Information processing device, vehicle, information processing method, and program

Abstract

To provide a technique that can realize speed control according to a cluster of crew members and so on.SOLUTION: An information processor has: an acquisition part which acquires a cluster concerning crew members other than an operator riding on a vehicle and a cluster concerning loads of the vehicle from a plurality of clusters; and a determination part which determines speed control parameters which define speed change of the vehicle on the basis of the clusters acquired by the acquisition part.SELECTED DRAWING: Figure 3

Description

[Technical Field]

[0001] The present invention relates to an information processing device, a vehicle, an information processing method, and a program. [Background technology]

[0002] Currently, technological developments toward autonomous driving are progressing. For example, Patent Document 1 discloses a technology that changes acceleration depending on the situation while autonomous driving control is being executed. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Patent Publication No. 2021-041839 Summary of the Invention [Problem to be solved by the invention]

[0004] Current autonomous driving technology is capable of automatically accelerating and decelerating a vehicle, such as by accelerating (accelerating) within a speed limit and suddenly decelerating (braking) when an obstacle is detected. However, in autonomous vehicles intended for passenger transportation, such as buses and taxis, to achieve smooth autonomous driving that satisfies passengers, it is desirable to be able to adjust driving operations such as acceleration and deceleration according to passenger preferences so that passengers feel comfortable. Similar issues also apply to vehicles that transport cargo, such as trucks. In other words, to achieve autonomous driving, it is desirable to control speed according to a group (cluster) of driving methods that are grouped according to the characteristics of the passengers or cargo.

[0005] Therefore, an object of the present invention is to provide a technology that can realize speed control according to clusters such as occupants. [Means for solving the problem]

[0006] An information processing device according to one aspect of the present invention has an acquisition unit that acquires, from a plurality of clusters, a cluster relating to passengers other than the driver riding in the vehicle or a cluster relating to cargo in the vehicle, and a determination unit that determines a speed control parameter that defines a change in the speed of the vehicle based on the cluster acquired by the acquisition unit.

[0007] In the above aspect, the speed control parameters may include a plurality of speed control parameters for each combination of start speed and end speed, and the determination unit may determine, from among the plurality of speed control parameters, the speed control parameter whose start speed and end speed correspond to the current speed and target speed of the vehicle and which has the highest evaluation value corresponding to the cluster acquired by the acquisition unit, as the speed control parameter to be applied to the vehicle.

[0008] In the above aspect, the determination unit may determine the evaluation value by inputting the speed control parameter into an evaluation model that is predetermined for each of the clusters.

[0009] In the above aspect, the evaluation model may be a trained model generated by training a machine learning model. [Effects of the Invention]

[0010] According to the present invention, it is possible to provide a technology that can realize speed control according to clusters such as passengers. [Brief explanation of the drawings]

[0011] [Figure 1] FIG. 1 is a diagram illustrating an example of an autonomous driving system according to a first embodiment. [Figure 2] 2 is a diagram illustrating an example of the hardware configuration of an in-vehicle device and a server according to the first embodiment. FIG. [Figure 3] 2 is a diagram showing an example of a functional block configuration of an in-vehicle device according to the first embodiment; FIG. [Figure 4] FIG. 2 is a diagram illustrating an example of a functional block configuration of a server according to the first embodiment. [Figure 5] 10 is a flowchart showing an example of a processing procedure for collecting various data related to driving operations performed by a professional driver or the like. [Figure 6] FIG. 10 is a diagram illustrating an example of a collected data DB. [Figure 7] 10 is a flowchart illustrating an example of a process for generating a speed control parameter and an evaluation model. [Figure 8] FIG. 10 is a diagram illustrating a method for calculating a constant that fits time series data. [Figure 9] FIG. 10 is a diagram showing an example of a speed control parameter DB. [Figure 10] 10 is a flowchart illustrating an example of a processing procedure when an in-vehicle device executes automatic driving control. [Figure 11] FIG. 10 is a diagram showing an example of a functional block configuration of an in-vehicle device according to a third embodiment. [Figure 12] FIG. 11 is a diagram illustrating an example of a functional block configuration of a server according to the third embodiment. [Figure 13] FIG. 11 is a sequence diagram showing a processing procedure between an in-vehicle device and a server according to the third embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0012] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS The present invention will be described with reference to the accompanying drawings, in which the same reference numerals denote the same or similar components.

