Information processing device and program

Abstract

The present invention achieves reduction in workload relating to identification of an anomaly item in a vehicle.　An information processing device according to the present invention executes simulation processing of executing simulation of a vehicle behavior by using a plurality of vehicle models different in parameter setting and model identification processing of evaluating similarity of the vehicle behavior obtained in the simulation processing for each vehicle model to an actually measured vehicle behavior that is a measured vehicle behavior of a vehicle, and identifying a vehicle model that satisfies a predetermined similarity condition.

Description

[Technical field]

[0001] The present invention relates to an information processing device and a program, and more particularly to a technical field relating to a simulation of vehicle behavior using a vehicle model. [Background technology]

[0002] The following Patent Document 1 discloses a technology for predicting the occurrence of failures, i.e., predicting future failures of components included in a vehicle, based on the results of simulating the behavior of a digital twin vehicle on a server when the vehicle is driven in a driving environment reproduced in a virtual space. By predicting failures, it is possible to improve the efficiency of vehicle maintenance services and prevent accidents caused by failures. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Patent No. 6825634 Summary of the Invention [Problem to be solved by the invention]

[0004] Here, in order to identify the faulty part or other abnormality occurring in the vehicle (hereinafter referred to as "abnormality item"), a worker at a maintenance shop or the like inspects the vehicle. However, such an inspection is undesirable because it may increase the workload of personnel. For example, depending on the type of abnormality that occurs, it may be difficult to identify the location of the abnormality, and in such cases, the workload of identifying the abnormal item increases. In addition, depending on the type of abnormality, it may be necessary to estimate the degree of occurrence of the abnormality, but estimating the degree of occurrence of the abnormality in addition to the presence or absence of the abnormality during the inspection leads to an increase in the workload.

[0005] The present invention has been made in consideration of the above circumstances, and has an object to reduce the workload involved in identifying abnormal items in a vehicle. [Means for solving the problem]

[0006] The information processing device of the present invention comprises one or more processors and one or more storage media on which a program executed by the one or more processors is stored, the program including one or more instructions that cause the one or more processors to execute a simulation process that simulates vehicle behavior using a plurality of vehicle models having different parameter settings based on driving operation information of the vehicle, and a model identification process that evaluates the similarity between the vehicle behavior for each vehicle model obtained by the simulation process and an actual vehicle behavior, which is the vehicle behavior of the vehicle that has been actually measured, and identifies the vehicle model that satisfies a predetermined similarity condition. Effect of the Invention

[0007] According to the present invention, it is possible to reduce the workload associated with identifying abnormal items in a vehicle. [Brief description of the drawings]

[0008] [Figure 1] 1 is a diagram showing an outline of the configuration of an information processing system including an information processing device according to an embodiment of the present invention. [Diagram 2] 1 is a block diagram showing an example of the configuration of a vehicle according to an embodiment; [Diagram 3] 1 is a block diagram illustrating an example of the configuration of an information processing device according to an embodiment. [Figure 4] FIG. 1 is a diagram for explaining an abnormal item identification method according to an embodiment. [Diagram 5] FIG. 13 is a diagram showing an example of classification of abnormal items related to wheel toe angles. [Figure 6] 1 is a flowchart illustrating an example of a processing procedure for implementing an abnormal item identifying method according to an embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0009] <1. System configuration> Hereinafter, an embodiment of the present invention will be described with reference to the accompanying drawings. FIG. 1 is a diagram showing an outline of the configuration of an information processing system including an information processing device according to an embodiment of the present invention. The information processing system is configured to include at least a server device 1 and a vehicle 50. The server device 1 is one embodiment of an information processing device according to the present invention, and is configured as a computer device having a CPU.

[0010] The vehicle 50 is, for example, a four-wheeled vehicle that can run using an engine or a motor as a drive source. The vehicle 50 of this embodiment is provided with a computer device that can communicate with an external device. In this example, the vehicle 50 is capable of performing data communication with the server device 1 via a network NT, which is a communication network such as the Internet. This enables the vehicle 50 to input various information to the server device 1, such as driving operation information that is information indicating driving operations performed on the vehicle 50, and vehicle behavior information that is information indicating the behavior of the vehicle 50 in response to the driving operations.

