JP6664318B2 - Risk estimation system and risk estimation method - Google Patents

Description

  The present invention relates to a risk estimation system and a risk estimation method.

  Conventionally, expected rainfall information of each region and each time zone is stored, and based on the stored network data, a guidance route from a departure place to a destination that satisfies a route search condition is obtained, and the stored expected rainfall information is stored. An apparatus is disclosed that calculates rainfall amount in the acquired guidance route based on the acquired guidance route, creates rainfall guidance information indicating the calculated rainfall amount in association with the guidance route, and displays the created rainfall guidance information on a display unit. (See Patent Document 1).

JP 2012-8047 A

However, in the above device, attention is paid to the weather information in the guide route, but the influence of the weather information on the road is not considered. For this reason, useful information may not be able to be provided to the user.
The present invention has been made in view of such circumstances, and an object of the present invention is to provide a risk estimation system and a risk estimation method that can provide more useful information.

(1): Radio waves on which information is superimposed are received from a plurality of satellites constituting a global positioning system and a quasi-zenith satellite constituting a quasi-zenith satellite system, and based on information extracted from the received radio waves. A position measuring unit that specifies a position of the vehicle, an extracting unit that extracts a caution area to be cautious when traveling based on the position specified by the position measuring unit at a lane level of a road, Based on information obtained by equipment mounted or brought into a vehicle existing around the area and information on weather obtained by a weather observation device, a risk that a predetermined event occurs in the attention area is determined on the road. and a risk estimation unit that estimates at the lane level, information obtained by mounting or brought in device in a vehicle, the device to obtain a change of state of the vehicle Information acquired Te, information based on the image captured in the imaging unit that captures an image of a periphery of the vehicle or of the information obtained by the radar device for detecting the state of the periphery of the vehicle, comprises at least one of information It is a risk estimation system.

(2) The risk estimation system according to (1) , wherein the risk estimation unit obtains information obtained by a device mounted on or brought into a vehicle existing around the caution area, which is obtained in advance. The risk of the occurrence of the predetermined event is estimated with reference to the correlation between the information on the weather acquired by the weather observation device and the risk of the occurrence of the predetermined event in the attention area.

(3) In the risk estimation system according to (1) or (2) , the information based on the image captured by the imaging unit is recognition accuracy of an image obtained from an analysis result of the image. The information acquired by the radar device is the detection accuracy of the object of the radar device.

(4): Radio waves on which information is superimposed are received from a plurality of satellites constituting the global positioning system and a quasi-zenith satellite constituting the quasi-zenith satellite system, and based on information extracted from the received radio waves. A position measuring unit that specifies a position of the vehicle, an extracting unit that extracts a caution area to be cautious when traveling based on the position specified by the position measuring unit at a lane level of a road, Based on information obtained by equipment mounted or brought into a vehicle existing around the area and information on weather obtained by a weather observation device, a risk that a predetermined event occurs in the attention area is determined on the road. A risk estimating unit for estimating at a lane level, wherein the extracting unit acquires information indicating a behavior of a vehicle in which the position positioning unit is mounted or brought in, and performs the position positioning. A position specified by, based on the behavior of the acquired vehicle, to the attention region is a risk estimation system for estimating at lane level road.

(5) In the risk estimation system according to any one of (1) to (4) , the extraction unit may include a trajectory of the position positioning unit recognized based on the position specified by the position positioning unit. Based on this, the attention area is extracted at the lane level of the road.

(6): Radio waves on which information is superimposed are received from a plurality of satellites constituting the global positioning system and a quasi-zenith satellite constituting the quasi-zenith satellite system, and based on the information extracted from the received radio waves. A position measuring unit that specifies a position of the vehicle, an extracting unit that extracts a caution area to be cautious when traveling based on the position specified by the position measuring unit at a lane level of a road, Based on information obtained by equipment mounted or brought into a vehicle existing around the area and information on weather obtained by a weather observation device, a risk that a predetermined event occurs in the attention area is determined on the road. A risk estimating unit for estimating at the lane level, wherein the risk estimating unit is acquired by a device mounted on or brought into a vehicle existing around the attention area. Information and, based on the information on the weather obtained by weather stations, the likelihood that a given event is resolved in the attention region is a risk estimation system for estimating at lane level road.

(7): In the risk estimation system according to any one of (1) to (6) , the information on the weather is a rainfall amount.

(8) In the risk estimation system according to any one of (1) to (7) , the predetermined event includes at least one of flooding and freezing of a road surface.

(9): The risk estimation system according to any one of (1) to (8) , wherein the risk estimation unit stores information including a result of the estimation in a terminal device or a vehicle of a road manager. The information is transmitted to the terminal device carried by the occupant.

(10): a position positioning unit that specifies its own position, an extraction unit that extracts a caution area to be careful when traveling on a road based on the position specified by the position positioning unit, Risk estimation for estimating a risk that a predetermined event will occur in the attention area based on information acquired by a device mounted or brought into a nearby vehicle and information on weather acquired by a weather observation device. And information obtained by a device mounted on or brought into the vehicle, information obtained by a device that obtains a change in the state of the vehicle, imaged by an imaging unit that images the periphery of the vehicle. information based on the image or of the information acquired by the radar device for detecting the state of the periphery of the vehicle, risk estimation system includes at least one information, A.

