State estimation device, state estimation method, and state estimation program

Abstract

To ensure good road surface damage detection accuracy regardless of influence of external factors and incidental vibration.SOLUTION: A state estimation device is provided, comprising a behavior acquisition unit configured to acquire information on vehicle behavior of front wheels and rear wheels of a vehicle, and an estimation unit configured to estimate the presence of road surface damage if the information on vehicle behavior indicates that a value related to the front wheels exceeds a first threshold and a value related to the rear wheels exceeds a second threshold.SELECTED DRAWING: Figure 4

Description

[Technical field]

[0001] The present disclosure relates to a state estimation device, a state estimation method, and a state estimation program. [Background technology]

[0002] Patent Document 1 discloses a technology that can improve the efficiency of inspections of multiple road-related structures and equipment. In this technology, the pavement surface is photographed with a visible light camera, and the shape of the pavement surface is collected by a pavement surface measurement unit. To converge. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2011-242293 A Summary of the Invention [Problem to be solved by the invention]

[0004] Prior art describes detecting damage to the shape of a pavement surface using image recognition. However, when images are used, the visibility of road conditions such as night, rain, snow, fallen leaves, and puddles can change. Therefore, images may not be correctly recognized in conditions where road damage is difficult to see. It is also assumed that road damage can be detected using changes in the number of rotations or vibrations related to the vehicle, but accidental changes or vibrations may be detected, resulting in insufficient detection accuracy.

[0005] The present disclosure aims to provide a state estimation device, a state estimation method, and a state estimation program that enable ensuring the accuracy of detecting road surface damage regardless of external influences or accidental vibrations. [Means for solving the problem]

[0006] The state estimation device according to claim 1 includes a behavior acquisition unit that acquires information about vehicle behavior of front and rear wheels of a vehicle, and an estimation unit that estimates that road damage exists when a value related to the front wheels exceeds a first threshold value and a value related to the rear wheels exceeds a second threshold value in the information about the vehicle behavior. The behavior acquisition unit acquires information regarding the vehicle behavior from each of a plurality of vehicles, and the estimation unit determines, for each of the plurality of vehicles, whether a value related to the front wheels of the vehicle exceeds a first threshold value and whether a value related to the rear wheels of the vehicle exceeds a second threshold value, and estimates that road surface damage exists when the number of vehicles exceeding the first threshold value and the number of vehicles exceeding the second threshold value satisfy predetermined conditions.

[0007] The state estimation device according to claim 1 can ensure detection accuracy of road surface damage regardless of the influence of external factors or accidental vibrations. Also, road surface damage can be detected robustly against external factors. In addition, road surface damage is estimated based on conditions for multiple vehicles, so road surface damage can be detected with high accuracy.

[0008] The state estimation device of claim 2 is the state estimation device of claim 1, wherein the estimation unit determines whether the information regarding the vehicle behavior exceeds the first threshold for each of the front left wheel and the front right wheel, and determines whether the information regarding the vehicle behavior exceeds the second threshold for each of the rear left wheel and the rear right wheel, and estimates that road surface damage exists when the front left wheel exceeds the first threshold and the rear left wheel exceeds the second threshold, or when the front right wheel exceeds the first threshold and the rear right wheel exceeds the second threshold.

[0009] According to the state estimation device described in claim 2, the presence of road damage is estimated by judging the threshold values ​​of the front left wheels and the rear left wheels, or the threshold values ​​of the front left wheels and the rear left wheels, so that road damage can be detected robustly against accidental influences on the left and right sides of the vehicle.

[0010] A state estimation device according to a third aspect of the present invention is the state estimation device according to the first or second aspect, wherein the information relating to the vehicle behavior uses a variation in the wheel rotation speed of tires of the vehicle.

[0011] According to the state estimating device recited in claim 3, road damage can be detected using information that can be acquired as vehicle information.

[0014] Claim 4 The state estimation device according to the present invention comprises: 3In the state estimation device of any one of the claims described above, the behavior acquisition unit acquires information regarding the vehicle behavior from each of the plurality of vehicles for each specified area, and the estimation unit performs the judgment using the first threshold value and the second threshold value for each specified area, and estimates that the road surface damage exists when the condition is satisfied.

[0015] Claim 4 According to the condition estimation device described in the above, road surface damage can be estimated for each area.

