Log management system and log management method

Abstract

To provide a log management system which enables recording and verification of a change in information detected by a sensor that is equipped in a vehicle to recognize an ambient environment.SOLUTION: A log management system records detection information detected by a recognition sensor at a specific point traveled by a vehicle in log data by linking detection information to the specific point traveled when the log management system determines that the vehicle has traveled to one or more specific points; acquires past detection information associated with the same specific point as the specific point traveled with reference to the log data; compares currently recorded detection information with previously acquired detection information to determine whether there is a significant difference; and records in the log data that it has determined that there is a significant difference when the log management system determines that there is the significant difference.SELECTED DRAWING: Figure 6

Description

[Technical field]

[0001] The present disclosure relates to a technique for managing log data related to vehicle control. [Background technology]

[0002] In recent years, various technologies have been proposed for utilizing machine learning models as artificial intelligence (AI) in the field of vehicle control. For example, the following Patent Document 1 is a document that discloses a technology for utilizing machine learning models in the field of vehicle control. In addition, the following Patent Documents 2 and 3 are documents that show the technical level in this technical field. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2020-067762 A [Patent Document 2] JP 2008-070128 A [Patent Document 3] JP 2010-025598 A Summary of the Invention [Problem to be solved by the invention]

[0004] Vehicle control is performed based on information about the vehicle's surrounding environment. The vehicle's surrounding environment is recognized by sensors provided in the vehicle. The information detected by these sensors may change slightly due to version changes, aging, and the like. On the other hand, in machine learning models, inference results may change significantly in response to small input changes. For this reason, when a machine learning model is used to control a vehicle, there is a risk that sufficient control performance cannot be ensured due to changes in the information detected by the sensors.

[0005] In view of the above-mentioned problems, one object of the present disclosure is to provide a technology that enables recording and verifying changes in information detected by a sensor for recognizing the surrounding environment. [Means for solving the problem]

[0006] A first aspect of the present disclosure relates to a log management system.

[0007] A log management system according to a first aspect includes one or more processors that manage log data related to vehicle control, and one or more storage devices that store the log data and specific point information that specifies one or more specific points. Here, the vehicle is equipped with a recognition sensor for recognizing the surrounding environment. When it is determined based on the specific point information that the vehicle has traveled through one or more specific points, the one or more processors are configured to execute the following processes: a process of linking detection information detected by the recognition sensor at the specific point through which the vehicle has traveled to the specific point through which the vehicle has traveled, with the specific point through which the vehicle has traveled, and recording the linking information in the log data; a process of acquiring past detection information linked to the same specific point through which the vehicle has traveled, with reference to the log data; a process of comparing the currently recorded detection information with the acquired past detection information to determine whether or not there is a significant difference; and a process of recording the determination that there is a significant difference in the log data, when it is determined that there is a significant difference.

[0008] A second aspect of the present disclosure relates to a log management method for managing log data related to vehicle control by a computer, where the computer includes one or more storage devices for storing the log data and specific point information defining one or more specific points, and the vehicle includes a recognition sensor for recognizing a surrounding environment.

[0009] A log management method according to a second aspect is executed by a computer, when it is determined based on specific point information that a vehicle has traveled through one or more specific points, to link detection information detected by a recognition sensor at the specific point traveled through to the specific point traveled through and record it in log data, refer to the log data to obtain past detection information linked to the same specific point traveled through as the specific point traveled through, compare the currently recorded detection information with the obtained past detection information to determine whether there is a significant difference, and, when it is determined that there is a significant difference, record in the log data that it has been determined that there is a significant difference. Effect of the Invention

[0010] According to the present disclosure, it is possible to record and verify changes in detection information detected by a recognition sensor for recognizing the surrounding environment of a vehicle. [Brief description of the drawings]

