Factor estimation system and vehicle

Abstract

To appropriately estimate a factor of an abnormality in a recognition device of a vehicle.SOLUTION: A factor estimation system for estimating a factor of an abnormality in an on-vehicle detector for detecting an environment state of a vehicle includes: a storage section for storing abnormality information transmitted from a vehicle where an abnormality of the on-vehicle detector has been detected; an acquisition section for acquiring weather information of a travel zone in which the vehicle that has transmitted the abnormality information is traveling when the abnormality is detected; an extraction section for extracting the abnormality information having correlation with the weather information of the travel zone from a plurality of pieces of abnormality information stored in the storage section; and a model generation section for generating a factor estimation model to estimate a factor corresponding to the abnormality in the on-vehicle detector with respect to the abnormality information extracted in the extraction section.SELECTED DRAWING: Figure 2

Description

Technical Field

[0001] The present invention relates to a cause estimation system for estimating the cause of an abnormality of an in-vehicle detector that detects the external situation of a vehicle, and to a vehicle.

Background Art

[0002] As this type of technology, there is known a technology for determining, for each application, whether to adjust the parameters of an image recognition application, remove dirt from a lens, or determine an application failure by discriminating dirt on the lens of an in-vehicle camera (see Patent Document 1).

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional technology, although application failures are determined, the cause thereof has not been considered up to the point of estimating the cause. In-vehicle detectors necessary for vehicle control are essential for driving support, autonomous driving, etc. Technology for estimating the cause of an abnormality of such an in-vehicle detector leads to early recovery of the in-vehicle detector, thereby improving traffic convenience and safety. As a result, it is possible to contribute to the development of a sustainable transportation system.

Means for Solving the Problems

[0005] One aspect of the present invention is a cause estimation system for estimating the cause of an abnormality in an in-vehicle detector that detects the external situation of a vehicle, including a storage unit that stores abnormality information transmitted from a vehicle in which an abnormality of the in-vehicle detector has been detected, an acquisition unit that acquires weather information of a driving area in which the vehicle that transmitted the abnormality information was driving when the abnormality was detected, an extraction unit that extracts abnormality information having a relevance to the weather information of the driving area from among a plurality of pieces of abnormality information stored in the storage unit, and a model generation unit that generates a cause estimation model for estimating the cause leading to the abnormality of the in-vehicle detector with respect to the abnormality information extracted by the extraction unit. A vehicle according to another aspect of the present invention includes a storage unit that stores a cause estimation model generated by the cause estimation system of the above aspect, an in-vehicle detector that detects the external situation of the own vehicle, a removal device that removes water droplets or ice adhering to the in-vehicle detector, an own vehicle position detection unit that detects the position of the own vehicle, an acquisition unit that acquires current weather information of a driving area including the position of the own vehicle from an external device, and a control unit that operates the removal device based on the weather information and the cause estimation model.

Advantages of the Invention

[0006] According to the present invention, it becomes possible to appropriately estimate the cause of an abnormality in an in-vehicle detector of a vehicle.

Brief Description of the Drawings

[0007]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Embodiments for Carrying Out the Invention

[0008] Hereinafter, embodiments of the invention will be described with reference to the drawings. <Overview of the Cause Estimation System> When it is determined that a malfunction (which may also be referred to as an abnormality) has occurred during the diagnosis of an in-vehicle detector of a vehicle, the cause estimation system according to the embodiment of the invention estimates the cause that led to the malfunction of the in-vehicle detector for a temporary failure among the malfunctions. A temporary failure refers to a malfunction that is once diagnosed as an abnormality but is resolved and returns to normal after a certain period of time has elapsed. By estimating the cause of a temporary failure, it becomes possible to avoid performing unnecessary repairs or replacements on the in-vehicle detector that has experienced a temporary failure. In addition, by taking measures against the estimated cause, it becomes possible to shorten the time until the in-vehicle detector that has experienced a temporary failure returns to normal.

[0009] FIG. 1 is a schematic configuration diagram of a cause estimation system 50 according to an embodiment. In FIG. 1, vehicles 101 and 102, a server device 10 as a cause estimation device, and an external server device 30 that provides weather information are exemplified as the cause estimation system 50. As described above, when the cause estimation system 50 diagnoses a temporary failure of an in-vehicle detector through self-diagnosis in the vehicle 101 or the like, it estimates the cause that led to the temporary failure of the in-vehicle detector.

[0010] Vehicles 101 and 102 are each equipped with control systems 101U and 102U. The control systems 101U and 102U are configured to be able to communicate with each other via a communication network 20 and the server device 10. The communication network 20 includes not only a public wireless communication network represented by the Internet network or a mobile phone network, but also a closed communication network provided for each predetermined management area, such as a wireless LAN (Local Area Network), Wi-Fi (registered trademark), etc. In FIG. 1, only vehicles 101 and 102 are shown, but there may be a number of vehicles other than vehicles 101 and 102. In this case, it becomes possible to use a plurality of information obtained when a number of vehicles each travel. Further, for example, only one of the vehicle 101 or the vehicle 102 may communicate with the server device 10. In this case, it becomes possible to use a plurality of pieces of information obtained when one vehicle travels a plurality of times.

