Route management system

Abstract

To secure transparency and easiness in verification of automatic drive control when storing log data related to the automatic drive control for a vehicle.SOLUTION: A traveling route management system generates a travelling route in an automatic drive control for a vehicle. The travelling route management system includes: a storage device storing a travelling history managing a process where the vehicle traveled by the automatic drive control in the past; and one or more processors. The vehicle includes a target storage device storing log data related to the aromatic drive control. One or more processors are constituted so as to execute: processing for acquiring residual capacity of the target storage device; processing for generating one or more candidate routes; and processing for selecting the travelling route in one or more candidate routes. The processing for selecting the travelling route comprises selecting the travelling route among the one or more candidate routes while using a large number of common points with the travelling history as an index when the residual capacity of the target storage device is smaller than a prescribed capacity.SELECTED DRAWING: Figure 3

Description

Technical Field

[0005]

[0001] The present disclosure relates to a travel route management system that generates a travel route in automatic driving control.

Background Art

[0002] Patent Document 1 discloses a driving information management device that can record a route traveled in the past by automatic driving as a history route. The driving information management device is mounted on a vehicle equipped with an automatic driving device capable of switching between manual driving and automatic driving. According to the driving information management device, when the automatic driving device is switched to automatic driving, generation of automatic driving history data indicating a history of the travel route traveled by automatic driving is automatically started. The automatic driving history data is stored in a database, and a route that can be automatically driven can be called from the past history when the vehicle is traveling.

[0003] In addition, as documents showing the technical level of the technical field related to the present disclosure, Patent Document 2 and Patent Document 3 below can be exemplified in addition to the above-mentioned Patent Document 1.

Prior Art Documents

[0006] One of the purposes of this disclosure is to provide a technology that enables transparency and ease of verification of autonomous driving control when storing log data related to the autonomous driving control of a vehicle. [Means for solving the problem]

[0007] This disclosure provides a driving path management system for generating driving paths in the automated driving control of a vehicle. The driving route management system comprises a storage device that stores a driving history, which manages the routes that a vehicle has traveled in the past using automated driving control, and one or more processors. The vehicle is equipped with a storage device that stores log data related to autonomous driving control. One or more processors are configured to perform the following processes: obtaining the remaining capacity of the target storage device; generating one or more candidate routes; and selecting a route from among the one or more candidate routes. The process of selecting a travel route includes, when the remaining capacity of the target storage device is less than a predetermined amount, selecting a travel route from one or more candidate routes based on the number of commonalities with the travel history. [Effects of the Invention]

[0008] According to the technology disclosed herein, the driving route management system includes a storage device that stores a driving history, which manages the routes that a vehicle has previously traveled using automated driving control. First, the driving route management system generates candidate routes. Then, if the remaining capacity of the storage device that stores log data related to automated driving control is below a predetermined amount, it selects a driving route from the candidate routes based on the number of commonalities with the driving history. When driving a driving route generated in this way, a large portion of the data related to automated driving control can be supplemented by log data that has been stored in the past, without needing to be stored.

[0009] Thus, this disclosure makes it possible to ensure transparency and ease of verification of autonomous driving control. [Brief explanation of the drawing]

[0010] [Figure 1] This figure shows an example configuration related to the automatic driving control of a vehicle according to this embodiment. [Figure 2] This figure shows an example of the configuration of the automated driving system according to this embodiment. [Figure 3] This flowchart shows an example of the process involved in generating a travel route. [Figure 4] This flowchart shows an example of the process for saving control data. [Figure 5] This flowchart shows an example of the process for generating the travel path in the first modified example. [Modes for carrying out the invention]

[0011] 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.

[0012] Vehicle 1 includes a sensor group 10, a recognition unit 20, a planning unit 30, a control quantity calculation unit 40, a travel route management unit 50, and a travel device 60.

