collecting location information based on flight control by the flight control unit 132.

[0042] As a first example, the flight control unit 132 controls the flying object 200a to fly at a specified position ahead of the vehicle ((1-1) in FIG. 4). For example, the flight control unit 132 controls the flying object 200a to fly ahead of the vehicle 10 at a "position at a distance of 20 m and an altitude of 5 m" to collect location information. Note that the specific numerical values ​​of the distance and altitude described above are merely examples, and any other numerical values ​​may be used.

[0043] Furthermore, the flight control unit 132 controls the flying object 200a to fly ahead of the vehicle 10 while maintaining a distance from the vehicle based on the vehicle's navigation information (planned route) ((1-2) in FIG. 4). For example, the flight control unit 132 controls the flying object 200a to fly ahead of the vehicle 10 along the planned route and collect location information based on the condition set to No. "1" shown in FIG. 3.

[0044] The flight control unit 132 controls at least one of the distance between the vehicle and the aircraft and the flight altitude of the aircraft, depending on the vehicle's moving speed ((1-3) in FIG. 4). For example, the flight control unit 132 controls the distance between the vehicle 10 and the aircraft 200a and the flight altitude of the aircraft 200, based on the condition set to No. "2" shown in FIG. 3.

[0045] As a second example, the flight control unit 132 controls the aircraft 200b to move ahead of the vehicle 10 to a target location that satisfies predetermined conditions and collect location information ((2) in Figure 4).

[0046] For example, the flight control unit 132 moves the flying object 200b to the target point 1 (intersection) based on the condition set to No. "3" in FIG. 3. Then, the flight control unit 132 causes the system to collect point information indicating that, at the target point 1 (intersection), a car 11 is approaching from the blind spot as seen from the location of the autonomously driving bus 10a. The flight control unit 132 also causes the system to collect point information indicating that, at the target point 1 (intersection), a pedestrian 12 is walking in the blind spot as seen from the location of the autonomously driving bus 10a. The flight control unit 132 also causes the system to collect point information indicating that, at the target point 1 (intersection), a construction site 13 is located in the blind spot as seen from the location of the autonomously driving bus 10a.

[0047] As a third example, the flight control unit 132 executes control to prohibit the flight of the aircraft if the airspace in which the aircraft is flying is within at least one of a no-fly zone, a flight restricted zone, or a point where the flight conditions of the aircraft are not met.

[0048] For example, based on the condition set in No. "4" shown in Figure 3, in the event of bad weather such as precipitation or wind speed exceeding a specified value, the flight control unit 132 controls the aircraft 200c to stop flying and return to a waiting position such as a charging spot installed on the vehicle ((3-1) in Figure 4).

[0049] In addition, based on the condition set in No. "5" shown in Figure 3, if the planned flight airspace is a no-fly zone, the flight control unit 132 controls the flight of the aircraft 200c to stop flying and return to a waiting position such as a charging spot installed on the vehicle ((3-2) in Figure 4).

[0050] In addition, based on the condition set in No. "6" shown in Figure 3, if the planned flight airspace is a flight restricted area where flight altitude is restricted, such as a tunnel, the flight control unit 132 controls the flight of the aircraft 200c to stop flying and return to a waiting position such as a charging spot installed on the vehicle ((3-3) in Figure 4).

[0051] Furthermore, when the remaining charge of the flying object 200c falls below a specified value, the flight control unit 132 controls the flying object 200c to return to a waiting position such as a charging spot provided on the vehicle ((3-4) in FIG. 4). Note that this condition is not shown in the conditions in FIG. 3.

[0052] As a fourth example, when there is another aircraft identical to or similar to the aircraft, the flight control unit 132 performs at least one of the following as a predetermined linked action shown in (7) of Figure 3 ((4) of Figure 4): acquiring information collected by the other aircraft and evacuating from the airspace in which the other aircraft is flying.

[0053] For example, based on the condition set to No. "7" shown in Figure 3, when aircraft 200a and another aircraft 200d are present in the same airspace, the flight control unit 132 controls aircraft 200a to stop flying so as to prevent contact between aircraft 200a and aircraft 200d, and to return to a waiting position such as a charging spot provided on the vehicle.

[0054] Furthermore, the flight control unit 132 controls the flying body 200a to collect point information from the flying body 200d when the flying body 200a and another flying body 200d are present in the same airspace, based on the condition set in No. "7" shown in Fig. 3. The point information collected from the flying body 200d is acquired as point information by the acquisition unit 131 described above.