[0011] Here, the information input from the vehicle 50 to the server device 1 can be performed by a means other than the communication via the network NT. For example, it is conceivable to connect the vehicle 50 and the server device 1 by wire and input the target information such as the driving operation information and the vehicle behavior information from the vehicle 50 to the server device 1 by wired communication. Alternatively, it is conceivable to input the target information such as the driving operation information and the vehicle behavior information stored in the vehicle 50 to the server device 1 via a removable recording medium such as a USB (Universal Serial Bus) memory. Furthermore, it is conceivable to transfer the target information stored in the vehicle 50 to a computer device of a user such as a driver, for example, a smartphone or a PC (personal computer), and then input the target information from the computer device to the server device 1 via the network NT. There are various possible methods for inputting information from the vehicle 50 to the server device 1, and the method is not limited to a specific one.

[0012] Fig. 2 is a block diagram showing a configuration example of the vehicle 50. Note that Fig. 2 shows only electrical components according to the embodiment among the components of the vehicle 50. As shown in the figure, a vehicle 50 includes a sensor unit 51, a control unit 52, a memory unit 53, and a communication unit .

[0013] The sensor unit 51 comprehensively represents, among various sensors that the vehicle 50 has, sensors that are particularly related to the embodiment. As shown in the figure, the sensor unit 51 has a yaw rate sensor 51a, an acceleration sensor 51b, a vehicle attitude sensor 51c, a Global Navigation Satellite System (GNSS) sensor 51d, a steering wheel angle sensor 51e, and a wheel speed sensor 51f.

[0014] The yaw rate sensor 51a detects the yaw rate of the vehicle 50. The acceleration sensor 51b detects acceleration (G) acting in a specific direction of the vehicle 50, and in this embodiment, is capable of detecting at least the longitudinal G and lateral G of the vehicle 50. The vehicle attitude sensor 51c detects the attitude of the vehicle 50, specifically, the attitude in the roll direction (roll angle) and the attitude in the pitch direction (pitch angle). The GNSS sensor 51d detects the position of the vehicle 50 on the Earth.

[0015] The steering wheel angle sensor 51e detects the rotation angle of the steering wheel of the vehicle 50. The wheel speed sensor 51f detects the rotation speed of the wheels (four wheels in this example) of the vehicle 50.

[0016] The control unit 52 is configured with a microcomputer having, for example, a CPU (Central Processing Unit), a ROM (Read Only Memory), a RAM (Random Access Memory), etc., and corresponds to an ECU that executes the processing related to the embodiment among various ECUs (Electronic Control Units) possessed by the vehicle 50.

[0017] As shown in the figure, a memory unit 53 and a communication unit 54 are connected to the control unit 52. The memory unit 53 is a non-volatile storage device such as an HDD (Hard Disk Drive) or an SSD (Solid State Drive), and the communication unit 54 is a communication device for performing network communication or inter-device communication, etc., in accordance with a predetermined communication standard via wired or wireless communication between external devices of the vehicle 50.

[0018] The control unit 52 is capable of receiving detection information from the above-mentioned sensors of the sensor unit 51. The control unit 52 is also capable of storing the received detection information from the sensors in the memory unit 53, and transmitting the information to an external device such as the server device 1 via the communication unit 54.

[0019] FIG. 3 is a block diagram showing an example of the configuration of the server device 1. As shown in FIG. As shown in the figure, the server device 1 includes a CPU 11. The CPU 11 is configured as a signal processing unit having at least a CPU, and functions as an arithmetic processing unit that executes various types of processing. The CPU 11 executes various processes according to a program stored in the ROM 12 or a program loaded from the storage unit 19 to the RAM 13. The RAM 13 also stores data and the like necessary for the CPU 11 to execute various processes.

[0020] The CPU 11, the ROM 12, and the RAM 13 are connected to one another via a bus 14. To this bus 14, an input / output interface (I / F) 15 is also connected.

[0021] An input unit 16 consisting of operators and operation devices is connected to the input / output interface 15. For example, the input unit 16 may be various operators and operation devices such as a keyboard, a mouse, a key, a dial, a touch panel, a touch pad, a remote controller, or the like. An operation by a user is detected by the input unit 16, and a signal corresponding to the input operation is interpreted by the CPU 11.