(11): the vehicle computer, based on the specified position by the position measurement unit for specifying a position of the own body, issued extracted attention region noted when the vehicle is traveling on a road, present around the attention area and information obtained by mounting or brought in equipment, based on the information on the weather obtained by weather stations, predetermined event to estimate the risk arising in the attention region, mounted or carried on the vehicle The information obtained by the device obtained is information obtained by a device that obtains a change in the state of the vehicle, information based on an image captured by an imaging unit that captures an image around the vehicle, or information around the vehicle. This is a risk estimation method that includes at least one piece of information acquired by a radar device that detects a state .

(1) - (5), (7), (8), (10), according to (11), the risk estimation unit, by a predetermined event to estimate the risk occurring in the attention region, More useful information can be provided.

According to (6) , the risk estimating unit estimates the possibility that the predetermined event will be resolved in the caution area at the lane level of the road, thereby providing more useful information.

According to (9) , the risk estimating unit transmits information including the estimated risk to a terminal device owned by the road manager or a terminal device owned by a vehicle occupant. Thereby, the road manager or the occupant of the vehicle can recognize the risk of the event occurring. As a result, the road manager can maintain the road or perform desired processing according to the risk. Further, the occupant of the vehicle can control the vehicle so as to travel while avoiding the attention area.

FIG. 2 is a diagram illustrating a functional configuration of a risk estimation system 1. FIG. 2 is a functional configuration diagram of the vehicle-mounted system 10. It is a conceptual diagram of the processing result of the position positioning part 24. FIG. 11 is a sequence diagram illustrating a process executed when a caution region is extracted. 5 is a flowchart illustrating a flow of a process executed by an extraction unit 82. FIG. 9 is a diagram for describing a specific example of extraction of an attention area. 6 is a flowchart illustrating a flow of a process executed by a correlation learning unit 62. FIG. 7 is a diagram illustrating an example of an information table 63 used when the correlation learning unit 62 learns a correlation. 6 is a flowchart illustrating a flow of a process executed by a risk calculating unit. It is a conceptual diagram of the process performed by the risk estimation system 1 of this embodiment. FIG. 7 is a diagram illustrating an example of an image IM displayed on a display unit of the navigation device 98.

  Hereinafter, an embodiment of a risk estimation system and a risk estimation method of the present invention will be described with reference to the drawings.

  FIG. 1 is a diagram illustrating a functional configuration of the risk estimation system 1. The risk estimation system 1 includes, for example, a vehicle on which the in-vehicle system 10 is mounted, a performance generation device 40, a weather information management device 50, a measurement device 54, an information provision device 56, a risk calculation device 60, and traffic information. It includes a processing device 70, an attention area extraction device 80, and a guidance information generation device 90. These devices communicate with each other via a network NW such as a local area network (LAN), a wide area network (WAN), a mobile phone network, a Wi-Fi network, and the Internet. Note that the risk estimation system 1 may include a plurality of vehicles equipped with the vehicle-mounted system 10.

  FIG. 2 is a functional configuration diagram of the in-vehicle system 10. The in-vehicle system 10 is a device mounted on a vehicle such as a two-wheel or four-wheel vehicle. The in-vehicle system 10 includes, for example, a GPS (Global Positioning System) antenna 12, a quasi-zenith antenna 14, various sensors 16, a radar device 18, a camera 20, an image analysis unit 22, a position measurement unit 24, It includes a unit 26, a communication unit 28, a control unit 30, a display unit 32, and map information 34. The various sensors 16 are an example of “a device that acquires a change in the state of the vehicle”.

  Note that the in-vehicle system 10 may be a device that forms a part of a mobile terminal. In this case, the occupant of the vehicle transmits the position information corresponding to the position information of the vehicle to the record generation device 40 by carrying or bringing the portable terminal equipped with the in-vehicle system 10 into the vehicle. In this case, the various sensors 16, the radar device 18, and the camera 20 are omitted in the portable terminal and provided in the vehicle. The communication unit 28 of the mobile terminal acquires information held by the various sensors, the radar device 18 and the camera 20 provided in the vehicle by communicating with the communication unit provided in the vehicle and the like, and records the acquired information as a result. It is transmitted to the generation device 40. Note that the device included in the mobile terminal may be a part of the various sensors 16.

  The image analysis unit 22 and the control unit 30 may be realized by a processor such as a CPU (Central Processing Unit) executing a program stored in the storage unit. All or some of these functional units are realized by hardware such as an LSI (Large Scale Integration), an ASIC (Application Specific Integrated Circuit), and an FPGA (Field-Programmable Gate Array). May be provided for realizing the above function. Further, these functional units may be realized by cooperation of software and hardware. The map information 34 is stored in a non-volatile storage medium such as a flash memory and an HDD (Hard Disk Drive).