[0011] [Figure 1] FIG. 2 is a diagram illustrating an example of a configuration related to an automatic driving control according to the present embodiment. [Diagram 2] 1 is a diagram illustrating a hardware configuration of a log management system according to an embodiment of the present invention. [Diagram 3] 1 is a diagram illustrating a functional configuration of a log management system according to an embodiment of the present invention. [Figure 4] FIG. 2 is a diagram showing an example of a part of the process of the log management system according to the embodiment; [Diagram 5] 3 is a diagram showing an example of log data recorded by the log management system according to the embodiment; FIG. [Figure 6] 4 is a flowchart showing a process executed by the log management system according to the embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0012] 1. Log Management System This embodiment relates to a log management system for managing log data related to vehicle control. In particular, the following describes a case where log data related to automatic driving control of a vehicle is managed. However, as will be understood from the following description, this embodiment can also be applied to a case where log data related to other controls is managed in the same manner.

[0013] FIG. 1 is a block diagram showing an example of a configuration related to the automatic driving control of a vehicle 1 according to this embodiment. Automatic driving refers to automatically performing at least one of steering, acceleration, and deceleration of the vehicle 1 without the driver's driving operation. Automatic driving control is a concept that includes not only fully automatic driving control, but also risk avoidance control, lane keep assist control, and the like. The operator may be a driver who rides in the vehicle 1, or a remote operator who remotely operates the vehicle 1.

[0014] The vehicle 1 includes a sensor group 10, a recognition unit 20, a planner 30, a control amount calculation unit 40, and a traveling device 50.

[0015] The sensor group 10 includes a recognition sensor 11 used to recognize the situation around the vehicle 1. Examples of the recognition sensor 11 include a camera, a LIDAR (Laser Imaging Detection and Ranging), a radar, and the like. The sensor group 10 may further include a status sensor 12 that detects the status of the vehicle 1, a position sensor 13 that detects the position of the vehicle 1, and the like. Examples of the status sensor 12 include a speed sensor, an acceleration sensor, a yaw rate sensor, a steering angle sensor, and the like. Examples of the position sensor 13 include a GNSS (Global Navigation Satellite System) sensor.

[0016] The sensor detection information SEN is information detected by the sensor group 10. For example, the sensor detection information SEN includes image data captured by a camera. Alternatively, the sensor detection information SEN may include information (relative position, relative speed, shape, etc.) regarding a specific object (pedestrian, preceding vehicle, white line, bicycle, road sign, etc.) captured in the image. For example, the sensor detection information SEN may include point cloud data obtained by LIDAR. For example, the sensor detection information SEN may include information regarding the relative position and relative speed of an object detected by radar. The sensor detection information SEN may include vehicle state information indicating the state of the vehicle 1. The sensor detection information SEN may include position information indicating the position of the vehicle 1.

[0017] The recognition unit 20 receives the sensor detection information SEN. The recognition unit 20 recognizes the situation around the vehicle 1 based on the sensor detection information SEN detected by the recognition sensor 11. For example, the recognition unit 20 recognizes the current position of the object around the vehicle 1 on the spatial map. Examples of the object include pedestrians, other vehicles (preceding vehicles, parked vehicles, etc.), white lines, bicycles, road structures (e.g., guardrails, curbs), fallen objects, traffic lights, intersections, signs, etc. Furthermore, the recognition unit 20 may predict the behavior of the object around the vehicle 1 on the spatial map. Also, for example, the recognition unit 20 may generate a risk map around the vehicle 1. The recognition result information RES indicates the recognition result by the recognition unit 20.

[0018] The planner 30 receives the recognition result information RES from the recognition unit 20. The planner may also receive map information generated in advance. The planner 30 generates a driving plan for the vehicle 1 based on the received information. The driving plan may be for reaching a preset destination, or for avoiding risks. Examples of the driving plan include maintaining the current driving lane, changing lanes, overtaking, turning right or left, steering, accelerating, decelerating, and stopping. Furthermore, the planner 30 generates a target trajectory TRJ required for the vehicle 1 to travel according to the driving plan. The target trajectory TRJ includes a target position and a target speed.