[0055] (Prediction section 133) Continuing the explanation by returning to Fig. 2, the prediction unit 133 executes a predetermined risk prediction based on a prediction model or the like that outputs a prediction result about the occurrence of risk at a target point, based on inputs such as still image data or video image data captured at the target point, the presence or absence of an obstacle detected by a sensor, and weather information.

[0056] Specifically, the prediction unit 133 performs risk prediction for vehicle traffic using location information collected by the flying object controlled by the flight control unit 132. For example, the prediction unit 133 inputs still image data or video image data captured at a target location and the presence or absence of obstacles detected by a sensor, which are stored in the location information DB 122, into a prediction model, and outputs a risk prediction result such as the presence of other vehicles, pedestrians, construction sites, and other locations at the location where vehicle traffic requires caution. The prediction unit 133 also inputs weather information for the target location stored in the location information DB 122 into the prediction model, and outputs a risk prediction result such as the presence of bad weather, frozen roads, etc. at the location.

[0057] Furthermore, the prediction unit 133 uses location information collected by the air vehicle and surrounding information collected by the autonomously driven vehicle to perform risk prediction for vehicle traffic. For example, the prediction unit 133 inputs the location information and surrounding information described above into a prediction model and outputs risk prediction results such as "there are locations at the location where caution is required for vehicle traffic, such as other vehicles, pedestrians, and construction sites," "the occurrence of bad weather at the location," and "the occurrence of road freezing."

[0058] (output unit 134) The output unit 134 outputs the prediction result predicted by the prediction unit 133. Specifically, the output unit 134 outputs the prediction result of the risk prediction related to vehicle traffic by the prediction unit 133 to a device that controls automatic driving of the automatically driving vehicle.

[0059] Furthermore, the output unit 134 outputs the prediction result of the risk prediction related to vehicle traffic by the prediction unit 133 to the user operating the vehicle. Here, an example of the risk prediction result output by the output unit 134 will be described with reference to Fig. 5. Fig. 5 is a diagram showing an example of the output of the risk prediction result according to the embodiment.

[0060] For example, based on the risk prediction results predicted by the prediction unit 133, the output unit 134 displays information such as "An accident has occurred at the next intersection," "There is a lot of pedestrian traffic at the next intersection at the current time, so be careful," and "Be careful as the road surface conditions are deteriorating" to the user driving the vehicle.

[0061] The output unit 134 may display the above-mentioned information, for example, by displaying it on a console installed in the driver's seat of the vehicle ((1) in FIG. 5) or by projecting it onto the windshield in front of the driver based on known technology ((2) in FIG. 5).

[0062] (Aircraft 200) The flying object 200 is controlled by the flight control unit 132 and is an object that flies ahead of a vehicle, etc. For example, the flying object 200 may be an unmanned flying rotorcraft (helicopter), an airplane, a drone, etc.

[0063] (Automatic driving control device 300) The automatic driving control device 300 is an information processing device or the like installed in an automatic driving vehicle, and is a device that controls the automatic driving of the automatic driving vehicle. The automatic driving control device 300 according to this embodiment performs control such as reducing the vehicle speed in areas where caution is required for other vehicles, pedestrians, and vehicle traffic such as construction sites, areas where bad weather occurs at the area, areas where roads are frozen, etc., based on the risk prediction results output from the prediction device 100.

[0064] Note that the control of autonomous driving by the autonomous driving control device 300 may be based on known technology and is not limited to a method of controlling autonomous driving. Furthermore, the autonomous driving control device 300 may be an on-premise computer installed in the vehicle itself, or a computer running on a cloud server.

[0065] (Processing procedure by prediction device 100) Next, the procedure of the process implemented by the prediction device 100 according to this embodiment will be described with reference to Fig. 6 and Fig. 7. Fig. 6 and Fig. 7 are diagrams showing flowcharts of the process performed by the prediction device 100 according to this embodiment.

[0066] Fig. 6 is a flowchart that forms the basis of processing by the prediction device 100. Fig. 7 is a flowchart that shows processing when surrounding information is collected by an automatic driving control device or the like.

[0067] First, a flowchart that forms the basis of processing by the prediction device 100 will be described with reference to Fig. 6. The flight control unit 132 controls the flight of the flying object 200 based on preset flight conditions and the like (S101).

[0068] Here, the flying object 200 waits for processing until collection of point information is executed (No in S102). Then, when the execution conditions for collection of point information are met (Yes in S102), the flying object 200 starts collecting point information (S103). Note that the execution conditions for collection of point information here are any conditions that are set in advance, and may be, for example, conditions such as constantly collecting point information while the vehicle is traveling, or collecting point information of points where there are blind spots when viewed from the vehicle.

