Automatic driving system

Abstract

The invention relates to an automatic driving system. In a vehicle that performs automatic driving control using a machine learning model, a situation in which the spare capacity of a storage device of the vehicle for storing log data associated with the automatic driving control is insufficient is avoided in advance. Performing a process for automatic driving control of the vehicle; a process for storing log data relating to the automatic driving control in one or more storage devices during execution of the automatic driving control; and performing a process of predicting the cruising distance of the vehicle. In the process of predicting the cruising distance, the spare capacity of one or more storage devices for storing log data is acquired. In addition, the cruising distance is set according to the acquired spare capacity. The smaller the acquired spare capacity is, the shorter the cruising distance is set.

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 an autonomous driving technology has been promoted, which uses a model generated by machine learning (machine learning model) to control the vehicle based on data from sensors mounted on the vehicle. In International Publication No. 2019 / 116423, a method for collecting training data for use in generating a machine learning model is proposed.

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

[0004] Prior art literature

[0005] Patent Literature

[0006] Patent Document 1: International Publication No. 2019 / 116423

[0007] Patent Document 2: Japanese Patent Application Publication No. 2011-113494

[0008] Patent Document 3: Japanese Patent Application Publication No. 2022-44235

[0009] Patent Document 4: Japanese Patent No. 6761002

[0010] It is desirable to verify the autonomous driving control of a vehicle using a machine learning model afterwards. As a method for achieving this verification, it is considered to store the log data associated with the autonomous 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, it is considered that when the amount of the log data reaches a certain amount or more, it is sent to the outside and deleted from the storage device. However, during the execution of the autonomous driving control, log data associated with the autonomous driving control is generated all the time. Therefore, when the free capacity of the storage device is tight due to the log data before being sent to the outside and the log data generated during the autonomous driving control, the latter log data may not be saved from the middle. Therefore, it is desirable to develop technology to avoid such a tight situation in advance. Summary of the invention

[0011] One object of the present disclosure is to provide a technology that can prevent in advance a situation in which free capacity of a storage device of a vehicle for storing log data associated with autonomous driving control using a machine learning model is running out.

[0012] The present disclosure is an automatic driving system mounted on a vehicle and has the following features.

[0013] The autonomous driving system includes one or more processors and one or more storage devices.

[0014] The one or more processors are configured to perform: processing for autonomous driving control of the vehicle; saving log data related to the autonomous driving control in the one or more storage devices during the execution of the autonomous driving control; and processing for predicting the vehicle's cruising range.

[0015] The one or more processors are configured to: obtain the free capacity of the one or more storage devices for storing the log data in the process of predicting the cruising range; and set the cruising range according to the free capacity. The smaller the free capacity, the shorter the cruising range is set.

[0016] Effects of the Invention

[0017] According to the present disclosure, the cruising range of the vehicle is predicted based on the free capacity of one or more storage devices. In addition, the less free capacity there is, the shorter the cruising range is set to. Therefore, the situation of tight free capacity can be avoided in advance. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 This is a block diagram showing a configuration example associated with automatic driving control of a vehicle according to an implementation manner.

[0019] Figure 2 This is a conceptual diagram showing an example of the configuration of an automatic driving system according to an implementation method.

[0020] Figure 3 This is a conceptual diagram of mobile services.

[0021] Figure 4 This is a diagram showing an example of the relationship between the duration of execution of the automatic driving control and the free capacity of the recording device.

[0022] Figure 5 This is a diagram for explaining a process of increasing the available capacity of a recording device.

[0023] Figure 6This is a diagram for explaining the total amount of log data generated while the vehicle is traveling along the candidate routes.

[0024] Description of Reference Numerals

[0025] 1: vehicle, 10: sensor group, 20: identification unit, 30: planning unit, 40: control amount calculation unit, 50: driving device, 100: automatic driving system, 110: processor, 120: storage device, 200: management server, CL: current location, DS: destination, QC: free capacity, RT, RT1~RT3, RTk, RTn: routes, US, US1, US2, USn: users, Ck: route candidates, CON: control amount, LOG: log data, RES: identification 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 the storage device 120, TQgn: total amount of log data LOG generated during driving of the vehicle 1, QC(Tcl): current value of free capacity QC, QC_Ck(Tds): future value of free capacity QC. DETAILED DESCRIPTION

[0026] 1. Autonomous driving of vehicles

[0027] Figure 1 1 is a block diagram showing an example of a configuration associated with the automatic driving control of the vehicle 1 of the present embodiment. Automatic driving refers to automatically performing at least one of steering, acceleration, and deceleration of the vehicle 1 without the aid of a driving operation performed by an operator. 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 can be either a driver riding in the vehicle 1 or a remote operator who remotely operates the vehicle 1.