[0013] The sensor group 10 includes a recognition sensor 11, a state sensor 12, and a position sensor 13. The recognition sensor 11 is 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 state sensor 12 detects the state of the vehicle 1. Examples of state sensors 12 include speed sensors, acceleration sensors, yaw rate sensors, steering angle sensors, etc. The position sensor 13 detects the position of the vehicle 1. An example of a position sensor 13 is a GNSS (Global Navigation Satellite System) sensor.

[0014] Sensor detection information SEN is information obtained by the sensor group 10. Sensor detection information SEN includes recognition sensor information, vehicle status information, and location information. Recognition sensor information is information obtained when the recognition sensor 11 recognizes the surroundings of vehicle 1. For example, recognition sensor information includes images captured by the camera and point cloud information obtained by LIDAR. Vehicle status information is information indicating the status of vehicle 1, obtained by the status sensor 12. Location information is information indicating the position of vehicle 1, and is obtained from the location sensor 13.

[0015] The recognition unit 20, the planning unit 30, and the control amount calculation unit 40 constitute an "automatic driving control unit" that controls the automatic driving of the vehicle 1. The recognition unit 20 receives sensor detection information SEN including at least recognition sensor information from the sensor group 10. The recognition unit 20 recognizes the situation around the vehicle 1 based on the received sensor detection information SEN. For example, the recognition unit 20 recognizes the objects around the vehicle 1. Examples of the objects include pedestrians, other vehicles (preceding vehicles, parked vehicles, etc.), white lines, road structures (e.g., guardrails, curbs), falling objects, traffic signals, intersections, signs, etc. The recognition result information RES indicates the recognition result by the recognition unit 20. For example, the recognition result information RES includes object information indicating the relative position and relative speed of the object with respect to the vehicle 1, and information regarding the curvature and road width of the road on which the vehicle 1 travels.

[0016] The travel route management unit 50 generates and manages a travel route indicating the route through which the vehicle 1 travels to the destination. The travel route may include the designation of the lane in which the vehicle 1 travels within the route. The generation of the travel route by the travel route management unit 50 will be described later.

[0017] The planning unit 30 receives the recognition result information RES from the recognition unit 20. The planning unit 30 also receives the travel route from the travel route management unit 50. In addition, the planning unit 30 may receive vehicle state information, position information, and pre-generated map information. The map information may be high-precision 3D map information. The planning unit 30 generates a travel plan for traveling according to the travel route based on the received information. Examples of the travel plan include maintaining the current travel lane, changing lanes, overtaking, making right or left turns, steering, accelerating, decelerating, stopping, etc. Further, the planning unit 30 generates a target trajectory TRJ necessary for the vehicle 1 to travel according to the travel plan. The target trajectory TRJ includes a target position and a target speed. The travel plan and the target trajectory TRJ may include those generated to avoid risks.

[0018] The control quantity calculation unit 40 receives the target trajectory TRJ from the planning unit 30. The control quantity calculation unit 40 calculates a control quantity CON necessary for the vehicle 1 to follow the target trajectory TRJ. The control quantity CON can also be said to be a control quantity required to reduce the deviation between the vehicle 1 and the target trajectory TRJ. The control quantity CON includes at least one of a steering control quantity, a driving control quantity, and a braking control quantity. Examples of the steering control quantity include a target steering angle, a target torque, a target motor angle, a target motor drive current, etc. Examples of the driving control quantity include a target speed, a target acceleration, etc. Examples of the braking control quantity include a target speed, a target deceleration, etc.

[0019] The traveling device 60 includes a steering device 61, a driving device 62, and a braking device 63. The steering device 61 steers the wheels. For example, the steering device 61 includes an electric power steering (EPS) device. The driving device 62 is a power source that generates a driving force. Examples of the driving device 62 include an engine, an electric motor, an in-wheel motor, etc. The braking device 63 generates a braking force. The traveling device 60 receives the control quantity CON from the control quantity calculation unit 40. The traveling device 60 operates the steering device 61, the driving device 62, and the braking device 63 according to each of the steering control quantity, the driving control quantity, and the braking control quantity. Thereby, the vehicle 1 travels so as to follow the target trajectory TRJ.

