Autonomous driving system

Abstract

To prevent an available space of a vehicle's storage device, which stores log data related to automatic operation control, from becoming insufficient in a vehicle provided with automatic operation control using machine learning model.SOLUTION: An automatic operation system performs processing to: execute automatic operation control for a vehicle; store log data related to the automatic operation control in one or more storage devices while the automatic operation control is in progress; and predict a vehicle's cruising distance. During the processing to predict the cruising distance, an available free space in one or more storage devices where the log data is stored is determined, and the cruising distance is set according to the available free space determined. The smaller the available free space determined the shorter the cruising distance is set.SELECTED DRAWING: Figure 4

Description

Technical Field

[0001] The present disclosure relates to a system for performing automatic driving control of a vehicle.

Background Art

[0002] In recent years, the development of automatic driving technology for controlling a vehicle from data such as sensors mounted on the vehicle using a model (machine learning model) generated through machine learning has been progressing. In International Publication No. 2019 / 116423, a method for collecting training data for use in generating a machine learning model has been proposed.

[0003] As documents showing the technical level of the technical field related to the present disclosure, in addition to International Publication No. 2019 / 116423, Japanese Unexamined Patent Application Publication No. 2011-113494, Japanese Unexamined Patent Application Publication No. 2022-44235, and Patent No. 6761002 can be exemplified.

Prior Art Documents

Patent Documents

[0004]

Patent Document 1

Patent Document 2

Patent Document 3

Patent Document 4

Summary of the Invention

Problems to be Solved by the Invention

[0005] Automated vehicle driving control performed using machine learning models should ideally be verified retrospectively. One way to enable this verification is to store log data related to the vehicle's automated driving control in the vehicle's storage device. However, the storage device has limited capacity. Therefore, when the amount of log data reaches a certain level, it may be possible to send it externally and delete it from the storage device. However, log data related to automated driving control is generated moment by moment during execution. Therefore, if the storage device's free space becomes limited by the log data before it is sent externally and the log data generated during automated driving control, it may become impossible to save the latter log data. Therefore, technological development is desired to prevent such a critical situation from occurring.

[0006] One of the purposes of this disclosure is to provide a technology that can prevent a situation in which the storage capacity of a vehicle's memory device, where log data related to autonomous driving control using a machine learning model is stored, becomes depleted. [Means for solving the problem]

[0007] This disclosure relates to an autonomous driving system installed in a vehicle, and has the following features: The aforementioned autonomous driving system comprises one or more processors and one or more storage devices. The one or more processors are configured to perform processing for automatic driving control of the vehicle, processing to save log data related to the automatic driving control to the one or more storage devices while the automatic driving control is being executed, and processing to predict the remaining driving range of the vehicle. The one or more processors are configured to obtain the available space in the one or more storage devices where the log data is stored, and to set the cruising range according to the available space, in the process of predicting the cruising range. The cruising range is set to a shorter distance the less available space there is. [Effects of the Invention]

[0008] According to this disclosure, the vehicle's driving range is predicted based on the available capacity of one or more storage devices. Furthermore, this driving range is set to be shorter the less available capacity there is. Therefore, it is possible to prevent situations where the available capacity becomes insufficient. [Brief explanation of the drawing]

[0009] [Figure 1] This is a block diagram showing an example configuration related to the automatic driving control of a vehicle according to the embodiment. [Figure 2] This is a conceptual diagram showing an example configuration of an automated driving system according to an embodiment. [Figure 3] This is a diagram illustrating the concept of mobility services. [Figure 4] This diagram shows an example of the relationship between the duration of execution of automated driving control and the available capacity of the recording device. [Figure 5] This diagram illustrates the process of expanding the free capacity of a recording device. [Figure 6] This diagram illustrates the total amount of log data generated while a vehicle is traveling along a proposed route. [Modes for carrying out the invention]

[0010] 1. Autonomous driving of vehicles Figure 1 is a block diagram showing an example configuration related to the automatic driving control of vehicle 1 according to this embodiment. Automatic driving means that at least one of the steering, acceleration, and deceleration of vehicle 1 is performed automatically without driver operation. Automatic driving control is a concept that includes not only fully automatic driving control but also risk avoidance control, lane keeping assist control, etc. The operator may be a driver riding in vehicle 1 or a remote operator who remotely controls vehicle 1.

