Autonomous driving system

Abstract

To provide an automatic driving system capable of ensuring storage of log data used for post-verification of a calculation result of automatic driving control.SOLUTION: An automatic driving system 100 stores output data about automatic driving control in a storage part 7 of a vehicle 1, the output data calculated based on a result detected by a sensor 2 of the vehicle 1. The automatic driving system 100 comprises: a log acquisition part for associating the output data and a driving scene where the output data is calculated, and acquiring them as log data; an influence degree acquisition part for acquiring a preset influence degree at which the driving scene gives influence to the periphery of the vehicle 1 based on the driving scene; and a log storage part for storing the log data in the storage part 7 of the vehicle 1 at a priority degree according to the influence degree of the driving scene associated with the log data.SELECTED DRAWING: Figure 1

Description

Technical Field

[0001] The present disclosure relates to an automatic driving system.

Background Art

[0002] There is known a technique of assigning a label according to whether a vehicle has performed an avoidance operation on external environment information collected by a camera or the like mounted on the vehicle (for example, International Publication No. 2019 / 116423).

Prior Art Document

Patent Document

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In an automatic driving system, automatic driving control calculations are performed based on the detection results of in-vehicle sensors. For post-verification of the calculation results of automatic driving control, it is conceivable to collect and store output data related to automatic driving control during vehicle operation as log data. However, when the output data becomes large, it may not be possible to store all the log data in the vehicle's memory, which may hinder the collection of log data.

[0005] An object of the present disclosure is to provide an automatic driving system capable of ensuring the storage of log data used for post-verification of the calculation results of automatic driving control.

Means for Solving the Problems

[0006] One aspect of the present disclosure is an autonomous driving system that stores output data related to autonomous driving control calculated based on detection results of on-board sensors of a vehicle in a storage unit of the vehicle, comprising: a log acquisition unit that associates the output data with the driving scene from which the output data was calculated and acquires it as log data; an influence acquisition unit that acquires a preset influence level that the driving scene has on the surroundings of the vehicle based on the driving scene; and a log storage unit that stores the log data in the storage unit of the vehicle with a priority according to the influence level of the driving scene associated with the log data.

[0007] In an automated driving system according to one aspect of this disclosure, log data, in which output data and driving scenes are associated with each other, is stored in the vehicle's memory with priority according to the degree of influence of the driving scene. For example, by prioritizing the storage of log data corresponding to driving scenes that have a large impact on the surroundings of the vehicle in the vehicle's memory, useful log data can be effectively collected. Therefore, according to an automated driving system according to one aspect of this disclosure, the storage of log data used for post-verification of the calculation results of automated driving control can be made more reliable.

[0008] In one embodiment, the autonomous driving system includes a capacity shortage prediction unit that predicts a future capacity shortage of the vehicle's memory based on the time required for autonomous driving control to the vehicle's destination and road conditions. The log storage unit may store log data in the vehicle's memory with priority according to the degree of impact when a capacity shortage of the vehicle's memory is predicted. For example, if the vehicle's memory becomes insufficient, it may fail to record log data corresponding to driving scenes that have a significant impact on the vehicle's surroundings. Therefore, by storing log data in the vehicle's memory with priority according to the degree of impact when a capacity shortage of the vehicle's memory is predicted, the reliability of storing log data corresponding to driving scenes that have a significant impact on the vehicle's surroundings can be ensured.

[0009] In one embodiment, the autonomous driving system includes an external storage unit that stores log data transmitted from the vehicle via a network, and a communication unit provided in the vehicle that communicates with the external storage unit. The log storage unit may transmit log data to the external storage unit and delete the transmitted log data from the vehicle's storage unit. In this case, by storing the log data in the external storage unit and deleting the log data from the vehicle's storage unit, it is possible to ensure the reliable storage of log data while suppressing insufficient storage capacity in the vehicle's storage unit. [Effects of the Invention]

[0010] According to this disclosure, it is possible to ensure the reliable storage of log data used for post-verification of calculation results of autonomous driving control. [Brief explanation of the drawing]

[0011] [Figure 1] This is a schematic block diagram illustrating the configuration of an automated driving system according to the embodiment. [Figure 2] Figure 1 is a schematic block diagram illustrating the configuration of a vehicle in an autonomous driving system. [Figure 3] Figure 1 is a flowchart illustrating the processing of the ECU. [Modes for carrying out the invention]

[0012] The following describes exemplary embodiments with reference to the drawings. In the following description, the same or equivalent elements will be denoted by the same reference numerals, and redundant descriptions may be omitted.