[0011] <Server device> FIG. 2 is a block diagram showing a main configuration of the server device 10 in FIG. 1. The server device 10 is managed by, for example, an entity that provides maintenance services for the vehicles 101 and 102. The server device 10 may be configured using a virtual server function on the cloud, or may be configured to be distributed among a plurality of terminals. For example, it may be distributed and arranged for each predetermined management area.

[0012] The server device 10 includes a communication unit 11, an information acquisition unit 12, a processing unit 13, and a storage unit 14. The communication unit 11 is configured to be able to communicate with external devices such as the control systems 101U and 102U mounted on the vehicles 101 and 102 via the communication network 20. With such a configuration, the server device 10 can transmit and receive necessary information to and from the control systems 101U and 102U.

[0013] The information acquisition unit 12 acquires movement information of the traveling vehicle 101 or the like from the control system 101U or the like of the vehicle at a predetermined time interval together with time information via the communication unit 11. The movement information of the vehicle 101 or the like includes, for example, information indicating the vehicle ID, traveling direction, speed, traveling position, and winker (direction indicator) operation state of the vehicle. The vehicle ID is, for example, a VIN (Vehicle Identification Number). The information acquisition unit 12 also acquires abnormality information from the control system 101U or the like of the vehicle 101 or the like that has detected an abnormality in the in-vehicle detector via the communication unit 11. The abnormality information includes, for example, a failure code (hereinafter referred to as DTC (Diagnostic Trouble Code)), the occurrence (detection) date and time, and information indicating the position (latitude and longitude) of the vehicle 101 or the like at the time of occurrence (detection). The information acquisition unit 12 further acquires, from the external server device 30 via the communication unit 11, the weather information of the area where the vehicle 101 or the like has traveled, based on the abnormality information transmitted from the control system 101U or the like of the vehicle 101 or the like.

[0014] The processing unit 13 is configured to include a computer having a CPU (microprocessor) and its peripheral circuits and the like. The processing unit 13 executes predetermined processing based on the information acquired by the information acquisition unit 12 and the data stored in the storage unit 14 and the like. The processing unit 13 also outputs control signals to the communication unit 11, the information acquisition unit 12, and the storage unit 14. The processing unit 13 further functions as an extraction unit 131, a generation unit 132, and an estimation unit 133 by executing a program stored in the storage unit 14 in advance.

[0015] The extraction unit 131 extracts, from among a plurality of pieces of abnormality information stored in the abnormality information area 142 of the storage unit 14, the abnormality information having a relevance to the weather information of the travel area of the vehicle 101 or the like that has transmitted each piece of abnormality information to the server device 10. For example, the abnormality information having weather information such as the temperature being X °C or less and the relative humidity being Y % or more at the time of abnormality detection, or the abnormality detection being before sunrise, is extracted. The abnormality information extracted here does not necessarily have the same failure content (the same DTC). Note that for the plurality of pieces of abnormality information stored in the abnormality information area 142, the corresponding weather information is acquired by the information acquisition unit 12 and associated therewith. The association may be referred to as linking. Specifically, the processing unit 13 causes the information acquisition unit 12 to acquire, from the external server device 30, the weather information of the travel area where the vehicle 101 or the like that has transmitted each piece of abnormality information to the server device 10 has detected an abnormality, and links the acquired weather information with the corresponding abnormality information. Further, when the extraction unit 131 has acquired abnormal information a plurality of times within a predetermined time (for example, 30 minutes) on the same day for the same vehicle among the plurality of pieces of abnormal information stored in the abnormal information area 142, the extraction unit 131 shall exclude the abnormal information after the second time. Specifically, when the abnormal information continuously acquired four times within a predetermined time on the same day for the same vehicle is included, the extraction is performed by excluding the abnormal information for three times after the second time.

[0016] The extraction unit 131 further extracts abnormal information indicating a decrease in the detection accuracy of the in-vehicle detector from the abnormal information extracted as described above from the abnormal information associated with the weather information. The abnormal information indicating a decrease in the detection accuracy of the in-vehicle detector refers to, for example, abnormal information including a DTC corresponding to "camera shielding" indicating that the camera image is blurred.

[0017] The generation unit 132 generates a factor estimation model for estimating the factor leading to the abnormality of the in-vehicle detector for the abnormal information extracted by the extraction unit 131. In the embodiment, as an example, based on the weather information associated with the abnormal information including the DTC corresponding to camera shielding extracted by the extraction unit 131, the weather conditions that cause a specific weather event (for example, frost or fog) as the factor leading to the abnormality of the in-vehicle detector are generated as the factor estimation model. Specifically, the generation unit 132 generates a threshold value for at least one observation item among the weather information (for example, air temperature, dew point temperature, relative humidity, and visibility) acquired from the external server device 30 as the factor estimation model. The threshold value for the observation item may be generated empirically by verifying the correlation between the observed value of the weather information and the DTC based on a large number of sample data, or may be generated using a machine learning method such as SVM (Support Vector Machine).