[0016] Claim 5 The state estimation device according to the present invention comprises: 4 In the state estimation device according to any one of claims 1 to 5, the first threshold value and the second threshold value are set to different values ​​for each type of the vehicle in accordance with information relating to the load of the vehicle.

[0017] Claim 5 According to the state estimation device described in the above, a threshold value can be set for each type of vehicle.

[0018] Claim 6 The state estimation device according to claim 5 In the state estimation device described in , when the vehicle type has a body structure of front-wheel drive, the first threshold value is set smaller than the second threshold value.

[0019] Claim 6 According to the state estimation device described in the above, the threshold value can be set in accordance with the vehicle body structure.

[0020] Claim 7 The state estimation device according to the present invention comprises: 6 In the state estimation device of any one of claims 1 to 5, the first threshold value and the second threshold value are set to different values ​​for each type of vehicle using a trained model trained by machine learning based on information regarding the load of the vehicle, information regarding the vehicle behavior for learning collected for the vehicle type, and correct labels of road surface damage.

[0021] Claim7 According to the state estimation device described in the above, a threshold can be set using a trained model.

[0022] Claim 8 The state estimation method described in the above includes a processor that acquires information on vehicle behavior of the front wheels and the rear wheels of the vehicle, and estimates that road damage exists when a value related to the front wheels exceeds a first threshold value and a value related to the rear wheels exceeds a second threshold value in the information on the vehicle behavior. the acquiring process acquires information on the vehicle behavior from each of a plurality of vehicles, and the estimating process determines, for each of the plurality of vehicles, whether a value related to the front wheels of the vehicle exceeds a first threshold value, and determines whether a value related to the rear wheels of the vehicle exceeds a second threshold value, and estimates that the road surface damage exists when the number of vehicles exceeding the first threshold value and the number of vehicles exceeding the second threshold value satisfy a predetermined condition. The processing is carried out by a computer.

[0023] Claim 9 The state estimation program according to the present invention further comprises: a processor that acquires information about a vehicle behavior of a front wheel and a rear wheel of a vehicle; and a value related to the front wheel in the information about the vehicle behavior is a first value. If the first threshold value is exceeded and the value related to the rear wheels is exceeded a second threshold value, it is presumed that road damage exists. the acquiring process acquires information on the vehicle behavior from each of a plurality of vehicles, and the estimating process determines, for each of the plurality of vehicles, whether a value related to the front wheels of the vehicle exceeds a first threshold value, and determines whether a value related to the rear wheels of the vehicle exceeds a second threshold value, and estimates that the road surface damage exists when the number of vehicles exceeding the first threshold value and the number of vehicles exceeding the second threshold value satisfy a predetermined condition. The processing is executed by a computer. Effect of the Invention

[0024] According to the technology disclosed herein, it is possible to ensure the accuracy of detecting road damage regardless of external influences or accidental vibrations. [Brief description of the drawings]

[0025] [Figure 1] FIG. 13 is a diagram showing an example of an image when traveling on a section of road surface that has been damaged. [Diagram 2] 1 is a graph comparing the maximum value and frequency of rotation speed fluctuations obtained from vehicles traveling on roads with and without road damage. [Diagram 3] 11 is a diagram for explaining threshold determination for either the left or right front wheel and the rear wheel. FIG. [Figure 4] 1 is a diagram illustrating a schematic configuration of a state estimation system according to an embodiment. [Diagram 5] 1 is a block diagram showing a hardware configuration of a vehicle according to an embodiment; [Figure 6]FIG. 2 is a block diagram showing a hardware configuration of a server according to the embodiment. [Figure 7A] FIG. 4 is a diagram showing an example of a graph of rotation speed fluctuation. [Figure 7B] FIG. 4 is a diagram showing an example of a graph of rotation speed fluctuation. [Figure 8] FIG. 2 is a block diagram showing a functional configuration of a server according to the embodiment. [Figure 9] 10 is a flowchart showing a flow of a state estimation process executed in the server of the embodiment. [Figure 10] This is a graph in which maximum values ​​of rotation speed fluctuations on a road with road surface damage are collected and plotted. [Figure 11] This is a graph in which maximum values ​​of rotation speed fluctuations on roads without road surface damage are collected and plotted. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0026] The method of this embodiment is premised on a technology for detecting road surface damage using fluctuations in rotation speed (hereinafter referred to as rotation speed fluctuations) and vibrations related to a vehicle. Note that rotation speed includes the rotation speed of the wheels of a tire, the rotation speed of a drive shaft, the rotation speed of a crankshaft of an engine, and the rotation speed of the engine. Vibration includes vibrations of parts installed in a vehicle (resonance of shock absorbers, coil springs, and sheet metal parts, and vibrations of parts attached to the body, etc.) and vibrations of parts due to sounds inside and outside the vehicle. In this embodiment, an example of rotation speed fluctuations of the wheels of a tire will be described.