[0022] In addition, the input / output interface 15 is connected, either integrally or separately, to a display unit 17 consisting of a display device capable of displaying images, such as an LCD (Liquid Crystal Display) or an organic EL (Electro-Luminescence) display, and an audio output unit 18 consisting of a speaker, etc. The display unit 17 is used to display various types of information, and is configured, for example, by a display device provided in the housing of the server device 1, a separate display device connected to the server device 1, or the like.

[0023] The display unit 17 executes display of images for various image processing, moving images to be processed, etc. on the display screen based on instructions from the CPU 11. Furthermore, the display unit 17 performs display of various operation menus, icons, messages, etc., that is, as a GUI (Graphical User Interface), based on instructions from the CPU 11.

[0024] The input / output interface 15 may be connected to a storage unit 19 configured with a HDD or solid-state memory, or a communication unit 20 configured with a modem or the like.

[0025] The communication unit 20 performs communication processing via a transmission path such as the Internet, and communication with various devices via wired / wireless communication, bus communication, and the like.

[0026] A drive 21 is also connected to the input / output interface 15 as required, and a removable recording medium 22 such as a magnetic disk, optical disk, magneto-optical disk, or semiconductor memory is appropriately mounted thereon.

[0027] The drive 21 allows data files such as programs used in each process to be read from the removable recording medium 22. The read data files are stored in the storage unit 19, and images and sounds contained in the data files are output on the display unit 17 and the sound output unit 18. In addition, the computer programs and the like read from the removable recording medium 22 are installed in the storage unit 19 as necessary.

[0028] In the server device 1 having the above hardware configuration, for example, software for the processing of this embodiment can be installed via network communication by the communication unit 20 or the removable recording medium 22. Alternatively, the software may be stored in advance in the ROM 12, the storage unit 19, etc.

[0029] The CPU 11 performs processes based on various programs, thereby executing information processing and communication processing required for the server device 1, as described below.

[0030] <2. Method for identifying abnormal items as an embodiment> An abnormal item identifying method according to an embodiment will be described with reference to FIG. In this embodiment, in order to identify an abnormality item of the vehicle 50, a plurality of vehicle models are prepared in the server device 1 as shown as a vehicle model group in the drawing. The vehicle model here is a vehicle model in digital twin technology, and means a computational model configured to be able to reproduce vehicle behavior in response to driving operations.

[0031] In this embodiment, vehicle models are prepared as the multiple vehicle models, each of which has parameters set according to a different abnormality item among the abnormality items of the vehicle 50. When there are n expected abnormalities, from abnormality item M1 to abnormality item Mn, n vehicle models corresponding to the respective abnormalities are prepared as shown in the figure.

[0032] Here, the abnormality items of the vehicle 50 can be said to be the types of abnormalities occurring in the vehicle 50, and can be defined not only as types based on the location where the abnormality occurs, such as wheel alignment abnormalities, brake pad abnormalities, throttle abnormalities, etc., but also as types based on the difference in the manner in which the abnormality occurs even in the same location (for example, in the case of a wheel alignment abnormality, the difference is whether the abnormality is a toe angle abnormality or a camber angle abnormality, and in the case of a throttle abnormality, the difference is whether the abnormality is a response speed abnormality or an opening / closing amount abnormality, etc.) or differences in the degree of abnormality.

[0033] As an example, FIG. 5 shows an example of classification of abnormal items related to wheel toe angles. In the example of Figure 5, for the toe angle abnormality item, classification is made taking into consideration the difference in toe-in (toe_in) / toe-out (toe_out) of the left and right wheels and the quantitative difference (degree of abnormality) of that toe-in (toe_in) / toe-out (toe_out).

[0034] It is not essential to classify abnormal items in such a way that takes into account the degree of abnormality, nor is it essential to classify abnormalities in a certain portion according to the difference in the manner in which the abnormality occurs.

[0035] 4, for each vehicle model used as a vehicle model group, parameters are set according to vehicle specification information about the vehicle 50, that is, information such as the size (total width, total length, total height, wheelbase, etc.) and weight of the vehicle 50. This allows the vehicle behavior of the vehicle 50 to be appropriately simulated.