[0018] An example of the weather conditions that cause frost is (air temperature - 3°C) ≤ dew point temperature, and (air temperature - 3°C) ≤ 0°C. In addition, an example of the meteorological conditions for generating fog is that the relative humidity is 75% or more and the visibility is less than 13 km. When the observation items of the meteorological information provided by the external server device 30 include the presence or absence of fog, the observed values of the relative humidity and visibility provided together with the presence of fog may be reflected in the generation of the threshold value as the factor estimation model.

[0019] Based on the factor estimation model (threshold value for a predetermined observation item of meteorological information) generated by the generation unit 132, the estimation unit 133 estimates that the factor leading to the abnormality of the in-vehicle detector is frost or fog. For example, when the air temperature in the driving area where the vehicle is currently traveling, acquired from the external server device 30, is -9.8°C, the dew point temperature is -11.0°C, the relative humidity is 91%, and the visibility is 20 km, it is estimated to be frost. For example, when the air temperature in the driving area where the vehicle is currently traveling, acquired from the external server device 30, is 4.6°C, the dew point temperature is 4.6°C, the relative humidity is 100%, and the visibility is 0.6 km, it is estimated to be fog.

[0020] The storage unit 14 has a volatile or non-volatile memory (not shown). The storage unit 14 stores various programs and various data executed by the processing unit 13. The storage unit 14 also functions as a meteorological information area 141, an abnormality information area 142, and a factor estimation model area 143. Recording and reading of data and the like to and from the storage unit 14 are performed by the processing unit 13.

[0021] The meteorological information area 141 is a memory area in which meteorological information associated with the abnormality information is recorded. More specifically, the meteorological information acquired from the external server device 30 by the information acquisition unit 12, which is the meteorological information of the driving area where the vehicle 101 etc. that transmitted the abnormality information to the server device 10 detected the abnormality, is recorded after being associated with the abnormality information.

[0022] The abnormal information area 142 is a memory area where the abnormal information transmitted from the vehicle 101 or the like to the server device 10 is recorded. More specifically, among a plurality of vehicles 101 or the like equipped with in-vehicle detectors, the abnormal information transmitted from the vehicle that has detected an abnormality in the in-vehicle detector is recorded.

[0023] The factor estimation model area 143 is a memory area where the factor estimation model generated by the generation unit 132 for estimating the factor leading to the abnormality of the in-vehicle detector with respect to the abnormal information is recorded. In the embodiment, as an example, the meteorological conditions that generate frost or fog as a factor leading to the abnormality of the in-vehicle detector are recorded as the factor estimation model.

[0024] The external server device 30 is managed by, for example, an entity that provides meteorological information or the like. The observation items of the provided meteorological information include at least the air temperature, dew point temperature, relative humidity, and visibility for each predetermined area. In addition to these, atmospheric pressure, wind direction, wind speed, weather, precipitation, the presence or absence of fog generation, etc. may also be included.

[0025] <Vehicle> First, the configuration of the autonomous vehicle will be described. The vehicle 101 may be any of an engine vehicle having an internal combustion engine (engine) as a driving source, an electric vehicle having a driving motor as a driving source, and a hybrid vehicle having an engine and a driving motor as driving sources. FIG. 3 is a block diagram illustrating a schematic configuration of the control system 101U of the vehicle 101. Although illustration is omitted, the control system 102U of the vehicle 102 is the same as that in FIG. 3.

[0026] As shown in FIG. 3, the control system 101U mainly includes a controller 8, an external sensor group 1, an internal sensor group 2, an input / output device 3, a positioning unit 4, a map database 5, a navigation device 6, a communication unit 7, and a traveling actuator AC, which are respectively communicably connected to the controller 8 via a CAN (Controller Area Network) communication line or the like.

[0027] The external sensor group 1 is a general term for a plurality of sensors (external sensors) that detect the external situation, which is the surrounding information of the host vehicle. The external sensor group 1 includes, for example, an imaging element (image sensor) such as a CMOS sensor, a camera that images the surroundings (front, rear, and sides) of the host vehicle, a lidar that irradiates laser light and detects the reflected light to detect the position (distance and direction from the host vehicle, etc.) of an object around the host vehicle, a radar that irradiates electromagnetic waves and detects the reflected wave to detect the position of an object around the host vehicle, and the like.

[0028] The internal sensor group 2 is a general term for a plurality of sensors (internal sensors) that detect the driving state of the host vehicle. The internal sensor group 2 includes, for example, a vehicle speed sensor that detects the vehicle speed of the host vehicle, an acceleration sensor that detects the acceleration in the longitudinal and lateral directions of the host vehicle, a rotational speed sensor that detects the rotational speed of the driving power source, and the like. A sensor that detects the driving operations of the driver in the manual driving mode, such as the operation of the accelerator pedal, the brake pedal, the steering wheel, etc. is also included in the internal sensor group 2.