[0019] The control amount calculation unit 40 receives the target trajectory TRJ from the planning unit 30. The control amount calculation unit 40 may further receive sensor detection information SEN such as vehicle state information and position information. The control amount calculation unit 40 calculates a control amount CON required for the vehicle 1 to follow the target trajectory TRJ. It can also be said that the control amount CON is a control amount required to reduce the deviation between the vehicle 1 and the target trajectory TRJ. The control amount CON includes at least one of a steering control amount, a drive control amount, and a braking control amount. Examples of the steering control amount include a target steering angle, a target torque, a target motor angle, a target motor drive current, etc. Examples of the drive control amount include a target speed, a target acceleration, etc. Examples of the braking control amount include a target speed, a target deceleration, etc.

[0020] The traveling device 50 includes a steering device 51, a driving device 52, and a braking device 53. The steering device 51 steers the wheels. For example, the steering device 51 includes an electric power steering (EPS) device. The driving device 52 is a power source that generates a driving force. Examples of the driving device 52 include an engine, an electric motor, and an in-wheel motor. The braking device 53 generates a braking force. The traveling device 50 receives a control amount CON from the control amount calculation unit 40. The traveling device 50 operates the steering device 51, the driving device 52, and the braking device 53 according to the steering control amount, the driving control amount, and the braking control amount, respectively. As a result, the vehicle 1 travels so as to follow the target trajectory TRJ.

[0021] The recognition unit 20 includes at least one of a rule-based model and a machine learning model. The rule-based model performs recognition processing based on a group of predetermined rules. Examples of the machine learning model include a Neural Network (NN), a Support Vector Machine (SVM), a regression model, a decision tree model, and the like. The NN may be a Convolutional Neural Network (CNN), a Recurrent Neural Network (RNN), or a combination thereof. The type of each layer, the number of layers, and the number of nodes in the NN are arbitrary. The machine learning model is generated in advance through machine learning. The recognition unit 20 performs recognition processing by inputting the sensor detection information SEN to the model. The recognition result information RES is output from the model, or is generated based on the output from the model.

[0022] Similarly, the planner 30 includes at least one of a rule-based model and a machine learning model. The planner 30 performs planning processing by inputting the recognition result information RES to the model. The target trajectory TRJ is output from the model or is generated based on the output from the model.

[0023] Similarly, the control amount calculation unit 40 includes at least one of a rule-based model and a machine learning model. The control amount calculation unit 40 performs a control amount calculation process by inputting a target trajectory TRJ to the model. The control amount CON is output from the model or is generated based on the output from the model.

[0024] Two or more of the recognition unit 20, the planner 30, and the control amount calculation unit 40 may be integrally configured. All of the recognition unit 20, the planner 30, and the control amount calculation unit 40 may be integrally configured (end-to-end configuration). For example, the recognition unit 20 and the planner 30 may be integrally configured by a NN that outputs a target trajectory TRJ from the sensor detection information SEN. Even in the case of an integral configuration, intermediate products such as recognition result information RES and target trajectory TRJ may be output. For example, when the recognition unit 20 and the planner 30 are integrally configured by a NN, the recognition result information RES may be the output of an intermediate layer of the NN.

[0025] The recognition unit 20, the planning unit 30, and the control amount calculation unit 40 constitute an "automatic driving control unit" that controls the automatic driving of the vehicle 1. In this embodiment, a machine learning model is used in at least a part of the automatic driving control unit. That is, at least one of the recognition unit 20, the planning unit 30, and the control amount calculation unit 40 includes a machine learning model. The automatic driving control unit performs automatic driving control of the vehicle 1 by using the machine learning model.

[0026] The log management system according to this embodiment manages log data related to the above-mentioned automatic driving control of the vehicle 1. FIG. 2 is a diagram showing an example of a hardware configuration of the log management system 100 according to this embodiment. In FIG. 2, the control device 200 represents a computer having at least the functions of the above-mentioned automatic driving control unit. For example, the control device 200 is a group of ECUs (Electronic Control Units) provided in the vehicle 1.