[0036] Here, when identifying an abnormality item of the vehicle 50, driving operation information of the vehicle 50 is input to the server device 1 as input information for the vehicle model. In this example, as the driving operation information as input information, information on the steering wheel angle and wheel speed is input from the vehicle 50 to the server device 1 as shown in the figure.

[0037] The wheel speed information is input as information corresponding to driving operations such as accelerator operation and brake operation of the vehicle 50. When a so-called two-wheel model is used as the vehicle model, it is sufficient to input information detected for at least two corresponding wheels regarding the wheel speed.

[0038] In this example, it is assumed that only abnormal items related to steering are targeted for identification of abnormal items, and therefore, only steering wheel angle information is input as well as wheel speed information as driving operation information.

[0039] For example, when identifying an abnormality related to the acceleration of the vehicle 50, such as a throttle abnormality, the input information (driving operation information) may include information indicating the accelerator opening and the throttle opening. For example, when identifying an abnormality related to the deceleration of the vehicle 50, such as a brake pad abnormality, the input information may include information indicating the amount of brake depression.

[0040] For confirmation, the steering wheel angle and wheel speed information included in the driving operation information are detected by the steering wheel angle sensor 51e and the wheel speed sensor 51f, respectively.

[0041] Furthermore, when identifying an abnormality item of the vehicle 50, information on the actual vehicle behavior is input from the vehicle 50 to the server device 1. The actual vehicle behavior means the vehicle behavior of the vehicle 50 that is actually measured in the vehicle 50, and specifically, the vehicle behavior in response to the driving operation indicated by the driving operation information to be input to the vehicle model that is actually measured in the vehicle 50. In this example, as shown in the figure, information on the yaw rate, acceleration (longitudinal G, lateral G), and vehicle attitude (roll, pitch) is input from the vehicle 50 to the server device 1 as information on the actually measured vehicle behavior. The above-mentioned yaw rate, acceleration, and vehicle attitude information used as information on the actual vehicle behavior are detected by a yaw rate sensor 51a, an acceleration sensor 51b, and a vehicle attitude sensor 51c, respectively.

[0042] The type of information to be used as the measured vehicle behavior information should be determined depending on the type of abnormality to be identified, and is not limited to the information exemplified above.

[0043] Here, in this example, position information of the vehicle 50 detected by the GNSS sensor 51d of the vehicle 50 is input to the server device 1. Specifically, as this position information, information indicating the position of the vehicle 50 when the driving operation indicated by the driving operation information input to the vehicle model is performed is input. Before executing a simulation using each vehicle model, the server device 1 performs a process of converting this position information into road surface condition information indicating the traveling road surface condition of the vehicle 50. For example, this conversion process may be performed using a database indicating the correspondence between position information and traveling road surface conditions. The server device 1 then sets parameters for each vehicle model according to the road surface condition information obtained by the above conversion process. As a result, the simulation of the vehicle behavior based on the driving operation information of the vehicle 50 is performed using a vehicle model in which parameters are set according to the road surface conditions on which the vehicle is traveling. This makes it possible to perform a simulation of the vehicle behavior that reflects the actual road surface conditions on which the vehicle 50 is traveling, thereby improving the accuracy of the simulation of the vehicle behavior using each vehicle model.

[0044] In addition, it is also possible to distinguish between wet and dry road conditions, and in that case, it is also possible to set parameters for each vehicle model according to the road surface conditions estimated not only from the position information of vehicle 50 but also from weather information at the position indicated by the position information.

[0045] The server device 1 identifies an abnormality of the vehicle 50 as follows, using the driving operation information and the measured vehicle behavior information input from the vehicle 50, and a plurality of vehicle models. That is, by providing driving operation information as input information for each vehicle model, a simulation of vehicle behavior is performed for each vehicle model (i.e., for each abnormality item). As a result, the simulation results of vehicle behavior for each abnormality item are obtained as shown in the figure. In this example, each vehicle model is configured to output at least information indicating the vehicle behavior similar to the information on the actual vehicle behavior, i.e., yaw rate, acceleration (forward / rearward G, lateral G), and vehicle attitude (roll, pitch).