[0029] The input / output device 3 is a general term for a device through which commands are input from the driver or information is output to the driver. For example, the input / output device 3 includes various switches through which the driver inputs various commands by operating the operation members, a microphone through which the driver inputs commands by voice, a display that provides information to the driver via a display image, a speaker that provides information to the driver by voice, and the like.

[0030] The positioning unit 4 has a positioning sensor that receives the positioning signal transmitted from the positioning satellite, and measures the current position (latitude, longitude, altitude) of the host vehicle using the positioning information received by the positioning sensor. The positioning satellite is an artificial satellite such as a GPS satellite or a quasi-zenith satellite. The positioning sensor may be included in the internal sensor group 2. Also, the positioning unit 4 may be referred to as a GNSS (Global Navigation Satellite System) unit.

[0031] The map database 5 is a device that stores general map information used in the navigation device 6, and is composed of, for example, a hard disk or a semiconductor element. The map information includes road position information, road shape (such as curvature) information, and intersection and branch point position information. Note that the map information stored in the map database 5 is different from the map information of the high-precision map (referred to as the environmental map) stored in the storage unit 82 of the controller 8.

[0032] The navigation device 6 is a device that searches for a target route on the road to a destination input by the driver and provides guidance along the target route. The input of the destination and the guidance along the target route are performed via the input / output device 3. The target route is calculated based on the current position of the host vehicle measured by the positioning unit 4 and the map information stored in the map database 5. It is also possible to measure the current position of the host vehicle using the detection values of the external sensor group 1, and calculate the target route based on this current position and the environmental map information stored in the storage unit 82.

[0033] The communication unit 7 communicates with an external device (such as the server device 10) via the communication network 20 (Fig. 1), and periodically or at an arbitrary timing acquires map information, driving history information, traffic information, etc. from the server. When the acquired map information is the above general map information, the map in the map database 5 is updated. When the acquired map information is environmental map information, the environmental map in the storage unit 82 is updated. The communication unit 7 can also communicate with the communication units of other vehicles.

[0034] The actuator AC is a driving actuator for controlling the running of the host vehicle. When the driving power source is an engine, the actuator AC includes a throttle actuator for adjusting the opening degree of the throttle valve of the engine (throttle opening). When the driving power source is a driving motor, the driving motor is included in the actuator AC. The brake actuator for operating the braking device of the host vehicle and the steering actuator for driving the steering device are also included in the actuator AC.

[0035] The controller 8 is constituted by an electronic control unit (ECU). More specifically, the controller 8 includes a computer having an arithmetic unit 81 such as a CPU (microprocessor), a storage unit 82 such as a ROM and a RAM, and other peripheral circuits (not shown) such as an I / O interface. Although a plurality of ECUs with different functions such as an engine control ECU, a traveling motor control ECU, and a braking device ECU can be provided separately, in FIG. 3, for convenience, the controller 8 is shown as a set of these ECUs. The controller 8 is provided with a diagnostic function for an external sensor group 1 and the like as in-vehicle detectors. When the controller 8 determines that an abnormality has occurred in the in-vehicle detector, it transmits abnormality information to the server device 10 via the communication unit 7. As described above, the abnormality information includes DTC, the occurrence (detection) date and time, and information indicating the position (latitude and longitude) of the vehicle 101 and the like at the time of occurrence (detection).

[0036] The storage unit 82 stores high-precision environmental map information. The environmental map includes road position information, road shape (curvature, etc.) information, road gradient information, intersection and branch point position information, number of lanes (which may be called driving lanes) information, lane width and position information for each lane (information on the center position of the lane and the boundary lines of the lane positions), landmark (traffic signal, sign, building, etc.) position information as a landmark on the map, road surface profile information such as road surface unevenness, and the like. The storage unit 82 stores the environmental map (its data) and reliability information indicating the reliability of the environmental map as environmental map information. The storage unit 82 can further store travel history information indicating a travel trajectory based on the detection values of the external sensor group 1 and the internal sensor group 2.

[0037] The arithmetic unit 81 functionally includes a host vehicle position recognition unit 83, an external world recognition unit 84, a behavior plan generation unit 85, and a travel control unit 86.

[0038] The host vehicle position recognition unit 83 recognizes the position of the host vehicle on the map (host vehicle position) based on the position information of the host vehicle obtained by the positioning unit 4 and the map information of the map database 5. Further, the host vehicle position may be recognized using the ambient map information stored in the storage unit 82 and the peripheral information of the host vehicle detected by the external sensor group 1, and the host vehicle position can be recognized with high accuracy. When it is possible to measure the host vehicle position with a sensor installed outside on the road or beside the road, the host vehicle position may be recognized by communicating with the sensor via the communication unit 7.

[0039] The host vehicle position recognition unit 83 further performs a position estimation process of the host vehicle. The position estimation estimates the position of the host vehicle based on the change in the position of a ground object (feature point) over time. The position estimation process is performed, for example, according to the SLAM (Simultaneous Localization and Mapping) algorithm using signals from the external sensor group 1 (camera or lidar).