[0027] Figure 1 shows an example of an image of driving over a section with road damage. As shown in Figure 1, road damage is a damaged area on the road, and when a vehicle passes over a section with road damage, a fluctuation occurs in the rotation speed of the vehicle. The road damage shown in Figure 1 is a depression in the road surface known as a bothole. However, it is assumed that the rotation speed of the wheels of a vehicle may fluctuate due to accidental events other than road damage. Examples of accidental events other than road damage include driving over a step in a gutter due to a fallen object or evasive maneuver. Such accidental events may cause a fluctuation in the rotation speed of the vehicle even for one of the four wheels.

[0028] FIG. 2 is a graph comparing the maximum value and frequency of rotational speed fluctuations obtained from vehicles traveling on roads with and without road damage. The vertical axis indicates the maximum value of rotational speed fluctuations, and the horizontal axis indicates the frequency. Basically, the maximum value of rotational speed fluctuations on a damaged road surface is larger than that on a road without damage. Although the frequency of traveling on a damaged road surface is low, it is considered that it can be observed with a sufficient probability if data can be obtained from a large number of vehicles. Here, the condition (α) to be set as a threshold value is the value of rotational speed fluctuations that increases the frequency of damaged roads. However, even if there is no damage, the rotational speed fluctuations may take a large value due to an accidental event. Note that the maximum value or fluctuation value of rotational speed fluctuations, or the maximum value or fluctuation value of vibrations is an example of information on vehicle behavior disclosed in this disclosure.

[0029] Therefore, in this embodiment, a measure is introduced to reduce the possibility of false detection of an accidental event. In this embodiment, a threshold value is set for each of the front and rear wheels, and road damage is estimated when the value observed at the same point exceeds the threshold value for either the left or right front and rear wheels. This is because an accidental event is unlikely to occur at both the front and rear wheels at the same point. In addition, by determining the threshold value for either the left or right front and rear wheels, it is possible to deal with the case where road damage is present on one side of the vehicle. An important aspect of the method of this embodiment is that both the rotation speed fluctuation and vibration have peaks of a certain magnitude or greater.

[0030] 3 is a diagram for explaining threshold value judgment for either the left or right front wheel and rear wheel. The threshold value judgment for the left wheel is a case where the left front wheel (Fl) and the left rear wheel (Rl) exceed their respective threshold values. The threshold value judgment for the right wheel is a case where the right front wheel (Fr) and the right rear wheel (Rr) exceed their respective threshold values. In this embodiment, if a condition is met in either the threshold value judgment for the left wheel or the threshold value judgment for the right wheel, it is estimated that there is road surface damage.

[0031] (Overall composition) A state estimation system according to an embodiment of the present invention will be described. As shown in Fig. 4, a state estimation system 10 according to the embodiment of the present invention includes a plurality of vehicles 12 and a server 30 as a state estimation device. Each vehicle 12 is equipped with an on-board device 20. The vehicles 12 (the on-board device 20) and the server 30 are connected to each other via a network N.

[0032] (vehicle) As shown in FIG. 5, the vehicle 12 according to this embodiment includes an in-vehicle device 20, a plurality of ECUs (Electronic Control Units) 22, and a plurality of in-vehicle devices 24.

[0033] The vehicle-mounted device 20 includes a central processing unit (CPU) 20A, a read only memory (ROM) 20B, a random access memory (RAM) 20C, an in-vehicle communication interface (I / F) 20D, and a wireless communication interface 20E. The CPU 20A, the ROM 20B, the RAM 20C, the in-vehicle communication interface 20D, and the wireless communication interface 20E are connected to each other so as to be able to communicate with each other via an internal bus 20G.

[0034] The CPU 20A is a central processing unit that executes various programs and controls each part. That is, the CPU 20A reads out the programs from the ROM 20B and executes the programs using the RAM 20C as a working area.