[0028] The vehicle 1 includes a sensor group 10 , a recognition unit 20 , a planning unit 30 , a control variable calculation unit 40 , and a travel device 50 .

[0029] The sensor group 10 includes an identification sensor 11 for identifying the surrounding conditions of the vehicle 1. Examples of the identification sensor 11 include a camera, LIDAR (Laser Imaging Detection and Ranging), and a radar. In addition, the sensor group 10 may also include a state sensor 12 for detecting the state of the vehicle 1, a position sensor 13 for detecting the position of the vehicle 1, and the like. Examples of the state sensor 12 include a speed sensor, an acceleration sensor, a yaw rate sensor, and a steering angle sensor. Examples of the position sensor 13 include a GNSS (Global Navigation Satellite System) sensor.

[0030] The sensor detection information SEN is information obtained by the sensor group 10. For example, the sensor detection information SEN includes an image captured by a camera. As another example, the sensor detection information SEN may also include point group information obtained by LIDAR. The sensor detection information SEN may also include vehicle state information indicating the state of the vehicle 1. The sensor detection information SEN may also include position information indicating the position of the vehicle 1.

[0031] The recognition unit 20 receives the sensor detection information SEN. The recognition unit 20 recognizes the conditions 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 obtained 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 relative to the vehicle 1.

[0032] The planner 30 receives the recognition result information RES from the recognition unit 20. In addition, the planner 30 may also receive vehicle status 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 a plan for reaching a predetermined destination or a plan for avoiding risks. Examples of driving plans include maintaining the current driving lane, changing lanes, overtaking, turning right / 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.

[0033] The control amount calculation unit 40 receives the target trajectory TRJ from the planning unit 30. The control amount calculation unit 40 calculates the control amount CON required for the vehicle 1 to follow the target trajectory TRJ. The control amount CON can also be said to be a control amount requested in order 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. As the steering control amount, a target steering angle, a target torque, a target motor angle, a target motor drive current, etc. are exemplified. As the drive control amount, a target speed, a target acceleration, etc. are exemplified. As the braking control amount, a target speed, a target deceleration, etc. are exemplified.

[0034] The travel device 50 includes a steering device 51, a drive device 52, and a brake device 53. The steering device 51 steers the wheels. For example, the steering device 51 includes an electric power steering (EPS: Electric Power Steering) device. The drive device 52 is a power source that generates a driving force. As the drive device 52, an engine, an electric motor, an in-wheel motor, etc. are exemplified. The brake device 53 generates a braking force. The travel device 50 receives the control amount CON from the control amount calculation unit 40. The travel device 50 operates the steering device 51, the drive device 52, and the brake device 53 according to the steering control amount, the drive control amount, and the brake control amount, respectively. As a result, the vehicle 1 travels in a manner of following the target trajectory TRJ.

[0035] 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 rule group. As machine learning models, NN (Neural Network), SVM (Support Vector Machine), regression model, decision tree model, etc. are given as examples. NN can also be CNN (Convolutional Neural Network), RNN (Recurrent Neural Network) or a combination thereof. The type of each layer in NN, the number of layers, and the number of nodes are arbitrary. The machine learning model is pre-generated by machine learning. The recognition unit 20 performs recognition processing by inputting sensor detection information SEN into the model. Recognition result information RES is output from the model, or recognition result information RES is generated based on the output from the model.

[0036] The planning unit 30 also includes at least one of a rule-based model and a machine learning model. The planning unit 30 performs planning processing by inputting recognition result information RES to the model. The target trajectory TRJ is output from the model, or the target trajectory TRJ is generated based on the output from the model.

[0037] The control amount calculation unit 40 also includes at least one of a rule-based model and a machine learning model. The control amount calculation unit 40 performs control amount calculation processing by inputting the target trajectory TRJ into the model. The control amount CON is output from the model, or the control amount CON is generated based on the output from the model.