[0013] As shown in Figures 1 and 2, the automated driving system 100 according to this embodiment is a system that performs automated driving of vehicle 1. Vehicle 1 is not particularly limited and may be a passenger car or a cargo vehicle. Vehicle 1 is an automated driving vehicle capable of automated driving. Vehicle 1 may also be capable of manual driving by a driver.

[0014] The autonomous driving system 100 stores output data related to autonomous driving control, calculated based on the detection results of the vehicle's onboard sensors, in the vehicle's memory unit. The autonomous driving system 100 includes sensors 2, a map database 3, a GNSS receiver 4, an actuator 5, a communication unit 6, a memory unit 7, and an ECU [Electronic Control Unit] 10.

[0015] Sensor 2 is an on-board sensor that detects information regarding at least one of the driving state of vehicle 1 and the surrounding conditions. Sensor 2 includes an external sensor and an internal sensor. The external sensor is a sensor that acquires information about the surrounding environment of vehicle 1. The external sensor includes at least one of, for example, a camera, millimeter-wave radar, or LiDAR (Light Detection and Ranging). The internal sensor is a detection device that detects the driving state of vehicle 1. The internal sensor includes at least one of, for example, a vehicle speed sensor, an acceleration sensor, and a yaw rate sensor. Sensor 2 transmits the detection results to ECU 10.

[0016] Map database 3 is a storage device that stores map information. Map database 3 is formed in a storage medium such as an HDD (Hard Disk Drive) installed in vehicle 1. Map information includes information such as the location and shape of roads, intersections, and junctions (for example, the location and shape of intersections, lane widths, lane markings, and pedestrian crossings). Map information may also include information on structures (such as the location and type of traffic lights at intersections) and various traffic rule information (such as information on one-way streets, no right or left turns, and no U-turns). Note that some of the map information included in map database 3 may be stored in a storage device other than an HDD. Map database 3 may also be formed in a computer at a facility such as a management center that can communicate with vehicle 1.

[0017] The GNSS receiver 4 measures the current position of vehicle 1 (for example, the latitude and longitude of vehicle 1) by receiving signals from positioning satellites. The GNSS receiver 4 transmits the measured position information of vehicle 1 to the ECU 10.

[0018] The actuator 5 is a controller for controlling the running of the vehicle 1. The actuator 5 may include, for example, an actuator for controlling the output of an engine or a motor, or a brake actuator, in order to control the speed of the vehicle 1. The actuator 5 may include, for example, a steering actuator for controlling the steering angle or the steering torque, in order to control the steering of the vehicle 1.

[0019] The communication unit 6 is a communication device for controlling wireless communication with the outside of the vehicle 1. The communication unit 6 communicates various information with, for example, a server for an automatic driving system (external storage unit) 50 via a communication network N. The communication unit 6 communicates various information with, for example, other vehicles (external storage unit) 20 around the vehicle 1 via the communication network N. The communication unit 6 is not particularly limited, and various known communication devices can be used.

[0020] The storage unit 7 stores log data for use in post-verification of the calculation results of automatic driving control. The storage unit 7 is mounted on the vehicle 1. The storage unit 7 is, for example, a recording device such as an HDD mounted on the vehicle 1. The storage unit 7 has a log storage area for storing log data. The log storage area has a finite capacity. The log data will be described in detail later.

[0021] The ECU 10 is an electronic control unit having a CPU [Central Processing Unit], a ROM [Read Only Memory], a RAM [Random Access Memory], etc. The ECU 10 realizes various functions by, for example, loading a program recorded in the ROM into the RAM and executing the program loaded into the RAM with the CPU. The ECU 10 may be composed of a plurality of electronic control units. As a functional configuration, the ECU 10 has an automatic driving processing unit 11, a log acquisition unit 12, an influence degree acquisition unit 13, a capacity shortage prediction unit 14, and a log storage unit 15.