[0035] The ROM 20B stores various programs and various data. In the present embodiment, the ROM 20B stores a control program that collects vehicle information related to the state and control of the vehicle 12 from the ECU 22 and controls the functions of the vehicle 12. The ROM 20B also stores history information, which is backup data for the vehicle information. The RAM 20C temporarily stores programs or data as a working area.

[0036] The in-vehicle communication I / F 20D is an interface for connecting to each ECU 22. The interface uses a communication standard based on the CAN protocol. The in-vehicle communication I / F 20D is connected to the external bus 20H.

[0037] The wireless communication I / F 20E is a wireless communication module for communicating with the server 30. The wireless communication module uses communication standards such as 5G, LTE, and Wi-Fi (registered trademark). The wireless communication I / F 20E is connected to a network N.

[0038] The ECU 22 includes at least an ADAS (Advanced Driver Assistance System)-ECU 22A, a steering ECU 22B, a brake ECU 22C, and an engine ECU 22D. The ECU 22 detects a value (maximum value) of a rotation speed fluctuation related to the vehicle 12 by using the function of each ECU, associates it with position information detected by a GPS device 29 or the like, and transmits it from the wireless communication I / F 20E to the server 30. The server 30 classifies the position information into areas.

[0039] The ADAS-ECU 22A controls the advanced driving assistance system. A vehicle speed sensor 24A, a yaw rate sensor 24B, and an external sensor 24C, which constitute the in-vehicle device 24, are connected to the ADAS-ECU 22A. The external sensor 24C is a group of sensors used to detect the surrounding environment of the vehicle 12. The external sensor 24C includes, for example, a camera that captures an image of the surroundings of the vehicle 12, a millimeter wave radar that transmits a detection wave and receives a reflected wave, and a lidar (Laser Imaging Detection and Ranging) that scans the area ahead of the vehicle 12.

[0040] The steering ECU 22B controls the power steering. A steering angle sensor 24D constituting the in-vehicle device 24 is connected to the steering ECU 22B. The steering angle sensor 24D is a sensor that detects the steering angle of the steering wheel.

[0041] The brake ECU 22C controls the brake system of the vehicle 12. A brake actuator 24E constituting the in-vehicle device 24 is connected to the brake ECU 22C.

[0042] The engine ECU 22D controls the engine of the vehicle 12. A throttle actuator 24F and sensors 24G constituting the in-vehicle device 24 are connected to the engine ECU 22D. The sensors 24G include an oil temperature sensor for measuring the temperature of the engine oil, an oil pressure sensor for measuring the oil pressure of the engine oil, and a rotation sensor for detecting the engine speed.

[0043] The information ECU 22E controls a car navigation system, audio, and the like. The information ECU 22E also has a function of displaying road surface damage output from the server 30 on a map such as a GUI. A GPS device 29 constituting the in-vehicle device 24 is connected to the information ECU 22E. The GPS device 29 is a device for measuring the current position of the vehicle 12. The GPS device 29 includes an antenna (not shown) that receives signals from GPS satellites. The GPS device 29 may be directly connected to the in-vehicle device 20.

[0044] (server) 6, the server 30 includes a CPU 30A, a ROM 30B, a RAM 30C, a storage 30D, and a communication I / F 30E. The CPU 30A, the ROM 30B, the RAM 30C, the storage 30D, and the communication I / F 30E are connected to each other via an internal bus 30G so as to be able to communicate with each other. The functions of the CPU 30A, the ROM 30B, the RAM 30C, and the communication I / F 30E are the same as those of the CPU 20A, the ROM 20B, the RAM 20C, and the wireless communication I / F 20E of the vehicle-mounted device 20 described above. The communication I / F 30E may perform wired communication.

[0045] The storage 30D as a memory is configured by a HDD (Hard Disk Drive) or an SSD (Solid State Drive) and stores various programs and various data. In the present embodiment, the storage 30D stores a processing program 100, a vehicle information DB (database) 110, an area information DB 120, and a setting information DB 130. The ROM 30B may store the processing program 100, the vehicle information DB 110, the area information DB 120, and the setting information DB 130.

[0046] The processing program 100, which serves as a state estimation program, is a program for controlling the server 30. With the execution of the processing program 100, the server 30 executes a road damage estimation process.