[0011] Vehicle 1 includes a sensor group 10, a recognition unit 20, a planning unit 30, a control quantity calculation unit 40, and a driving device 50.

[0012] The sensor group 10 includes recognition sensors 11 used to recognize the surrounding conditions of the vehicle 1. Examples of recognition sensors 11 include cameras, LIDAR (Laser Imaging Detection and Ranging), radar, etc. The sensor group 10 may further include state sensors 12 for detecting the state of the vehicle 1, position sensors 13 for detecting the position of the vehicle 1, etc. Examples of state sensors 12 include speed sensors, acceleration sensors, yaw rate sensors, steering angle sensors, etc. An example of a position sensor 13 is a GNSS (Global Navigation Satellite System) sensor.

[0013] Sensor detection information SEN is information obtained by the sensor group 10. For example, sensor detection information SEN includes images captured by a camera. As another example, sensor detection information SEN may include point cloud information obtained by a LIDAR. Sensor detection information SEN may include vehicle state information indicating the state of vehicle 1. Sensor detection information SEN may include position information indicating the position of vehicle 1.

[0014] The recognition unit 20 receives sensor detection information SEN. Based on the information obtained by the recognition sensor 11, the recognition unit 20 recognizes the surroundings of the vehicle 1. 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 velocity of the object with respect to the vehicle 1.

[0015] The planner 30 receives the recognition result information RES from the recognition unit 20. Also, the planner 30 may receive vehicle state information, position information, and pre-generated map information. The map information may be high-precision 3D map information. Based on the received information, the planner 30 generates a driving plan for the vehicle 1. 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, stopping, etc. Furthermore, the planner 30 generates a target trajectory TRJ necessary for the vehicle 1 to drive 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 planner 30. The control amount calculation unit 40 calculates a control amount CON necessary for the vehicle 1 to follow the target trajectory TRJ. The control amount CON can also be said to be the 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 driving 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 driving 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, an in-wheel motor, etc. 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. Thereby, 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 predetermined set of rules. Examples of the machine learning model include a neural network (NN), a support vector machine (SVM), a regression model, a decision tree model, etc. The NN may be a convolutional neural network (CNN), a recurrent neural network (RNN), or a combination thereof. The type, number of layers, and number of nodes in each layer of 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 into the model. The recognition result information RES is output from the model or generated based on the output from the model.

[0019] Similarly, the planning unit 30 includes at least one of a rule-based model and a machine learning model. The planning unit 30 performs planning processing by inputting the recognition result information RES into the model. The target trajectory TRJ is output from the model or generated based on the output from the model.

[0020] Similarly, the control variable calculation unit 40 includes at least one of a rule-based model and a machine learning model. The control variable calculation unit 40 performs control variable calculation processing by inputting a target trajectory TRJ to the model. The control variable CON is output from the model or generated based on the output from the model.

[0021] Two or more of the recognition unit 20, planning unit 30, and control variable calculation unit 40 may be configured as a single unit. The recognition unit 20, planning unit 30, and control variable calculation unit 40 may all be configured as a single unit (end-to-end configuration). For example, the recognition unit 20 and planning unit 30 may be configured as a single unit by a neural network (NN) that outputs a target trajectory TRJ from sensor detection information SEN. Even in the case of a single unit configuration, intermediate products such as recognition result information RES and target trajectory TRJ may be output. For example, if the recognition unit 20 and planning unit 30 are configured as a single unit by an NN, the recognition result information RES may be the output of the intermediate layer of the NN.

[0022] The recognition unit 20, the planning unit 30, and the control variable calculation unit 40 constitute an "automatic driving control unit" that controls the automatic driving of 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 variable calculation unit 40 includes a machine learning model. The automatic driving control unit uses the machine learning model to perform at least a part of the automatic driving control of vehicle 1.