[0022] The automatic driving processing unit 11 executes automatic driving control based on the detection results of the sensor 2. The automatic driving processing unit 11 calculates output data related to automatic driving control based on the detection results of the sensor 2, the map information, and the vehicle position. The output data is calculated in the ECU 10 and output to the actuator 5, and is data for performing automatic driving. The output data includes, for example, data for controlling at least one of driving, braking, and steering of the vehicle 1.

[0023] As an example, the automatic driving processing unit 11 calculates output data related to automatic driving control using the machine learning model 11a. The automatic driving processing unit 11, for example, inputs the detection results of the sensor 2 into the machine learning model 11a, and outputs the control signal obtained thereby to the actuator 5, thereby controlling the driving, braking, and steering of the vehicle 1 to perform automatic driving.

[0024] The machine learning model 11a is a recursive deep learning model. The machine learning model 11a is a recursive neural network [RNN: Recurrent neural network]. A convolutional neural network [CNN: Convolutional Neural Network] including a plurality of layers including a plurality of convolutional layers and pooling layers may be used for at least a part of the neural network. In the machine learning model 11a, deep learning by deep learning is performed. The machine learning model 11a is a learned model learned using data of the vehicle 1 under predetermined learning conditions. For example, the machine learning model 11a may be learned using teacher data for the output to the actuator 5 when various detection results of the sensor 2 are input, for example.

[0025] The log acquisition unit 12 identifies the driving scene when the automated driving processing unit 11 calculates the output data based on the detection results of the vehicle's sensor 2, map information, and vehicle position. A driving scene refers to the driving conditions of vehicle 1. A driving scene includes, for example, the road shape of the road on which vehicle 1 is traveling (straight road shape, curved shape, etc.), the situation of other vehicles around vehicle 1, and the progress of vehicle 1. Examples of driving scenes include lane changes, right and left turns at intersections, approach of emergency vehicles, passing through construction sites, driving in traffic jams, and driving in bad weather. Bad weather refers to, for example, rain, snow, and fog.

[0026] The log acquisition unit 12 associates the calculated driving scene with the output data and acquires it as log data. The log data includes, for example, the output data for each driving scene as a set of time-series data. In the log data, the output data is basically compressed. Compression of the output data is not essential for the log data. The log acquisition unit 12 calculates the amount of data for each driving scene as the memory capacity required to store one event.

[0027] The impact acquisition unit 13 acquires the degree of impact that a driving scene has on the surroundings of vehicle 1, for example, based on the driving scene identified by the log acquisition unit 12. The impact degree represents the possibility of traffic safety impacts, risks, or nuisances occurring to other vehicles. The impact degree is preset according to the driving scene in which vehicle 1 may be placed. The impact degree may be set so that a larger impact value is more important in the post-verification of the calculation results of the automatic driving control. For example, the impact degree of turning right or left at an intersection may be greater than the impact degree of changing lanes. The impact degree of turning right or left at an intersection with pedestrians or oncoming vehicles may be greater than the impact degree of turning right or left at an intersection without pedestrians or oncoming vehicles. The impact degree may be stored in the ECU 10 or acquired from outside vehicle 1 via the communication unit 6.

[0028] The capacity shortage prediction unit 14 predicts a future capacity shortage of the storage unit 7 of vehicle 1 based on the time required for automated driving control of vehicle 1 to its destination and the road conditions. A capacity shortage of storage unit 7 means a state in which the remaining capacity of storage unit 7 becomes so small that log data cannot be stored in storage unit 7, hindering the collection of log data. For example, the capacity shortage prediction unit 14 predicts a future capacity shortage of the storage unit 7 of vehicle 1 by comparing the difference between the current remaining capacity of storage unit 7 and an estimated value of the amount of log data with a predetermined capacity shortage threshold.

[0029] The estimated amount of log data is an estimate of the amount of log data used to predict future capacity shortages in the storage unit 7 of vehicle 1. The estimated amount of log data is set in advance for each driving scene, for example, based on the amount of data for each driving scene (storage capacity required to store one event) acquired in past tests or simulations. The estimated amount of log data may also be calculated or corrected in real time for each driving scene based on the amount of data for each driving scene (storage capacity required to store one event) acquired in the past by the log acquisition unit 12. For log data of regular driving scenes acquired as a routine at regular intervals, the estimated amount of log data may be calculated according to the time of automatic driving control to the destination and the average amount of log data.

