Automated driving system

Abstract

To prevent a situation in which a free capacity of a vehicle's storage device in which log data related to automated driving control is stored is strained in the vehicle in which the automated driving control using a machine learning model is performed.SOLUTION: An automated driving route along which automated driving control of a vehicle is performed is set. In a setting of the automated driving route, at least two candidates of a route from a current location to a destination of the vehicle are set. Also, a fluctuation amount of log data that fluctuates in a storage device in which the log data related to the automated driving control is stored is predicted during the travel of the vehicle along each of the candidates of the route. Further, a future value of a free capacity in the storage device at which the vehicle arrives at the destination of the route for each of at least two candidates is predicted on the basis of the fluctuation amount of the log data. Then, a candidate of the route from the candidates of the route of which the future value of the free capacity is maximum is selected as the automated driving route.SELECTED DRAWING: Figure 4

Description

[Technical field]

[0001] The present disclosure relates to a system for controlling automatic driving of a vehicle. [Background technology]

[0002] In recent years, there has been progress in the development of autonomous driving technology that uses models generated through machine learning (machine learning models) to control vehicles based on data from sensors mounted on the vehicles, etc. International Publication No. WO 2019 / 116423 proposes a method for collecting training data to be used in generating machine learning models.

[0003] In addition to International Publication No. 2019 / 116423, examples of documents showing the technical state of the technical field related to the present disclosure include JP 2011-113494 A, JP 2021-146770 A, and Japanese Patent No. 6761002 A. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] International Publication No. 2019 / 116423 [Patent Document 2] JP 2011-113494 A [Patent Document 3] JP 2021-146770 A [Patent Document 4] Patent No. 6761002 Summary of the Invention [Problem to be solved by the invention]

[0005] It is desirable to verify the automatic driving control of a vehicle performed using a machine learning model after the fact. As a method for enabling this verification, it is conceivable to store log data related to the automatic driving control of the vehicle in a storage device of the vehicle. However, the capacity of the storage device of the vehicle is limited. Therefore, when the amount of data of this log data reaches a certain amount, it is conceivable to transmit it to the outside and delete it from the storage device. However, during the execution of the automatic driving control, log data related to this is generated every moment. Therefore, when the free space of the storage device becomes tight due to the log data before being transmitted to the outside and the log data generated during the automatic driving control, it may become impossible to store the latter log data from the middle. Therefore, technological development is desired to prevent such a tight situation from occurring.

[0006] One objective of the present disclosure is to provide a technology that can prevent a situation in which the free space of a storage device of a vehicle in which log data related to autonomous driving control using a machine learning model is stored becomes limited, in advance. [Means for solving the problem]

[0007] The present disclosure relates to an autonomous driving system installed in a vehicle and has the following features. The autonomous driving system includes one or more processors and one or more memory devices. The one or more processors: Setting an automatic driving route indicating a route of the vehicle along which automatic driving control of the vehicle is performed; While the vehicle is traveling along the autonomous driving route, log data relating to the autonomous driving control is stored in the one or more storage devices. In setting the automated driving route, the one or more processors setting at least two route candidates from the current location of the vehicle to the destination; predicting a variation of the log data that varies in the one or more storage devices while the vehicle is traveling along each of the candidate routes; predicting a future value of free space in the one or more storage devices at the time of arrival of the at least two route candidates at the destination based on the predicted fluctuation amount of the log data for each of the route candidates; From among the route candidates, the route candidate that maximizes the future value of the available capacity is selected as the automated driving route. Effect of the Invention

[0008] According to the present disclosure, while the vehicle is traveling along at least two route candidates from the current location to the destination, the amount of fluctuation in log data related to the autonomous driving control that fluctuates in one or more storage devices is predicted. In addition, based on the predicted amount of fluctuation, the future value of the free space in one or more storage devices at the time of arrival at the destination is predicted for each route candidate. Then, the route candidate with the largest future value of the free space is selected as the route of the vehicle on which the autonomous driving control is performed (i.e., the autonomous driving route). Therefore, according to the present disclosure, it is possible to prevent the free space of the storage device of the vehicle, in which the log data related to the autonomous driving control of the vehicle is stored, from becoming tight. [Brief description of the drawings]

[0009] [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

[0010] 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.

[0011] 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.

[0012] 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.

[0013] 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.

[0014] 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.

[0015] 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.

[0016] 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.

[0017] 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.

[0018] 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.

[0019] 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.

[0020] 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.

[0021] 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.

[0022] 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.

[0023] 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.

[0024] 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.

[0025] The program 130 is a computer program for controlling the vehicle 1, and is executed by the processor 110. Various 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.

[0026] 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.

[0027] During the autonomous driving control, the processor 110 acquires "log data LOG" related to the autonomous driving control. 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.

