Vehicle data management method and management device
By determining AI involvement and storing data based on conditions, the method efficiently manages data storage for autonomous vehicle control, preventing storage device overflow and ensuring sufficient capacity.
Patent Information
- Application Number
- JP2023080304
- Authority / Receiving Office
- JP · JP
- Patent Type
- Applications
- Current Assignee / Owner
- Filing Date
- 2023-05-15
- Publication Date
- 2024-11-27
- Estimated Expiration
- Not applicable · inactive patent
Smart Images

Figure 2024164659000001_ABST
Abstract
Description
[Technical field]
[0001] The present disclosure relates to a method and apparatus for managing data acquired by a vehicle. [Background technology]
[0002] JP 2020-144450 A discloses a system for collecting data related to a vehicle. In this conventional system, data related to the vehicle is collected when a preset scene occurs. Examples of preset scenes include a scene in which the vehicle is accelerating or decelerating rapidly in light of a predetermined criterion, a scene in which an override to the ongoing automatic driving is detected, a scene in which a collision of the vehicle is predicted, a scene in which the lateral displacement of the lane is large in light of a predetermined criterion, and a scene in which a warning is issued to the driver of the vehicle about closing his or her eyes. In collecting data related to the vehicle, the type and unit of data to be collected are also set in advance. The collected data is transmitted from the vehicle to a server that analyzes the data.
[0003] In addition to JP 2020-144450 A, JP 2019-185783 A can be cited as examples of documents showing the technical state of the technical field related to the present disclosure. [Prior art documents] [Patent documents]
[0004] [Patent Document 1] JP 2020-144450 A [Patent Document 2] JP 2019-185783 A Summary of the Invention [Problem to be solved by the invention]
[0005] Artificial intelligence (AI), which has been evolving remarkably in recent years, is beginning to be applied to some parts of autonomous vehicle control. Examples of the application of AI to autonomous vehicle control include computer processing such as "surrounding recognition" by the vehicle, "route planning" by the vehicle, and "motion planning" by the vehicle.
[0006] When AI is applied to autonomous driving control, it is desirable to conduct evaluation and verification of this application in real time or after the fact. In this case, it is ideal to temporarily store all data related to computer processing for autonomous driving control in an on-board storage device and transmit it appropriately to an external server for storage.
[0007] However, while it is expected that the amount of data involved in computer processing for autonomous driving control will be enormous, the capacity of on-board storage devices is limited. Therefore, when AI is involved in computer processing for autonomous driving control, there is room for consideration as to which data involved in this computer processing should be stored in the on-board storage device. In addition, there is room for development regarding the method of storing this data in the on-board storage device.
[0008] One objective of the present disclosure is to provide technology that can appropriately store data related to computer processing for automatic driving control of a vehicle, including data involving AI, in an on-board storage device, while preventing a situation in which the storage device runs out of free space due to this storage. [Means for solving the problem]
[0009] A first aspect of the present disclosure is a method for managing data related to a vehicle undergoing automatic driving control, and has the following features. The method comprises: A step of determining whether artificial intelligence is involved in the computer processing for performing the automatic driving control; determining whether a predetermined storage condition is met; When it is determined that the artificial intelligence is involved in the computer processing and the predetermined storage condition is satisfied, storing input and output data of the computer processing within a predetermined storage time based on the timing at which it is determined that the predetermined storage condition is satisfied in a storage device of the vehicle; Includes.