[0047] The vehicle information DB 110 stores vehicle information acquired from the vehicle 12 and position information at the time of acquisition. The vehicle information includes information related to driving operations and traveling, such as the value of rotation speed fluctuation for each wheel, vehicle speed, acceleration, yaw rate, steering angle, accelerator opening, and brake pedal force or stroke. The vehicle information DB 110 also stores the maximum value of rotation speed fluctuation for each wheel as information related to vehicle behavior. The maximum value of rotation speed fluctuation is acquired from the value of rotation speed fluctuation for each wheel in the vehicle information. The maximum value of rotation speed fluctuation is acquired for each of the front left wheel, front right wheel, rear left wheel, and rear right wheel. The position information of the vehicle 12 is the position of the vehicle 12 acquired from the GPS device 29.

[0048] An example of a graph of rotation speed fluctuation is shown in Fig. 7A. The vertical axis represents wheel rotation speed fluctuation [km / h·s], and the horizontal axis represents time [s]. The graph in Fig. 7B is an enlarged view of the peak of the fluctuation in Fig. 7A. The transition indicated by the two-dot chain line in the graph represents the vehicle speed. The behavior acquisition unit 200, which will be described later, regards the MAX or MIN peak value as an absolute value and acquires it as the maximum value of the rotation speed fluctuation.

[0049] The area information DB 120 stores map data for acquiring the position on a map of the road on which the vehicle 12 has traveled and the area. The area is, for example, a section that defines a certain range on a road that is to be used as a unit of road damage detection. The behavior acquisition unit 200 described below collects vehicle information for each area, and the estimation unit 202 estimates road damage for each area. A plurality of areas may be defined in stages. The area as the section is an example of a predetermined area in the present disclosure. When an area is not used, the maximum value of rotation speed fluctuation may be acquired at surrounding positions using position information to estimate road damage.

[0050] The setting information DB 130 stores a first threshold value and a second threshold value. The first threshold value is a threshold value for the maximum value of the rotation speed fluctuation related to the front wheels. The second threshold value is a threshold value for the maximum value of the rotation speed fluctuation related to the rear wheels. The first threshold value and the second threshold value are set to different values ​​for each type of vehicle according to information related to the load of the vehicle 12. The setting of the first threshold value and the second threshold value will be described later.

[0051] As shown in FIG. 8, in the server 30 of this embodiment, a CPU 30A executes a processing program 100 to function as a behavior acquisition unit 200 and an estimation unit 202.

[0052] The behavior acquisition unit 200 acquires the maximum value of the rotation speed fluctuation for each wheel from the vehicle information of each vehicle 12 for each area, and stores the maximum value in the vehicle information DB 110.

[0053] The estimation unit 202 determines whether or not the maximum value of the rotational speed fluctuation for each wheel, which is information on the vehicle behavior, for each of the vehicles 12 exceeds a first threshold value for each of the front left wheel and the front right wheel of the vehicle for each area. In addition, the estimation unit 202 determines whether or not the maximum value of the rotational speed fluctuation for each of the vehicles 12 exceeds a second threshold value for each of the rear left wheel and the rear right wheel of the vehicle for each area. In addition, the estimation unit 202 estimates that road surface damage exists on the road surface of the area when the number of times the front left wheel exceeds the first threshold value and the rear left wheel exceeds the second threshold value for each area satisfies a predetermined condition, or when the number of times the front right wheel exceeds the first threshold value and the rear right wheel exceeds the second threshold value for each area satisfies a predetermined condition. The condition may be set to a case where the number of times the threshold value is exceeded for each wheel is equal to or greater than a certain number, or the ratio of each of the vehicles 12 to the total number is equal to or greater than a certain number, etc.

[0054] In the above description, the road surface damage is estimated when a predetermined condition is satisfied using data from a plurality of vehicles 12 for each area, but the present invention is not limited to this. For example, the estimation unit 202 may make a determination for each vehicle 12 using the maximum value of the rotation speed fluctuation for each wheel obtained from the vehicle 12, and estimate the road surface damage for each vehicle 12 individually for the area or position where the vehicle 12 has traveled.

[0055] (Flow of Control) The flow of processing as a state estimation method executed by the server 30 of this embodiment will be described with reference to the flowchart of Fig. 9. Fig. 9 is a flowchart showing the flow of state estimation processing executed by the server 30 of the embodiment. The processing in the server 30 is executed by the CPU 30A functioning as each part of the server 30.

[0056] In step S100, CPU 30A acquires, for each area, from the vehicle information of each vehicle 12, the maximum value of the rotation speed fluctuation for each wheel, and stores it in vehicle information DB 110.

[0057] In step S102, CPU 30A sets an area to be processed.