[0028] The processor 110 stores the log data LOG acquired during the automatic driving control in the storage device 120. The processor 110 may temporarily store the log data LOG in the storage device 120 for only a certain period of time.

[0029] The management server 200 is an external device that exists outside the vehicle 1. The management server 200 communicates with one or more vehicles 1 via a communication network. During the autonomous driving control or after the autonomous driving control is completed, the processor 110 of the vehicle 1 may upload at least a part of the log data LOG stored in the local storage device 120 to the management server 200. The log data LOG uploaded to the management server 200 is used for verifying the autonomous driving control using a machine learning model, etc. The processor 110 may erase the log data LOG uploaded to the management server 200 from the local storage device 120.

[0030] 3. Self-driving route In this embodiment, a case is considered in which automatic driving control of the vehicle 1 is performed in a section where automatic driving is possible (for example, a section of a highway, a section dedicated to automatic driving, etc.). In this case, a route of the vehicle 1 where this automatic driving control is performed (hereinafter also referred to as an "automatic driving route") is set. The process of setting the automatic driving route (hereinafter also referred to as a "route setting process") may be performed by the processor 110, or may be performed by a processor other than the processor 110 mounted on the vehicle 1 (for example, a processor of a navigation system).

[0031] While the vehicle 1 is traveling along the autonomous driving route, log data LOG is generated as autonomous driving control is executed. The generated log data LOG is stored in the storage device 120 of the vehicle 1. Here, while autonomous driving control is being executed, log data LOG continues to be generated. Therefore, the total amount Qlog of log data LOG in the storage device 120 continues to increase, while the free space QC of the storage device 120 continues to decrease. As a result, if the free space QC becomes tight, it may become impossible to store the log data LOG generated while the vehicle 1 is traveling along the autonomous driving route, from the middle of the autonomous driving route.

[0032] 3-1. First example of route setting process In consideration of this problem, in the route setting process, at least two candidates RTn for the autonomous driving route are set (n≧2). In the route setting process, the total amount QA_RTn of log data LOG generated while the vehicle 1 is traveling along these candidates RTn is also predicted. FIG. 3 is a diagram for explaining the total amount QA_RTn. In FIG. 3, candidates RT1, RT2, and RT3 are depicted as route candidates RTn. These candidates are all three route candidates leading from the current location CL of the vehicle 1 to the destination DS. The time Tcl shown on the horizontal axis of FIG. 3 represents the current time. In addition, times T1, T2, and T3 represent the times at which the vehicle 1 arrives at the destination DS when the vehicle 1 travels along the candidates RT1, RT2, and RT3, respectively.

[0033] The vertical axis of FIG. 3 represents the amount ΔQA_RTn of log data LOG generated per unit time. As shown in FIG. 3, the amount ΔQA_RTn of generation differs between candidates RT1 to RT3. This is because at least a portion of the routes differ between candidates RT1 to RT3. If at least a portion of the routes differ, there will be differences in the frequency and difficulty of events that generate log data LOG (object recognition events, driving plan generation events, control amount calculation events, etc.). In general, the higher the frequency of events per unit time, the higher the amount ΔQA_RTn of generation. Also, the higher the difficulty of the events, the higher the amount ΔQA_RTn of generation.

[0034] The total amount QA_RT1 of log data LOG generated while vehicle 1 is traveling along candidate RT1 is represented by the value ∫ΔQA_RT1dt obtained by integrating the amount ΔQA_RT1 generated from time Tcl to time T1. The total amount QA_RT2 is represented by the value ∫ΔQA_RT2dt obtained by integrating the amount ΔQA_RT2 generated from time Tcl to time T2. The total amount QA_RT3 is represented by the value ∫ΔQA_RT3dt obtained by integrating the amount ΔQA_RT3 generated from time Tcl to time T3.

[0035] In the route setting process, the future value QC_RTn(Tds) of the available capacity QC at the time of arrival at the destination DS (arrival time Tds) is further calculated based on the total amount QA_RTn. The future value QC_RTn(Tds) can be expressed by the following formula (1) using the value of the available capacity QC at the time Tcl (i.e., the current value) QC(Tcl). QC_RTn(Tds)=QC(Tcl)-∫ΔQA_RTndt···(1)

[0036] In the first example of the route setting process, the candidate RTn with the largest future value QC_RTn(Tds) calculated by formula (1) is selected as the autonomous driving route. If the candidate RTn has the largest future value QC_RTn(Tds), it is possible to prevent the free capacity QC from becoming tight on the way to the destination DS. In the example of FIG. 3, the total amount QA_RT2 is the smallest. Therefore, the candidate RTn with the largest future value QC_RTn(Tds) shown in formula (1) is candidate RT2, which is selected as the autonomous driving route.