[0020] FIG. 2 is a conceptual diagram showing a configuration example of the automatic driving system 100 according to the present embodiment. The automatic driving system 100 is mounted on the vehicle 1 and performs automatic driving control of the vehicle 1. The automatic driving system 100 has at least the functions of the above-described automatic driving control unit. The automatic driving system 100 may further include a sensor group 10 and a traveling device 60.

[0021] The automatic driving system 100 includes one or more processors 110 (hereinafter simply referred to as the processor 110) and one or more storage devices 120 (hereinafter simply referred to as the storage device 120).

[0022] The processor 110 performs various processes. Examples of processors 110 include CPUs (Central Processing Units), GPUs (Graphics Processing Units), ASICs (Application Specific Integrated Circuits), FPGAs (Field-Programmable Gate Arrays), etc.

[0023] The storage device 120 stores the program 130 and various other information. Examples of storage devices 120 include HDDs (Hard Disk Drives), SSDs (Solid State Drives), volatile memory, non-volatile memory, etc.

[0024] Program 130 is a computer program for controlling vehicle 1 and is executed by processor 110. Program 130 may be recorded on a computer-readable recording medium. Various processes by the automated driving system 100 are realized through the cooperation of processor 110 executing program 130 and storage device 120. In other words, the recognition unit 20, planning unit 30, control quantity calculation unit 40, and driving path management unit 50 are realized by processor 110 executing program 130. Each functional unit may be realized by a single processor 110 or by separate processors 110.

[0025] The various types of information stored in the storage device 120 include map information and driving history DAT. Driving history DAT is data that manages the routes that vehicle 1 has traveled in the past under automatic driving control. Examples of driving history DAT include data on the routes that vehicle 1 has traveled in the past, data on the lanes that vehicle 1 has traveled in the past, and information on the road shape within the routes that vehicle 1 has traveled in the past. Furthermore, driving history DAT may also include information on the time periods in which vehicle 1 traveled in the past.

[0026] Data relating to the routes previously traveled by Vehicle 1 may, for example, show the routes previously traveled by Vehicle 1 on a map. Information regarding the road shape within the routes previously traveled by Vehicle 1 may, for example, show the curvature, gradient, and road width of at least a portion of the routes previously traveled by Vehicle 1. Alternatively, it may be information indicating whether or not a specific road shape was included within the routes previously traveled by Vehicle 1. Examples of specific road shapes include curves with a predetermined curvature, ramps with a predetermined gradient, junctions, merges, road markings, roads under construction, and roads separated by means other than lanes, such as balls or pylons.

[0027] Refer to Figure 1 again. 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 machine learning models include NN (Neural Network), SVM (Support Vector Machine), regression models, decision tree models, etc. The NN may be a CNN (Convolutional Neural Network), an RNN (Recurrent Neural Network), or a combination thereof. The type of each layer, the number of layers, and the number of nodes in the NN are arbitrary. The machine learning model is generated in advance through machine learning. The recognition unit 20 performs recognition processing by inputting 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.

[0028] 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 by inputting 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.

[0029] 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 into the model. The control variable CON is output from the model or generated based on the output from the model. The storage device 120 stores data from the models included in the recognition unit 20, the planning unit 30, and the control variable calculation unit 40, and is used for automatic driving control.

[0030] 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.

[0031] In this embodiment, a machine learning model is used in at least a part of the automatic driving control unit. Specifically, 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 the vehicle 1.

[0032] During autonomous driving control, the processor 110 acquires a log of data related to autonomous driving control. Hereinafter, this data will be referred to as control data. The processor 110 saves a log of some or all of the control data acquired during autonomous driving control as log data LOG in the storage device 120. The processor 110 may save the control data in the storage device 120 only for a certain period of time. The saving of control data is done to ensure the explainability of autonomous driving control.