[0040] The external situation recognition unit 84 recognizes the external situation around the host vehicle based on signals from the external sensor group 1. For example, it recognizes the positions, speeds, and accelerations of surrounding vehicles (front vehicles and rear vehicles) traveling around the host vehicle, the positions of surrounding vehicles parked or stopped around the host vehicle, and the positions and states of other objects. Other objects include signs, traffic lights, markings such as road dividers and stop lines, buildings, guardrails, utility poles, billboards, pedestrians, bicycles, etc. The states of other objects include the colors of traffic lights (red, blue, yellow), the moving speeds and directions of pedestrians and bicycles, etc.

[0041] The action plan generation unit 85 generates a driving trajectory (target trajectory) of the host vehicle from the current time to a predetermined time in the future based on, for example, the target route calculated by the navigation device 6, the map information stored in the map database 5 (which may be the environmental map information stored in the storage unit 82), the position of the host vehicle recognized by the host vehicle position recognition unit 83, and the external situation recognized by the external situation recognition unit 84. When there are a plurality of trajectories that are candidates for the target trajectory on the target route, the action plan generation unit 85 selects the optimal trajectory that complies with the laws and regulations and meets criteria such as efficient and safe driving from among them, and sets the selected trajectory as the target trajectory. Then, the action plan generation unit 85 generates an action plan corresponding to the generated target trajectory. The action plan generation unit 85 generates various action plans corresponding to overtaking driving for overtaking the preceding vehicle, lane change driving for changing the driving lane, following driving for following the preceding vehicle, lane keep driving for maintaining the lane so as not to deviate from the driving lane, deceleration driving, or acceleration driving. When generating the target trajectory, the action plan generation unit 85 first determines the driving mode and generates the target trajectory based on the driving mode.

[0042] In the automatic driving mode, the driving control unit 86 controls each actuator AC so that the host vehicle travels along the target trajectory generated by the action plan generation unit 85. More specifically, in the automatic driving mode, the driving control unit 86 calculates the required driving force for obtaining the target acceleration per unit time calculated by the action plan generation unit 85 in consideration of the driving resistance determined by the road gradient and the like. Then, for example, the actuator AC is feedback-controlled so that the actual acceleration detected by the internal sensor group 2 becomes the target acceleration. That is, the actuator AC is controlled so that the host vehicle travels at the target vehicle speed and the target acceleration. When the driving mode is the manual driving mode, the driving control unit 86 controls each actuator AC according to the driving command (such as a steering operation) from the driver acquired by the internal sensor group 2.

[0043] <Explanation of flowchart> FIG. 4 is a flowchart for explaining the process of creating a temporary failure cause estimation model in the server device 10 of the cause estimation system 50. The processing unit 13 of the server device 10 repeatedly executes a program for performing the process illustrated in FIG. 4.

[0044] In step S10, the processing unit 13 acquires abnormality information. More specifically, the information acquisition unit 12 acquires, via the communication unit 11, abnormality information from a vehicle 101 or the like in which the in-vehicle detector abnormality has been detected by the diagnostic function of the controller 8, and proceeds to step S20.

[0045] In step S20, the processing unit 13 acquires weather information. More specifically, the information acquisition unit 12 acquires, via the communication unit 11, from the external server device 30, the weather information of the travel area in which the vehicle 101 or the like that transmitted the above abnormality information traveled, and proceeds to step S30.

[0046] In step S30, the processing unit 13 associates the abnormality information and the weather information and records them in the storage unit 14. More specifically, the processing unit 13 records the abnormality information in the abnormality information area 142 of the storage unit 14, and records the corresponding weather information in the weather information area 141 of the storage unit 14, and proceeds to step S40.

[0047] In step S40, the processing unit 13 extracts predetermined abnormality information from among the plurality of abnormality information stored in the abnormality information area 142 of the storage unit 14 by the extraction unit 131. More specifically, the extraction unit 131 extracts abnormality information that has a correlation with the weather information of the travel area of the vehicle 101 or the like that transmitted the abnormality information to the server device 10. For example, when there are a plurality of abnormality information with substantially equal associated weather information, the extraction unit 131 extracts this plurality of abnormality information. That the associated weather information is substantially equal means that the observed values of a plurality of observation items, such as the temperature being X ° C or less, the relative humidity being Y% or more, and the observation time being before sunrise, are common among the plurality of abnormality information.

[0048] Further, when there is abnormal information that has been acquired multiple times within a predetermined time (for example, 30 minutes) on the same day for the same vehicle among the multiple pieces of abnormal information stored in the abnormal information area 142, the processing unit 13 shall exclude the abnormal information after the second time. The processing unit 13 further extracts abnormal information indicating a decrease in the detection accuracy of the in-vehicle detector. Abnormal information including a DTC corresponding to "camera shielding" indicating that the camera image is blurred indicates a decrease in the detection accuracy of the in-vehicle detector. When the processing unit 13 extracts abnormal information as described above, it proceeds to step S50.