[0037] 3-2. Second example of route setting process In the calculation example of the future value QC_RTn(Tds) described with reference to Fig. 3, the amount of fluctuation of the log data LOG in the storage device 120 that fluctuates while traveling along the candidate RTn is expressed by the total amount QA_RTn. However, if a communication spot (e.g., a charging or refueling spot, a service area on a highway, etc.) is included on or near the candidate RTn, the log data LOG can be transmitted to the management server 200 on the way to the destination DS. In this case, the transmitted log data LOG can be compressed and stored in the storage device 120, or the transmitted log data LOG can be deleted from the storage device 120.

[0038] FIG. 4 is a diagram showing an example of the transition of the total amount Qlog of log data LOG in the storage device 120 when the transmitted log data LOG is compressed or deleted. In the example shown in FIG. 4, the log data LOG is transmitted to the management server 200 during driving along the candidate RTn. Then, this transmitted log data LOG is compressed and stored in the storage device 120. As a result, the total amount Qlog is reduced by the data amount QB_RTn, while the free space QC of the storage device 120 increases. Therefore, when a communication spot is included on the candidate RTn or in the vicinity of the candidate RTn, the future value QC_RTn(Tds) can be expressed by the following formula (2). QC_RTn(Tds)=QC(Tcl)-∫ΔQA_RTndt+QB_RTn···(2)

[0039] In the second example of the route setting process, the candidate RTn that maximizes the future value QC_RTn(Tds) calculated by the formula (2) is selected as the automated driving route. In this way, the amount of fluctuation in the log data LOG in the storage device 120 that varies during driving along the candidate RTn can also be expressed by a combination of the total amount QA_RTn and the data amount QB_RTn.

[0040] In this way, according to the first or second example, the candidate RTn with the maximum future value QC_RTn(Tds) is selected as the autonomous driving route. This makes it possible to prevent the free capacity QC from becoming tight while the vehicle 1 is traveling along the autonomous driving route.

[0041] 4. Example of processing by the processor 5 is a flowchart particularly related to this embodiment, showing the flow of processing by processor 110. Note that the routines shown in FIG. 5 are each repeatedly executed at a predetermined control period.

[0042] 5, first, various information is acquired (step S11). Examples of the information acquired in the process of step S11 include information on the current position of the vehicle 1 (latitude and longitude information), map information, and information on the free space QC of the storage device 120.

[0043] Following the processing of step S11, it is determined whether or not the vehicle 1 is located in a section where autonomous driving is possible (step S12). The determination in step S12 is performed, for example, based on the information on the current position of the vehicle 1 acquired in step S11 and map information. If the determination result in step S12 is negative, it can be determined that autonomous driving control is not performed. Therefore, in this case, the processing ends.

[0044] If the determination result in step S12 is positive, it can be determined that automatic driving control is performed. Therefore, it is determined whether or not the current value QC(Tcl) of the free space QC of the storage device 120 is equal to or less than the upper limit value UL (step S13). In the process of step S13, the value of the free space QC acquired in step S11 is used as the current value QC(Tcl). The upper limit value UL is set in advance as, for example, an average amount of log data LOG generated during one trip. The average amount of log data LOG may be an average amount for one or more vehicles 1, or may be an average amount for the vehicle 1 in which the processor 110 is installed.

[0045] If the determination result in step S13 is negative, route setting processing (normal) is performed (step S14). In the processing in step S14, an autonomous driving route from the current location CL of the vehicle 1 to the destination DS is set based on a viewpoint other than the log data LOG. Examples of the viewpoint other than the log data LOG include the time required to reach the destination DS, the distance traveled, and the fare.

[0046] If the determination result of step S13 is positive, route setting processing (reduced data) is performed (step S15). In the processing of step S15, candidates RTn are set according to the first or second example described above, and the total amount QA_RTn (first and second examples) of log data LOG generated while the vehicle 1 is traveling along these candidates RTn and the amount QB_RTn (second example) of log data LOG reduced while the vehicle 1 is traveling along these candidates RTn are predicted. Then, the candidate RTn with the maximum future value QC_RTn (Tds) calculated based on formula (1) or (2) is selected as the autonomous driving route.

[0047] The process of step S13 is not essential to the present disclosure. Therefore, if the determination result of step S12 is positive, the process of step S13 may be skipped and the process of step S15 may be performed. In addition, in the process of step S15, before calculating the future value QC_RTn(Tds), an intermediate progress amount QA_RTn(Tmw) of the log data LOG generated while the vehicle 1 is traveling along the candidate RTn may be calculated. Furthermore, the candidates RTn may be narrowed down based on this intermediate progress amount QA_RTn(Tmw).