[0027] The log management system 100 is configured to be able to communicate with the sensor group 10 and the control device 200. The log management system 100 may be mounted on the vehicle 1, or may be implemented in a server external to the vehicle 1. When mounted on the vehicle 1, the log management system 100 connects to an in-vehicle network such as a Control Area Network (CAN). When implemented in a server external to the vehicle 1, the log management system 100 communicates with the vehicle 1 via, for example, a mobile communication network. The log management system 100 may be configured to communicate with multiple vehicles.

[0028] The log management system 100 includes one or more processors 110 (hereinafter simply referred to as processor 110) and one or more storage devices 120 (hereinafter simply referred to as storage devices 120). The processor 110 executes various processes. The processor 110 may be configured, for example, as a central processing unit (CPU) including an arithmetic unit, a register, and the like. The storage device 120 stores various information. The storage device 120 may be configured, for example, as a recording medium such as a read only memory (ROM), a random access memory (RAM), a hard disk drive (HDD), or a solid state drive (SSD).

[0029] The storage device 120 stores a computer program 121, specific location information 122, and log data 123.

[0030] The computer program 121 is executed by the processor 110. Various processes by the log management system 100 may be realized by cooperation between the processor 110, which executes the computer program 121, and the storage device 120. The computer program 121 may be recorded in a computer-readable recording medium.

[0031] The specific point information 122 is information that specifies one or more specific points. Each of the one or more specific points may be set arbitrarily. The specific point information 122 includes information (such as type, display content, sample image, relative position to the specific point, shape, color, etc.) on road signs, signs, structures, etc., provided at each specific point. It is desirable that the specific point information 122 is constant information for each specific point. For this reason, it is advantageous to adopt information on road signs (hereinafter referred to as "sign information") as the specific point information 122. This is because the arrangement of road signs is not easily changed. Furthermore, since road signs are usually managed by map information in the vehicle 1, corrections can also be made based on the map information. From this perspective, each of the one or more specific points may be a point where some road sign is provided. The specific point information 122 may include information on the position of each specific point on the map.

[0032] The log data 123 is recorded by a process executed by the processor 110. In this embodiment, while the vehicle 1 is executing the automatic driving control, the processor 110 acquires data related to the automatic driving control and records it in the log data 123. Examples of the data related to the automatic driving control include the sensor detection information SEN, the recognition result information RES, the target trajectory TRJ, and the control amount CON. In addition, the data related to the automatic driving control may include the reason for the judgment in the recognition process by the recognition unit 20, the reason for the judgment in the planning process by the planning unit 30, the presence or absence of operator intervention in the automatic driving control, and the like. Furthermore, when the log management system 100 communicates with multiple vehicles, the log data 123 may include data of each vehicle. It is expected that the log data 123 will be used for verifying the automatic driving control, etc. Regarding the recording of the log data 123, the details of the process executed by the processor 110 will be described later.

[0033] 2. Log management system functions The autonomous driving control unit performs autonomous driving control of the vehicle 1 based on the sensor detection information SEN detected by the sensor group 10. In particular, in the autonomous driving control, a driving plan and a target trajectory TRJ are determined according to the situation around the vehicle 1. The situation around the vehicle 1 is recognized by the recognition unit 20 based on the sensor detection information SEN detected by the recognition sensor 11. In this respect, the sensor detection information SEN detected by the recognition sensor 11 has a large impact on the operation of the autonomous driving control. In this embodiment, a machine learning model is used in at least a part of the autonomous driving control unit.

[0034] Incidentally, the information detected by the recognition sensor 11 may change slightly due to version changes, aging, etc. On the other hand, since the inference result by the machine learning model is output based on probabilistic inference based on training data, the inference result may change significantly in response to a small change in input in the machine learning model. Therefore, there is a risk that the control performance of the autonomous driving control may not be sufficiently ensured due to a change in the sensor detection information SEN detected by the recognition sensor 11.