  The GPS antenna 12 receives radio waves on which information (positioning information) is superimposed from a plurality of GPS satellites. The GPS antenna 12 is not limited to a GPS satellite, and may receive radio waves from a satellite constituting a global navigation satellite system (GNSS) such as GLONASS and Galileo, for example.

  The quasi-zenith antenna 14 receives a radio wave on which information (positioning information and correction information described later) is superimposed from one or more quasi-zenith satellites among a plurality of quasi-zenith satellites constituting the quasi-zenith satellite system. The quasi-zenith satellite system is a satellite system in which a plurality of satellites having orbits that pass through the zenith (right above) of a certain area (for example, Japan) are combined. The quasi-zenith antenna 14 is highly likely to be able to receive radio waves not affected by multipath caused by a high-rise building or the like from the quasi-zenith satellite. Note that the GPS antenna 12 and the quasi-zenith antenna 14 may be integrated.

  The various sensors 16 include, for example, an acceleration sensor, a direction sensor, a vehicle speed sensor, a steering angle sensor, and the like. The acceleration sensor is, for example, a triaxial acceleration sensor. The acceleration sensor detects the acceleration of the vehicle and outputs a detection result to the collection unit 26. The direction sensor measures the magnetism to detect the direction of the vehicle with respect to the earth, and outputs the detection result to the collection unit 26. The vehicle speed sensor includes, for example, a wheel speed sensor attached to each wheel, and a controller that integrates these detection results. The vehicle speed sensor detects the speed of the vehicle and outputs a detection result to the collection unit 26. The steering angle sensor detects the steering angle of the steering wheel, and outputs a detection result to the collection unit 26.

  The various sensors 16 include a brake pressure sensor and a detection unit that detects an operation state of an ABS (Anti-lock Braking System) device. When the ABS device determines that the braking control is performed based on the detection result of the brake pressure sensor, the vehicle speed estimated from the detection result of the rotation speed sensor that detects the rotation speed of the axle, and the vehicle detected by the vehicle speed sensor If the speed does not match, it is determined that a tire slip has occurred, and control for suppressing wheel lock is executed.

  The radar device 18 emits radio waves such as millimeter waves and ultrasonic waves around the vehicle, detects radio waves (reflected waves) reflected by an object, analyzes the distribution of the reception level of the detected radio waves, At least the position (distance and direction) of the object is detected. The radar device 18 outputs a processing process or a processing result such as information indicating object detection accuracy to the collection unit 26. One or more of the radar devices 18 are attached to an arbitrary portion of the vehicle. The radar device 18 may detect the position and the speed of the object by an FM-CW (Frequency Modulated Continuous Wave) method.

  Further, the in-vehicle system 10 may include a finder. The finder is LIDAR (Light Detection and Ranging or Laser Imaging Detection and Ranging) that measures scattered light with respect to irradiation light and detects the distance to the target.

  The camera 20 is attached to, for example, an upper portion of a front windshield, a rear surface of a room mirror, or the like. The camera 20 is a camera using a solid-state image sensor such as a charge coupled device (CCD) or a complementary metal oxide semiconductor (CMOS). The camera 20 repeatedly captures an image of the front of the vehicle at a predetermined cycle, for example, and outputs data of the captured image to the image analysis unit 22.

  The image analysis unit 22 detects a weather condition around the vehicle based on, for example, an image captured by the camera 20. The image analysis unit 22 outputs information indicating the recognition accuracy of the image obtained from the image analysis result to the collection unit 26. Further, the image analysis unit 22 may detect raindrops or snow around the vehicle or the front window, and estimate a rainfall amount or the like based on the detection result. The image analysis unit 22 outputs a processing result to the collection unit 26. The function of the image analysis unit 22 may be included in the weather information management device 50.

  Based on the radio wave on which the information received by the GPS antenna 12 is superimposed and the radio wave on which the information received by the quasi-zenith antenna 14 is superimposed, the position positioning unit 24 is provided at a predetermined sampling interval, for example, based on the principle of triangulation. The position of the vehicle is specified by performing a positioning calculation for specifying the position of the own device.

  The positioning information includes satellite orbit information (ephemeris and almanac) relating to the corresponding satellite, a correction value of the clock, and a correction coefficient of the ionosphere. The correction information is information derived by a reference device which is an electronic reference point provided at a predetermined position in advance. This correction information has been transmitted from the equipment on the ground side to the quasi-zenith satellite in advance. The reference device calculates a geometric distance from the own device to the target satellite based on a position of the own device and a position of a GPS satellite or a quasi-zenith satellite (hereinafter, a target satellite) acquired in advance. Derive. In addition, the reference device derives a pseudo distance between the own device and the target satellite based on the propagation time of radio waves acquired from the target satellite. The reference device acquires the difference between the pseudo distance and the geometric distance as an error. Then, the reference device transmits the error information to the ground station device. The ground station apparatus derives parameters of a function for deriving a pseudo-range error for each coordinate point based on the errors obtained from the plurality of reference apparatuses, and transmits the parameters of the derived function to the quasi-zenith satellite as correction information. .