[0010] A second aspect of the present disclosure is an apparatus for managing data related to a vehicle in which autonomous driving control is performed, and has the following features. The device includes a processor that performs computer processing to perform the autonomous driving control. The processor, determining whether the computer processing involves artificial intelligence; determining whether a predetermined storage condition is satisfied; If it is determined that the artificial intelligence is involved in the computer processing and the specified storage conditions are determined to be satisfied, the input and output data of the computer processing within a specified storage time based on the timing at which it is determined that the specified storage conditions are satisfied is stored in a storage device of the vehicle. Effect of the Invention
[0011] According to the present disclosure, when it is determined that AI is involved in the computer processing and that a predetermined storage condition is satisfied, the input and output data of the computer processing can be stored in the storage device of the vehicle. Therefore, it is possible to appropriately store data related to the computer processing for performing automatic driving control that involves AI in the storage device of the vehicle. In addition, since not all data involving AI is stored, but only data within a predetermined storage time based on the time when it is determined that the storage condition is satisfied, it is also possible to prevent a situation in which the free space of the storage device is insufficient. [Brief description of the drawings]
[0012] [Figure 1]1 is a block diagram showing an example of a configuration related to automatic driving control of a vehicle according to an embodiment. FIG. [Diagram 2] FIG. 1 is a conceptual diagram illustrating a configuration example of an autonomous driving system according to an embodiment. [Diagram 3] FIG. 11 is a diagram showing an example of an instruction regarding management of log data. [Figure 4] 11 is a diagram illustrating a storage time when log data is extracted and stored. FIG. [Diagram 5] 10 is a flowchart showing a process flow by a processor, which is particularly related to the embodiment. [Figure 6] 10 is a flowchart showing a process flow by a processor, which is particularly related to the embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS
[0013] 1.Autonomous driving of vehicles 1 is a block diagram showing an example of a configuration related to the automatic driving control of a vehicle 1 according to the present embodiment. Automatic driving refers to automatically performing at least one of steering, acceleration, and deceleration of the vehicle 1 without the driver's 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 obtained by the sensor group 10. For example, the sensor detection information SEN includes images captured by a camera. As another example, the sensor detection information SEN may include point cloud information obtained by a LIDAR. 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 information obtained by the recognition sensor 11. For example, the recognition unit 20 recognizes objects around the vehicle 1. Examples of objects include pedestrians, other vehicles (preceding vehicles, parked vehicles, etc.), white lines, road structures (e.g., guardrails, curbs), fallen objects, traffic lights, intersections, signs, etc. The recognition result information RES indicates the recognition result by the recognition unit 20. For example, the recognition result information RES includes object information indicating the relative position and relative speed of the object with respect to the vehicle 1.
[0018] The planner 30 receives the recognition result information RES from the recognition unit 20. The planner 30 may also receive vehicle state information, position information, and pre-generated map information. The map information may be high-precision three-dimensional map information. The planner 30 generates a driving plan for the vehicle 1 based on the received information. The driving plan may be for reaching a pre-set 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 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 at least a part of the automatic driving control of the vehicle 1 by using the machine learning model.
[0026] 2.Autonomous Driving System 2 is a conceptual diagram showing a configuration example of an autonomous driving system 100 according to this embodiment. The autonomous driving system 100 is mounted on a vehicle 1 and controls autonomous driving of the vehicle 1. The autonomous driving system 100 has at least the functions of the autonomous driving control unit described above. The autonomous driving system 100 may further include a sensor group 10 and a traveling device 50.
[0027] The autonomous driving system 100 includes one or more processors 110 (hereinafter simply referred to as "processors" 110) and one or more storage devices 120 (hereinafter simply referred to as "storage devices 120"). The processors 110 execute various processes. Examples of the processors 110 include a central processing unit (CPU), a graphics processing unit (GPU), an application specific integrated circuit (ASIC), and a field-programmable gate array (FPGA). The recognition unit 20, the planning unit 30, and the control amount calculation unit 40 may be realized by a single processor 110, or may be realized by separate processors 110. The storage device 120 stores various information. Examples of the storage device 120 include a hard disk drive (HDD), a solid state drive (SSD), a volatile memory, and a non-volatile memory.
[0028] The program 130 is a computer program for controlling the vehicle 1, and is executed by the processor 110. Various computer processes by the autonomous driving system 100 may be realized by cooperation between the processor 110, which executes the program 130, and the storage device 120. The program 130 is stored in the storage device 120. The program 130 may be recorded on a computer-readable recording medium.
[0029] The model data 140 is data of a model included in the recognition unit 20, the planning unit 30, and the control amount calculation unit 40. As described above, in this embodiment, 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 model data 140 is stored in the storage device 120 and is used for automatic driving control.