[0048] FIG. 6 is a diagram for explaining the progress amount QA_RTn(Tmw). FIG. 6 depicts the candidate RT1 described in FIG. 3. As described in the description of FIG. 3, the total amount QA_RT1 of log data LOG generated while the vehicle 1 is traveling along the candidate RT1 is a value ∫ΔQA_RT1dt obtained by accumulating the generated amount ΔQA_RT1 from time Tcl to time T1. The progress amount QA_RTn(Tmw) is the total amount of log data LOG generated up to the time (time T4 in the example of FIG. 6) before the vehicle 1 reaches the destination DS.

[0049] When the progress amount QA_RTn(Tmw) is calculated in the process of step S15, the value of the free space QC at the time Tmw (i.e., the progress value) may be calculated based on this progress amount QA_RTn(Tmw). In this case, the progress value QC_RTn(Tmw) can be expressed by the following formula (3). QC_RTn(Tmw)=QC(Tcl)-QA_RTn(Tmw)...(3)

[0050] When the progress value QC_RTn(Tmw) is calculated, the progress value QC_RTn(Tmw) may be further compared with a tolerance AC. The tolerance AC is set to, for example, zero or a value close to zero. If the comparison results in a candidate RTn having a progress value QC_RTn(Tmw) equal to or less than the tolerance AC, the candidate RTn is excluded from the candidates for the autonomous driving route. It can be said that such a candidate RTn is one in which the available capacity QC becomes scarce on the way to the destination DS of the vehicle 1. Therefore, according to an example in which the candidates RTn are narrowed down based on the progress amount QA_RTn(Tmw), it is possible to more reliably achieve the effect of the present embodiment, that is, to prevent the available capacity QC from becoming scarce. [Explanation of symbols]

[0051] 1...vehicle, 10...sensor group, 20...recognition unit, 30...planning unit, 40...control amount calculation unit, 50...driving device, 100...automatic driving system, 110...processor, 120...storage device, 200...management server, 220...database, AC...tolerance, CL...current location, DS...destination, QC...available space, RTn...candidate, UL...upper limit, CON...control amount, LOG...log data, RES...recognition result information, SEN...sensor detection information, TRJ...target trajectory, ΔQA_RTn...log data L Amount of OG generated per unit time, QA_RTn...total amount of log data LOG generated while vehicle 1 is traveling along candidate RTn, QA_RTn(Tmw)...interim amount of log data LOG generated while vehicle 1 is traveling along candidate RTn, QB_RTn...amount of log data LOG that decreases while vehicle 1 is traveling along candidate RTn, QC(Tcl)...current value of free space QC, QC_RTn(Tds)...future value of free space QC, QC_RTn(Tmw)...interim value of free space QC

Claims

1. An automated driving system installed in a vehicle, one or more processors; one or more storage devices; Equipped with The one or more processors: Setting an automatic driving route indicating a route of the vehicle along which automatic driving control of the vehicle is performed; While the vehicle is traveling along the automated driving route, log data related to the automated driving control is stored in the one or more storage devices; In setting the automated driving route, the one or more processors setting at least two candidates for a route from the current location of the vehicle to the destination; predicting a variation of the log data that varies in the one or more storage devices while the vehicle is traveling along each of the candidate routes; predicting a future value of free space in the one or more storage devices at the time of arrival of the at least two route candidates at the destination based on the predicted fluctuation amount of the log data for each of the route candidates; From among the route candidates, a route candidate that has the largest future value of the available capacity is selected as the automated driving route. An automated driving system characterized by

2. The automated driving system according to claim 1, The one or more processors, in setting the automated driving route, determining whether the current value of the free space is equal to or less than an upper limit value; The prediction of the amount of change in the log data and the prediction of the future value of the free space are performed when it is determined that the current value of the free space is equal to or less than the upper limit value. An automated driving system characterized by

3. The automated driving system according to claim 1 or 2, In predicting the amount of fluctuation in the log data, the one or more processors Calculating, for each of the at least two candidates, a total amount of the log data generated while the vehicle is traveling along each of the at least two candidates and an amount of the log data decreased from the one or more storage devices while the vehicle is traveling along each of the at least two candidates; A total amount of the log data generated while the vehicle is traveling and an amount of the log data decreased from the one or more storage devices while the vehicle is traveling are added for each of the at least two candidates to calculate a variation amount of the log data. An automated driving system characterized by

4. The automated driving system according to claim 1 or 2, The one or more processors further include, in setting the automated driving route, Calculating an amount of the log data generated per unit time in the one or more storage devices while the vehicle is traveling along each of the at least two candidates, predicting an intermediate value indicating a value of the available capacity on the way to the destination for each of the at least two candidates based on the current value of the available capacity and the integrated value of the amount of available capacity generated per unit time; The candidate whose intermediate value is equal to or less than the allowable value is excluded from the candidates of the route. An automated driving system characterized by

Images