[0033] As described above, the automated driving system 100 according to this embodiment is configured. In the automated driving system 100, the driving route management system according to this embodiment is realized by a processor 110 that realizes the driving route management unit 50 and a storage device 120 that stores the driving history DAT. The storage device 120 may separately include a storage device for storing the driving history DAT and a storage device for storing log data LOG.

[0034] 2. Processing related to the generation of the travel route Figure 3 is a flowchart illustrating an example of the process for generating a driving route, which is performed in the driving route management unit 50. The process shown in the flowchart in Figure 3 is executed when the automated driving system 100 determines the driving route for vehicle 1. The timing for determining the driving route for vehicle 1 is, for example, when vehicle 1 starts driving under automated driving conditions. Alternatively, the driving route may be changeable at any time after vehicle 1 has started driving, and the process may be executed at the time the driving route is changed.

[0035] In step S110, the processor 110 generates candidate routes. A candidate route is a route that can be used as a driving route. For example, the processor 110 obtains the destination input by the operator, the location information of vehicle 1 included in the sensor detection information SEN, and the map information stored in the storage device 120, and generates a route connecting the current location of vehicle 1 and the destination as a candidate route. There may be multiple candidate routes. In addition to the route that vehicle 1 will travel, the candidate route may also include information specifying the lane that vehicle 1 will travel in within the route.

[0036] In step S120, the processor 110 obtains the remaining capacity of the storage device 120. If the storage device 120 includes multiple storage devices, the remaining capacity of the storage device for storing the log data LOG is obtained here.

[0037] In step S130, the processor 110 determines whether the remaining capacity obtained in step S120 is less than a predetermined amount. If the remaining capacity is less than the predetermined amount (step S130; Yes), the process proceeds to step S140. On the other hand, if the remaining capacity is equal to or greater than the predetermined amount (step S130; No), the process proceeds to step S160.

[0038] In step S140, the processor 110 selects a travel route from among the candidate routes generated in step S110. At this time, the processor 110 uses the number of commonalities with the travel history DAT as an indicator and selects the candidate route with the most commonalities as the travel route.

[0039] This section explains the degree of commonality between candidate routes and the driving history DAT. The degree of commonality is determined, for example, by the amount of common parts in the routes. The processor 110 obtains routes that vehicle 1 has traveled in the past from the driving history DAT and compares them with candidate routes. It then determines that a candidate route has more commonalities if it includes many routes that vehicle 1 has traveled in the past. Including many routes that vehicle 1 has traveled in the past means, for example, that a large proportion of the candidate route overlaps with routes that vehicle 1 has traveled in the past, or that the length of the portion of the route excluding routes that vehicle 1 has traveled in the past is short.

[0040] If a candidate route includes information specifying the lane in which vehicle 1 travels within the route, the degree of commonality with the driving history DAT may be determined by the degree of commonality in the lanes in which vehicle 1 travels. For example, the processor 110 obtains information from the driving history DAT about routes that vehicle 1 has traveled in the past and which lanes it traveled in within those routes. The processor then determines that a candidate route has more commonality with the driving history DAT if it includes many lanes that vehicle 1 has traveled in the past. In this case, the processor 110 may also determine that lanes are common even for candidate routes that travel in the same lane on different routes. For example, suppose the driving history DAT only contains data on vehicle 1 traveling in the left lane in the past, and does not contain data on vehicle 1 traveling in the right lane. In this case, the processor may determine that a candidate route has more commonality if it includes many parts that specify the left lane as the lane in which vehicle 1 travels.

[0041] If none of the candidate routes include a route that vehicle 1 has traveled in the past, the degree of commonality between the candidate routes and the travel history DAT may be determined by the number of commonalities in road shapes. In this case, the processor 110 obtains information about the road shapes included in each of the candidate routes from, for example, map information stored in the storage device 120. The processor then determines that a candidate route that contains many road shapes common to road shapes that vehicle 1 has experienced in the past has more commonalities with the travel history DAT. Here, vehicle 1 having experienced a specific road shape means that that specific road shape existed on a route that vehicle 1 has traveled in the past. For example, suppose vehicle 1 has experienced a merge in the past, but has never experienced a ramp with a predetermined gradient. And suppose, as a result of obtaining information about the road shapes included in each of the candidate routes, there are candidate routes that include a merge and candidate routes that include a ramp with a predetermined gradient. In this case, the processor 110 may determine that the candidate route that includes a merge has more commonalities.