[0030] The capacity shortage threshold is a threshold value for the remaining capacity of the storage unit 7 of vehicle 1, used to determine whether a future capacity shortage of the storage unit 7 is predicted. The capacity shortage threshold may be a preset parameter or may be adjusted in real time. The capacity shortage threshold can be set to different values ​​based on road conditions for each driving scenario. The capacity shortage threshold may also be adjusted according to the type of road.

[0031] Depending on the type of road, the estimated amount of log data tends to be larger for intersections and smaller for straight roads. The estimated amount of log data tends to be larger when traffic volume is high. The estimated amount of log data tends to be larger when the log data includes multiple driving scenes. The estimated amount of log data tends to be larger on general roads other than expressways compared to expressways. This is because expressways have a simple structure, a defined direction of travel, and a low possibility of sudden changes in vehicle behavior. Therefore, the capacity shortage threshold may be set to a larger value compared to other road types, for example, in road types where the average amount of log data tends to be larger compared to other road types, in line with this trend.

[0032] The capacity shortage threshold may be adjusted based on the frequency of near-miss incidents. For example, in road conditions where near-miss incidents are likely to occur, the capacity shortage threshold may be set to a larger value compared to road conditions where near-miss incidents are less likely to occur, because the amount of log data for non-routine events tends to increase. A near-miss incident refers to an event that was not anticipated in advance for each driving scenario. Specific examples of road conditions where near-miss incidents are likely to occur include junctions, merging points, and narrow roads. This is because on narrow roads, there is a risk of pedestrians suddenly appearing, and the distance to other road participants tends to be closer.

[0033] The log storage unit 15 stores log data in the storage unit 7 of the vehicle 1. For example, if a future capacity shortage of the storage unit 7 of the vehicle 1 is predicted, the log storage unit 15 stores log data in the storage unit 7 of the vehicle 1 with priority according to the degree of impact of the driving scene associated with the log data. However, if a future capacity shortage of the storage unit 7 of the vehicle 1 is not predicted, the log storage unit 15 may store log data in the storage unit 7 of the vehicle 1 regardless of the degree of impact the driving scene has on the surroundings of the vehicle 1.

[0034] The log storage unit 15 may transmit log data to the external storage unit via the communication unit 6 if it is possible to use the external storage unit when a future capacity shortage of the storage unit 7 of the vehicle 1 is anticipated. In this case, the log storage unit 15 may delete the transmitted log data from the storage unit 7 of the vehicle 1 that was stored in the storage unit 7 of the vehicle 1. The log storage unit 15 does not need to store log data acquired by the log acquisition unit 12 and transmitted without being stored in the storage unit 7 of the vehicle 1.

[0035] The log storage unit 15 may determine whether or not the external storage unit can be used based on the communication quality of the communication network N. The log storage unit 15 may use, for example, radio wave strength or the transmission frame rate obtained in conjunction with the transmission of images, etc., as the communication quality of the communication network N. Alternatively, the log storage unit 15 may determine whether or not the external storage unit can be used based on the remaining capacity of the external storage unit.

[0036] As an example of an external storage unit, an automated driving system server 50 may be used. The automated driving system server 50 is a server that can communicate with the vehicle 1. The automated driving system server 50 includes a communication unit 51, a storage unit 52, and an analysis event DB 53. The communication unit 51 communicates various information with the vehicle 1, for example, via a communication network N. The communication unit 51 is not particularly limited, and various known communication devices can be used.

[0037] The storage unit 52 stores log data for use in post-verification of the calculation results of the automated driving control. The storage unit 52 is, for example, a recording device such as an HDD provided in the automated driving system server 50. The storage unit 52 has a log storage area for storing log data. That is, the automated driving system server 50 functions as an external storage unit that stores log data transmitted from the vehicle 1 via the communication network N. The log storage area has a finite capacity.

[0038] The analysis event DB 53 is a storage device that stores analysis information. The analysis event DB 53 is formed, for example, in a recording device such as an HDD installed in the server 50 for the automated driving system. The analysis information includes information on whether or not an analysis is performed to verify the calculation results of automated driving control using log data, and information on the analysis results.