  FIG. 3 is a conceptual diagram of a processing result of the position positioning unit 24. FIG. 3A shows a trajectory of a position specified using information transmitted from a GPS satellite, and FIG. 3B shows a trajectory specified using information transmitted from a GPS satellite and a quasi-zenith satellite. The trajectory of the position is shown. In FIG. 3A, the position information is plotted on the lane L1, the position outside the lane L1, and the lane L2 due to the positioning error of the specified position. In FIG. 3B, since the positioning error of the specified position is smaller than in the example of FIG. 3A, the position information is plotted in an area excluding the area AR of the lane L1 where the vehicle actually travels. Have been. As a result, the position positioning unit 24 of the embodiment can more accurately specify the position where the vehicle equipped with the in-vehicle system 10 has actually traveled at the lane level of the road. In the drawing, an area AR is an example of an attention area extracted by an extraction unit 82 of an attention area extraction device 80 described later.

  In the present embodiment, the position is specified using the information transmitted from the GPS satellite and the quasi-zenith satellite. However, the information transmitted from the quasi-zenith satellite is omitted, and the information transmitted from the GPS satellite is omitted. Only one may be used.

  Further, the position positioning unit 24 may derive a change in the position of the vehicle based on the detection results of the various sensors 16 and the like mounted on the vehicle. In this case, the position positioning unit 24 corrects the position of the vehicle by performing positioning calculation based on the derived position change.

  The collection unit 26 collects the position information specified by the position positioning unit 24, the detection results of the various sensors 16, the processing results of the radar device 18, and the analysis results of the image analysis unit 22, and collects a predetermined amount of information. Then, the information collected by using the communication unit 28 is transmitted to the performance generation device 40.

  The control unit 30 generates information to be presented to the user based on the information generated by the risk calculation device 60, and causes the display unit 32 to display the generated information. The display unit 32 includes a display device such as an LCD (Liquid Crystal Display) or an organic EL (Electroluminescence) display.

  The map information 34 is, for example, information in which a road shape is represented by a link indicating a road and a node connected by the link. The map information 34 may include a curvature of a road, POI (Point Of Interest) information, and the like. The map information 34 includes, for example, road information such as information on the center of a lane or information on a boundary of a lane. The road information includes information indicating the type of road such as an expressway, toll road, national road, or prefectural road, the number of lanes of the road, the width of each lane, the gradient of the road, and the position of the road (coordinates including longitude and latitude). , The curvature of the curve of the lane, the position of the junction of the lane, and the position of the branch point. The map information 29 may be updated at any time by the information acquired by the communication unit 28.

  The result generation device 40 includes, for example, map information 42, a map matching unit 44, and a driving result generation unit 36. The map information 42 has information equivalent to the map information 34.

  The map matching unit 44 performs a map matching process on the information acquired from the in-vehicle system 10. The map matching unit 44 determines which of the elements (for example, links) included in the map information 42 is present on which link based on the acquired position information and the map information 42. is there. By this map matching processing, it is determined which link and which lane are included in the map information 42.

  The traveling record generation unit 46 acquires the processing result of the map matching unit 44 and generates traveling record information based on the acquired information. The traveling performance information is information indicating the actual traveling performance of the vehicle on which the vehicle-mounted system 10 is mounted. The travel record information includes, for example, information on the position where the vehicle has actually traveled, road links, information on road lanes, and the like. The traveling result information is transmitted to the vehicle and the attention area extraction device 80.

  The weather information management device 50 includes, for example, weather disaster information 52. In the weather disaster information 52, information on weather or information on disaster associated with each area is stored. The meteorological disaster information 52 stores, for example, a measurement result (for example, rainfall) of the measuring device 54 obtained from the measuring device 54, and information (for example, heavy rain information) about weather or a disaster obtained from the information providing device 56. .

  The measuring device 54 is, for example, a weather observation device provided at a predetermined position. The measuring device 54 observes, for example, precipitation, wind direction, wind speed, temperature, sunshine duration, and the like.

  The information providing device 56 is, for example, a server device managed by the national government, local governments, or the like, and provides weather information and disaster information to the weather information management device 50. The information on disaster is, for example, information on natural disasters such as heavy rain, heavy snow, and earthquake.

  The risk calculating device 60 includes, for example, a correlation learning unit 62, a risk calculating unit 64, and past calculated risk information 66. The correlation learning unit 62 includes a risk that a predetermined event occurs in the attention area, at least one of information obtained by a device mounted on or brought into a vehicle existing around the attention area, and the weather information management apparatus 50. To derive the correlation between the information on the weather acquired by The risk calculation unit 64 estimates the risk of occurrence of a predetermined event in the attention area at the lane level of the road based on the correlation derived by the correlation learning unit 62. The predetermined event is an event that is inconvenient for the running of the vehicle, such as flooding of the road or freezing of the road surface. The past calculated risk information 66 is information on past risks calculated by the risk calculating unit 64.