[0058] In step S104, CPU 30A sets vehicle 12 to be determined.

[0059] In step S106, the CPU 30A judges whether the first threshold value is exceeded for the front left wheel of the vehicle 12 being judged. If it is judged that the wheel speed exceeds the first threshold value, the process proceeds to step S106-2, where the wheel speed is counted as the front left wheel that has exceeded the first threshold value. If it is judged that the wheel speed does not exceed the first threshold value, the process proceeds to step S108.

[0060] In step S108, CPU 30A judges whether the first threshold value is exceeded for the front right wheel of vehicle 12 to be judged. If it is judged that the wheel is exceeded, the process proceeds to step S108-2, where the wheel is counted as the front right wheel that has exceeded the first threshold value. If it is judged that the wheel is not exceeded, the process proceeds to step S110.

[0061] In step S110, the CPU 30A judges whether the second threshold value is exceeded for the rear left wheel of the vehicle 12 being judged. If it is judged that the wheel is exceeded, the process proceeds to step S110-2, where the wheel is counted as the rear left wheel that has exceeded the second threshold value. If it is judged that the wheel is not exceeded, the process proceeds to step S112.

[0062] In step S112, the CPU 30A judges whether the second threshold value is exceeded for the rear right wheel of the vehicle 12 being judged. If it is judged that the second threshold value is exceeded, the process proceeds to step S112-2, where the rear right wheel is counted as having exceeded the second threshold value. If it is judged that the second threshold value is not exceeded, the process proceeds to step S114.

[0063] In step S114, CPU 30A determines whether or not the determination has been completed for all of the vehicles 12 to be determined. If the determination has been completed, the process proceeds to step S116, and if the determination has not been completed, the process returns to step S104 to set the next vehicle 12 and repeat the process.

[0064] In step S116, CPU 30A determines whether the number of times the front left wheel exceeds the first threshold and the number of times the rear left wheel exceeds the second threshold for the area to be processed satisfies a condition. If the condition is satisfied, the process proceeds to step S120. If the condition is not satisfied, the process proceeds to step S118.

[0065] In step S118, CPU 30A determines whether the number of times the front right wheel exceeds the first threshold and the number of times the rear right wheel exceeds the second threshold for the area to be processed satisfies a condition. If the condition is satisfied, the process proceeds to step S120. If the condition is not satisfied, the process proceeds to step S122.

[0066] In step S120, CPU 30A estimates that there is road damage on the road surface in the area, and stores the estimation result in area information DB 120, etc. Note that the estimation result of road damage in the area may be transmitted to each of vehicles 12.

[0067] In step S122, CPU 30A estimates that there is no road damage on the road surface in the area, and stores the estimation result in area information DB 120 or the like.

[0068] In step S124, CPU 30A determines whether or not the processing has been completed for all areas to be processed. If the processing has been completed, the processing routine ends. If the processing has not been completed, the process returns to step S102 to set the next vehicle 12 and repeat the processing.

[0069] (Example of setting the first and second thresholds) Here, an example of setting the first threshold and the second threshold will be described. FIG. 10 is a graph in which the maximum values ​​of the rotational speed fluctuations on a road with road surface damage are collected and plotted. FIG. 11 is a graph in which the maximum values ​​of the rotational speed fluctuations on a road without road surface damage are collected and plotted. In both graphs, the vertical axis is the maximum value of the rotational speed fluctuations, and the horizontal axis is the vehicle speed [km / h]. Focusing on the data in FIG. 10 and FIG. 11, in the case of the front wheels, the lower limit of no road surface damage may be higher than the lower limit of road surface damage, so in that case the lower limit of no road surface damage is used to set the first threshold. In addition, in the case of the rear wheels, the lower limit of road surface damage is higher than the lower limit of no road surface damage, so the second threshold of the rear wheels may be set using the lower limit of road surface damage. Note that the maximum value of the rotational speed fluctuations may be a value converted in unit.

[0070] In this way, the first threshold and the second threshold may be set by statistically comparing the collected data. In the above-mentioned example, the first threshold is set to a value smaller than the second threshold. This is because the load of the vehicle differs depending on the type of vehicle, whether the body structure is front-wheel drive or rear-wheel drive. The load of the vehicle also varies depending on the load of the vehicle. When the body structure is front-wheel drive, the maximum value of the fluctuation in the rotation speed of the front wheels is observed to be small. Therefore, when the body structure of the vehicle type is front-wheel drive, the first threshold is set to be smaller than the second threshold. In this way, the thresholds are set to be different based on the body structure that changes depending on the drive system. The body structure and the load of the vehicle are examples of information related to the load of the vehicle of the present disclosure.