[0038] Two or more of the recognition unit 20, the planning unit 30, and the control amount calculation unit 40 may also be integrally configured. The recognition unit 20, the planning unit 30, and the control amount calculation unit 40 may all be integrally configured (end-to-end configuration). For example, the recognition unit 20 and the planning unit 30 may also be integrally configured by a NN that outputs a target trajectory TRJ based on the sensor detection information SEN. Even in the case of an integral configuration, an intermediate product such as the recognition result information RES and the target trajectory TRJ may be output. For example, in the case where the recognition unit 20 and the planning unit 30 are integrally configured by a NN, the recognition result information RES may be the output of an intermediate layer of the NN.

[0039] The recognition unit 20, the planning unit 30, and the control amount calculation unit 40 constitute an "autonomous driving control unit" that controls the autonomous driving of the vehicle 1. In this embodiment, a machine learning model is used for at least a part of the autonomous 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 autonomous driving control unit uses the machine learning model to perform at least a part of the autonomous driving control of the vehicle 1.

[0040] 2. Autonomous Driving System

[0041] Figure 2 1 is a conceptual diagram showing an example of the configuration of an automatic driving system 100 according to the present embodiment. The automatic driving system 100 is mounted on a vehicle 1 and performs automatic driving control of the vehicle 1. The automatic driving system 100 has at least the functions of the automatic driving control unit described above. Furthermore, the automatic driving system 100 may also include a sensor group 10 and a driving device 50.

[0042] 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. As the processor 110, a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), an ASIC (Application Specific Integrated Circuit), an FPGA (Field-Programmable Gate Array), etc. are exemplified. The recognition unit 20, the planning unit 30, and the control amount calculation unit 40 can be implemented by a single processor 110 or by different processors 110. The storage device 120 stores various information. As the storage device 120, an HDD (Hard Disk Drive), an SSD (Solid State Drive), a volatile memory, a non-volatile memory, etc. are exemplified.

[0043] The program 130 is a computer program for controlling the vehicle 1, and is executed by the processor 110. Various processes performed by the automatic driving system 100 can also be realized by the cooperation between the processor 110 executing the program 130 and the storage device 120. The program 130 is stored in the storage device 120. The program 130 can also be recorded in a computer-readable recording medium.

[0044] 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 the present 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.

[0045] During the process of autonomous driving control, the processor 110 obtains "log data LOG" associated with 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 also include the control amount CON output from the autonomous driving control unit. The log data LOG may also include the recognition result information RES output from the recognition unit 20. The log data LOG may also include the target trajectory TRJ output from the planning unit 30. The log data LOG may also include the reason for the judgment in the recognition processing implemented by the recognition unit 20. The log data LOG may also include the reason for the judgment in the planning processing implemented by the planning unit 30. The log data LOG may also include the presence or absence of operator intervention in the autonomous driving control.

[0046] 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 only during a certain period.

[0047] 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. Alternatively, during the process of autonomous driving control or after the end of autonomous driving control, the processor 110 of the vehicle 1 uploads 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 autonomous driving control using a machine learning model, etc. The processor 110 may also erase the log data LOG uploaded to the management server 200 from the local storage device 120.

[0048] 3. Endurance distance

[0049] In this embodiment, consider the case where one or more vehicles 1 are used for a mobile service. A mobile service is a service that uses a vehicle to transport people. Examples of mobile services include taxi services, bus services, and carpooling services. The management of mobile services is performed, for example, by a management server 200. The management of mobile services includes the management of vehicles 1 such as the storage and selection (scheduling) of vehicles 1 used for mobile services, and the management of users US of mobile services. The management of mobile services also includes the verification of the above-mentioned automatic driving control using the log data LOG.

[0050] Figure 3 This is a conceptual diagram of mobile services. Figure 3 1 depicts one of the one or more vehicles 1. The vehicle 1 transports a user US1 from a location P1 to a location P2 in response to a request from a user US1 of a mobile service.