[0013] <<First Embodiment>> <System configuration> 1 is a diagram illustrating an example of an autonomous driving system 1 according to a first embodiment. The autonomous driving system 1 includes an in-vehicle device 10 and a server 20. The autonomous driving system 1 may further include a vehicle 30.

[0014] The in-vehicle device 10 is mounted on a vehicle 30 and realizes autonomous driving by controlling the accelerator operation, brake operation, etc. of the vehicle 30. The in-vehicle device 10 may be a general-purpose computer or a dedicated computer specialized for in-vehicle use. The in-vehicle device 10 may also be called an information processing device.

[0015] The server 20 generates data necessary for the in-vehicle device 10 to realize autonomous driving, and provides the generated data to the in-vehicle device 10. The server 20 can communicate with the in-vehicle device 10 via a wireless network. The server 20 may be configured from one or more physical servers, or may be configured using a virtual server operating on a hypervisor, or may be configured using a cloud server. The server 20 may also be called an information processing device.

[0016] The autonomous driving system 1 learns the driving operations (ride feel) performed by skilled drivers such as professional drivers of buses, taxis, trucks, etc. The autonomous driving system 1 reflects driving operations that are considered to be particularly lacking in current autonomous driving, such as how to apply and release the accelerator and brakes that occupants feel are skilled drivers, into the autonomous driving.

[0017] More specifically, before starting autonomous driving control of the vehicle 30, the autonomous driving system 1 acquires, from among a plurality of clusters related to driving methods (hereinafter referred to as "driving method clusters"), a cluster that corresponds to the occupant's preferences regarding the driving operation of the vehicle 30, or a cluster that corresponds to the characteristics of the cargo loaded on the vehicle 30. Next, the autonomous driving system 1 applies to the vehicle 30 an acceleration / deceleration pattern that corresponds to the acquired cluster from among a plurality of acceleration / deceleration patterns, thereby realizing autonomous driving that satisfies the occupants or that is appropriate for the cargo.

[0018] The "driving method cluster" may be classified into any type, but may be classified into three levels, for example, a cluster that places particular emphasis on safe driving (hereinafter referred to as the "safe driving cluster"), a cluster that places emphasis on both safe driving and arrival time (hereinafter referred to as the "cluster that places emphasis on both"), and a cluster that places emphasis on arrival time (hereinafter referred to as the "time-focused cluster"). Passengers belonging to the safe driving cluster are a cluster that prefers driving with gradual speed changes, the time-focused cluster is a cluster that prefers brisk driving with quick speed changes (i.e., driving that arrives quickly), and the both-focused cluster may be a cluster that prefers speed changes intermediate between the safe driving cluster and the time-focused cluster.

[0019] The same is true for driving method clusters according to the characteristics of the cargo. For example, cargo belonging to the safe driving cluster is fragile cargo, cargo belonging to the time-sensitive cluster is cargo such as fresh food that is desirable to arrive at the destination quickly, and cargo belonging to the time-sensitive cluster may be cargo such as beverages, dried goods, and canned goods that are not fragile but that are desirable to arrive at the destination quickly.

[0020] In the first embodiment, the acceleration / deceleration pattern performed by the vehicle 30 during autonomous driving is defined by a function including one or more constants. A set of one or more constants included in the function is called a "speed control parameter." The function may be any function, including a linear function, a quadratic function, a cubic function, an exponential function, etc.

[0021] The in-vehicle device 10 uses an evaluation model prepared for each driving style cluster when determining speed control parameters to be applied to acceleration or deceleration of the vehicle 30. The evaluation model is a model that estimates (outputs) an evaluation value that represents the satisfaction with the driving style felt by occupants belonging to each driving style cluster for the acceleration / deceleration pattern of the vehicle 30, or an evaluation value that represents the suitability of the driving style for the load belonging to each driving style cluster.

[0022] For example, occupants in the safe driving cluster are expected to be highly satisfied with driving with gentle speed changes, but not with driving with rapid speed changes. On the other hand, occupants in the time-conscious cluster are expected to be dissatisfied with driving with gentle speed changes, but highly satisfied with driving with rapid speed changes.

[0023] The evaluation model may be any model that can output the occupant satisfaction or the suitability of the load for the driving style cluster and the speed control parameter. The evaluation model may be, for example, a trained model generated by training a machine learning model, or may be a predetermined evaluation function.