[0023] 2. Autonomous driving system Figure 2 is a conceptual diagram showing an example configuration of the automated driving system 100 according to this embodiment. The automated driving system 100 is mounted on the vehicle 1 and performs automated driving control of the vehicle 1. The automated driving system 100 has at least the functions of the automated driving control unit described above. The automated driving system 100 may further include a group of sensors 10 and a driving device 50.

[0024] The autonomous driving 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 device 120"). The processor 110 performs various processes. Examples of processors 110 include CPU (Central Processing Unit), GPU (Graphics Processing Unit), ASIC (Application Specific Integrated Circuit), FPGA (Field-Programmable Gate Array), etc. The recognition unit 20, the planning unit 30, and the control variable calculation unit 40 may be implemented by a single processor 110 or by separate processors 110. The storage device 120 stores various information. Examples of storage devices 120 include HDD (Hard Disk Drive), SSD (Solid State Drive), volatile memory, non-volatile memory, etc.

[0025] Program 130 is a computer program for controlling vehicle 1 and is executed by processor 110. Various processes by the autonomous driving system 100 may be realized through the cooperation of processor 110 executing program 130 and storage device 120. Program 130 is stored in storage device 120. Program 130 may be recorded on a computer-readable recording medium.

[0026] The model data 140 is the model data included in the recognition unit 20, the planning unit 30, and the control variable calculation unit 40. As described above, in this embodiment, at least one of the recognition unit 20, the planning unit 30, and the control variable calculation unit 40 includes a "machine learning model". The model data 140 is stored in the storage device 120 and used for automatic driving control.

[0027] During autonomous driving control, the processor 110 acquires "log data LOG" related to 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 quantity 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 planning unit 30. The log data LOG may include the reason for the decision made in the recognition process by the recognition unit 20. The log data LOG may include the reason for the decision made in the planning process by the planning unit 30. The log data LOG may include whether or not there was operator intervention in the autonomous driving control.

[0028] The processor 110 saves the log data LOG acquired during automatic driving control to the storage device 120. The processor 110 may temporarily save the log data LOG to the storage device 120 for a certain period of time.

[0029] The management server 200 is an external device located outside of vehicle 1. The management server 200 communicates with one or more vehicles 1 via a communication network. During or after automated driving control, the processor 110 of vehicle 1 may upload at least a portion 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 verification of automated driving control using machine learning models, etc. The processor 110 may delete the log data LOG uploaded to the management server 200 from the local storage device 120.

[0030] 3. Driving range In this embodiment, we consider the case where one or more vehicles 1 are applied to a mobility service. A mobility service is a service that transports people using vehicles. Examples of mobility services include taxi services, bus services, ride-sharing services, etc. The management of the mobility service is performed, for example, by a management server 200. The management of the mobility service includes the management of vehicles 1, such as storage and selection (dispatch) of vehicles 1 applied to the mobility service, and the management of users US of the mobility service. The management of the mobility service also includes verification of automated driving control using the log data LOG described above.

[0031] Figure 3 is a conceptual diagram of a mobility service. Figure 3 shows one of one or more vehicles 1. This vehicle 1 transports user US1 from point P1 to point P2 in response to a request from user US1 of the mobility service.

[0032] When Vehicle 1 transports User US1, Vehicle 1 departs from storage location ST and heads to point P1. Storage location ST is, for example, a mobility service hub. Upon arriving at point P1, Vehicle 1 picks up User US1. After picking up User US1, Vehicle 1 heads from point P1 to point P2. Upon arriving at point P2, Vehicle 1 drops off User US1. After dropping off User US1, Vehicle 1 heads from point P2 to storage location ST. While traveling from point P2 to storage location ST, Vehicle 1 may transport User US2, who is a different user from User US1, at the request of User US2.

[0033] Consider a route RT1 that starts from storage location ST, passes through points P1 and P2, and returns to storage location ST. While vehicle 1 is traveling along part or all of this route RT1, automatic driving control is performed. When automatic driving control is performed, log data LOG is generated. The generated log data LOG is stored in the storage device 120 of vehicle 1.