[0046] The server device 1 then performs a process of evaluating the similarity between the vehicle behavior for each vehicle model obtained as described above and the actually measured vehicle behavior, and identifies a vehicle model that satisfies a predetermined similarity condition. In this example, in response to the use of the yaw rate, acceleration, and vehicle attitude information as the information on the actual vehicle behavior as described above, the yaw rate, acceleration, and vehicle attitude information among the information on the vehicle behavior obtained by each vehicle model are used in the evaluation of the similarity. In other words, the types of vehicle behavior information used in the evaluation of the similarity are consistent.

[0047] In this embodiment, it is assumed that the vehicle 50 inputs to the server device 1, as driving operation information and information on the measured vehicle behavior, time waveform information (time series sampling information) for a certain period of time, such as several minutes or several tens of seconds, rather than temporarily. In the server device 1, such time waveform information is used as information on both the vehicle behavior based on each vehicle model and the measured vehicle behavior in the above-mentioned similarity evaluation. That is, the server device 1 in this case evaluates the similarity between the vehicle behavior obtained by the simulation based on the vehicle model and the measured vehicle behavior based on the time waveform indicating the vehicle behavior.

[0048] Specifically, the server device 1 in this example calculates the similarity Sv between the two vehicle behaviors in evaluating the similarity between the simulated vehicle behavior and the actual vehicle behavior. This similarity Sv is calculated as the sum of correlation values ​​(1 is the maximum value = highest correlation) calculated using a cross-correlation function for each of the time waveforms of the yaw rate, longitudinal G, lateral G, roll angle, and pitch angle of both the simulated vehicle behavior and the actual vehicle behavior. In this case, since there are five types of time waveforms used for evaluation, the maximum value of the similarity Sv is "5".

[0049] The server device 1 specifies a vehicle model in which the degree of similarity calculated as described above is equal to or greater than a predetermined threshold value THd. In other words, the server device 1 specifies a vehicle model in which the degree of similarity between the vehicle behavior obtained as a simulation result and the actual vehicle behavior is high. By carrying out such a vehicle model identification process, abnormal items of the vehicle 50 are identified.

[0050] In the above example, the similarity Sv is calculated by a common calculation method for each vehicle model (i.e., for each abnormality item), but the calculation method for the similarity Sv may be different depending on the type of abnormality item. For example, it may be possible to use different weights when summing up the correlation values ​​calculated for each time waveform depending on the type of abnormality item. Moreover, it is also possible to vary the threshold value THd depending on the type of abnormality item.

[0051] Here, in this example, before performing the process of identifying abnormal items based on the similarity between the simulation results using multiple vehicle models as described above and the actual vehicle behavior, the server device 1 performs a process of determining whether or not there is an abnormality using a standard vehicle model for the vehicle 50 (hereinafter referred to as the "standard vehicle model"). The standard vehicle model referred to here means a vehicle model whose parameters are set so as to reproduce the vehicle behavior in response to driving operations of a vehicle 50 having no abnormalities, such as a brand new vehicle 50. As this standard vehicle model, a vehicle model whose parameters are set differently from the parameter settings corresponding to the assumed abnormality items may be used.

[0052] As a process for determining the presence or absence of an abnormality using the standard vehicle model, the server device 1 first performs a simulation of a vehicle behavior using the standard vehicle model, and then determines whether or not the similarity of the vehicle behavior obtained by the simulation to the actually measured vehicle behavior is equal to or lower than a predetermined similarity. In this case, the similarity may be calculated using the same calculation method as the similarity Sv described above.

[0053] Then, on condition that the server device 1 determines that the similarity to the actual vehicle behavior is equal to or lower than a predetermined similarity based on the above-mentioned judgment, it performs the process for identifying abnormal items described above, i.e., the process for identifying a vehicle model based on the similarity between the simulation results using multiple vehicle models as a vehicle model group and the actual vehicle behavior.

[0054] As a result, if it is determined that there is no abnormality in the vehicle, there is no need to perform processing to identify abnormal items based on the results of simulations using multiple vehicle models, thereby improving processing efficiency.

[0055] When the server device 1 identifies an abnormal item, it performs a process of notifying the notification target such as a user of the identified abnormal item. Furthermore, when the server device 1 determines that there is no abnormality as a result of the above-mentioned process of determining whether or not there is an abnormality, it performs a process of notifying the notification target of information indicating that fact. Possible forms of these notifications include, for example, via a computer device such as a smartphone or PC used by the user of the vehicle 50, or a computer device installed in a maintenance facility such as a dealer. Alternatively, if the vehicle 50 is connected to the server device 1 so as to be able to communicate with the vehicle 50, the notifications may be sent via a display unit provided on the vehicle 50.