[0024] <Hardware configuration> 2 is a diagram showing an example of the hardware configuration of the in-vehicle device 10 and the server 20 according to the first embodiment. The in-vehicle device 10 and the server 20 each include a processor 11 such as a CPU (Central Processing Unit) or a GPU (Graphical Processing Unit), a storage device 12 such as a memory, an HDD (Hard Disk Drive) and / or an SSD (Solid State Drive), a communication IF (Interface) 13 for wired or wireless communication, an input device 14 for accepting input operations, and an output device 15 for outputting information. The input device 14 is, for example, a keyboard, a touch panel, a mouse, and / or a microphone. The output device 15 is, for example, a display, a touch panel, and / or a speaker.

[0025] <Function block configuration> (In-vehicle device) FIG. 3 is a diagram showing an example of a functional block configuration of the in-vehicle device 10 according to the first embodiment. The in-vehicle device 10 includes a storage unit 100, an acquisition unit 101, a determination unit 102, a control unit 103, and a communication processing unit 104. The storage unit 100 can be realized using the storage device 12 included in the in-vehicle device 10. The acquisition unit 101, the determination unit 102, the control unit 103, and the communication processing unit 104 can be realized by the processor 11 of the in-vehicle device 10 executing a program stored in the storage device 12. The program can be stored in a storage medium. The storage medium storing the program may be a non-transitory computer-readable medium. The non-transitory storage medium is not particularly limited, and may be, for example, a storage medium such as a USB memory or a CD-ROM.

[0026] The storage unit 100 stores a speed control parameter DB 100a and an evaluation model 100b. The speed control parameter DB 100a stores a plurality of predefined speed control parameters. The evaluation model 100b stores an evaluation model for each driving method cluster.

[0027] The acquisition unit 101 acquires, from among a plurality of driving method clusters (clusters), a driving method cluster related to the occupants aboard the vehicle 30 or a driving method cluster related to the cargo of the vehicle 30. Note that the autonomous driving of the vehicle 30 includes a case where the vehicle 30 is driven completely autonomously without a driver by traveling on a dedicated road or the like, and a case where a driver is aboard the vehicle 30 and assists the autonomous driving as needed. Therefore, when a driver is aboard the vehicle 30, the acquisition unit 101 may acquire, from among the plurality of driving method clusters, a driving method cluster related to the "occupants other than the driver" aboard the vehicle 30 or a driving method cluster related to the cargo of the vehicle 30.

[0028] The determination unit 102 determines a speed control parameter that defines a speed change of the vehicle 30 based on the driving style cluster acquired by the acquisition unit 101. Here, the determination unit 102 may determine an evaluation value by inputting the speed control parameter into an evaluation model that is predetermined for each driving style cluster. For example, the determination unit 102 may use the evaluation model to determine the speed control parameter so that the evaluation value (occupant satisfaction or suitability for cargo) is maximized.

[0029] The control unit 103 controls the speed of the vehicle 30 using the speed control parameters determined by the determination unit 102. For example, the control unit 103 may control the acceleration and deceleration of the vehicle 30 by instructing an accelerator opening and a brake operation to an on-board computer of the vehicle 30, according to an acceleration and deceleration pattern expressed by setting the speed control parameters as a function.

[0030] The communication processing unit 104 performs various communications with the server 20. For example, the communication processing unit 104 acquires data related to rate control parameters and evaluation models from the server 20 and performs processing to update the rate control parameter DB 100a and the evaluation model 100b.

[0031] (server) FIG. 4 is a diagram showing an example of a functional block configuration of the server 20 according to the first embodiment. The server 20 includes a storage unit 200, a communication processing unit 201, a generation unit 202, and a collection unit 203. The storage unit 200 can be realized using the storage unit 12 included in the server 20. The communication processing unit 201, the generation unit 202, and the collection unit 203 can be realized by the processor 11 of the in-vehicle device 10 executing a program stored in the storage unit 12. The program can be stored in a storage medium. The storage medium storing the program may be a computer-readable non-transitory storage medium. The non-transitory storage medium is not particularly limited, and may be, for example, a storage medium such as a USB memory or a CD-ROM.