[0042] As an example of candidate routes, consider the following five cases: The first is a candidate route in which the entire route from the starting point to the destination overlaps with a route included in the driving history DAT, and the lanes are also the same. The second is a candidate route in which the entire route is the same as the driving history DAT, but the lanes are not the same. The third is a candidate route in which some routes are not the same as the driving history DAT, but the proportion of the route that is the same is large. The fourth is a candidate route in which no routes are the same as the driving history DAT, but some road shapes are the same. The fifth is a candidate route in which no routes are the same as the driving history DAT, and many road shapes are not the same as the driving history DAT. In this case, it is judged that the first candidate route has the most common points, and the common points gradually decrease as you move to the fifth candidate route.

[0043] If the remaining capacity is greater than or equal to a predetermined amount, in step S160, the processor 110 selects a travel route from the candidate routes generated in step S130. The selection of a travel route from one or more candidate routes is the same as in step S140. However, when a travel route is selected in step S160, the degree of commonality with the travel history DAT is not used as an indicator for selecting the travel route.

[0044] The method for selecting the driving route in step S160 is arbitrary. For example, the processor 110 may select the shortest route from the candidate routes, the route with the least gradient, or the route from the perspective of fuel efficiency.

[0045] If a travel route is selected in step S140 or step S160, the series of processes ends. In this way, a travel route is generated by the series of processes. The generated travel route is acquired by the planning unit 30, which generates a travel plan for vehicle 1 to travel along the travel route. If a travel route has already been generated when the series of processes ends, the travel route is modified, and the planning unit 30 generates a new travel plan to travel along the new travel route.

[0046] 3. Processing related to saving control data As described above, the processor 110 acquires control data while automatic driving control is being performed and saves it to the storage device 120 as log data LOG. Figure 4 is a flowchart showing the process related to saving control data. The process shown in the flowchart in Figure 4 is executed repeatedly at a predetermined processing cycle, for example, while automatic driving control is being performed.

[0047] In step S210, the processor 110 acquires data related to autonomous driving control. Here, basically all data used in autonomous driving control is acquired, with the expectation that it will be used for later verification, etc. For example, sensor detection information SEN input to the recognition unit 20 and recognition result information RES output from the recognition unit 20 are acquired. Alternatively, for example, if the recognition unit 20, planning unit 30, and control variable calculation unit 40 are configured as an integrated unit, sensor detection information SEN input to the autonomous driving control unit, recognition result information RES and target trajectory TRJ as intermediate products, and control variable CON output from the autonomous driving control unit are acquired. The acquired data may further include the reasons for decisions in the recognition processing by the recognition unit 20, the reasons for decisions in the planning processing by the planning unit 30, whether or not there was operator intervention in autonomous driving control, etc.

[0048] In step S220, the processor 110 obtains the remaining capacity of the storage device 120. The amount of remaining capacity of the storage device 120 obtained here represents the amount of capacity available to newly store control data. If the storage device 120 includes multiple storage devices, the remaining capacity of the storage device for storing log data LOG is obtained here.

[0049] In step S230, the processor 110 determines whether the remaining capacity obtained in step S210 is less than a predetermined amount. The predetermined amount here may be more than or the same as the predetermined amount in step S130 in Figure 3. If the remaining capacity is less than the predetermined amount (step S230; Yes), the process proceeds to step S240.