[0034] During the execution of the automated driving control, log data LOG continues to be generated. Therefore, the total amount of log data LOG TQst in the storage device 120 continues to increase during the execution of the automated driving control. Figure 4 shows an example of the relationship between the duration of the execution of the automated driving control and the available capacity QC. The horizontal axis of Figure 4 shows the duration of the execution of the automated driving control. The vertical axis on the right side of Figure 4 shows the available capacity QC.

[0035] The left vertical axis of Figure 4 further shows the amount of log data LOG generated per unit time, ΔQt_RT1. As the execution of automatic driving control continues, the total amount TQst, which is the cumulative value of the generated amount ΔQt_RT1, increases. As a result, the free capacity QC of the storage device 120 continues to decrease. Consequently, if the free capacity QC becomes depleted, it may become impossible to save the log data LOG from partway through route RT1.

[0036] In view of this problem, in this embodiment, the cruising range (Milage) ML of vehicle 1 is set. The cruising range ML is set according to the available capacity QC. For example, the relationship between the distance traveled by the execution of automatic driving control and the total amount of log data LOG TQgn generated during this travel is calculated in advance. This relationship may be calculated by focusing on the travel history of one vehicle 1, or by focusing on the travel history of multiple vehicles 1. Using this relationship, the amount of log data LOG generated per unit distance (e.g., 1 km) ΔQl can be determined. The cruising range ML can be calculated based on the following equation (1). ML = QC / ΔQl ···(1)

[0037] A concept similar to the driving range ML is the driving range DTE (Distance To Empty). The driving range DTE is set based on the remaining battery charge supplying power to the vehicle's drive system and the remaining fuel. Therefore, the calculated value of the driving range DTE is fundamentally different from that of the driving range ML. However, vehicle 1 cannot travel a distance exceeding the driving range DTE. Therefore, if the driving range ML calculated based on equation (1) exceeds the driving range DTE, the driving range ML may be changed. In this case, the value of the driving range DTE is set as the driving range ML.

[0038] The cruising range ML is set, for example, while vehicle 1 is waiting at storage location ST for the provision of mobility services. Setting the cruising range ML while waiting for the provision of mobility services makes it possible to prevent a situation where the available capacity QC becomes strained. For example, vehicle 1 with a cruising range ML shorter than the distance L_RTn of route RTn, which includes the transportation of mobility service user USn (n≧1), is excluded from the candidates for transporting this user USn in the selection by the management server 200.

[0039] In another example, the range ML is set while the mobility service is being provided (for example, while vehicle 1 is traveling along route RTn). Even if the range ML is set while the mobility service is being provided, it is possible to prevent a situation where the available capacity QC becomes strained. However, in this case, as the available capacity QC decreases, the range ML decreases, and the execution of the automated driving control is restricted or suspended. While the execution of the automated driving control is restricted or suspended, for example, the operator of vehicle 1 performs manual driving. The switch from automated driving control to manual driving is triggered, for example, by a request generated by the processor 110 when the range ML decreases to a predetermined distance THml (described later).

[0040] 4. Processing to increase free space 4-1. Example 1 In this embodiment, if the cruising range ML, which is set according to the available capacity QC, is less than or equal to a predetermined distance THml, the available capacity QC may be expanded. Figure 5 is a diagram illustrating the process of expanding the available capacity QC. As explained with reference to Figure 4, if the execution of automatic driving control continues, the available capacity QC will continue to decrease. Here, the amount ΔQt_RT1 shown in Figure 4 may fluctuate depending on the location, time, surrounding environment, scene, etc. Therefore, if the rate of decrease of the available capacity QC continues to be high, the available capacity QC will become strained.

[0041] In the first example, a comparison is made between the cruising range ML and a predetermined distance THml. This comparison may be performed while the mobility service is being provided or while it is waiting to be provided. If the comparison determines that the cruising range ML is less than or equal to the predetermined distance THml, an expansion process is performed. Figure 5 shows an example of the change in available capacity QC when the expansion process is performed while the mobility service is being provided. In the expansion process, for example, log data LOG in the storage device 120 that has already been sent to the management server 200 is compressed and stored in the storage device 120. In another example, log data LOG that has already been sent to the management server 200 is deleted from the storage device 120.