[0030] During the autonomous driving control, the processor 110 acquires "log data LOG." The log data LOG may include sensor detection information SEN input to the autonomous driving control unit. The log data LOG may include control amount CON output from the autonomous driving control unit. The log data LOG may include recognition result information RES output from the recognition unit 20. The log data LOG may include target trajectory TRJ output from the planner 30. The log data LOG may include reasons for judgments made in the recognition process by the recognition unit 20. The log data LOG may include reasons for judgments made in the planning process by the planner 30. The log data LOG may include the presence or absence of operator intervention in the autonomous driving control.
[0031] The processor 110 temporarily "holds" the log data LOG acquired during the autonomous driving control. Specifically, the processor 110 "holds" the log data LOG acquired during the autonomous driving control for a predetermined holding period Phold. Hereinafter, the temporarily held log data LOG is also referred to as "log data LOG_HOLD". Note that the log data LOG_HOLD corresponds to "temporarily held data" in the present disclosure. The processor 110 deletes the log data LOG that has been held after the holding period Phold from the storage device 120. The processor 110 may compress and store the log data LOG that has been held after the holding period Phold in the storage device 120, without deleting it.
[0032] The processor 110 also makes a determination as to whether to "save" the log data LOG_HOLD (hereinafter also referred to as "save determination"). Then, the processor 110 saves at least a portion of the log data LOG_HOLD in the storage device 120 based on the result of the save determination. Details of the save determination will be described later. Hereinafter, the log data LOG_HOLD saved in the storage device 120 based on the result of the save determination will also be referred to as "log data LOG_SAVE". The processor 110 may delete the log data LOG_HOLD that is not saved in the storage device 120 based on the result of the save determination from the storage device 120 without waiting for the retention period Phold to elapse.
[0033] The processor 110 generates a copy of at least a portion of the log data LOG_SAVE (hereinafter also referred to as "log data LOG_COPY") and transmits (uploads) it to a storage device external to the vehicle 1. Note that the log data LOG_COPY corresponds to "copy data" in this disclosure. When the processor 110 transmits the log data LOG_COPY to the external storage device, it deletes the original log data LOG corresponding to the log data LOG_COPY (i.e., the log data LOG_SAVE) from the storage device 120. The processor 110 may compress this original log data LOG and continue to store it in the storage device 120 without deleting it.
[0034] The management server 200 is a computer that exists outside the vehicle 1. The management server 200 communicates with one or more vehicles 1 (hereinafter simply referred to as "vehicles 1") via a communication network. The management server 200 has a database 220. The management server 200 receives log data LOG_COPY from the vehicle 1. The management server 200 also stores the received log data LOG_COPY in the database 220. The log data LOG_COPY is stored in the database 220 for a predetermined storage period. Hereinafter, the log data LOG_COPY stored in the database 220 is also referred to as "log data LOG_STORE".
[0035] The management server 200 transmits instructions INS_LOG regarding the management of the log data LOG to the vehicle 1. The instructions INS_LOG specify predetermined events PE, etc., that are to be saved as log data LOG, among events related to the behavior of the vehicle 1. The instructions INS_LOG are provided to the vehicle 1 from the management server 200 at a predetermined timing in a day (for example, when the ignition of the vehicle 1 is turned ON). The original data of the instructions INS_LOG is stored in the database 220. The contents of this original data are updated by the management server 200.
[0036] Fig. 3 is a diagram showing an example of instruction INS_LOG. In the example shown in Fig. 2, instruction INS_LOG includes items of group ID, event ID, event name EN, priority PL, and event judgment On / Off. Note that instruction INS_LOG may include items other than these items. Examples of other items include a pattern for acquiring log data LOG and a list of points (latitude and longitude) for acquiring log data LOG.
[0037] The group ID is an item for identifying a group to which a predetermined event PE belongs. In the example shown in FIG. 3, GI1, GI2, and GIm (m is a natural number equal to or greater than 3) are set as group IDs. GI1 is, for example, an ID of a group related to automatic driving control of the vehicle 1. GI2 is, for example, an ID of a group related to external recognition by the vehicle 1. GIm is, for example, an ID of a group related to the occurrence of abnormalities in various systems installed in the vehicle 1.