[0071] The first and second thresholds may be set using a trained model. When a trained model is used, model learning using machine learning may be performed by the learning process of the processing program 100. The processing program 100 learns a model that outputs a first threshold and a model that outputs a second threshold for each vehicle type based on the learning data. The learning data includes information on the vehicle load according to the vehicle type, information on the vehicle behavior for learning collected for the vehicle type (maximum value of rotation speed fluctuation for each wheel with position information), and correct label of road surface damage with position information. The model may be further divided into clusters according to the characteristics of each region or area for learning. As a result, the first and second thresholds are set to different values ​​using a trained model trained by machine learning.

[0072] As described above, the server 30 as the state estimation device of this embodiment determines for each area whether the vehicle behavior information for each of the vehicles 12 exceeds the first threshold for each of the front left wheel and the front right wheel, and if the condition is satisfied, estimates that road damage exists on the road surface in the area. In this way, the server 30 can ensure the detection accuracy of road damage regardless of the influence of external factors or accidental vibration.

[0073] In contrast to the technology that detects road surface damage based on time-series changes, the method of the present embodiment estimates road surface damage directly from the magnitude of rotational speed fluctuations, making it possible to comprehensively detect pre-existing road surface damage that does not change over time. Furthermore, in road maintenance work, it is necessary to comprehensively grasp the damage state of the road. The method of the present embodiment is useful from the viewpoint of road maintenance, since it can comprehensively detect road surface damage from the road area.

[0074] In the above embodiment, the case where the tire rotational speed fluctuation is used as the information on the vehicle behavior has been described as an example, but the concept of observing large fluctuations both in the front and rear of the vehicle allows for a wide variety of applicable configurations and various applications. As a modified example, the information on the vehicle behavior can be, for example, vibrations of shock absorbers and coil springs supporting the four wheels of the tire. Furthermore, the information on the vehicle behavior can be vibrations of acceleration sensors arranged in various parts of the vehicle. Furthermore, the information on the vehicle behavior can be changes in the volume and frequency characteristics of sounds generated in the front and rear of the vehicle. Furthermore, the information on the vehicle behavior can be vibrations of parts in various parts of the vehicle. Note that the present invention can also be applied to vehicles such as BEVs (Battery Electric Vehicles) and FCEVs (Fuel Cell Electric Vehicles), and when a system is constructed for these vehicles, it is expected that noise caused by protrusions and dents in the road surface, such as engine vibrations, can be reduced, and the detection accuracy of road damage can be improved.

[0075] In addition, in the method of this embodiment, vehicle information is collected from a wide range of vehicles and treated as big data, so that the entire target area can be subject to detection. In this case, the processing cost increases as the amount of data increases, but as a method for reducing the data processing load, for example, when performing the same processing multiple times for an area, points (areas) where road surface damage may occur are selected from the previous results, and processing is performed only at the selected points. In addition, processing is performed only on roads with high traffic volume or in the surrounding area where road surface damage has been detected.

[0076] In the above embodiment, various processes executed by the CPU 20A and the CPU 30A by reading the software (programs) may be executed by various processors other than the CPU. In this case, examples of the processor include a PLD (Programmable Logic Device) such as an FPGA (Field-Programmable Gate Array) whose circuit configuration can be changed after manufacture, and a dedicated electric circuit such as an ASIC (Application Specific Integrated Circuit) which is a processor having a circuit configuration designed exclusively for executing a specific process. In addition, each of the above-mentioned processes may be executed by one of these various processors, or may be executed by a combination of two or more processors of the same or different types (for example, a plurality of FPGAs, a combination of a CPU and an FPGA, etc.). In addition, the hardware structure of these various processors is, more specifically, an electric circuit that combines circuit elements such as semiconductor elements.

[0077] In the above embodiment, each program is described as being prestored (installed) in a non-transitory computer-readable recording medium. For example, the program in the vehicle-mounted device 20 is prestored in the ROM 20B, and the processing program 100 in the server 30 is prestored in the storage 30D. However, the present invention is not limited to this, and each program may be provided in a form recorded in a non-transitory recording medium such as a CD-ROM (Compact Disc Read Only Memory), a DVD-ROM (Digital Versatile Disc Read Only Memory), or a USB (Universal Serial Bus) memory. Also, the program may be downloaded from an external device via a network.