[0056] <4. Processing Procedure> An example of a specific processing procedure for implementing the abnormal item identifying method according to the embodiment described above will be described with reference to the flowchart of FIG. The process shown in FIG. 6 is executed by the CPU 11 of the server device 1 in accordance with a program stored in a predetermined storage device such as the ROM 12 or the storage unit 19.

[0057] In this example, it is assumed that the driving operation information and the measured vehicle behavior information for the target period have already been input from the vehicle 50 to the server device 1 when the process shown in FIG. It is also possible to execute the process shown in FIG. 6 using driving operation information and measured vehicle behavior information input from the vehicle 50 in real time.

[0058] First, in step S101, the CPU 11 executes a simulation using a standard vehicle model. That is, the CPU 11 executes a simulation of the vehicle behavior by providing driving operation information input from the vehicle 50 as input information for the above-mentioned standard vehicle model.

[0059] In step S102 following step S101, the CPU 11 calculates the similarity with the actually measured vehicle behavior, that is, calculates the similarity Sv between the vehicle behavior obtained by the simulation executed in step S101 and the actually measured vehicle behavior.

[0060] In step S103 following step S102, the CPU 11 determines whether or not the similarity Sv is equal to or smaller than the threshold value THp. As will be understood from the above description, this determination process corresponds to the process of determining whether or not the vehicle 50 has an abnormality. The threshold value THp may be the same as or different from the above-mentioned threshold value THd.

[0061] If it is determined in step S103 that the similarity Sv is not equal to or less than the threshold value THp, the CPU 11 proceeds to step S112 to execute a no-abnormality notification process, i.e., to notify a notification target such as a user of information indicating that the vehicle 50 is normal, as described above. After executing the process of step S112, the CPU 11 ends the series of processes shown in FIG.

[0062] On the other hand, if it is determined in step S103 that the similarity Sv is equal to or less than the threshold value THp, the CPU 11 proceeds to step S104 and performs a process of setting the abnormal item identifier M to "1." The abnormal item identifier M is an identifier for identifying an abnormal item to be processed among the abnormal items M1 to Mn.

[0063] In step S105 following step S104, the CPU 11 executes a simulation using the vehicle model of the Mth abnormality item. That is, the CPU 11 executes a simulation of the vehicle behavior by providing the driving operation information input from the vehicle 50 as input information to the vehicle model of the Mth abnormality item.

[0064] In step S106 following step S105, the CPU 11 calculates a similarity Sv with the actually measured vehicle behavior, and in the subsequent step S107, determines whether or not the similarity Sv is equal to or greater than a threshold value THd.

[0065] If it is determined in step S107 that the similarity Sv is greater than or equal to the threshold value THd, the CPU 11 proceeds to step S108, and performs a process of storing the Mth abnormal item, i.e., a process of storing information indicating the Mth abnormal item in a predetermined storage device such as the RAM 13 or the memory unit 19. Then, the process proceeds to step S109.

[0066] On the other hand, if it is determined in step S107 that the similarity Sv is not equal to or greater than the threshold value THd, the CPU 11 skips the storage process in step S108 and advances the process to step S109.

[0067] In step S109, the CPU 11 determines whether the abnormal item identifier M is equal to or larger than a maximum value Mmax, where Mmax=“n”. In step S109, if it is determined that the abnormal item identifier M is not equal to or greater than the maximum value Mmax (i.e., the number of processed abnormal items is less than n), the CPU 11 advances the process to step S110, increments the abnormal item identifier M by 1, and returns to step S105, whereupon the process is performed on the next abnormal item.

[0068] On the other hand, if it is determined in step S109 that the abnormal item identifier M is equal to or greater than the maximum value Mmax, the CPU 11 proceeds to step S111 and executes a notification process for the identified abnormal item. That is, the CPU 11 executes a process for notifying a notification target such as a user of information indicating the abnormal item stored in the previous storage process in step S108. After executing the process of step S111, the CPU 11 ends the series of processes shown in FIG.