[0039] Another example of an external storage unit is another vehicle 20. Another vehicle 20 is a vehicle in the vicinity of vehicle 1 that is within communication range of vehicle 1. Another vehicle 20 comprises an ECU 21, a communication unit 22, and a storage unit 23. The ECU 21 is an electronic control unit that performs processing related to communication with vehicle 1 and storage of log data in the other vehicle 20. The communication unit 22 communicates various information with vehicle 1, for example, via a communication network N. The communication unit 22 is not particularly limited, and various known communication devices can be used.

[0040] The storage unit 23 stores log data for use in post-verification of the calculation results of the automated driving control. The storage unit 23 is, for example, a recording device such as an HDD provided in the automated driving system server 50. The storage unit 23 has a log storage area for storing log data. That is, the other vehicle 20 functions as an external storage unit that stores log data transmitted from vehicle 1 via the communication network N. The log storage area has a finite capacity.

[0041] If the log storage unit 15 can determine, based on the analysis information in the analysis event DB 53, that the log data acquired by the log acquisition unit 12 is an event that has already been analyzed using log data already stored in the automated driving system server 50 or other vehicles 20, then the log storage unit 15 does not need to store the log data acquired by the log acquisition unit 12 in the storage unit 7 of vehicle 1. In this case, the log storage unit 15 may store in the storage unit 7 any information from the log data acquired by the log acquisition unit 12 that is specific to vehicle 1.

[0042] Based on the analysis information in the analysis event DB 53, the log storage unit 15 may determine that the log data acquired by the log acquisition unit 12 is an unanalyzed event using log data already stored in the automated driving system server 50 or other vehicle 20. In such cases, the log storage unit 15 may store all of the log data acquired by the log acquisition unit 12 in the storage unit 7 or external storage unit.

[0043] Information specific to vehicle 1 may include, for example, information regarding the specifications of vehicle 1, calculation results by the machine learning model 11a, and control instruction values ​​for the actuator 5. Information specific to vehicle 1 may also include difference data between log data already stored in the autonomous driving system server 50 or other vehicle 20 and log data acquired by the log acquisition unit 12. Information specific to vehicle 1 may also include data based on the detection results of on-board sensors of a type not provided by other vehicle 20, among the detection results of sensor 2.

[0044] The log storage unit 15 may also use the storage device of an information processing terminal held by the occupants of vehicle 1 as an external storage unit to store the log data acquired by the log acquisition unit 12 for backup purposes.

[0045] Next, the processing of the ECU 10 will be explained with reference to Figure 3. Figure 3 is a flowchart showing an example of the log storage processing of the ECU. The flowchart shown in Figure 3 is repeatedly executed at predetermined intervals, for example, each time the automatic driving processing unit 11 calculates a certain amount of output data during the automatic driving of vehicle 1.

[0046] As shown in Figure 3, the ECU 10, in step S11, acquires log data using the log acquisition unit 12. The automatic driving processing unit 11 calculates output data related to automatic driving control based on the detection results of the vehicle 1's sensor 2, for example, using a machine learning model 11a. The log acquisition unit 12 identifies the driving scene at the time the output data was calculated, based on the detection results of the vehicle 1's sensor 2, map information, and vehicle position. The log acquisition unit 12 associates the driving scene from which the output data was calculated with the output data and acquires it as log data.

[0047] In S12, the ECU 10 acquires the impact level using the impact level acquisition unit 13. The impact level acquisition unit 13 acquires a preset impact level that a driving scene has on the surroundings of the vehicle 1, for example, based on the driving scene identified by the log acquisition unit 12.

[0048] In S13, the ECU 10 uses a capacity shortage prediction unit 14 to predict future capacity shortages in the vehicle 1's memory unit 7. The capacity shortage prediction unit 14 predicts future capacity shortages in the vehicle 1's memory unit 7 based on the time required for automatic driving control to the vehicle 1's destination and the road conditions.

[0049] In S14, the ECU 10 uses the log storage unit 15 to determine whether or not a future capacity shortage of the vehicle 1's storage unit 7 is predicted. The log storage unit 15 determines, for example, whether or not a future capacity shortage of the vehicle 1's storage unit 7 is predicted based on a comparison between the future capacity of the vehicle 1's storage unit 7 estimated by the capacity shortage prediction unit 14 and a predetermined capacity threshold.