[0049] In step S50, the processing unit 13 generates, by the generation unit 132, a factor estimation model for estimating the factor leading to the abnormality of the in-vehicle detector for the abnormal information extracted by the extraction unit 131. More specifically, the generation unit 132 generates, as the factor estimation model, a threshold value for at least one observation item among the meteorological information (for example, temperature, dew point temperature, relative humidity, and visibility) associated with the abnormal information including the DTC corresponding to camera shielding, and then proceeds to step S60.

[0050] In step S60, the processing unit 13 records the factor estimation model generated in step S50 in the factor estimation model area 143 of the storage unit 14 and ends the processing according to FIG. 4.

[0051] FIG. 5 is a flowchart for explaining the flow of processing for estimating frost or fog as the cause of a temporary failure in the server device 10 of the factor estimation system 50. The processing unit 13 of the server device 10 repeatedly executes a program for performing the processing illustrated in FIG. 5.

[0052] The processing from step S10 to step S30 is the same as that in the case of FIG. 4, so the description is omitted. Note that the recording process in step S30 may be omitted in the factor estimation process of FIG. 5. However, by performing the recording process in step S30 to record the abnormal information and the meteorological information associated with the abnormal information in the storage unit 14, it becomes possible to further enrich the factor estimation model generated in the process of FIG. 4.

[0053] In step S110, the processing unit 13 determines whether the acquired weather information matches the cause estimation model stored in the cause estimation model area 143 of the storage unit 14. When the observed value of a predetermined observation item among the weather information acquired in step S20 exceeds the threshold of the observation item of the cause estimation model, the processing unit 13 makes an affirmative determination in step S110 and proceeds to step S120. When the observed value of a predetermined observation item among the weather information acquired in step S20 does not exceed the threshold of the observation item of the cause estimation model, the processing unit 13 makes a negative determination in step S110 and ends the processing according to FIG. 5. When the processing unit 13 makes a negative determination in step S110, the estimation unit 133 does not estimate that frost or fog is the cause of the temporary failure.

[0054] In step S120, the processing unit 13 estimates, by the estimation unit 133, that the cause leading to the abnormality of the in-vehicle detector is frost or fog, and ends the processing according to FIG. 5.

[0055] According to the embodiment described above, the following operational effects can be obtained. (1) The cause estimation system 50 for estimating the cause of the abnormality of the external sensor group 1 as an in-vehicle detector for detecting the external situation of the vehicle 101 or the like includes a storage unit 14 (142) for storing the abnormality information transmitted from the vehicle 101 or the like in which the abnormality of the external sensor group 1 is detected, an information acquisition unit 12 for acquiring the weather information of the traveling area where the vehicle 101 or the like that transmitted the abnormality information was traveling when the abnormality was detected, an extraction unit 131 for extracting the abnormality information having a relevance to the weather information of the traveling area from among the plurality of pieces of abnormality information stored in the storage unit 14 (142), and a generation unit 132 for generating a cause estimation model for estimating the cause leading to the abnormality of the external sensor group 1 with respect to the abnormality information extracted by the extraction unit 131. With such a configuration, for abnormal information among a plurality of pieces of abnormal information that has a correlation with the weather information in the driving area, such as abnormal information of a temporary failure, it becomes possible to appropriately generate a factor estimation model for estimating the factors leading to the abnormality of the external sensor group 1. If the factors of a temporary failure can be estimated, it becomes possible to avoid performing unnecessary repairs or replacements on the external sensor group 1 even though the malfunction is resolved and it returns to normal after a certain period of time has elapsed.

[0056] (2) In the factor estimation system 50 of (1) above, the extraction unit 131 further extracts abnormal information indicating a decrease in the detection accuracy by the external sensor group 1 from the extracted abnormal information, and the generation unit 132 generates, as a factor estimation model, the weather conditions that cause frost or fog as factors leading to the abnormality of the external sensor group 1 based on the weather information corresponding to the abnormal information extracted by the extraction unit 131. With such a configuration, it becomes possible to generate, as a factor estimation model, the weather conditions that cause a decrease in detection accuracy, such as blurring of the camera image, due to frosting, dew condensation, etc. on the front windshield, the cover or case of the external sensor group 1, etc., which are the weather conditions that cause frost or fog as factors leading to the abnormality of the external sensor group 1.

[0057] (3) In the factor estimation system 50 of (1) above, the information acquisition unit 12 acquires weather information from the external server device 30 as an external device, and the generation unit 132 generates, as a factor estimation model, a threshold value for at least one observation item among the weather information acquired from the external server device 30. With such a configuration, it becomes possible to generate an appropriate factor estimation model based on the observation items included in accurate weather information from, for example, the Japan Meteorological Agency or private weather information providers.