[0032] The storage unit 200 stores a collected data DB 200a, a speed control parameter DB 200b, and an evaluation model 200c. The collected data DB 200a stores evaluation values given by occupants in response to driving operations performed by a professional driver or the like, cluster data indicating the driving method cluster to which the occupant belongs, and time-series data of vehicle speed indicating the driving operations performed by the professional driver or the like. The speed control parameter DB 200b stores speed control parameters generated from the collected time-series data of vehicle speed. The evaluation model 200c stores parameter data of a trained model generated by training a machine learning model using the evaluation data and the speed control parameters, or data indicating an evaluation function generated using the evaluation data and the speed control parameters.

[0033] The communication processing unit 201 performs various communications with the in-vehicle device 10. For example, the communication processing unit 201 acquires speed control parameters from the speed control parameter DB 200b in the storage unit 200 and transmits them to the in-vehicle device 10. The communication processing unit 201 also acquires data related to the evaluation model from the evaluation model 200c in the storage unit 200 and transmits them to the in-vehicle device 10.

[0034] The generation unit 202 generates a trained model by training a machine learning model using the evaluation data and time-series data of vehicle speed stored in the collected data DB 200a, and stores parameter data of the generated trained model in the evaluation model 200c. The generation unit 202 also generates an evaluation function using the evaluation data and time-series data of vehicle speed stored in the collected data DB 200a, and stores data indicating the generated evaluation function in the evaluation model 200c.

[0035] The collection unit 203 collects evaluation data indicating the evaluation values given by the occupants in response to the driving operations performed by the professional driver, etc., cluster data indicating the driving method cluster to which the occupant belongs, and time series data of vehicle speed indicating the driving operations performed by the professional driver, etc. from the in-vehicle device 10 and the smartphone, etc. used by the occupants, and stores them in the memory unit 200.

[0036] <Processing Procedure> (Data collection related to driving operations) Fig. 5 is a flowchart showing an example of a processing procedure for collecting various data related to driving operations performed by a professional driver, etc. The processing procedure shown in Fig. 5 is performed, for example, when a passenger is on board a bus, taxi, etc. that is being driven by the professional driver.

[0037] In step S10 , the collection unit 203 collects, from each of one or more occupants riding in the vehicle 30 , a driving style cluster for each occupant.

[0038] In step S11, the collection unit 203 collects time-series data from the vehicle 30, which indicates a change in speed of the vehicle 30 traveling or stopped at a certain speed, as the vehicle 30 accelerates and decelerates until it reaches a target speed. For example, assume that the vehicle 30, traveling at 20 km / h at 15:35:40, decelerates for five seconds from 15:35:40, and stops at 15:35:45. In this case, the collection unit 203 may collect time-series data consisting of six data items, such as (time, speed) = (0 seconds, 20 km / h), (1 second, 15 km / h), (2 seconds, 10 km / h), (3 seconds, 7 km / h), (4 seconds, 3 km / h), and (5 seconds, 0 km / h). Also assume that the vehicle 30 traveling at 20 km / h accelerates for six seconds from 15:35:40, reaches a constant speed of 50 km / h, and continues traveling at a constant speed. In this case, the collection unit 203 may collect time series data consisting of seven pieces of data: (time, speed) = (0 seconds, 20 km / h), (1 second, 25 km / h), (2 seconds, 30 km / h), (3 seconds, 40 km / h), (4 seconds, 45 km / h), (5 seconds, 48 km / h), and (6 seconds, 50 km / h). Note that this time series data is merely an example and is not limited to this. For example, the measurement interval of the time series data may be 0.1 seconds or 0.5 seconds instead of 1 second, and may not be equal intervals.

[0039] In step S12, the collection unit 203 collects evaluation values for acceleration-related driving operations and deceleration-related driving operations from one or more occupants of the vehicle 30. The evaluation values may be on any number of levels. For example, evaluation values may be collected on a 10-level scale (1 to 10) for the time-series data exemplified in the processing procedure of step S11. Note that the processing procedure of step S12 may collect an evaluation value from the occupants each time an acceleration or deceleration operation is performed, or may collect an evaluation value for a series of driving operations from the occupants after a series of driving operations from the departure point to the destination is completed. When collecting evaluation values for the series of driving operations, the collection unit 203 may assign the same evaluation value to all acceleration or deceleration operations performed during the series of driving operations.