[0069] The acquisition unit 131 acquires location information from the flying object 200 (S104). Next, the prediction unit 133 performs risk prediction using the location information acquired by the acquisition unit 131 (S105). The output unit 134 outputs the result of the risk prediction (S106). Then, the prediction device 100 ends the process.

[0070] Next, a flowchart of processing when surrounding information is collected by an automatic driving control device, etc. will be described with reference to Figure 7. The flight control unit 132 controls the flight of the flying object 200 based on preset flight conditions, etc. (S201).

[0071] Here, the flying object 200 waits for processing until collection of point information is executed (No in S202). Then, when the execution conditions for collection of point information are satisfied (Yes in S202), the flying object 200 starts collecting point information (S203). Next, the acquisition unit 131 acquires point information from the flying object 200 (S204).

[0072] Here, if the vehicle collects surrounding information (Yes in S205), the acquisition unit 131 acquires the surrounding information from the vehicle (S206). Next, the prediction unit 133 executes risk prediction using the point information and surrounding information (S207).

[0073] On the other hand, if the vehicle does not collect surrounding information (No in S205), the process of S206 is not performed, and the prediction unit 133 performs risk prediction using the location information (S208). The output unit 134 outputs the result of the risk prediction (S209). Then, the prediction device 100 ends the process.

[0074] (effect) Next, we will explain the effects of the prediction device 100 according to this embodiment. To ensure the safe passage of autonomous vehicles, it is necessary to collect information about abnormalities on roads in advance, but with the reference technology, it may be difficult to collect information about abnormalities on the roads.

[0075] Therefore, the flight control unit 132 of the prediction device 100 according to this embodiment controls the flight of the flying object flying ahead of the vehicle based on predetermined conditions. The prediction unit 133 of the prediction device 100 uses location information collected by the flying object controlled by the flight control unit 132 to predict dangers related to vehicle passage.

[0076] The above-described process enables the prediction device 100 according to this embodiment to appropriately predict hazards on roads. As a result, when there is a blind spot with poor visibility from the vehicle, or when there is a possibility of danger due to a deterioration in road conditions, a pedestrian jumping out into the road, construction work, or the presence of a vehicle driving recklessly, the prediction device 100 can provide information to avoid the danger in advance and perform automatic driving control.

[0077] Furthermore, the prediction device 100 according to this embodiment achieves the following effects by executing the following processes.

[0078] The flight control unit 132 controls the flight controller 132 to maintain a distance from the vehicle and fly ahead of the vehicle based on the vehicle's navigation information. By performing the above-described processing, the prediction device 100 flies ahead of the vehicle along the vehicle's traveling direction, thereby achieving the effect of being able to predict dangers that may occur on the vehicle's planned path.

[0079] The flight control unit 132 controls at least one of the distance between the aircraft and the vehicle and the flight altitude of the aircraft according to the vehicle's moving speed. Through the above-described processing, the prediction device 100 can perform control such as flying away from the vehicle when the vehicle's speed is fast and flying close to the vehicle when the vehicle's speed is slow. As a result, the prediction device 100 achieves the effect of enabling more accurate risk prediction based on appropriate flight control according to the vehicle's speed.

[0080] The flight control unit 132 controls the aircraft to move ahead of the vehicle to a target location that satisfies predetermined conditions and collect location information. Through the above-described processing, the prediction device 100 can collect location information about locations ahead of the vehicle where a dangerous event may occur or locations where a dangerous event has occurred in the past. As a result, the prediction device 100 can predict danger earlier than conventional methods, thereby enabling the vehicle to appropriately avoid dangerous events.

[0081] The flight control unit 132 executes control to prohibit the flight of the aircraft if the airspace in which the aircraft flies is within at least one of a no-fly zone, a flight restricted zone, or a point where the flight conditions of the aircraft are not met.

[0082] By the above-described processing, the prediction device 100 can appropriately suspend flight at a location where flight of the aircraft is prohibited or where flight of the aircraft is not safe. As a result, the prediction device 100 has the effect of being able to perform appropriate risk prediction without violating laws, etc.

[0083] If there is another aircraft identical to or similar to the aircraft, the flight control unit 132 performs at least one of the following: acquiring information collected by the other aircraft, or evacuating from the airspace in which the other aircraft is flying.

[0084] Through the above-described processing, the prediction device 100 can control the flight of the aircraft so that it flies in conjunction with aircraft located in nearby airspace. For example, when other aircraft are present, the prediction device 100 can safely fly the aircraft by evacuating the aircraft from the airspace, thereby avoiding collisions with the other aircraft. Furthermore, by receiving location information acquired by other aircraft, the prediction device 100 can increase the amount of information it collects and acquire location information relating to a wider area.