[0035] The log management system 100 according to this embodiment makes it possible to record and verify changes in the sensor detection information SEN (hereinafter simply referred to as "detection information") detected by the recognition sensor 11.

[0036] 2-1.Functional configuration Fig. 3 is a diagram showing an example of a functional configuration of the log management system 100 according to this embodiment. In Fig. 3, a specific point determination unit P10, a log data recording unit P20, a log data acquisition unit P30, a significant difference determination unit P40, and a control performance verification unit P50 may be realized by a processor 110.

[0037] The specific point determination unit P10 determines whether the vehicle 1 has traveled through one or more specific points based on the specific point information 122. For example, when the specific point information 122 includes sign information of each specific point, the specific point determination unit P10 can determine that the vehicle 1 has traveled through one or more specific points by comparing the detection information with the sign information. In this case, the comparison is performed, for example, by checking whether the type of road sign matches, the display content matches, the feature points match with the sample image, the relative position matches, the shape matches, the color matches, and the like. FIG. 4(A) is a conceptual diagram showing an example of the comparison between the detection information and the sign information. In FIG. 4(A), the type, the display content, the relative position with respect to the specific point, and the sample image are given as the sign information. In the example shown in FIG. 4(A), the specific point determination unit P10 can determine that the vehicle 1 has traveled through point A by the comparison. By configuring the specific point determination unit P10 in this way, it is possible to precisely determine whether the vehicle 1 has traveled through one or more specific points. In addition, if the specific point information 122 includes information on the position of each specific point on a map, the specific point determination unit P10 can be configured to determine whether or not the vehicle 1 has traveled through one or more specific points from the position information of the vehicle 1.

[0038] Referring again to Fig. 3, the specific point determination unit P10 notifies the log data recording unit P20 and the log data acquisition unit P30 of the determination result including information about the specific points traveled.

[0039] The log data recording unit P20 records data related to the automatic driving control of the vehicle 1 in the log data 123. In particular, when the log data recording unit P20 receives a determination result indicating that the vehicle 1 has traveled through one or more specific points, the log data recording unit P20 records in the log data 123 the detection information and an inference result based on a machine learning model used in the automatic driving control unit (hereinafter simply referred to as a "machine learning model") in association with the specific point through which the vehicle 1 has traveled.

[0040] Fig. 5 shows an example of the log data 123 managed by the log management system 100 according to this embodiment. In the example shown in Fig. 5, dataX1 and dataX2, dataY1 and dataY2, etc. are recorded in association with specific points traveled.

[0041] Referring again to Fig. 3, the log data recording unit P20 notifies the currently recorded detection information and inference result data to the significant difference determination unit P40 and the control performance verification unit P50, respectively.

[0042] The log data acquisition unit P30 acquires data recorded in the log data 123. In particular, when the log data acquisition unit P30 receives a judgment result indicating that the vehicle 1 has traveled through one or more specific points, it acquires data of past detection information and inference results associated with the same specific point as the specific point traveled this time. For example, in the example shown in FIG. 5, when dataA1 and dataA2 are recorded, dataX1 and dataX2 and dataY1 and dataY2 associated with the same point A are acquired. The log data acquisition unit P30 notifies the significant difference determination unit P40 and the control performance verification unit P50 of the acquired data of past detection information and inference results, respectively. Note that the data acquired by the log data acquisition unit P30 may be data of another vehicle.

[0043] The significant difference determination unit P40 compares the detection information recorded this time with the previously obtained detection information to determine whether there is a significant difference. The significant difference determination unit P40 can determine whether there is a significant difference in the detection information recorded this time based on statistical data obtained from the past detection information. For example, when comparing image data, the significant difference determination unit P40 calculates a statistical model regarding the luminance value, distortion, tilt, number of detected specific objects, relative position of the detected specific objects, etc. of the past image data, and determines whether there is a significant difference in the detection information recorded this time with respect to the calculated statistical model. FIG. 4(B) is a conceptual diagram showing an example of a comparison between the image data recorded this time and the past image data. In the example shown in FIG. 4(B), the significant difference determination unit P40 can determine whether there is a significant difference by comparing the image data recorded this time with the past image data regarding the position, range, and number of detected specific objects (objects surrounded by dotted lines), for example.