[0069] In the above example, the simulation using a vehicle model (S105), the calculation of the similarity Sv (S106), and the similarity judgment based on the similarity Sv (S107) are performed separately for each abnormality item. Alternatively, it is also possible to perform simulations using multiple vehicle models together to obtain vehicle behavior for each abnormality item, and then perform the calculation of the similarity Sv (S106) and the similarity judgment based on the similarity Sv (S107) for each of these vehicle behaviors.

[0070] <5. Modifications> Although the embodiment of the present invention has been described above, the present invention is not limited to the above-mentioned specific examples, and various modified configurations can be adopted. For example, in the above, an example was given of determining whether the vehicle behavior obtained by simulation using a vehicle model and the actual vehicle behavior satisfy a predetermined similarity condition (hereinafter referred to as "similarity determination of vehicle behavior") by determining whether the similarity Sv is equal to or greater than a threshold value THd. However, there are various possible specific methods for determining the similarity of vehicle behavior, and the method is not limited to a specific method. For example, it is possible to use an AI (artificial intelligence) for judgment to determine the similarity of vehicle behavior. In this case, the AI ​​for judgment may be one that has been machine-learned to output a similarity / dissimilarity determination result using the actual vehicle behavior and the simulated vehicle behavior using a vehicle model as input data, or one that has been machine-learned to output a value indicating the degree of similarity.

[0071] In addition, although the above description refers to notifying a user or the like of identified abnormal items, it is also possible to periodically perform a simulation using a vehicle model and send a notification according to the progression of the abnormality. For example, if the periodic simulation determines that the abnormality is gradually progressing, the risk of failure can be estimated to be low, and therefore a maintenance notification can be sent. On the other hand, if the periodic simulation determines that the abnormality is rapidly progressing, the risk of failure can be estimated to be high, and therefore a repair notification can be sent.

[0072] In addition, it is also conceivable that the simulation of the vehicle behavior using the vehicle model and the similarity determination of the vehicle behavior are performed separately for each driving mode of the vehicle 50. For example, it is conceivable that the simulation and the similarity determination of the vehicle behavior are performed separately for when the vehicle 50 is traveling straight, when the vehicle 50 is turning, etc.

[0073] <6. Summary of the embodiment> As described above, an information processing device (server device 1) as an embodiment includes one or more processors (CPU 11) and one or more storage media (ROM 12 or memory unit 19) storing a program executed by the one or more processors, the program including one or more instructions, and the instructions cause the one or more processors to execute the following processes: That is, the system executes a simulation process for simulating vehicle behavior using a plurality of vehicle models with different parameter settings based on driving operation information of the vehicle (50), and a model identification process for evaluating the similarity between the vehicle behavior of each vehicle model obtained by the simulation process and the actual vehicle behavior, which is the vehicle behavior of a vehicle that has been actually measured, and identifying a vehicle model that satisfies a predetermined similarity condition. According to the above configuration, by preparing vehicle models that reproduce abnormalities of a vehicle as the multiple vehicle models, the abnormalities of the vehicle can be identified by identifying the vehicle model through the model identification process. In other words, it becomes possible to identify abnormalities of a vehicle without performing an inspection work on the vehicle. Therefore, the workload involved in identifying abnormalities in the vehicle can be reduced.

[0074] In addition, in the information processing device according to the embodiment, the multiple vehicle models used in the simulation process are vehicle models in which parameters are set according to different abnormality items among abnormality items of the vehicle. As a result, the model identification process identifies the vehicle model, and thus identifies abnormal items in the vehicle. Therefore, the workload involved in identifying abnormalities in the vehicle can be reduced.

[0075] Furthermore, in the information processing device of the embodiment, the simulation process performs a simulation using a vehicle model in which parameters are set according to the road surface conditions on which the vehicle is traveling, which are estimated from the vehicle position information, as a plurality of vehicle models. This makes it possible to perform a simulation of vehicle behavior that reflects the actual road surface conditions on which the vehicle is traveling. Therefore, the accuracy of simulating the vehicle behavior can be improved, and the accuracy of identifying abnormal items can be improved.