[0038] The event ID is an item for identifying a predetermined event PE. In the example shown in FIG. 3, EI1, EI2, EI3, EI4, and E15 are set as the event IDs of GI1. EI1 is, for example, an ID indicating detection of a sudden acceleration or deceleration of the vehicle 1. EI2 is, for example, an ID indicating detection of a driving change request (TD: Transition Demand) by the driver of the vehicle 1. EI3 is, for example, an ID indicating detection of a sharp turn of the vehicle 1. EI4 is, for example, an ID indicating detection of a behavior of the vehicle 1 that is different from the behavior of surrounding vehicles. EI5 is, for example, an ID indicating detection of a short distance between the vehicle 1 and a preceding vehicle or a following vehicle.
[0039] In the example shown in FIG. 3, EI6 to EI8 are set as the event IDs of GI2. EI6 is, for example, an ID indicating erroneous recognition. EI7 is, for example, an ID indicating detection of clouds. EI8 is, for example, an ID indicating detection of raindrops. EIn is set as the event ID of GIm (n is a natural number of 3 or more). EIn is, for example, an ID indicating detection of an abnormal signal.
[0040] The event name EN is an item that succinctly indicates the content of a predetermined event PE. In the example shown in Fig. 3, EN1 to ENn are set as the event names EN. EN1 to ENn correspond to EI1 to EIn, respectively.
[0041] The priority PL is an item indicating the priority order for storing the log data LOG (i.e., log data LOG_HOLD) in the storage device 120 when a predetermined event PE occurs. The priority PL is also an item indicating the priority order for transmitting the log data LOG (i.e., log data LOG_COPY) to the management server 200. In the example shown in FIG. 3, the priority PL is divided into five levels, 1 to 5. The higher the number of the priority PL, the higher the priority is given to storing the log data LOG of the predetermined event PE. Also, the higher the number of the priority PL, the higher the priority is given to transmitting the log data LOG.
[0042] Event judgment On / Off is an item that indicates whether or not a specific event PE is treated as a "storage target event STE." A storage target event STE is an event among the specific event PE, the log data LOG during which is stored in the storage device 21. A specific event PE with event judgment "On" is treated as a storage target event STE. A specific event PE with event judgment "Off" is not treated as a storage target event STE. In other words, the log data LOG during a specific event PE with event judgment "On" is stored in the storage device 21, and the log data LOG during other events is not stored in the storage device 21.
[0043] Here, the log data LOG during a predetermined event PE will be described with reference to Fig. 4. In the example shown in Fig. 4, a predetermined event PE with an event ID = EI3 occurs at time T1. Also, a predetermined event PE with an event ID = EI1 occurs at time T2. Note that both the predetermined events PE with event ID = EI1 and event ID = EI3 correspond to predetermined events PE with an "On" event determination (i.e., events STE to be saved) (see Fig. 3).
[0044] When a predetermined event PE that occurred at a certain time corresponds to a save target event STE, the log data LOG of this save target event STE is extracted for a predetermined save time Tsave. The extracted log data LOG is saved in the storage device 120. This log data LOG corresponds to the above-mentioned log data LOG_SAVE. The upper part of FIG. 4 illustrates log data LOG including sensor detection information SEN, control amount CON, recognition result information RES, and target trajectory TRJ. This log data LOG is in a state held in the storage device 120, that is, log data LOG_HOLD.
[0045] The save time Tsave at which the log data LOG is extracted and saved is set based on the time at which it is determined that a save target event STE has occurred. In the example shown in FIG. 4, it is determined that two types of save target events STE have occurred at times T1 and T2. The save time Tsave1 for the first save target event STE (event ID=EI3) includes a time zone Z1 before time T1 and a time zone Z2 after time T1. The save time Tsave2 for the second save target event STE (event ID=EI1) includes a time zone Z3 before time T2 and a time zone Z4 after time T2.