[0050] In step S240, the processor 110 stores differential data in the storage device 120. Differential data is the data that differs from the log data LOG among the data acquired in step S210. For example, if vehicle 1 is traveling on a route it has traveled in the past, the detection results for the surrounding scenery captured by the camera among the sensor detection information SEN input to the recognition unit 20, and the detection results for the position of the white lines among the recognition result information RES output by the recognition unit 20, are expected to be roughly the same as the data included in the log data LOG that has been saved in the past. The data remaining after removing such data that is equivalent to the log data LOG becomes the differential data. In other words, the storage device 120 newly stores data from the data acquired in step S210, excluding the parts that can be supplemented by the log data LOG that have been saved in the past.

[0051] On the other hand, if the remaining capacity is greater than or equal to a predetermined amount (step S230; No), the process proceeds to step S250. In step S250, the processor 110 stores all the data acquired in step S210 into the storage device 120.

[0052] The data stored in the storage device 120 in step S240 or step S250 is the control data. Once the control data is stored in the storage device 120, the series of processes ends.

[0053] 4. Effects The effects of these processes will now be explained. As mentioned above, control data is stored in preparation for situations where it may be necessary to verify how the automated driving control was performed at a later date. Therefore, it is desirable to store as much control data as possible during automated driving control, at least until verification is complete and it is determined that storage is no longer necessary.

[0054] However, since the storage device 120 has a limited capacity, there is also a limit to the amount of control data that can be stored in the storage device 120. If the remaining capacity of the storage device 120 decreases and falls short of the required capacity, it will become impossible to store new control data in the storage device 120. Therefore, if the remaining capacity of the storage device 120 decreases and there is a possibility that capacity will become limited, it is necessary to conserve the remaining capacity.

[0055] In this embodiment of the automated driving system 100, when the remaining capacity of the storage device 120 falls below a predetermined amount, a driving route with many similarities to routes previously driven by the vehicle 1 under automated driving control is generated. When driving along such a generated driving route, a large portion of the control data can be supplemented by previously saved log data LOG. This ensures transparency and ease of verification of automated driving control even when it is difficult to save control data.

[0056] Furthermore, according to this embodiment, the control data stored in the storage device 120 is differential data.

[0057] Differential data is data related to autonomous driving control, excluding portions that overlap with previously saved log data (LOG). Since the overlapping portions can be supplemented by past data, as long as differential data is stored, the explainability of the situation can be ensured by combining the previously acquired data with the currently obtained differential data. In other words, differential data can be said to be the minimum data that should be stored with the intention of being used for subsequent verification. When the remaining capacity becomes low, the amount of control data to be newly stored can be reduced by limiting the data to be stored to the minimum necessary data and omitting the storage of portions that can be explained by combining with past data.

[0058] Furthermore, selecting candidate routes that share many similarities with the driving history DAT is effective in reducing the size of the differential data. When driving on routes with many similarities, it is expected that much of the information input to and output from the automatic driving control unit during driving will be the same as the information contained in the previously saved log data LOG. In other words, the size of the differential data can be reduced, and the remaining capacity of the storage device 120 can be effectively preserved. Thus, the automatic driving system 100 according to this embodiment can effectively prevent a situation in which the remaining capacity of the storage device 120 becomes strained, while still ensuring the information necessary to guarantee explainability and verifiability.

[0059] 5. Variations 5-1. First variation Figure 5 is a flowchart showing an example of the process for generating the travel path in the first modified example. The timing of the process execution is the same as in the flowchart in Figure 3.

[0060] The processing from steps S310 to S340 is the same as the processing from steps S110 to S140 in Figure 3. However, in step S330, if the remaining capacity of the storage device 120 is equal to or greater than a first predetermined amount (step S330; No), the process proceeds to step S350. The first predetermined amount is the same as the predetermined amount in step S130 in Figure 3.

[0061] In step S350, the processor 110 determines whether the remaining capacity of the storage device 120 is greater than a second predetermined amount. The second predetermined amount may be greater than or equal to the first predetermined amount. If the remaining capacity of the storage device 120 is less than or equal to the second predetermined amount (step S350; No), the process proceeds to step S360. If the remaining capacity of the storage device 120 is greater than the second predetermined amount (step S350; Yes), the process proceeds to step S370.