[0040] In step S13, the collection unit 203 associates the set of driving method cluster type, time-series data, and evaluation value collected in the processing procedure of steps S10 to S12, and stores them in the collected data DB 200a. For example, suppose that a passenger in the safe driving cluster gave an evaluation value of 7 to the time-series data consisting of the above-mentioned six pieces of data. In this case, the collection unit 203 associates the time-series data consisting of the six pieces of data, the safe driving cluster, and the evaluation value of 7, and stores them in the collected data DB 200a. Similarly, suppose that a passenger in the time-focused cluster gave an evaluation value of 3 to the time-series data consisting of the above-mentioned six pieces of data. In this case, the collection unit 203 associates the time-series data consisting of the six pieces of data, the time-focused cluster, and the evaluation value of 3, and stores them in the collected data DB 200a.

[0041] The server 20 repeats the processing procedure of steps S10 to S13 to collect a large number of pairs of driving method cluster types, time-series data, and evaluation values.

[0042] Fig. 6 is a diagram showing an example of the collected data DB. An "identification number" is an identifier for identifying collected data, and is uniquely assigned when the collection unit 203 stores a set of a driving method cluster type, time-series data, and evaluation value in the collected data DB 200a. By repeatedly executing the processing procedure of steps S10 to S13 in Fig. 5 described above, records are added to the collected data DB 200a.

[0043] (Generation of speed control parameters and evaluation models) FIG. 7 is a flowchart showing an example of a process for generating a speed control parameter and an evaluation model.

[0044] In step S20, the generator 202 acquires time-series data from the collected data DB 200a and generates a speed control parameter from the acquired time-series data. An example of the function f that defines the acceleration / deceleration pattern of the vehicle 30 is shown in Equation (1).

number

[0045] Next, the generation unit 202 uses the least squares method as shown in equation (2) to calculate constants a, b, c, and d that best fit the time series data when the time series data is expressed using a function f.

number

[0046] FIG. 8 is a diagram illustrating a method for calculating constants that fit time-series data. The time-series data in FIG. 8 includes eight data points, i.e., i=1 to i=8. The data point i=1 indicates the speed at time 0, i.e., the running speed, and the data point i=8 indicates that the speed became zero after T seconds. The generator 202 calculates constants a, b, c, and d that best fit the eight time-series data points using equation (2). That is, for all data points i=1 to i=8 included in the time-series data, the generator 202 calculates the square of the value obtained by subtracting the speed calculated by the function f from the i-th speed in the time-series data acquired from the collected data DB 200a, and searches for a parameter p that minimizes the sum of the eight calculated values. The least-squares method may be used using an existing library or by exhaustively testing all possible values of the parameter p.

[0047] Next, the generation unit 202 sets the speed in the first data of the eight data included in the time series data (i.e., the speed at 0 seconds) as the starting speed of the vehicle 30, and the speed in the last data (i.e., the speed at T seconds) as the ending speed, and stores them in the speed control parameter DB200b together with the calculated constant.

[0048] FIG. 9 is a diagram showing an example of the rate control parameter DB 200b. The "identification number" is an identifier that uniquely identifies the rate control parameter. The identification number is set to the same identification number as that of the collected data DB 200a. For example, if a rate control parameter is generated using the time-series data in the first row of the collected data DB 200a, the identification number of the rate control parameter DB 200b is set to "0001", the same as that of the collected data DB 200a. The "rate control parameter" includes the start rate, end rate, and one or more constant values applied to the function. The one or more constants correspond to the constants a, b, c, and d in equation (1).

[0049] The generation unit 202 calculates constants for all time-series data stored in the collected data DB 200a according to the method described above, and stores the constants in the speed control parameter DB 200b together with the start speed and end speed. In the first embodiment, it is desirable to collect multiple pieces of time-series data of vehicle speed representing driving operations performed by a professional driver or the like, at least for each combination of start speed and end speed used in autonomous driving. As a result, the speed control parameter DB 200b stores multiple speed control parameters for each combination of start speed and end speed. Returning to FIG. 7, the explanation will continue.

[0050] In step S21, the generation unit 202 generates, for each driving method cluster, an evaluation model that outputs an evaluation value when a speed control parameter is input. The generation unit 202 may generate either an evaluation function or a trained model, or may generate both.