[0051] When the vehicle 1 is to transport the user US1, the vehicle 1 departs from the storage place ST and goes to the place P1. The storage place ST is, for example, a base of a mobile service. The vehicle 1 that arrives at the place P1 picks up the user US1 at the place P1. The vehicle 1 that has picked up the user US1 goes from the place P1 to the place P2. The vehicle 1 that arrives at the place P2 drops off the user US1 at the place P2. The vehicle 1 that has dropped off the user US1 goes from the place P2 to the storage place ST. While going from the place P2 to the storage place ST, the vehicle 1 may also transport the user US2 in response to a request from a user US2 that is different from the user US1.

[0052] Consider a route RT1 starting from the storage location ST via the location P1 and the location P2 and returning to the storage location ST. While the vehicle 1 is traveling along a portion or all of the route RT1, the automatic driving control is performed. When the automatic driving control is performed, log data LOG is generated. The generated log data LOG is stored in the storage device 120 of the vehicle 1.

[0053] Here, during the execution of the automatic driving control, the log data LOG is continuously generated. Therefore, during the execution of the automatic driving control, the total amount TQst of the log data LOG in the storage device 120 is continuously increased. Figure 4 is a diagram showing an example of the relationship between the duration of execution of the automatic driving control and the free capacity QC. Figure 4 The horizontal axis shows the duration of the execution of the autonomous driving control. Figure 4 The vertical axis on the right shows the free capacity QC.

[0054] Moreover, in Figure 4 The vertical axis on the left shows the amount ΔQt_RT1 of log data LOG generated per unit time. When the automatic driving control is continued, the total amount TQst, which is the accumulated value of the amount ΔQt_RT1 generated, increases. As a result, the free capacity QC of the storage device 120 continues to decrease. As a result, when the free capacity QC is tight, the log data LOG may not be saved from the middle of the route RT1.

[0055] In view of this problem, in the present embodiment, the cruising distance (Milage) ML of the vehicle 1 is set. The cruising distance ML is set according to the free capacity QC. For example, the relationship between the distance traveled by executing the automatic driving control and the total amount TQgn of the log data LOG generated during the driving is calculated in advance. This relationship can be calculated by focusing on the driving history of one vehicle 1 or the driving history of multiple vehicles 1. If this relationship is used, the amount ΔQl of log data LOG generated per unit distance (for example, 1 km) can be calculated. The cruising distance ML can be calculated based on the following formula (1).

[0056] ML=QC / ΔQl……(1)

[0057] As a concept close to the cruising distance ML, there is a cruising distance DTE (Distance To Empty: remaining drivable distance). The cruising distance DTE is set based on the remaining amount of the battery that supplies power to the vehicle's driving source and the remaining amount of fuel. Therefore, the calculated value of the cruising distance DTE is basically different from the calculated value of the cruising distance ML. However, the vehicle 1 cannot move a distance exceeding the cruising distance DTE. Therefore, it is also possible to change the cruising distance ML when the cruising distance ML calculated based on formula (1) exceeds the cruising distance DTE. In this case, the value of the cruising distance DTE is set to the cruising distance ML.

[0058] The setting of the cruising distance ML is performed, for example, while the vehicle 1 is waiting for the provision of the mobile service in the storage place ST. When the cruising distance ML is set while waiting for the provision of the mobile service, the situation where the vacant capacity QC is tight can be avoided in advance. For example, a vehicle 1 having a cruising distance ML shorter than the distance L_RTn of the route RTn for transporting the user USn (n≥1) including the mobile service is excluded from the candidate for transporting the user USn in the selection performed by the management server 200.

[0059] In another example, the setting of the cruising range ML is performed during the provision of mobile services (for example, while the vehicle 1 is traveling along the route RTn). When the setting of the cruising range ML is performed during the provision of mobile services, the situation where the free capacity QC is tight can also be avoided in advance. However, in this case, the cruising range ML decreases as the free capacity QC decreases, so the execution of the automatic driving control is restricted or terminated. During the period when the execution of the automatic driving control is restricted or terminated, manual driving is performed by the operator of the vehicle 1, for example. For example, when the cruising range ML is reduced to a specified distance THml (described later), switching from automatic driving control to manual driving is triggered by a request generated by the processor 110.