[0044] The detection information recorded this time and the previously obtained detection information are each detected at the same location by the recognition sensor 11. Therefore, it is expected that each has equivalent information. Therefore, if it is determined that there is a significant difference, it can be considered that the detection information has changed due to a version change or aging of the recognition sensor 11.

[0045] Referring again to Fig. 3, the significant difference determination unit P40 notifies the log data recording unit P20 and the control performance verification unit P50 of the determination result.

[0046] When the log data recording unit P20 receives a judgment result indicating that it has been judged that there is a significant difference, it further records in the log data 123 that it has been judged that there is a significant difference. In the example shown in FIG. 5, it is recorded that it has been judged that there is a significant difference between dataA1 and dataA2. Data that is judged to have a significant difference is highly likely to be data that requires verification. Therefore, by recording that it has been judged that there is a significant difference in this way, it is possible to effectively proceed with the verification of the autonomous driving control.

[0047] Furthermore, the log data recording unit P20 may be configured to record the detection information and the inference result in the log data 123 in association with the determination that there is a significant difference for a certain period from the time when it is determined that there is a significant difference, or for a certain range from the specific point traveled this time. In the example shown in FIG. 5, the detection information data (detection information data) and the inference result data (inference result data) are recorded for a certain period from the time when it is determined that there is a significant difference between dataA1 and dataA2. There is a high possibility that the data after it is determined that there is a significant difference is also data that requires verification. Therefore, by configuring in this way, it is possible to more effectively proceed with the verification of the automatic driving control.

[0048] In addition, in the case where data recorded in the log data 123 is periodically deleted, data determined to have a significant difference or data recorded in relation to the determination that there is a significant difference may be configured to be stored for a longer period than usual, or may be configured not to be deleted.

[0049] When the control performance verification unit P50 receives a judgment result indicating that a significant difference is determined, it verifies the performance of the autonomous driving control by comparing the currently recorded inference result with the previously acquired inference result. For example, when a machine learning model is used in the recognition unit 20, the control performance verification unit P50 verifies the recognition performance by comparing the position on the spatial map of a specific object in the inference result. The control performance verification unit P50 may be configured to issue a warning when it detects that a certain level of control performance is not ensured. In this way, the control performance verification unit P50 can appropriately verify the performance of the autonomous driving control when a change in the detection information occurs.

[0050] 2-2. Processing Fig. 6 is a flowchart showing an example of a process executed by the log management system 100 based on the above-described functional configuration, more specifically, a process executed by the processor 110. The flowchart shown in Fig. 6 may be repeatedly executed at a predetermined cycle while the vehicle 1 is executing the autonomous driving control.

[0051] In step S110, the processor 110 acquires various information including the detection information and the specific point information 122.

[0052] Next, in step S120, the processor 110 determines, based on the specific point information 122, whether the vehicle 1 has traveled through one or more specific points.

[0053] When it is determined that the vehicle 1 has not traveled through any of the specific points (step S120; No), the processor 110 ends the current process. When it is determined that the vehicle 1 has traveled through one or more specific points (step S120; Yes), the process proceeds to step S130.

[0054] In step S130, the processor 110 records in the log data 123 the detection information and the inference result data at the specific point where the vehicle has traveled.

[0055] Next, in step S140, the processor 110 refers to the log data 123 and acquires data of past detection information and inference results associated with the same specific point as the specific point traveled this time.

[0056] Next, in step S150, processor 110 compares the currently recorded detection information with the past detection information to determine whether there is a significant difference.