[0042] The predetermined distance THml may be a fixed value or may be set based on the route RTn. If set based on the route RTn, for example, the average value of the total amount of log data LOG TQgn generated during past travel on the route RTn is used. The average value of the total amount of TQgn is calculated by, for example, the management server 200 referencing the travel history of one or more vehicles 1 and extracting routes that are the same as or similar to the route RTn. Then, the average value is calculated based on the total amount of log data LOG TQgn generated during travel on these extracted routes. The predetermined distance THml is set by adding a margin to this average value. The information of the predetermined distance THml set in this way is transmitted to the vehicle 1 that provides mobility services to the user USn.

[0043] 4-2. Second Example In the second example of the expansion process, the total distance L_AD of the sections S_AD in which automatic driving control can be performed may be calculated, which are sections S_RTk that constitute the route RTk (1≦k≦n) from the current location of vehicle 1 to the destination. At least one of the processes of setting the route RTk and identifying the sections S_AD is performed by the management server 200 or the processor 110 of vehicle 1 based on the location information of the current location of vehicle 1 and the destination. The current location of vehicle 1 includes the storage location ST (when waiting to provide mobility services) and a point along the route RTn (when providing mobility services). The destination of vehicle 1 includes points P1, P2 and storage location ST shown in Figure 3. Note that the location information of the current location and the destination is included in the various information stored in the storage device 120.

[0044] Examples of sections S_AD include sections of highways and sections dedicated to autonomous driving. Once the section S_AD is identified, the total distance L_AD can be calculated. The calculation of the total distance L_AD is performed by the processor 110 of vehicle 1. In the second example of the expansion process, the total distance L_AD is compared with the remaining range ML. If the result of this comparison determines that the total distance L_AD is greater than or equal to the remaining range ML, the expansion process is performed. The specific example of the expansion process is the same as that in the first example of the expansion process described above.

[0045] 5. Route configuration process In this embodiment, the route RTk setting process is performed. This route RTk is the route from the current location of vehicle 1 to the destination, as described in the second example of the expansion process. The route RTk setting process is performed by the management server 200 or the processor 110 of vehicle 1 based on the location information of the current location of vehicle 1 and the destination. The current location of vehicle 1 includes the storage location ST (when waiting for the provision of mobility services) and points along the route RTn (when mobility services are being provided). The destination of vehicle 1 includes points P1, P2 and storage location ST shown in Figure 3.

[0046] When the route RTk setting process is performed by the processor 110 of vehicle 1, at least two candidate route RTk Ck may be set. In this case, the total amount of log data LOG TQgn_Ck generated during vehicle 1's journey along each of these candidate Ck is predicted. Figure 6 is a diagram illustrating the total amount TQgn_Ck. Figure 6 shows candidate Ck1, Ck2, and Ck3 as candidate route RTk Ck. All of these candidates are three candidate route RTk from vehicle 1's current location CL to the destination DS. The time Tcl shown on the horizontal axis of Figure 6 represents the current time. The times T1, T2, and T3 represent the times when vehicle 1 will arrive at the destination DS, respectively, if vehicle 1 travels along candidate Ck1, Ck2, and Ck3.

[0047] The vertical axis in Figure 6 shows the amount of log data LOG generated per unit time, ΔQt_Ck. As shown in Figure 6, the amount of ΔQt_Ck differs among candidate Ck1 to Ck3. This is because at least some of the routes differ between candidate Ck1 to Ck3. If at least some of the routes differ, differences will occur in the frequency and difficulty of events that generate log data LOG (such as object recognition events, driving plan generation events, and control variable calculation events). Generally, the higher the frequency of events per unit time, the greater the amount of ΔQt_Ck generated. Also, the higher the difficulty of the events, the greater the amount of ΔQt_Ck generated.