[0058] (4) In the factor estimation system 50 of (1) above, the extraction unit 131 excludes the abnormal information after the second time among the abnormal information acquired multiple times within a predetermined time on the same day for the same vehicle 101, etc. from among the plurality of pieces of abnormal information stored in the storage unit 14 (142). With such a configuration, when generating a cause estimation model by verifying the correlation between the observed values of meteorological information corresponding to each abnormal information and the DTC while including data of duplicate abnormal information, it becomes possible to generate a more appropriate cause estimation model compared to the case of generating a cause estimation model without excluding duplicate data. Also, by excluding duplicate data, it becomes possible to suppress the computational load on the processing unit 13.

[0059] (5) In the cause estimation system 50 of (1) above, an estimation unit 133 is further provided that estimates that the cause leading to an abnormality in the external sensor group 1 is frost or fog based on the cause estimation model generated by the generation unit 132. With such a configuration, it becomes possible to appropriately estimate the cause leading to a temporary failure of the external sensor group 1. If the cause of the temporary failure can be estimated, it becomes possible to avoid performing unnecessary repairs or replacements on the external sensor group 1 even though the malfunction is resolved and the system returns to normal after a certain period of time has elapsed.

[0060] The above-described embodiment can be modified in various forms. Hereinafter, modification examples will be described. (Modification Example 1) In the above-described embodiment, when the extraction unit 131 extracts abnormal information having a relevance to the meteorological information in the driving area from among a plurality of pieces of abnormal information, the case where the abnormality is detected before sunrise is exemplified. However, other extraction conditions may be defined for extraction. For example, the extraction may be limited to the period from 5:00 am to 8:00 am when the abnormality is detected, or the extraction may be limited to within a predetermined time (e.g., 5 minutes) from the start time of driving of the vehicle 101 or the like (it may also be after that), and the extraction conditions may be changed as appropriate.

[0061] (Modification Example 2) In the above-described embodiment, an example of estimating the cause by the server device 10 is shown. However, it may be configured to estimate the cause by the vehicle 101 or the like. In Modification Example 2, a cause estimation model generated in advance by the server device 10 is recorded in a predetermined memory area of the storage unit 82 of the controller 8.

[0062] When the controller 8 such as the control system 101U determines that an abnormality has occurred in the in-vehicle detector, it acquires the weather information of the driving area where the vehicle 101 etc. has traveled from the external server device 30 via the communication unit 7.

[0063] The controller 8 determines whether the acquired weather information matches the cause estimation model stored in a predetermined memory area of the storage unit 82. When the observed value of a predetermined observation item among the acquired weather information exceeds the threshold value of the observation item of the cause estimation model, the controller 8 estimates that the cause leading to the abnormality of the in-vehicle detector is frost or fog. On the other hand, when the observed value of a predetermined observation item among the acquired weather information does not exceed the threshold value of the observation item of the cause estimation model, the controller 8 does not estimate that frost or fog is the cause of the temporary failure.

[0064] According to Modification 2, by recording the cause estimation model generated by the server device 10 in the controller 8 such as the control system 101U, it becomes possible to appropriately estimate the cause of the temporary failure of the in-vehicle detector also in the vehicle 101 etc.

[0065] (Modification 3) Even when the vehicle 101 has not detected an abnormality in the external sensor group 1 as the in-vehicle detector, it may be configured to perform a predetermined process for dealing with frost or fog that can be a cause of temporary failure. In Modification 3, the external sensor group 1 of the vehicle 101 is provided with a defrosting device for melting frost within the field of view such as a camera and a removing device for removing water droplets etc. within the field of view. The defrosting device and the removing device are, for example, a heating device, a compressed air injection device, a cleaning liquid ejection device, a wiper mechanism, etc. Also, similar to the case of Modification 2, the cause estimation model generated by the server device 10 in advance is recorded in a predetermined memory area of the storage unit 82 of the controller 8.

[0066] FIG. 6 is a flowchart for explaining the flow of a predetermined process for dealing with frost or fog by the controller 8 of the control system 101U mounted on the vehicle 101. The controller 8 of the control system 101U repeatedly executes a program for performing the process illustrated in FIG. 6.

[0067] In step S210, the controller 8 acquires vehicle information and proceeds to step S220. More specifically, the vehicle position recognized by the host vehicle position recognition unit 83 is acquired.

[0068] In step S220, the controller 8 acquires the weather information of the current driving area. More specifically, the weather information of the driving area in which the vehicle 101 has traveled is acquired from the external server device 30 via the communication unit 7 and proceeds to step S230.

[0069] In step S230, the controller 8 determines whether the acquired weather information matches the factor estimation model stored in a predetermined memory area of the storage unit 82. When the observed value of a predetermined observation item among the acquired weather information exceeds the threshold value of the observation item of the factor estimation model, the controller 8 makes an affirmative determination in step S230 and proceeds to step S240. When the observed value of a predetermined observation item among the acquired weather information does not exceed the threshold value of the observation item of the factor estimation model, the controller 8 makes a negative determination in step S230 and ends the process according to FIG. 6. When the controller 8 makes a negative determination in step S230, it does not send a command to activate the defrosting device that melts the frost within the field of view of a camera or the like and the removing device that removes water droplets or the like within the field of view to the external sensor group 1.