[0050] If it is determined that no future capacity shortage is predicted for the storage unit 7 of vehicle 1 (S14: NO), the ECU 10 proceeds to the process in S15. In S15, the ECU 10 has the log storage unit 15 store the log data in the storage unit 7 of vehicle 1. The log storage unit 15 stores the log data in the storage unit 7 of vehicle 1, for example, regardless of the degree to which the driving scene affects the surroundings of vehicle 1. After that, the ECU 10 terminates the process shown in Figure 3.

[0051] On the other hand, if the ECU 10 determines that a future capacity shortage of the vehicle 1's storage unit 7 is predicted (S14: YES), it proceeds to the process in S16. In S16, the ECU 10 uses the log storage unit 15 to determine whether or not it is possible to communicate with the external storage unit. The log storage unit 15 determines, for example, whether or not it is possible to communicate with the automated driving system server 50 or other vehicles 20 around the vehicle 1, based on the communication quality information of the communication network N.

[0052] If it is determined that communication with the external storage unit is possible (S16: YES), the ECU 10 proceeds to the process in S17. In S17, the ECU 10 uses the log storage unit 15 to send log data to the external storage unit. The log storage unit 15 sends, for example, log data acquired by the log acquisition unit 12 and not stored in the storage unit 7 of vehicle 1, or log data stored in the storage unit 7 of vehicle 1, to the automated driving system server 50 or another vehicle 20. Subsequently, in S18, the ECU 10 uses the log storage unit 15 to delete the transmitted log data from the storage unit 7 of vehicle 1. For example, the log storage unit 15 deletes the log data transmitted in S17 from the storage unit 7 of vehicle 1 for log data stored in the storage unit 7 of vehicle 1. For log data acquired by the log acquisition unit 12 but not stored in the vehicle's storage unit 7, the log storage unit 15 can perform the S19 process to prevent it from being stored in the vehicle's storage unit 7, instead of deleting it from the vehicle's storage unit 7. After that, the process shown in Figure 3 is terminated.

[0053] On the other hand, if it is determined that communication with the external storage unit is not possible (S16: NO), the ECU 10 proceeds to the process in S19. In S19, the ECU 10 has the log storage unit 15 store the log data in the storage unit 7 of the vehicle 1 with priority according to the degree of impact. The log storage unit 15 stores the log data in the storage unit 7 of the vehicle 1 with priority according to the degree of impact of the driving scene associated with the log data. After that, the process shown in Figure 3 is terminated.

[0054] Here, a trained model generated by machine learning, such as machine learning model 11a, is not necessarily capable of achieving appropriate automated driving control in all driving scenarios. For example, if the surrounding environment of vehicle 1 changes, the inference results by the trained model may change. For instance, the appropriateness of the calculation results of automated driving control using the trained model may change depending on traffic conditions such as weather, time of day, and traffic volume. Therefore, in order to properly operate automated driving control using a trained model, a mechanism that allows for retrospective verification of the automated driving control is considered useful. For this reason, it is conceivable to collect log data used for retrospective verification of the calculation results of automated driving control. However, the log data of the calculation results of automated driving control can be enormous.

[0055] In this regard, as explained above, in the autonomous driving system 100, log data in which output data and driving scenes are associated with each other is stored in the storage unit 7 of the vehicle 1 with priority according to the degree of influence of the driving scene. For example, by prioritizing the storage of log data corresponding to driving scenes that have a large impact on the surroundings of the vehicle 1 in the storage unit 7 of the vehicle 1, useful log data can be effectively collected. Therefore, the autonomous driving system 100 makes it possible to ensure the reliable storage of log data used for post-verification of the calculation results of autonomous driving control.

[0056] The automated driving system 100 includes a capacity shortage prediction unit 14 that predicts a future capacity shortage of the storage unit 7 of the vehicle 1 based on the time required for automated driving control of the vehicle 1 to its destination and the road conditions. When a capacity shortage of the storage unit 7 of the vehicle 1 is predicted, the log storage unit 15 stores log data in the storage unit 7 of the vehicle 1 with priority according to the degree of impact. For example, if the storage unit 7 of the vehicle 1 runs out of capacity, it may fail to record log data corresponding to driving scenes that have a significant impact on the surroundings of the vehicle 1. Therefore, when a capacity shortage of the storage unit 7 of the vehicle 1 is predicted, the system stores log data in the storage unit 7 of the vehicle 1 with priority according to the degree of impact, thereby ensuring the reliable storage of log data corresponding to driving scenes that have a significant impact on the surroundings of the vehicle 1.