  The traffic information processing device 70 includes, for example, a four-wheel traffic information analyzer 72, two-wheel traffic information analyzers 74, and an integrated analyzer 76. The four-wheel traffic information analysis unit 72 acquires the information of the four-wheeled vehicle acquired by the performance generation device 40, and analyzes the acquired information of the four-wheeled vehicle. The two-wheel traffic information analysis unit 74 acquires the information of the two-wheeled vehicle acquired by the performance generation device 40, and analyzes the acquired information of the two-wheeled vehicle. The integrated analysis unit 76 generates traffic information based on the acquired information on the four-wheeled vehicle and the two-wheeled vehicle. The traffic information is, for example, information indicating a degree of congestion in a predetermined section of a road.

  The attention area extraction device 80 includes, for example, an extraction unit 82 and map information 84. Further, the extraction unit 82 extracts an area AR (see FIG. 3) in which the position information is not plotted as the attention area based on the locus of the position specified by the position positioning unit 24. The caution region is a region where the vehicle is not traveling on the road and it is estimated that there is some problem, and is a region where the vehicle should be careful when traveling.

  Further, the extraction unit 82 acquires information indicating the behavior of the vehicle in which the vehicle-mounted system 10 is mounted or brought in, and collects the position of the vehicle-mounted system 10 specified by the vehicle-mounted system 10 and the collection unit 26 of the vehicle-mounted system 10. The attention area is estimated at the lane level of the road based on the information indicating the behavior of the vehicle that has been performed. This processing will be described later with reference to FIGS.

  The guidance information generation device 90 includes, for example, a route generation unit 92 and a guidance information generation unit 94. The route generation unit 92 generates a route to a destination according to a request from a user. The guidance information generation unit 94 is information to be output to a user when traveling on the route generated by the route generation unit 92, and is configured to enable the vehicle to smoothly travel on the generated route. Generate guidance information for guidance. The guidance information generation unit 94 generates information for causing the user to recognize the attention area extracted by the extraction unit 82 at the lane level of the road. The route and information to the destination is sent to the vehicle that sent the request. The navigation device 98 mounted on the vehicle that has transmitted the request causes the display unit to display the route and information to the destination as an image or output the sound from a speaker according to the traveling position and traveling state of the vehicle. . The information obtained by each device included in the risk estimation system 1, the process of the device, and the processing result may be transmitted to the in-vehicle system 10, the administrator terminal 100 that manages the system, and the mobile terminal 110.

[Attention area extraction processing]
FIG. 4 is a sequence diagram illustrating a process executed when the attention area is extracted. First, the position positioning unit 24 of the in-vehicle system 10 acquires the position information of the own device (Step S100). Next, the collection unit 26 of the in-vehicle system 10 stores the position information, the detection results of the various sensors 16, the information acquired from the radar device 18, and the information acquired from the image analysis unit 22 in the storage device (not shown) of the own device. Hereinafter, such information will be referred to as “vehicle information”.) (Step S102). Next, the collection unit 26 of the in-vehicle system 10 transmits the accumulated vehicle information using the communication unit 28 to the record generation device 40 (Step S104).

  Next, the map matching unit 44 of the performance generation device 40 performs a map matching process based on the vehicle information (Step S106). Next, the driving record generation unit 46 of the driving record generation device 40 generates driving record information for each road (step S108). Next, the performance generation device 40 transmits the generated traveling performance information and vehicle information to the attention area extraction device 80 (Step S110). The travel record information may be transmitted to, for example, the vehicle-mounted system 10, and an image indicating the travel record information may be displayed on the display unit 32 of the vehicle-mounted system 10. The image indicating the traveling result information is, for example, an image in which the trajectory of the in-vehicle system 10 is displayed on a map.

  Next, the extraction unit 82 of the attention area extraction device 80 extracts an attention area based on the traveling result information (Step S112). Next, the extraction unit 82 transmits the extracted information of the attention area to the in-vehicle system 10 (Step S114). Thus, the processing of one routine of this flowchart ends.

  FIG. 5 is a flowchart illustrating a flow of a process performed by the extraction unit 82. A specific example of the processing of this flowchart will be described with reference to FIG. First, the extraction unit 82 analyzes the vehicle information based on the vehicle information (Step S200). Next, the extraction unit 82 associates the analysis result with the position of the vehicle at the time when the vehicle information was acquired. (Step S202). Next, the extraction unit 82 extracts a position at which the analysis result satisfies a predetermined criterion as an attention area (Step S204). Thus, the processing of this flowchart ends.