[0070] In step S240, the controller 8 executes a coping process and ends the process according to FIG. 6. More specifically, since frost or fog can be a cause of a temporary failure of the in-vehicle detector, as an example of the coping process, a command is sent to the external sensor group 1 to activate the defrosting device that melts the frost within the field of view of a camera or the like, or the removing device that removes water droplets or the like within the field of view.

[0071] The vehicle 101 according to Modification 3 includes a storage unit 82 that stores a cause estimation model generated by the cause estimation system 50, an external sensor group 1 as an in-vehicle detector that detects the external situation of the host vehicle, a removal device (attached to the external sensor group 1) that removes water droplets or ice adhering to the case, cover, etc. of the external sensor group 1, a host vehicle position recognition unit 83 as a host vehicle position detector that detects the host vehicle position, a communication unit 7 that acquires current weather information of the driving area including the host vehicle position from the external server device 30, and a controller 8 as a control unit that operates the removal device based on the weather information and the cause estimation model. With this configuration, in a situation where frost or fog can be a cause of a temporary failure of the external sensor group 1, it becomes possible to appropriately execute the process of sending an operation command for the defrosting device or the removal device. As a result, it becomes possible to prevent the occurrence of a temporary failure of the external sensor group 1 due to frost or fog.

[0072] (Modification 4) In Modification 3, an example was described in which, in a situation where frost or fog can be a cause of a temporary failure of the external sensor group 1, the controller 8 sends a command to operate a defrosting device that melts the frost within the sensor's field of view or a removal device that removes water droplets, etc. within the field of view to the external sensor group 1. As another example to be performed in a situation where frost or fog can be a cause of a temporary failure of the external sensor group 1, for example, not starting the external sensor group 1, selecting an alternative sensor (such as a radar) instead of the camera, instructing the action plan generation unit 85 to change the driving trajectory to another route that avoids the basin or river from the current route along the basin or river, or instructing the degradation control in automatic driving may be performed.

[0073] The above description is merely an example, and the present invention is not limited to the above-described embodiments and modifications as long as the features of the present invention are not impaired. It is also possible to arbitrarily combine one or more of the above embodiments and modifications.

Description of Reference Numerals

[0074] 1 External sensor group, 4 Positioning unit, 8 Controller, 10 Server device, 11 Communication unit, 12 Information acquisition unit, 13 Processing unit, 14, 82 Memory unit, 30 External server device, 101, 102 Vehicles, 101U, 102U Control systems, 131 Extraction unit, 132 Generation unit, 133 Estimation unit, 141 Weather information area, 142 Abnormal information area, 143 Cause estimation model area

Claims

1. A cause estimation system for estimating the cause of an abnormality in an in-vehicle detector that detects the external situation of a vehicle, a storage unit that stores abnormality information transmitted from the vehicle in which the abnormality of the in-vehicle detector is detected; an acquisition unit that acquires weather information of a travel area in which the vehicle that transmitted the abnormality information was traveling when the abnormality was detected; an extraction unit that extracts abnormality information having a relevance to the weather information of the travel area from among the plurality of pieces of abnormality information stored in the storage unit; a model generation unit that generates a cause estimation model for estimating the cause leading to the abnormality of the in-vehicle detector with respect to the abnormality information extracted by the extraction unit; A cause estimation system characterized by comprising:

2. In the cause estimation system according to Claim 1, the extraction unit further extracts abnormality information indicating a decrease in detection accuracy by the in-vehicle detector from the extracted abnormality information, and the model generation unit generates, as the cause estimation model, weather conditions that generate frost or fog as a cause leading to the abnormality of the in-vehicle detector based on the weather information corresponding to the abnormality information extracted by the extraction unit. A cause estimation system characterized by:

3. In the cause estimation system according to Claim 1, the acquisition unit acquires the weather information from an external device, and the model generation unit generates, as the cause estimation model, a threshold value for at least one observation item of the weather information acquired from the external device. A cause estimation system characterized by:

4. In the cause estimation system according to Claim 1, the extraction unit excludes the abnormality information after the second time among the abnormality information acquired a plurality of times within a predetermined time by the same vehicle on the same day from among the plurality of pieces of abnormality information stored in the storage unit. A cause estimation system characterized by the following.

5. In the cause estimation system according to claim 1, further comprising a cause estimation unit that estimates that the cause leading to the abnormality of the in-vehicle detector is frost or fog based on the cause estimation model generated by the model generation unit. A cause estimation system characterized by the following.

6. a storage unit that stores the cause estimation model generated by the cause estimation system according to claim 1; an in-vehicle detector that detects the external situation of the host vehicle; a removal device that removes water droplets or ice adhering to the in-vehicle detector; a host vehicle position detection unit that detects the position of the host vehicle; an acquisition unit that acquires current weather information of a driving area including the position of the host vehicle from an external device; a control unit that operates the removal device based on the weather information and the cause estimation model; A vehicle characterized by comprising the following.

Images