[0076] Furthermore, in the information processing device as the embodiment, in the model identification process, the similarity between the vehicle behavior obtained in the simulation process and the actually measured vehicle behavior is evaluated based on the time waveform of the vehicle behavior. This makes it possible to evaluate the similarity between the simulated vehicle behavior and the actually measured vehicle behavior based on the correlation over a certain period of time, rather than on the temporary correlation between the two behaviors. Therefore, the accuracy of the similarity evaluation can be improved.

[0077] Also, in an information processing device as an embodiment, the instructions cause one or more processors to simulate vehicle behavior using a vehicle model having parameter settings different from the parameter settings corresponding to the abnormal item, and to execute a judgment process to determine whether the similarity of the vehicle behavior obtained by the simulation to the actual vehicle behavior is equal to or less than a predetermined similarity, and to execute the simulation process on the condition that the judgment process results in a determination that the similarity is equal to or less than the predetermined similarity. As described above, by performing a determination process using the simulation results of a vehicle model in which parameters are set differently from the parameter settings corresponding to the abnormality item, it becomes possible to determine whether or not there is an abnormality in the vehicle. Therefore, with the above configuration, when it is determined that there is no abnormality in the vehicle, there is no need to perform processing to identify abnormal items based on the simulation results using multiple vehicle models, thereby improving processing efficiency.

[0078] In addition, the program as an embodiment is a program readable by a computer device, and causes the computer device to execute a simulation process that simulates vehicle behavior using a plurality of vehicle models having different parameter settings based on driving operation information of a target vehicle, and a model identification process that evaluates the similarity between the vehicle behavior for each vehicle model obtained by the simulation process and an actual vehicle behavior, which is the behavior of the vehicle that has been actually measured, and identifies a vehicle model that satisfies a specified similarity condition. Such a program allows a computer device to function as the information processing device according to the above-described embodiment. [Explanation of symbols]

[0079] 1 Vehicle Control System 50 vehicles NT Network 11 CPU 12 ROM 13 RAM 14 Bus 15 Input / Output Interface 16 Input section 17 Display 18 Audio output section 19 Memory section 20 Communications Department 21 Drive 22 Removable Recording Media 51 Sensor section 51a Yaw rate sensor 51b Acceleration sensor 51c Vehicle attitude sensor 51d GNSS sensor 51e Steering wheel angle sensor 51f Wheel speed sensor 52 Control section 53 Memory section 54 Communications Department

Claims

1. one or more processors; one or more storage media storing a program executed by the one or more processors; The program includes one or more instructions, The instructions include for the one or more processors: A simulation process for simulating vehicle behavior using a plurality of vehicle models having different parameter settings based on driving operation information of the vehicle; and executing a model identification process for evaluating a similarity between the vehicle behavior for each vehicle model obtained by the simulation process and an actual vehicle behavior, which is an actually measured vehicle behavior of the vehicle, and identifying the vehicle model that satisfies a predetermined similarity condition. Information processing device.

2. The plurality of vehicle models used in the simulation process are vehicle models in which parameters are set according to different abnormality items among the abnormality items of the vehicle. The information processing device according to claim 1 .

3. In the simulation process, The simulation is performed using a vehicle model having parameters set according to road conditions on which the vehicle is traveling, the parameters being estimated from position information of the vehicle, as the plurality of vehicle models. The information processing device according to claim 1 .

4. In the model identification process, The similarity between the vehicle behavior obtained by the simulation process and the actually measured vehicle behavior is evaluated based on a time waveform of the vehicle behavior. The information processing device according to claim 1 .

5. The instructions include for the one or more processors: a vehicle model having parameters different from the parameters corresponding to the abnormality item is used to simulate a vehicle behavior, and a determination process is executed to determine whether or not a similarity between the vehicle behavior obtained by the simulation and the actual vehicle behavior is equal to or smaller than a predetermined similarity; The simulation process is executed on the condition that a determination result is obtained in the determination process that the similarity is equal to or less than the predetermined similarity. The information processing device according to claim 2 .

6. A computer readable program, A simulation process for simulating vehicle behavior using a plurality of vehicle models having different parameter settings based on driving operation information of a target vehicle; and a model identification process for evaluating a similarity between a vehicle behavior for each vehicle model obtained by the simulation process and an actual vehicle behavior that is an actually measured behavior of the vehicle, and identifying the vehicle model that satisfies a predetermined similarity condition. program.

Images