  FIG. 6 is a diagram for describing a specific example of the attention area extraction. The illustrated example shows a trajectory of a vehicle acquired at a predetermined sampling interval when the predetermined vehicle travels on the lane L1. The extraction unit 82 analyzes the vehicle information (speed, acceleration, angular velocity, operation state of the ABS device, detection accuracy of the object of the radar device 18, recognition accuracy of the image) in each trajectory, and integrates each element or a predetermined element. Derive the index. The index is a value that increases as the absolute value or the amount of change in the speed, acceleration, angular velocity, or the like during the observation period increases. The index is a value that increases when the operation state of the ABS device is on. The index is a value that increases as the degree of decrease in the detection accuracy of the radar device 18 increases or as the image recognition accuracy increases. Note that the index may be a value that increases as the angle between the displacement vectors when the displacement is extracted during the sampling period increases.

  Then, the extraction unit 82 compares the indices and sets a position where the behavior of the vehicle satisfies the predetermined criterion as the attention area. The predetermined reference is an element included in the behavior of the vehicle at time t (at least one of speed, acceleration, angular velocity, operation state of the ABS device, object detection accuracy of the radar device 18, and image recognition accuracy), At least one of the elements of the behavior of the vehicle (at least one of the speed, acceleration, angular velocity, operation state of the ABS device, detection accuracy of the object of the radar device 18, and recognition accuracy of the image) at time t + 1 deviates by a predetermined value or more. is there. Further, when the operation state of the ABS device is off at time t, but the operation state of the ABS device is on at time t + 1, it is determined that the predetermined criterion is satisfied. As described above, when the vehicle suddenly accelerates, decelerates, or turns sharply, or when the detection accuracy of the radar or the image recognition accuracy is reduced by a predetermined amount or more, it is determined that the analysis result satisfies the predetermined criterion.

  As described above, since the attention area is extracted based on the position information with higher accuracy, it is possible to provide information on the attention area with higher accuracy. The information of the attention area with high precision is information in which the position and the error of the actual area corresponding to the attention area are small.

  In the example described above, an index derived by analyzing the behavior of the vehicle is used. However, in addition (or instead), an index derived from a change in the position of the vehicle may be used. . The index derived from the change in the position of the vehicle is, for example, an index derived from at least one or more of the acceleration in the traveling direction, the acceleration in the lateral direction, and the degree of change in the turning angle derived from the trajectories of a plurality of vehicles. It is. In this case, it is determined whether each of the two indices derived based on the behavior of the vehicle and the change in the position of the vehicle or a result of statistically processing the two indices satisfies a predetermined criterion. .

[Correlation learning unit processing]
FIG. 7 is a flowchart illustrating a flow of a process performed by the correlation learning unit 62. First, the correlation learning unit 62 acquires the information of the attention area from the attention area extraction device 80 (Step S200). Next, the correlation learning unit 62 acquires information on weather from the weather information management device 50 (Step S202). Next, the correlation learning unit 62 acquires information indicating the state of the vehicle (step S204). Next, the correlation learning unit 62 learns the correlation between the position of the attention area, information related to weather, vehicle information, and the event in the attention area, and calculates the risk of the occurrence of the predetermined event in the predetermined attention area. Is derived (step S206). Note that the event in the attention area is set in advance based on the actually observed result. The learning result of the correlation learning unit 62 is stored in the storage device of the risk calculation device 60.

  FIG. 8 is a diagram illustrating an example of an information table 63 used when the correlation learning unit 62 learns a correlation. The information table 63 is, for example, information in which vehicle information, weather-related information, and events are associated with the attention area. For example, when a flood occurs in the attention area “001”, the correlation learning unit 62 learns vehicle information obtained by a vehicle traveling in the attention area and information on weather. Then, the correlation learning unit 62 derives a function (details will be described later) that derives a risk of occurrence of flooding in the attention area “001” based on the vehicle information and the information on weather. As described above, the correlation learning unit 62 derives conditions under which a predetermined event occurs in the attention area.

[Process of risk calculation unit]
FIG. 9 is a flowchart illustrating a flow of a process performed by the risk calculation unit 64. First, the risk calculation unit 64 acquires information on weather from the weather information management device 50 (step S300). Next, the risk calculation unit 64 acquires the information of the attention area from the attention area extraction device 80 (Step S302). Next, the risk calculation unit 64 determines whether or not an attention area exists in the area to be processed (step S304). If there is no attention area, the process proceeds to step S312. If there is an attention area, the risk calculation unit 64 determines whether or not a target attention area exists at the same position in the past (step S306). When there is no target attention area at the same position, the risk calculation unit 64 calculates the risk using a predetermined method (step S312). The predetermined method is a method of calculating a risk using a function that uses a predetermined element included in information about weather as a parameter.

  If there is a target attention area at the same position, the risk calculation unit 64 acquires vehicle information from vehicles around the target attention area (step S308). Next, the risk calculation unit 64 sets parameters of the function derived by the above-described correlation learning unit 62 based on the obtained vehicle information and information on weather (step S310), and based on the set parameters and the function. Then, a risk is calculated (step S312).