[0060] 4. Expansion of spare capacity

[0061] 4-1. The first example

[0062] In the present embodiment, when the cruising range ML set based on the free capacity QC is less than or equal to the predetermined distance THml, the free capacity QC may be increased. Figure 5 This is a diagram for explaining the expansion process of the free capacity QC. Figure 4 As explained above, when the automatic driving control is continued, the free capacity QC will continue to decrease. Figure 4The generation amount ΔQt_RT1 shown may vary depending on the location, time, surrounding environment, scene, etc. Therefore, if the situation where the reduction rate of the available capacity QC is high continues, the available capacity QC will be tight.

[0063] Therefore, in the first example, the cruising range ML is compared with the prescribed distance THml. This comparison can be performed while providing the mobile service or while waiting for the provision. If the result of the comparison is that the cruising range ML is determined to be less than or equal to the prescribed distance THml, an expansion process is performed. Figure 5 2 shows an example of the transition of the free capacity QC when the expansion process is performed in the provision of the mobile service. In the expansion process, for example, the log data LOG sent to the management server 200 among the log data LOG in the storage device 120 is compressed and stored in the storage device 120. In another example, the log data LOG sent to the management server 200 is deleted from the storage device 120.

[0064] The prescribed distance THml can be either a fixed value or set based on the route RTn. In the case of setting based on the route RTn, for example, the average value of the total amount TQgn of the log data LOG generated in the past travel of the route RTn is used. As for the average value of the total amount TQgn, for example, the management server 200 refers to the travel history of one or more vehicles 1 to extract the same or similar route as the route RTn. Then, the average value is calculated based on the total amount TQgn of the log data LOG generated in the travel of the extracted route. The prescribed distance THml is set by adding a margin to the average value. The information of the prescribed distance THml set in this way is sent to the vehicle 1 that provides the mobile service for the user USn.

[0065] 4-2. Second example

[0066] In a second example of the expansion process, the total distance L_AD of the interval S_AD in which the automatic driving control can be performed in the interval S_RTk constituting the route RTk (1≤k≤n) from the current location of the vehicle 1 to the destination may be calculated. At least one of the processing of setting the route RTk and determining the interval S_AD is performed by the management server 200 or the processor 110 of the vehicle 1 based on the location information of the current location and the destination of the vehicle 1. The current location of the vehicle 1 includes a storage place ST (when waiting for the provision of mobile services) and a location halfway along the route RTn (when providing mobile services). The destination of the vehicle 1 includes Figure 3 The location P1, the location P2, and the storage location ST are shown. It should be noted that the location information of the current location and the destination is included in the various information stored in the storage device 120.

[0067] As the section S_AD, a section of a highway, a section dedicated to automatic driving, etc. are exemplified. If the section S_AD is determined, the total distance L_AD can be calculated. The calculation of the total distance L_AD is performed by the processor 110 of the vehicle 1. In the second example of the expansion process, the total distance L_AD is compared with the cruising distance ML. When the result of the comparison is that the total distance L_AD is determined to be greater than or equal to the cruising distance ML, the expansion process is performed. The specific example of the expansion process is the same as the specific example in the first example of the expansion process described above.

[0068] 5. Route setting process

[0069] In this embodiment, a process of setting a route RTk is performed. The route RTk is a route from the current location of the vehicle 1 to the destination described in the second example of the expansion process. The process of setting the route RTk is performed by the management server 200 or the processor 110 of the vehicle 1 based on the location information of the current location of the vehicle 1 and the destination. The current location of the vehicle 1 includes a storage place ST (when waiting for the provision of mobile services) and a location halfway along the route RTn (when providing mobile services). The destination of the vehicle 1 includes Figure 3 The location P1, location P2 and storage location ST are shown.

[0070] When the process of setting the route RTk is performed by the processor 110 of the vehicle 1, at least two candidates Ck of the route RTk may be set. In this case, the total amount TQgn_Ck of the log data LOG generated when the vehicle 1 travels along these candidates Ck is predicted respectively. Figure 6 This is a diagram for explaining the total amount TQgn_Ck. Figure 6 , candidate Ck1, candidate Ck2, and candidate Ck3 are depicted as candidates Ck of the route RTk. These candidates are three candidates of the route RTk from the current location CL of the vehicle 1 to the destination DS. Figure 6 The time Tcl shown on the horizontal axis of represents the current time. In addition, the time T1, the time T2, and the time T3 represent the time when the vehicle 1 arrives at the destination DS when the vehicle 1 travels along the candidate Ck1, the candidate Ck2, and the candidate Ck3, respectively.