[0046] The length of each of the time periods Z1, Z2, Z3, and Z4 is, for example, 1 to 10 seconds. However, it may take time to determine whether or not a specific event PE corresponds to a save target event STE. Therefore, it is expected that the time at which it is determined that the save target event STE has occurred will be slightly later than the time at which the save target event STE occurred. Therefore, it is desirable to set the length of each of the time periods Z1, Z2, Z3, and Z4 (i.e., the length of the save times Tsave1 and Tsave2) for each content (event ID) of the save target event STE.
[0047] 3. Preservation judgment As already described, in the autonomous driving system 100, autonomous driving control is performed using at least one of a rule-based model and a machine learning model. When a machine learning model is used in even a part of the autonomous driving control, it is desirable to evaluate, verify, etc. the model. Therefore, in this embodiment, in order to enable evaluation, verification, etc. using the log data LOG, when a machine learning model is applied to at least a part of the functions of the autonomous driving control unit (i.e., the recognition unit 20, the planning unit 30, and the control amount calculation unit 40), information indicating the involvement of AI is added to the log data LOG.
[0048] Hereinafter, log data LOG with information indicating the involvement of AI is also referred to as "log data LOG_AI." To distinguish from log data LOG_AI, log data LOG in which all functions of the autonomous driving control unit are realized by a rule-based model is referred to as "log data LOG_RL."
[0049] In this embodiment, evaluation, verification, etc. of the automatic driving control using the machine learning model is performed in the management server 200. For this purpose, it is necessary to transmit the log data LOG_AI acquired during the automatic driving control to the management server 200 at an appropriate timing. However, since the capacity of the storage device 120 is limited, it is necessary to appropriately "store" in the storage device 120 the log data LOG corresponding to the log data LOG_AI from among the log data LOG acquired during the automatic driving control.
[0050] Therefore, in this embodiment, a save determination is made using the log data LOG_HOLD. In the save determination, it is determined whether or not information indicating the involvement of AI is added to the log data LOG_HOLD. Then, the log data LOG_HOLD to which the information indicating the involvement of AI is added is saved in the storage device 120. That is, in this embodiment, the log data LOG that is determined to be the log data LOG_AI and the log data LOG_HOLD is treated as the log data LOG_SAVE.
[0051] Log data LOG that is determined to be log data LOG_AI and log data LOG_HOLD is a target for generating log data LOG_COPY, and this log data LOG_COPY is also a target for transmission to the management server 200. Note that log data LOG that is log data LOG_RL and log data LOG_HOLD is not handled as log data LOG_SAVE. Therefore, the non-target log data LOG may be deleted from the storage device 120, or may be compressed and then saved in the storage device 120.
[0052] 4. Example of processing by the processor Figures 5 and 6 are flowcharts showing the flow of processing by the processor 110, which is particularly related to this embodiment. Figure 5 illustrates processing related to the handling of log data LOG_HOLD, and Figure 6 illustrates processing related to the handling of log data LOG_SAVE. The routines shown in Figures 5 and 6 are each repeatedly executed at a predetermined control period.
[0053] 5, first, the holding period phold of the log data LOG is counted (step S11). As already described, the log data LOG is acquired during the automatic driving control and temporarily held. The holding period phold of the temporarily held log data LOG (i.e., the log data LOG_HOLD) is counted from the time of acquisition by the processor 110.
[0054] Following the processing of step S11, it is determined whether the retention period phold of the log data LOG_HOLD is equal to or shorter than the retention period Phold (step S12). If the result of the determination in step S12 is negative, the log data LOG_HOLD is deleted (step S13). Log data LOG_HOLD is generated every moment. Therefore, in the processing of step S13, log data LOG_HOLD whose retention period phold exceeds the retention period Phold is sequentially deleted. Note that if the capacity of the storage device 120 is sufficient or if the capacity of the log data LOG_HOLD is small, log data LOG_HOLD whose retention period phold exceeds the retention period Phold may be compressed and then stored in the storage device 120.