Here, for example, a description will be given assuming that a flood has occurred in the past in the target attention area. The risk calculator 64 calculates the risk in the attention area based on, for example, the following equation (1). “P (t)” is a probability (risk) of flooding at time t, and “d” is a drainage capacity coefficient in a preset attention area. “F _{p, cp} ” is a function of the amount of precipitation ( _p ) at time t and the accumulated precipitation ( _cp ) from the time when a predetermined or more amount of precipitation occurs to the time t. Further, “Ir” is a coefficient corresponding to a degree of decrease in recognition accuracy of an image captured by the camera 20 of the vehicle existing near the attention area with respect to a preset first reference value, and “Rr” is Is a coefficient corresponding to the degree of decrease in the detection accuracy of the object of the radar device 18 of the vehicle existing near the attention area with respect to the second reference value set in advance. The reduction in image recognition accuracy is caused, for example, by halation caused by reflection from rain accumulated on the road. The detection accuracy of the radar device 18 for detecting an object is reduced due to, for example, raindrops around the vehicle. Note that “Ir” or “Rr” may be omitted.
P (t) = dF _{p, cp} (t) × {1- (Ir × Rr)} (1)

  Next, the risk calculating unit 64 stores the calculated risk in the past calculated risk information 66 (Step S314), and transmits information indicating the calculated risk to a vehicle or the like (Step S316). Thus, the processing of this flowchart ends.

  FIG. 10 is a conceptual diagram of a process executed by the risk estimation system 1 of the present embodiment. The attention area extraction device 80 extracts the attention area AR based on the trajectory of the position specified by the in-vehicle system 10 or the behavior of the vehicle at the specified position. The risk calculation unit 64 of the risk calculation device 60 includes information on the attention area AR, vehicle information existing near the attention area AR (for example, image recognition accuracy or object detection accuracy of the radar device 18), and information on the attention area AR. Information about the weather (for example, rainfall, accumulated rainfall) is obtained. Then, the risk calculation unit 64 applies the obtained information to a function derived from the correlation between the vehicle information when the event has occurred in the past in the attention area and the information on the weather, which is obtained in advance, and Derive the risk of occurrence.

  By the above-described processing, it is possible to derive a risk relating to the influence of weather information on a road, and notify the occupant of the vehicle and a road manager of the derived result.

  In the example described above, an example in which the risk of flooding is derived has been described. However, instead of (or in addition to) flooding, the risk of occurrence of other events may be derived based on the above-described concept. . The other risks include, for example, a risk that the road surface freezes, a risk of a road surface state in which a hydroplaning phenomenon may occur, and a risk that the road surface becomes a black ice burn state.

  Further, in the above-described example, the risk of occurrence of the event is derived. However, instead (or in addition), the possibility of the occurrence of the event being resolved may be derived based on the above-described idea. Good.

  FIG. 11 is a diagram illustrating an example of an image IM displayed on the display unit of the navigation device 98. Note that the image IM may be displayed on the display unit 32, the display unit of the administrator terminal 100, or the display unit of the mobile terminal 110. As shown in the figure, it is assumed that there is an attention area AR1 that may be submerged in the lane L2. For example, when the vehicle is traveling in the lane L2 and the vehicle reaches a position at a predetermined distance from the attention area AR1, the navigation device 98 may display, for example, "The attention area AR1 may be flooded. Please do so. "And the position of the attention area AR1 are displayed on the display unit so as to be superimposed on the map, or the above information is notified by voice. Thereby, the occupant of the vehicle can control the vehicle so as to avoid the attention area AR.

  In the example described above, an example in which the risk of an event occurring in the attention area is displayed on the display unit has been described. However, information on the risk of an event occurring in the attention area is used when automatic driving is performed. Is also good. In this case, for example, the vehicle that performs automatic driving may control the vehicle to avoid the attention area based on the risk of an event occurring in the attention area, or may allow the vehicle to move more safely when passing near the attention area. Or control the vehicle to pass through the area.

  According to the above-described embodiment, the receiving unit (the GPS antenna 12 and the quasi-zenith antenna 14) that receives radio waves on which information is superimposed from the quasi-zenith satellites constituting the quasi-zenith satellite system in the area where the GPS star and the device are located. )), Based on the information extracted from the electric wave received from the radio wave, a position positioning unit 24 for specifying the position information of the own device, and caution should be exercised when traveling based on the position specified by the position positioning unit 24. The extraction unit 82 extracts the attention area at the lane level of the road, information obtained by a device mounted or brought into a vehicle existing around the attention area, and information on weather obtained by the weather observation device. A risk calculating section 64 for estimating the risk of occurrence of a predetermined event in the attention area at the lane level of the road based on the It is possible to provide such information.

  As described above, the embodiments for carrying out the present invention have been described using the embodiments. However, the present invention is not limited to these embodiments at all, and various modifications and substitutions may be made without departing from the gist of the present invention. Can be added.