[0071] exist Figure 6 The vertical axis shows the amount of log data LOG generated per unit time ΔQt_Ck. Figure 6As shown, the amount ΔQt_Ck generated is different between candidate Ck1 to candidate Ck3. The reason is that at least a part of the route is different between candidate Ck1 to candidate Ck3. If at least a part of the route is different, the frequency and difficulty of the events (object recognition event, driving plan generation event, control amount calculation event, etc.) that generate log data LOG will be different. Generally speaking, the higher the frequency of events per unit time, the more ΔQt_Ck is generated. In addition, the higher the difficulty of the event, the more ΔQt_Ck is generated.

[0072] The total amount TQgn_Ck1 of the log data LOG generated while the vehicle 1 travels along the candidate Ck1 is represented by a value ∫ΔQt_Ck1dt obtained by integrating the amount ΔQt_Ck1 generated from the time Tcl to the time T1. The total amount TQgn_Ck2 is represented by a value ∫ΔQt_Ck2dt obtained by integrating the amount ΔQt_Ck2 generated from the time Tcl to the time T2. The total amount TQgn_Ck3 is represented by a value ∫ΔQt_Ck3dt obtained by integrating the amount ΔQt_Ck3 generated from the time Tcl to the time T3.

[0073] In the process of setting the route RTk, the future value QC_Ck(Tds) of the free capacity QC at the time of arrival at the destination DS (arrival time Tds) is also calculated based on the total amount TQgn_Ck. The future value QC_Ck(Tds) can be calculated by the following formula (2) using the value (that is, the current value) QC(Tcl) of the free capacity QC at the time Tcl.

[0074] QC_Ck(Tds)=QC(Tcl)-∫ΔQt_Ckdt……(2)

[0075] In the process of setting the route RTk, the candidate Ck with the largest future value QC_Ck(Tds) calculated by equation (2) is selected as the route RTk. If the candidate Ck with the largest future value QC_Ck(Tds) is selected, the situation where the available capacity QC is tight on the way to the destination DS can be avoided in advance. Figure 6 In the example, the total amount QC_Ck2 is the smallest. Therefore, the candidate Ck for which the future value QC_Ck(Tds) shown in equation (2) becomes the largest is candidate Ck2, and candidate Ck2 is selected as route RTk.

Claims

1. An automatic driving system, mounted on a vehicle, wherein the automatic driving system is characterized by comprising: one or more processors; and one or more storage devices, The one or more processors are configured to: processing for autonomous driving control of said vehicle; During the execution of the autonomous driving control, log data related to the autonomous driving control is stored in the one or more storage devices; as well as Processing for predicting the cruising range of the vehicle, The one or more processors are configured to: In the process of predicting the cruising range, Acquire the free capacity of the one or more storage devices for storing the log data; as well as The cruising range is set according to the free capacity. The smaller the free capacity is, the shorter the cruising distance is set to be.

2. The automatic driving system according to claim 1, characterized in that: The one or more processors are further configured to: When the cruising range set according to the spare capacity is less than or equal to a predetermined distance, a process of increasing the spare capacity is performed.

3. The automatic driving system according to claim 1, characterized in that: The one or more storage devices store the location information of the current location and destination of the vehicle. The one or more processors are further configured to: A process of calculating, based on the position information of the current location and the destination, a total distance of a section constituting a route from the current location to the destination in which the automatic driving control can be performed; as well as When the total distance is greater than or equal to the cruising range set according to the available capacity, the available capacity is increased.

4. The automatic driving system according to claim 1, characterized in that: The one or more storage devices store the location information of the current location and destination of the vehicle. The one or more processors further perform processing to set a route from the current location to the destination based on the location information of the current location and the destination, The one or more processors are configured to: In the process of setting the route, setting at least two candidates for the route; Predicting a total amount of the log data generated during each candidate travel of the vehicle along the route; Based on the total amount of the log data predicted for each candidate of the route, predicting the future value of the free capacity in the one or more storage devices when the candidate of the route arrives at the destination; as well as A route candidate having a maximum future value of the available capacity is selected from among the route candidates as the route.

Images