[0062] The processing in step S360 is the same as the processing in step S160 in Figure 3. On the other hand, in step S370, the processor 110 selects a driving route from among the candidate routes, using the smallest commonality with the driving history DAT as an indicator. Specifically, the processor 110 selects a candidate route with few commonalities with the driving history DAT as the driving route. Once a driving route is selected in step S370, the series of processes ends.

[0063] The control data acquired during autonomous driving and stored in the memory device 120 can be used as log data (LOG) for subsequent driving of vehicle 1. It can also be used as training data for machine learning models for subsequent autonomous driving control. Therefore, in this modified example, if the remaining capacity of the memory device 120 is greater than a predetermined amount, a driving route is selected that is expected to acquire a large amount of control data representing the difference from previously acquired data. In other words, when there is sufficient remaining capacity in the memory device 120, the autonomous driving system 100 selects a driving route that allows it to collect more new data that has not been experienced before.

[0064] The criteria for determining the lack of commonalities are basically the inverse of the criteria for determining the abundance of commonalities described in step S140 of the flowchart in Figure 3. In other words, in step S370, candidate routes with few commonalities with the driving history DAT are selected based on factors such as the lack of common parts in the routes, the lack of commonalities in the lanes that vehicle 1 travels in, and the lack of commonalities in the road shape.

[0065] For example, the processor 110 may select a candidate route that passes through a route that includes many road shapes not included in the driving history DAT. Alternatively, it may select a candidate route that travels in different lanes within the same route (for example, a candidate route that travels in the right lane if the driving history DAT includes data of driving in the left lane).

[0066] Alternatively, from the perspective of utilizing the data as new driving history or learning data, the criteria for determining the lack of commonality with the driving history DAT may also include aspects such as time of day and frequency. For example, a driving route that includes many routes that have not been driven frequently in the past may be judged to have few commonalities. Or, even if a driving route passes through the same area, if it is driven at a time of day that has not been driven in the past, it may be judged to have few commonalities. In this way, candidate routes that include many elements that vehicle 1 has not experienced in the past will be judged to have few commonalities.

[0067] 5-2. Second variation Next, a second modification will be described. In the second modification, vehicle 1 is connected to an external management server via a communication network. In this case, part of the processor 110 and storage device 120 may be included in the management server, and at least part of the processing shown in the flowchart of Figure 3 may be performed on the management server. In this case, for example, at the time of determining the travel route, the departure point, destination, and remaining capacity of the storage device 120 are transmitted from vehicle 1 to the management server. The processor of the management server then executes the processing shown in the flowchart of Figure 3 based on the received information and the information held by the management server, and determines the travel route. The determined travel route is then transmitted to vehicle 1. Alternatively, candidate routes may be generated on the management server, and the selection of the travel route may be performed on the vehicle. In this case, the departure point and destination are transmitted to the management server, and the management server generates candidate routes based on this information and its own information, and transmits one or more of the generated candidate routes to vehicle 1.

[0068] Furthermore, the management server may be a server that manages multiple vehicles 1. In this case, the driving history DAT may be aggregated data obtained from multiple vehicles 1. Similarly, in this case as well, part of the processor 110 and storage device 120 may be included in the management server. That is, the processing entity that generates candidate routes and selects driving routes may be the management server. Also, part or all of the driving history DAT may be stored in the management server's storage device, and the management server may distribute the stored data to the vehicles 1.

[0069] When the driving history data (DAT) is obtained from multiple vehicles, the commonalities between the driving history data and candidate routes do not necessarily mean commonalities with routes, lanes, or road shapes that vehicle 1 has previously experienced. In other words, a candidate route that has many commonalities with routes previously traveled by a different vehicle 1 may be selected as the driving route. By aggregating data from multiple vehicles 1, driving history data can be collected more efficiently, making it possible to reduce the amount of differential data.