[0078] The process flow described in the above embodiment is merely an example, and unnecessary steps may be deleted, new steps may be added, or the process order may be changed, without departing from the spirit of the invention. [Explanation of symbols]

[0079] 12 Vehicles 30 Server (state estimation device) 30A CPU (processor) 100 Processing program (state estimation program) 200 Behavior Acquisition Unit 202 Estimation section

Claims

1. A behavior acquisition unit that acquires information regarding vehicle behavior of front and rear wheels of the vehicle; an estimation unit that estimates that road damage exists when a value related to the front wheels exceeds a first threshold value and a value related to the rear wheels exceeds a second threshold value in the information related to the vehicle behavior; Including, The behavior acquisition unit acquires information about the vehicle behavior from each of a plurality of vehicles, the estimation unit determines, for each of the plurality of vehicles, whether a value related to the front wheels of the vehicle exceeds a first threshold value, and determines whether a value related to the rear wheels of the vehicle exceeds a second threshold value; A state estimation device that estimates that the road surface damage exists when the number of vehicles exceeding the first threshold and the number of vehicles exceeding the second threshold satisfy a predetermined condition.

2. the estimation unit determines whether or not the first threshold value is exceeded for each of a front left wheel and a front right wheel in the information related to the vehicle behavior, and determines whether or not the second threshold value is exceeded for each of a rear left wheel and a rear right wheel, It is estimated that the road surface damage exists when the front left wheel exceeds the first threshold and the rear left wheel exceeds the second threshold, or when the front right wheel exceeds the first threshold and the rear right wheel exceeds the second threshold. The state estimation device according to claim 1 .

3. The state estimation device according to claim 1 , wherein the information regarding the vehicle behavior is obtained by using a variation in the number of rotations of the wheels of the tires of the vehicle.

4. the behavior acquisition unit acquires information about the vehicle behavior from each of the plurality of vehicles for each predetermined area; The state estimation device according to claim 1 , wherein the estimation unit performs the judgment using the first threshold value and the second threshold value for each of the specified areas, and estimates that the road surface damage exists when the condition is satisfied.

5. The state estimation device according to claim 1 , wherein the first threshold value and the second threshold value are set to different values ​​for each type of the vehicle in accordance with information relating to the load of the vehicle.

6. The state estimation device according to claim 5 , wherein the first threshold value is set to be smaller than the second threshold value when the vehicle type has a front-wheel drive vehicle body structure.

7. The state estimation device of claim 5, wherein the first threshold value and the second threshold value are set to different values ​​for each type of vehicle using a trained model trained by machine learning based on information regarding the load of the vehicle, information regarding the vehicle behavior for learning collected for the vehicle type, and correct labels of road surface damage.

8. The processor: Acquire information regarding vehicle behavior of the front and rear wheels of the vehicle; When the value related to the front wheels exceeds a first threshold value and the value related to the rear wheels exceeds a second threshold value in the information related to the vehicle behavior, it is estimated that road damage exists; In the acquiring process, the information on the vehicle behavior is acquired from each of a plurality of vehicles; The estimation process is a condition estimation method in which a computer executes a process to determine, for each of the multiple vehicles, whether a value relating to the front wheels of the vehicle exceeds a first threshold value, and whether a value relating to the rear wheels of the vehicle exceeds a second threshold value, and estimates that road surface damage exists if the number of vehicles exceeding the first threshold value and the number of vehicles exceeding the second threshold value satisfy predetermined conditions.

9. The processor: Acquire information regarding vehicle behavior of the front and rear wheels of the vehicle; When the value related to the front wheels exceeds a first threshold value and the value related to the rear wheels exceeds a second threshold value in the information related to the vehicle behavior, it is estimated that road damage exists; In the acquiring process, the information on the vehicle behavior is acquired from each of a plurality of vehicles; The estimation process is a condition estimation program that causes a computer to execute a process in which, for each of the multiple vehicles, it is determined whether a value related to the front wheels of the vehicle exceeds a first threshold value, and whether a value related to the rear wheels of the vehicle exceeds a second threshold value, and if the number of vehicles exceeding the first threshold value and the number of vehicles exceeding the second threshold value satisfy predetermined conditions, it is estimated that road surface damage exists.

Images