[0051] Equation (3) is an example of the evaluation function u.

number

number

[0052] The generation unit 202 calculates the evaluation function u corresponding to the safe driving cluster by using the least squares method according to equation (4) for all pairs of speed control parameters and evaluation values whose driving method clusters correspond to the safe driving cluster. k is assigned an evaluation value obtained from the collected data DB 200a. That is, the generation unit 202 calculates the square of the value obtained by subtracting the evaluation value obtained by the evaluation function u from the occupant's evaluation value for all pairs of speed control parameter and evaluation value, and searches for the weighting factor w that minimizes the sum of the calculated values. The least squares method may be used using an existing library or the like, or may be performed by trying all possible patterns of weight w. The generation unit 202 stores data indicating the generated evaluation function in the evaluation model 200c in association with a driving method cluster (here, a safety method cluster).

[0053] Next, the generation unit 202 calculates evaluation formulas u corresponding to other driving method clusters (time-focused cluster and both-focused cluster) in a similar manner, and stores data indicating the generated evaluation functions in the evaluation model 200c in association with the driving method clusters.

[0054] The generation unit 202 acquires all pairs of speed control parameters and occupant evaluation values corresponding to the safe driving cluster from the collected data DB 200a and the speed control parameter DB 200b. Subsequently, the generation unit 202 trains a model using all or some of the acquired pairs of speed control parameters and occupant evaluation values as training data. Any algorithm may be used for the model, and for example, a neural network or gradient boosting may be used. The generation unit 202 stores a parameter set of the trained model generated by training in the evaluation model 200c in association with the driving method cluster (here, the safety method cluster). Furthermore, the generation unit 202 generates models corresponding to other driving method clusters (the time-focused cluster and the both-focused cluster) in a similar manner, and stores a parameter set of the trained model generated by training in the evaluation model 200c in association with the driving method cluster.

[0055] The communication processing unit 201 of the server 20 transmits the speed control parameter DB 200b and the evaluation model 200c generated by the processing procedure described above to the in-vehicle device 10. The communication processing unit 104 of the in-vehicle device 10 stores the speed control parameter DB 200b and the evaluation model 200c received from the server 20 in the speed control parameter DB 100a and the evaluation model 100b of the storage unit 100, respectively.

[0056] (Automatic driving control) FIG. 10 is a flowchart showing an example of a processing procedure when the in-vehicle device 10 executes automatic driving control.

[0057] In step S30, the acquisition unit 101 acquires, from the plurality of driving method clusters, a driving method cluster related to the occupants of the vehicle 30 or a driving method cluster related to the cargo of the vehicle 30. Specifically, if the vehicle 30 is intended to transport occupants, the acquisition unit 101 acquires a driving method cluster related to each of one or more occupants of the vehicle 30. Furthermore, if a driver is on board the vehicle 30, the acquisition unit 101 acquires a driving method cluster related to each of one or more occupants other than the driver. For example, the acquisition unit 101 may receive preferences regarding driving operations from each occupant of the vehicle 30, or may estimate a driving method cluster from an image captured by a camera mounted on the vehicle 30. For example, it is conceivable that an elderly woman may be estimated to belong to the safe driving cluster, and a man in a suit may be estimated to belong to the time-focused cluster.

[0058] Furthermore, when the vehicle 30 is intended to transport cargo, the acquiring unit 101 acquires a driving method cluster related to the cargo. In this case, the acquiring unit 101 may receive a designation of a driving method cluster corresponding to the cargo from a worker or the like who gets on the vehicle 30.

[0059] In step S31, the control unit 103 starts automatic driving control based on the acquired driving method cluster.

[0060] In step S32, if the control unit 103 determines that acceleration or deceleration is to be performed, the process proceeds to step S33. If the control unit 103 determines that acceleration or deceleration is not to be performed, the process proceeds to step S35.

[0061] In step S33, the control unit 103 determines to what km / h the vehicle 30 should be accelerated or decelerated from the current speed. That is, the control unit 103 determines a target speed. Next, the determination unit 102 determines a speed control parameter to be used for accelerating or decelerating the vehicle 30, based on the driving method cluster acquired in the processing procedure of step S30. For example, the determination unit 102 may determine, from among the multiple speed control parameters stored in the speed control parameter DB 100a, a speed control parameter whose start speed and end speed correspond to the current speed and target speed of the vehicle 30 and whose evaluation value corresponding to the driving method cluster acquired by the acquisition unit 101 is the highest, as the speed control parameter to be applied to the vehicle 30.