[0057] When it is determined that there is no significant difference (step S160; No), processor 110 ends the current process. When it is determined that there is a significant difference (step S160; Yes), processor 110 records the determination that there is a significant difference in log data 123 (step S170). In addition, processor 110 verifies the performance of the autonomous driving control by comparing the currently recorded inference result with a past inference result (step S180). After step S180, processor 110 ends the current process.

[0058] The functions of the log management system 100 according to this embodiment are realized by the processor 110 executing the processes in this manner. The log management method according to this embodiment is implemented by the processor 110 executing the processes in this manner. The log management program according to this embodiment is realized by the computer program 121 that causes the processor 110 to execute the processes in this manner.

[0059] 3.Effects As described above, according to this embodiment, when it is determined that the vehicle 1 has traveled through one or more specific points, the detection information detected by the recognition sensor 11 at the specific point through which the vehicle 1 has traveled is linked to the specific point through which the vehicle 1 has traveled and recorded in the log data 123. In addition, past detection information linked to the same specific point through which the vehicle 1 has traveled is acquired. Then, the currently recorded detection information is compared with the acquired past detection information to determine whether there is a significant difference, and the determination that there is a significant difference is recorded in the log data 123. In this way, according to this embodiment, changes in the detection information detected by the recognition sensor 11 can be recorded and verified. [Explanation of symbols]

[0060] 1 vehicle, 11 recognition sensor, 100 log management system, 110 processor, 120 storage device, 122 specific location information, 123 log data

Claims

1. one or more processors that manage log data related to vehicle control; one or more storage devices for storing the log data and specific location information defining one or more specific locations; Including, The vehicle is equipped with a recognition sensor for recognizing a surrounding environment, The one or more processors further include: a process of recording, in the log data, detection information detected by the recognition sensor at the specific point where the vehicle has traveled, in association with the specific point where the vehicle has traveled, when it is determined based on the specific point information that the vehicle has traveled. A process of acquiring the past detection information associated with the same specific point as the specific point traveled by referring to the log data; A process of comparing the currently recorded detection information with previously acquired detection information to determine whether there is a significant difference; When it is determined that there is a significant difference, a process of recording the determination that there is a significant difference in the log data; It is configured to run Log management system.

2. 2. The log management system according to claim 1, The control of the vehicle includes control using a machine learning model, When the one or more processors determine that there is a significant difference, the one or more processors further A process is executed to record the detection information and the inference result output by the machine learning model in the log data in association with the determination that there is a significant difference for a certain period of time from the time when it is determined that there is a significant difference, or for a certain range from the specific point of travel. It is configured as follows: Log management system.

3. 2. The log management system according to claim 1, The control of the vehicle includes control using a machine learning model, The one or more processors further include: A process of linking an inference result output by the machine learning model at the specific location traveled to the specific location traveled and recording it in the log data; A process of acquiring the past inference results associated with the same specific point as the specific point traveled by referring to the log data; a process of verifying the control performance of the vehicle by comparing the currently recorded inference result with the previously acquired inference result when it is determined that there is a significant difference; It is configured to run Log management system.

4. 4. The log management system according to claim 1, the specific point information includes sign information regarding road signs installed at each of the one or more specific points, The one or more processors compare the detection information with the sign information to determine that the vehicle has traveled through any one of the one or more specific points. It is configured as follows: Log management system.

5. A log management method for managing log data related to vehicle control by a computer, comprising: the computer includes one or more storage devices for storing the log data and specific location information defining one or more specific locations; The vehicle is equipped with a recognition sensor for recognizing a surrounding environment, The log management method includes: when it is determined that the vehicle has traveled to any one of the one or more specific points based on the specific point information, detecting information detected by the recognition sensor at the specific point that the vehicle has traveled is associated with the specific point that the vehicle has traveled to and recorded in the log data; acquiring the past detection information associated with the same specific point as the specific point traveled by referring to the log data; Comparing the currently recorded detection information with the previously acquired detection information to determine whether there is a significant difference; When it is determined that there is a significant difference, recording the determination that there is a significant difference in the log data; is executed by the computer. Log management methods.

Images