[0070] The first and second modifications can be combined. If the process shown in the first modification is performed as the process for generating the driving route, and multiple vehicles 1 are managed by the management server, the following embodiment is also possible. If there is missing data in the driving history DAT aggregated by the management server, the management server prompts the user of vehicle 1 to drive a route that will allow the collection of such data. For example, suppose that data for a route driven by vehicle 1 is not included in the driving history DAT. In this case, if there is sufficient remaining capacity in the storage device 120, it is desirable that a candidate route including that route be selected as the driving route, but this may increase the time required for driving. In such cases, if a candidate route with few commonalities with the driving history DAT is selected, the management server provides the user with an incentive such as point redemption, so that a driving route that allows for the acquisition of a lot of new data is selected while maintaining user satisfaction. [Explanation of symbols]

[0071] 1...Vehicle, 10...Sensor group, 20...Recognition unit, 30...Planning unit, 40...Control quantity calculation unit, 50...Driving path management unit, 60...Driving device, 100...Automated driving system, 110...Processor, 120...Storage device, DAT...Driving history, CON...Control quantity, RES...Recognition result information, SEN...Sensor detection information, TRJ...Target trajectory

Claims

1. A driving path management system for generating driving paths in the automated driving control of a vehicle, A memory device that stores a driving history, which manages the routes that the vehicle has traveled in the past using automatic driving control, One or more processors, Equipped with, The aforementioned vehicle is equipped with a storage device for storing log data related to automatic driving control, The one or more processors described above are: The process of obtaining the remaining capacity of the target storage device, A process for generating one or more candidate paths, A process of selecting the travel route from the one or more candidate routes, It is configured to perform, The process of selecting the aforementioned travel route includes, when the remaining capacity is less than a predetermined amount, selecting the aforementioned travel route from among the one or more candidate routes, using the number of commonalities with the aforementioned travel history as an indicator. The aforementioned driving history includes data relating to routes previously traveled by the vehicle. The one or more processors described above are: Among the one or more candidate routes mentioned above, the more a candidate route that includes a large number of routes previously traveled by the vehicle is judged to have more commonalities. A travel route management system characterized by being configured in such a way.

2. A travel route management system according to claim 1, The aforementioned driving history further includes data regarding the lanes the vehicle has traveled in the past, The aforementioned one or more candidate routes further include information specifying the lanes to be traveled in within the route, The one or more processors described above are: The more of the one or more candidate routes mentioned above that include a large number of lanes that the vehicle has traveled in the past, the more commonalities are determined to be. A travel route management system characterized by being configured in such a way.

3. A driving path management system for generating driving paths in the automated driving control of a vehicle, A memory device that stores a driving history, which manages the routes that the vehicle has traveled in the past using automatic driving control, One or more processors, Equipped with, The aforementioned vehicle is equipped with a storage device for storing log data related to automatic driving control, The one or more processors described above are: The process of obtaining the remaining capacity of the target storage device, A process for generating one or more candidate paths, A process of selecting the travel route from the one or more candidate routes, It is configured to perform, The process of selecting the aforementioned travel route includes, when the remaining capacity is less than a predetermined amount, selecting the aforementioned travel route from among the one or more candidate routes, using the number of commonalities with the aforementioned travel history as an indicator. The aforementioned driving history includes information about specific road shapes present on routes previously traveled by the vehicle. The one or more processors described above are: Further processing is performed to obtain information about the road shape included in each of the one or more candidate routes. The more candidate routes among the one or more candidate routes that contain the same road shape as the specific road shape, the more commonalities are determined to be. A travel route management system characterized by being configured in such a way.

4. A travel route management system according to any one of claims 1 to 3, The process of selecting the aforementioned travel route includes, when the remaining capacity is greater than a predetermined amount, selecting the aforementioned travel route from among the one or more candidate routes, using the least commonality with the aforementioned travel history as an indicator. A driving route management system characterized by the following:

Images