[0085] The output unit 134 outputs the prediction result of the risk prediction related to vehicle traffic made by the prediction unit 133 to the user operating the vehicle. By performing the above-described processing, the prediction device 100 displays the prediction result of the risk prediction to the user operating the vehicle, thereby enabling the user to sense the risk at an early stage and operate the vehicle safely.

[0086] The prediction unit 133 predicts risks related to vehicle traffic using location information collected by the air vehicle and surrounding information collected by the autonomously driven vehicle. The output unit 134 outputs the prediction results of the risk prediction related to vehicle traffic by the prediction unit 133 to a device that controls the autonomous driving of the autonomously driven vehicle.

[0087] By performing the above-described processing, the prediction device 100 outputs the results of risk prediction to the automatic driving control device, thereby enabling an automatically driving vehicle to detect risk at an early stage and operate the vehicle safely.

[0088] <Modification> Below, modifications realized by the prediction device 100 according to this embodiment will be described.

[0089] (Data, etc.) The flying objects, danger predictions, danger information, automatic driving control information, names of functional parts of the prediction device 100, steps, processes, names of steps or processes, etc. used in the description of the above embodiments are merely examples and can be changed as desired.

[0090] For example, the flight condition DB 121 stores, in a table format or the like, a "No.", which identifies individual data included in the flight conditions, in association with a "condition," and a "flight control." However, the stored items and contents are not limited. The location information DB 122 stores, as location information, still image data or video data captured at a target location, the presence or absence of obstacles detected by a sensor, weather information (temperature, humidity, precipitation / snowfall amount, fog occurrence, etc.), etc., but the type of information stored is not limited. The surrounding information DB 123 stores, as surrounding information, still image data or video data captured around the autonomously driven vehicle, the presence or absence of obstacles detected by a sensor, weather information (temperature, humidity, precipitation / snowfall amount, fog occurrence, etc.), etc., but the type of information stored is not limited. The prediction model DB 124 has been described as being capable of storing, as prediction models, predetermined models based on publicly known techniques, such as generative models such as large-scale language models, supervised machine learning models, unsupervised machine learning models, and reinforcement learning models. However, the stored models are not particularly limited.

[0091] (Flowcharts, etc.) The steps in the flowcharts may be interchanged as long as there is no contradiction, and some steps may not be performed. In addition, conjunctions such as "next," "continue," "further," "at this time," and "on this occasion" used in the explanation of the flowcharts do not limit the order or timing of the execution of the processes in the flowcharts.

[0092] <Hardware configuration> The components of each device shown in the figure are conceptual functional units and do not necessarily have to be physically configured as shown. In other words, the specific form of distribution or integration of each device is not limited to that shown, and all or part of the devices can be functionally or physically distributed or integrated in any unit depending on various loads, usage conditions, etc. Furthermore, all or any part of the processing functions performed by each device can be realized by a CPU and a program analyzed and executed by the CPU, or can be realized as hardware using wired logic.

[0093] Furthermore, among the processes described in this embodiment, all or part of the processes described as being performed automatically can also be performed manually using known methods. In addition, the information including the processing procedures, control procedures, specific names, various data, and parameters shown in the drawings can be changed as desired unless otherwise specified.

[0094] <Program> In one embodiment, the various devices constituting the prediction device 100 can be implemented by installing a prediction program as package software or online software on a desired computer. For example, the prediction program can be executed by an information processing device to function as the various devices constituting the prediction device 100. The information processing device referred to here includes desktop and notebook personal computers. In addition, the information processing device also includes mobile communication terminals such as smartphones and mobile phones, and slate terminals such as PDAs (Personal Digital Assistants).

[0095] 8 is a diagram illustrating an example of a computer that realizes the prediction device 100 according to the embodiment. The computer 1000 includes, for example, a memory 1010 and a CPU 1020. The computer 1000 also includes a hard disk drive interface 1030, a disk drive interface 1040, a serial port interface 1050, a video adapter 1060, and a network interface 1070. These components are connected by a bus 1080.

[0096] The memory 1010 includes a ROM (Read Only Memory) 1011 and a RAM 1012. The ROM 1011 stores, for example, a boot program such as a BIOS (Basic Input Output System). The hard disk drive interface 1030 is connected to a hard disk drive 1090. The disk drive interface 1040 is connected to a disk drive 1100. A removable storage medium such as a magnetic disk or optical disk is inserted into the disk drive 1100. The serial port interface 1050 is connected to, for example, a mouse 1110 and a keyboard 1120. The video adapter 1060 is connected to, for example, a display 1130.