[0057] The autonomous driving system 100 includes an external storage unit (an autonomous driving system server 50 or another vehicle 20) that stores log data transmitted from the vehicle 1 via a communication network N, and a communication unit 6 provided in the vehicle 1 that communicates with the external storage unit. The log storage unit 15 transmits the log data to the external storage unit and deletes the transmitted log data from the storage unit 7 of the vehicle 1. In this way, by storing the log data in the external storage unit and deleting the log data from the storage unit 7 of the vehicle 1, it is possible to ensure the reliable storage of log data while suppressing insufficient capacity in the storage unit 7 of the vehicle 1.

[0058] [Differentiation] Although various exemplary embodiments have been described above, the examples are not limited to those described above, and various omissions, substitutions, and modifications may be made.

[0059] In the above embodiment, the log storage unit 15 stored log data in the storage unit 7 of the vehicle 1 with priority according to the degree of impact when a capacity shortage in the storage unit 7 of the vehicle 1 was predicted, but the embodiment is not limited to this example. Prediction of a capacity shortage in the storage unit 7 of the vehicle 1 may be omitted. The log storage unit 15 may also store log data in the storage unit 7 of the vehicle 1 with priority according to the degree of impact, regardless of the remaining capacity of the storage unit 7 of the vehicle 1.

[0060] In the above embodiment, the log storage unit 15 transmits log data to the external storage unit and deletes the transmitted log data from the storage unit 7 of the vehicle 1, but the example is not limited to this. It is not essential for the log storage unit 15 to use the external storage unit.

[0061] In the above embodiment, the automated driving system 100 calculated output data related to automated driving control using a machine learning model 11a, but the use of a machine learning model is not essential.

[0062] The capacity shortage prediction unit 14 may determine whether or not a capacity shortage is predicted when setting the route for automated driving. If a capacity shortage is predicted, the capacity shortage prediction unit 14 may notify the occupants of vehicle 1 using the HMI of vehicle 1 or the like. The capacity shortage prediction unit 14 may notify the occupants of vehicle 1 using the HMI of vehicle 1 or the like to stop vehicle 1 for a certain period of time. The capacity shortage prediction unit 14 may notify the occupants of vehicle 1 using the HMI of vehicle 1 or the like to manually operate vehicle 1 for a certain period of time. The certain period of time may be, for example, the time until a capacity shortage in the storage unit 7 is no longer predicted after the log storage unit 15 performs the log data transmission and deletion process to the external storage unit (S17 and S18 above). The log storage unit 15 may be configured to transmit log data to the external storage unit by manual operation using the HMI of vehicle 1 or the like.

[0063] The log acquisition unit 12 may be configured to acquire log data only when a predetermined event occurs. [Explanation of symbols]

[0064] 1...Vehicle, 6...Communication unit, 7...Storage unit, 12...Log acquisition unit, 13...Impact acquisition unit, 14...Capacity shortage prediction unit, 15...Log storage unit, 20...Other vehicles (external storage unit), 50...Server for autonomous driving system (external storage unit), 100...Autonomous driving system.

Claims

1. An automated driving system that stores output data related to automated driving control, calculated based on the detection results of the vehicle's onboard sensors, in the vehicle's memory unit, A log acquisition unit that associates the calculated driving scene with the output data and acquires it as log data, An influence acquisition unit that acquires a predetermined degree of influence that the driving scene has on the surroundings of the vehicle, based on the aforementioned driving scene, An autonomous driving system comprising: a log storage unit that stores the log data in the vehicle's storage unit with priority according to the degree of influence of the driving scene associated with the log data.

2. The system includes a capacity shortage prediction unit that predicts a future capacity shortage in the vehicle's storage based on the time of the automated driving control to the vehicle's destination and the road conditions. The automated driving system according to claim 1, wherein the log storage unit, when a shortage of capacity in the storage unit of the vehicle is predicted, stores the log data in the storage unit of the vehicle with priority according to the degree of impact.

3. An external storage unit that stores the log data transmitted from the vehicle via the network, The vehicle is provided with a communication unit that communicates with the external storage unit, The automated driving system according to claim 1 or 2, wherein the log storage unit transmits the log data to the external storage unit and deletes the transmitted log data from the storage unit of the vehicle.

Images