[0055] If the result of the judgment in step S12 is positive, the process of step S14 is performed. In the process of step S14, it is judged whether or not the log data LOG_HOLD corresponds to the log data LOG_AI. The judgment made in the process of step S14 is the above-mentioned storage judgment. If the result of the judgment in step S14 is negative, the process of step S13 is performed. That is, if the log data LOG_HOLD corresponds to the log data LOG_RL, this log data LOG_HOLD is deleted. Note that the compression and storage process described in the explanation of the process of step S13 can also be applied to the log data LOG_HOLD corresponding to the log data LOG_RL.
[0056] If the result of the determination in step S14 is positive, the process of step S15 is performed. In the process of step S15, it is determined whether or not the storage condition is satisfied. Whether or not the storage condition is satisfied can be determined based on whether or not the storage target event STE has occurred. As already explained, the storage target event STE is an event among the predetermined events PE, during which the log data LOG is stored in the storage device 21. Therefore, it is determined whether or not the predetermined event PE has occurred, and if it is determined that the predetermined event PE has occurred, the instruction INS_LOG explained in FIG. 3 is referenced. This makes it possible to determine whether or not the storage target event STE has occurred.
[0057] If the result of the determination in step S15 is negative, the process returns to step S12. On the other hand, if the result of the determination in step S15 is positive, the log data LOG_HOLD is saved in the storage device 120 (step S16). In the process of step S16, first, based on the time when it is determined that the save target event STE has occurred, a predetermined period is extracted from the log data LOG_HOLD of this save target event STE. The concept of this predetermined period is as explained in FIG. 4. Then, the extracted log data LOG_HOLD is saved in the storage device 120. This log data LOG corresponds to the log data LOG_SAVE described above.
[0058] 6, first, a request signal for sending (uploading) the log data LOG_SAVE is sent to the management server 200 (step S21). Then, it is determined whether or not an acknowledgement signal has been received (step S22). The acknowledgement signal is a signal sent from the management server 200 in response to the request signal sent by the processing of step S21. The sending of the acknowledgement signal is put on hold depending on the state of the management server 200. For example, if the amount of data stored in the database 220 exceeds the allowable amount, the sending of the acknowledgement signal is put on hold.
[0059] The process of step S22 is repeated until a positive determination result is obtained. If a positive determination result is obtained, a copy of the log data LOG_SAVE, that is, log data LOG_COPY, is generated and transmitted to the management server 200 (step S23). When the log data LOG_COPY is transmitted, the data is encoded. When the transmission of all the log data LOG_COPY is completed, an end signal is transmitted to the management server 200.
[0060] Following the process of step S23, it is determined whether or not a confirmation signal has been received (step S24). The confirmation signal is a signal transmitted from the management server 200 in response to the end signal transmitted by the process of step S23. The transmission of the confirmation signal is put on hold depending on the state of the management server 200. For example, the transmission of the confirmation signal is put on hold until storage of all the log data LOG_COPY in the database 220 is completed.
[0061] The process of step S24 is repeated until a positive determination result is obtained. If a positive determination result is obtained, the log data LOG is deleted from the storage device 120 (step S25). The deleted log data LOG is the original log data LOG corresponding to the log data LOG_COPY (i.e., the log data LOG_SAVE). Note that if the capacity of the storage device 120 is sufficient or if the capacity of the original log data LOG is small, this log data LOG may be compressed and then stored in the storage device 120.
[0062] 4.Effects According to the present embodiment, the log data LOG determined to be the log data LOG_AI and the log data LOG_HOLD can be stored in the storage device 120. Therefore, it is possible to appropriately store the log data LOG corresponding to the log data LOG_AI from among the log data LOG acquired during the automatic driving control in the storage device 120. In addition, instead of storing all of the log data LOG determined to be the log data LOG_AI and the log data LOG_HOLD in the storage device 120, only the log data for the save time Tsave based on the time when it is determined that the save target event STE has occurred is stored, so that it is possible to prevent the free space of the storage device 120 from becoming insufficient.