[0097] The hard disk drive 1090 stores, for example, an OS (Operating System) 1091, an application program 1092, a program module 1093, and program data 1094. That is, a program that defines each process of the various devices that constitute the prediction device 100 is implemented as a program module 1093 in which computer-executable code is written. The program module 1093 is stored, for example, in the hard disk drive 1090. For example, a program module 1093 for executing the same process as the functional configuration of the various devices that constitute the prediction device 100 is stored in the hard disk drive 1090. Note that the hard disk drive 1090 may be replaced by an SSD (Solid State Drive).

[0098] Furthermore, setting data used in the processing of the above-described embodiment is stored as program data 1094, for example, in the memory 1010 or the hard disk drive 1090. Then, the CPU 1020 reads the program module 1093 or the program data 1094 stored in the memory 1010 or the hard disk drive 1090 into the RAM 1012 as necessary, and executes the processing of the above-described embodiment.

[0099] The program module 1093 and program data 1094 are not limited to being stored in the hard disk drive 1090, but may also be stored in, for example, a removable storage medium and read by the CPU 1020 via the disk drive 1100 or the like. Alternatively, the program module 1093 and program data 1094 may be stored in another computer connected via a network (such as a LAN or a WAN (Wide Area Network)). The program module 1093 and program data 1094 may then be read by the CPU 1020 from the other computer via the network interface 1070.

[0100] <Other> Although the present embodiment has been described above, the present embodiment is not limited by the descriptions and drawings that form part of the disclosure. In other words, other embodiments, examples, operational techniques, etc. that are made by those skilled in the art based on the present embodiment are all included in the scope of the present embodiment. [Explanation of symbols]

[0101] 100 Prediction Device 110 Communications Department 120 Storage section 121 Flight conditions DB 122 Location Information DB 123 Neighborhood Information DB 124 Prediction Model DB 130 Control Unit 131 Acquisition Department 132 Flight Control Unit 133 Prediction Department 134 Output section 200 flying objects 300 Automatic driving control device

Claims

1. a flight control unit that controls the flight of the flying object that flies ahead of the vehicle based on predetermined conditions; A prediction unit that predicts a risk related to the passage of the vehicle using information about the situation of a target point collected by the flying object controlled by the flight control unit; A prediction device comprising:

2. The flight control unit Controlling the drone to fly ahead of the vehicle while maintaining a distance from the vehicle based on navigation information of the vehicle; The prediction device according to claim 1 .

3. The flight control unit controlling at least one of the distance between the aircraft and the vehicle and the flight altitude of the aircraft according to the moving speed of the vehicle; The prediction device according to claim 2 .

4. The flight control unit Moving the aircraft ahead of the vehicle to a target point that satisfies a predetermined condition; controlling the air vehicle to collect information about the status of the target location; The prediction device according to claim 1 .

5. The flight control unit The airspace in which the aircraft flies is When the aircraft is in at least one of a no-fly zone, a flight restricted zone, and a point where the flight conditions of the aircraft are not satisfied, control is executed to prohibit the aircraft from flying.

5. The prediction device according to claim 1, wherein the prediction device comprises: a first predictor;

6. The flight control unit If there are other flying objects that are the same as or similar to the flying object, Execute at least one of acquiring information collected by the other aircraft and evacuating from an airspace in which the other aircraft is flying.

5. The prediction device according to claim 1, wherein the prediction device comprises: a first predictor;

7. An output unit is further provided that outputs a prediction result of the risk prediction related to traffic of the vehicle by the prediction unit to a user who operates the vehicle.

5. The prediction device according to claim 1, wherein the prediction device comprises: a first predictor;

8. The prediction unit Using information about the situation of the target point collected by the aircraft and surrounding information collected by an autonomously driven vehicle, a risk prediction is made regarding traffic of the vehicle; An output unit that outputs a prediction result of the risk prediction related to vehicle traffic by the prediction unit to a device that controls automatic driving of the vehicle that performs automatic driving, 5. The prediction device according to claim 1, wherein the prediction device comprises: a first predictor;

9. A prediction method to be executed by a prediction device, a flight control process for controlling the flight of the flying object flying ahead of the vehicle based on predetermined conditions; a prediction step of predicting a risk related to the passage of the vehicle using information about the situation of a target point collected by the aircraft controlled by the flight control step; A prediction method comprising:

10. a flight control step of controlling the flight of the flying object flying ahead of the vehicle based on predetermined conditions; a prediction step of predicting a risk related to the passage of the vehicle using information about the situation of a target point collected by the aircraft controlled by the flight control step; A prediction program that causes a computer to execute the following.

Images