[0048] The total amount of log data LOG TQgn_Ck1 generated while vehicle 1 is traveling along candidate Ck1 is represented by ∫ΔQt_Ck1dt, which is the sum of the generated amounts ΔQt_Ck1 from time Tcl to time T1. The total amount TQgn_Ck2 is represented by ∫ΔQt_Ck2dt, which is the sum of the generated amounts ΔQt_Ck2 from time Tcl to time T2. The total amount TQgn_Ck3 is represented by ∫ΔQt_Ck3dt, which is the sum of the generated amounts ΔQt_Ck3 from time Tcl to time T3.

[0049] In the route RTk configuration process, the future value QC_Ck(Tds) of the available capacity QC at the time of arrival at the destination DS (arrival time Tds) is calculated based on the total amount TQgn_Ck. The future value QC_Ck(Tds) can be expressed by the following equation (2) using the value of the available capacity QC at time Tcl (i.e., the current value) QC(Tcl). QC_Ck(Tds)=QC(Tcl)-∫ΔQt_Ckdt···(2)

[0050] In the route RTk setting process, the candidate Ck that maximizes the future value QC_Ck(Tds) calculated by equation (2) is selected as the route RTk. If the candidate Ck with the maximum future value QC_Ck(Tds) is selected, it is possible to prevent a situation where the available QC capacity becomes depleted on the way to the destination DS. In the example in Figure 6, the total amount QC_Ck2 is the smallest. Therefore, the candidate Ck that maximizes the future value QC_Ck(Tds) shown in equation (2) is candidate Ck2, and this will be selected as the route RTk. [Explanation of symbols]

[0051] 1...Vehicle, 10...Sensor group, 20...Recognition unit, 30...Planning unit, 40...Control quantity calculation unit, 50...Driving device, 100...Automated driving system, 110...Processor, 120...Storage device, 200...Management server, 220...Database, CL...Current location, DS...Destination, QC...Free space, RT,RT1~RT3,RTk,RTn...Route, US,US1,US2,USn...User, Ck...Route candidate, CON...Control quantity, LOG...Log data, RES...Recognition result information, SEN...Sensor detection information, TRJ...Target trajectory, ΔQt...Amount of log data LOG generated per unit time, TQst...Total amount of log data LOG in storage device 120, TQgn...Total amount of log data LOG generated while vehicle 1 is driving, QC(Tcl)...Current value of free space QC, QC_Ck(Tds)...Future value of free space QC

Claims

1. An autonomous driving system installed in a vehicle, One or more processors, One or more storage devices, Equipped with, The one or more processors described above are: Processing for automatic driving control of the aforementioned vehicle, During the execution of the automated driving control, the process includes saving log data related to the automated driving control to one or more storage devices, A process for predicting the cruising range of the vehicle, It is configured to do the following: In the process of predicting the cruising range, the one or more processors The free space of the one or more storage devices where the log data is stored is obtained, The cruising range is set according to the available capacity. It is configured in such a way, The aforementioned cruising range is set to a shorter distance the less available capacity there is. An autonomous driving system characterized by the following features.

2. An automated driving system according to claim 1, The one or more processors further include: If the cruising range set according to the available capacity is less than or equal to a predetermined distance, the system is configured to perform a process to increase the available capacity. An autonomous driving system characterized by this feature.

3. An automated driving system according to claim 1, The one or more storage devices mentioned above store location information of the vehicle's current location and destination. The one or more processors further include: Based on the location information of the current location and the destination, the process calculates the total distance of the sections that constitute the route from the current location to the destination, in which the automatic driving control can be executed. If the total distance is greater than or equal to the cruising range set according to the available capacity, the system is configured to perform a process to increase the available capacity. An autonomous driving system characterized by the following features.

4. An automated driving system according to claim 1, The one or more storage devices mentioned above store location information of the vehicle's current location and destination. The one or more processors further include: Based on the location information of the current location and the destination, a process is performed to set a route from the current location to the destination. In the process of setting the route, the one or more processors Set at least two candidate routes, The total amount of log data generated while the vehicle is traveling along each of the candidate routes is predicted. Based on the total amount of log data predicted for each of the candidate routes, the future value of the free space in the one or more storage devices upon arrival at the destination of each candidate route is predicted. From among the candidate routes, the route that maximizes the future value of the available capacity is selected as the route. An autonomous driving system characterized by the following features.

Images