1) Risk estimation system, 10) On-board system, 12) GPS antenna, 14) Quasi-zenith antenna, 16) Various sensors, 18) Radar device, 20) Camera, 22) Image analysis unit, 24) Positioning unit, 26) Collection unit, 28 communication unit, 32 display unit, 34 map information, 40 record generation unit, 44 map matching unit, 46 driving record generation unit, 50 weather information management device, 60 risk calculation device, 62 correlation learning unit, 64 risk calculation unit, 70 traffic information processing device, 80 attention area extraction device, 82 extraction unit

Claims (11)

From a plurality of satellites constituting the global positioning system, and a quasi-zenith satellite constituting the quasi-zenith satellite system, a radio wave on which information is superimposed is received, and based on information extracted from the received radio wave, its own A position positioning unit for specifying a position,
Based on the position specified by the position positioning unit, an attention area to be careful when traveling, an extraction unit that extracts at the lane level of the road,
Based on information obtained by a device mounted or brought into a vehicle existing around the attention area and information on weather obtained by a weather observation device, a risk that a predetermined event occurs in the attention area is reduced. A risk estimating unit for estimating at the lane level of the road ,
The information obtained by the device mounted or brought into the vehicle is information obtained by a device that obtains a change in the state of the vehicle, information based on an image captured by an imaging unit that captures an image around the vehicle, or Including at least one of information obtained by a radar device that detects a state around the vehicle;
Risk estimation system. The risk estimating unit is obtained in advance, information obtained by a device mounted or brought into a vehicle existing around the caution area, information on weather obtained by a weather observation device, and in the caution area With reference to the correlation with the risk of the occurrence of the predetermined event, estimating the risk of the occurrence of the predetermined event,
The risk estimation system according to claim 1. The information based on the image captured by the imaging unit is the recognition accuracy of the image obtained from the analysis result of the image,
The information acquired by the radar device is the detection accuracy of the object of the radar device,
The risk estimation system according to claim 1. From a plurality of satellites constituting the global positioning system, and a quasi-zenith satellite constituting the quasi-zenith satellite system, a radio wave on which information is superimposed is received, and based on information extracted from the received radio wave, its own A position positioning unit for specifying a position,
Based on the position specified by the position positioning unit, an attention area to be careful when traveling, an extraction unit that extracts at the lane level of the road,
Based on information obtained by a device mounted or brought into a vehicle existing around the attention area and information on weather obtained by a weather observation device, a risk that a predetermined event occurs in the attention area is reduced. A risk estimating unit for estimating at the lane level of the road,
The extraction unit acquires information indicating the behavior of the vehicle on which the position positioning unit is mounted or brought in, based on the position specified by the position positioning unit and the acquired behavior of the vehicle, Attention area is estimated at the lane level of the road,
Risk estimation system. The extraction unit, based on a trajectory of the position positioning unit recognized based on the position specified by the position positioning unit, to extract the attention area at the lane level of the road,
The risk estimation system according to claim 1. From a plurality of satellites constituting the global positioning system, and a quasi-zenith satellite constituting the quasi-zenith satellite system, a radio wave on which information is superimposed is received, and based on information extracted from the received radio wave, its own A position positioning unit for specifying a position,
Based on the position specified by the position positioning unit, an attention area to be careful when traveling, an extraction unit that extracts at the lane level of the road,
Based on information obtained by a device mounted or brought into a vehicle existing around the attention area and information on weather obtained by a weather observation device, a risk that a predetermined event occurs in the attention area is reduced. A risk estimating unit for estimating at the lane level of the road,
The risk estimating unit, based on information acquired by a device mounted or brought into a vehicle existing around the attention area, and information on weather acquired by a weather observation device, a predetermined value in the attention area Estimate the likelihood of the event going away at the lane level of the road,
Risk estimation system. The information on the weather is rainfall,
The risk estimation system according to any one of claims 1 to 6. The predetermined event includes at least one of flooding and freezing of a road surface,
The risk estimation system according to any one of claims 1 to 7. The risk estimating unit transmits information including a result of the estimation to a terminal device owned by a road manager or a terminal device owned by an occupant of a vehicle,
The risk estimation system according to claim 1. A position location unit that identifies its own position,
Based on the position specified by the position positioning unit, an extraction unit that extracts an attention area to be careful when traveling on a road,
Based on information obtained by a device mounted or brought into a vehicle existing around the attention area and information on weather obtained by a weather observation device, a risk that a predetermined event occurs in the attention area is reduced. And a risk estimating unit for estimating,
The information obtained by the device mounted or brought into the vehicle is information obtained by a device that obtains a change in the state of the vehicle, information based on an image captured by an imaging unit that captures an image around the vehicle, or Including at least one of information obtained by a radar device that detects a state around the vehicle;
Risk estimation system. Computer
Based on the identified position by the positioning unit to identify the position of themselves, attention areas to be aware of when traveling on a road out extract,
Based on information obtained by a device mounted or brought into a vehicle existing around the attention area and information on weather obtained by a weather observation device, a risk that a predetermined event occurs in the attention area is reduced. estimated constant,
The information obtained by the device mounted or brought into the vehicle is information obtained by a device that obtains a change in the state of the vehicle, information based on an image captured by an imaging unit that captures an image around the vehicle, or Including at least one of information obtained by a radar device that detects a state around the vehicle;
Risk estimation method.

Images