[0063] According to this embodiment, the log data LOG that has been held after the retention period Phold has elapsed can be deleted from the storage device 120, or compressed and stored in the storage device 120. According to this embodiment, the original log data LOG corresponding to the log data LOG_COPY can be deleted from the storage device 120, or compressed and stored in the storage device 120. These processes are processes for increasing the free space of the storage device 120, and therefore it is possible to further prevent the free space of the storage device 120 from becoming insufficient. [Explanation of symbols]
[0064] 1...vehicle, 10...sensor group, 20...recognition unit, 30...planning unit, 40...control amount calculation unit, 50...driving device, 100...autonomous driving system, 110...processor, 120...storage device, 200...management server, 220...database, CON...control amount, INS_LOG...instruction, LOG, LOG_COPY, LOG_HOLD, LOG_SAVE...log data, RES...recognition result information, SEN...sensor detection information, TRJ...target trajectory, Tsave, Tsave1, Tsave2...save time
Claims
1. A method for managing data related to a vehicle in which automatic driving control is performed, comprising: A step of determining whether artificial intelligence is involved in the computer processing for performing the automatic driving control; determining whether a predetermined storage condition is met; When it is determined that the artificial intelligence is involved in the computer processing and the predetermined storage condition is satisfied, storing input and output data of the computer processing within a predetermined storage time based on the timing at which it is determined that the predetermined storage condition is satisfied in a storage device of the vehicle; A vehicle data management method comprising:
2. 2. The method of claim 1 , temporarily storing said computer processing input and output data in a storage device of said vehicle; a step of counting a retention period in the storage device of the vehicle for each temporarily stored data indicating data temporarily stored in the storage device; Further comprising: When it is determined that the artificial intelligence is involved in the computer processing and that the predetermined storage condition is satisfied, data within the predetermined storage time is extracted from the temporarily stored data whose retention period is equal to or shorter than the predetermined retention period and stored in a storage device of the vehicle. A vehicle data management method comprising:
3. 3. The method of claim 2, A vehicle data management method, further comprising the step of deleting the temporarily held data, the holding period of which exceeds the predetermined holding period, from the storage device of the vehicle.
4. The method according to any one of claims 1 to 3, storing a copy of the input and output data of the computer processing during the predetermined storage time in a storage device external to the vehicle; deleting original data corresponding to the copy data stored in the external storage device from the storage device of the vehicle; The vehicle data management method further comprising:
5. An apparatus for managing data related to a vehicle in which automatic driving control is performed, A processor is provided for performing computer processing for performing the automatic driving control, The processor, determining whether the computer processing involves artificial intelligence; determining whether a predetermined storage condition is satisfied; When it is determined that the artificial intelligence is involved in the computer processing and the predetermined storage condition is satisfied, input and output data of the computer processing within a predetermined storage time based on the timing at which it is determined that the predetermined storage condition is satisfied is stored in a storage device of the vehicle. A vehicle data management device comprising:
6. 6. The apparatus of claim 5, The processor further comprises: Temporarily storing input and output data of the computer processing in a storage device of the vehicle; Counting the retention period in the vehicle storage device for each temporarily stored data indicating data temporarily stored in the storage device; When it is determined that the artificial intelligence is involved in the computer processing and that the predetermined storage condition is satisfied, data within the predetermined storage time is extracted from the temporarily stored data whose retention period is equal to or shorter than the predetermined retention period, and stored in a storage device of the vehicle. A vehicle data management device comprising:
7. 7. The apparatus of claim 6, The processor, A vehicle data management device, comprising: a storage device for the vehicle that deletes the temporarily held data, the temporarily held data having a holding period that exceeds the predetermined holding period.
8. The device according to any one of claims 5 to 7, The processor further comprises: transmitting a copy of the input and output data of the computer processing during the predetermined storage time to a storage device external to the vehicle; The original data corresponding to the copy data transmitted to the external storage device and stored in the storage device of the vehicle is deleted from the storage device of the vehicle. A vehicle data management device comprising:
Citation Information
Patent Citations
Vehicle electronic control apparatus
JP2018190045A
Vehicle recording device and information recording method
JP2021174413A
System and method for training mechanical learning model arranged in simulation platform
JP2019185783A
Vehicle data collection system
JP2020144450A