[0062] For example, suppose that the control unit 103 determines to stop the vehicle 30 traveling at 20 km / h. The driving style cluster for the occupant or cargo is a time-focused cluster. The evaluation value is determined using a trained model. In this case, the determination unit 102 references the speed control parameter DB 100a and acquires multiple speed control parameters whose starting speed and ending speed are 20 km / h and 0 km / h, respectively. The determination unit 102 then inputs parameters p(a, b, c, d) included in each of the acquired speed control parameters into a trained model corresponding to the time-focused cluster, thereby acquiring an evaluation value for each of the acquired speed control parameters. The determination unit 102 then determines the parameter p(a, b, c, d) with the highest acquired evaluation value as the speed control parameter to be applied to the vehicle 30.

[0063] Here, if the vehicle 30 is a bus or a taxi, etc., and has multiple occupants, it is assumed that each occupant will have a different driving style cluster. For example, if there are two occupants, one occupant may have a time-focused cluster and the other may have a both-focused cluster. That is, the driving style cluster acquired by the acquisition unit 101 in the processing procedure of step S30 may include multiple driving style clusters (i.e., driving style clusters for each occupant riding in the vehicle 30). In this case, the determination unit 102 may determine, as the speed control parameter to be applied to the vehicle 30, a speed control parameter whose start speed and end speed correspond to the current speed and target speed of the vehicle 30 and which has the highest total evaluation value corresponding to each of the multiple driving style clusters acquired by the acquisition unit 101, from among the multiple speed control parameters.

[0064] For example, suppose the control unit 103 determines to accelerate the stopped vehicle 30 to 40 km / h. Also, suppose there are two occupants, one in the time-focused cluster and one in the safe driving cluster. Furthermore, suppose the evaluation value is determined using an evaluation model. In this case, the determination unit 102 references the speed control parameter DB 100a and acquires multiple speed control parameters whose start speed and end speed are 0 km / h and 40 km / h, respectively. Next, the determination unit 102 inputs parameters p (a, b, c, d) included in each acquired speed control parameter into an evaluation model corresponding to the time-focused cluster and an evaluation model corresponding to the safe driving cluster, thereby acquiring an evaluation value for the time-focused cluster and an evaluation value for the safe driving cluster for each acquired speed control parameter.

[0065] Next, the determination unit 102 determines the speed control parameter that maximizes the evaluation value according to the following equation 5.

number

[0066] For example, assume that there are speed control parameters A and B whose start speed and end speed are 0 km / h and 40 km / h, respectively. c Assume that the importance of each driving method cluster is the same (for example, 1) for each driving method cluster. Assume that the evaluation values for speed control parameter A are "5" and "8" for the time-focused cluster and the safe driving cluster, respectively. Assume that the evaluation values for speed control parameter B are "9" and "2" for the time-focused cluster and the safe driving cluster, respectively. According to Equation 5, the sum of the evaluation values for each driving method cluster for speed control parameter A is 5 + 8 = 13. The sum of the evaluation values for speed control parameter B for each driving method cluster is 9 + 2 = 11. Therefore, the determination unit 102 determines speed control parameter A as the speed control parameter to be applied to the vehicle 30. This makes it possible to determine a speed control parameter even when multiple occupants with different driving method clusters are on board.

[0067] According to Equation 5, n c That is, the determination unit 102 may determine, as the speed control parameter to be applied to the vehicle 30, a speed control parameter whose start speed and end speed correspond to the current speed and target speed of the vehicle 30 and whose total of evaluation values obtained by multiplying the evaluation values corresponding to each of the driving method clusters acquired by the acquisition unit 101 by the number of occupants in the driving method cluster is the highest.

[0068] For example, in the above example, assume that there are three occupants, two of whom are in the time-focused cluster and one in the safe driving cluster. In this case, according to Equation 5, the sum of the evaluation values for the speed control parameter A for each driving method cluster is 5×2+8=18. Furthermore, the sum of the evaluation values for the speed control parameter B for each driving method cluster is 9×2+2=20. Therefore, the determination unit 102 determines the speed control parameter B as the speed control parameter to be applied to the vehicle 30. This makes it possible to determine the speed control parameter taking into account the number of occupants in each cluster, even when there are multiple occupants in different driving method clusters.

[0069] Furthermore, according to Equation 5, m c is multiplied by the evaluation value. A different value may be set for the importance for each driving method cluster. When determining the speed control parameters, the determination unit 102 may weight the evaluation values based on the importance of the driving method cluster. First, the determination unit 102 selects, from among the speed control parameters, multiple speed control parameter candidates whose start speeds and end speeds correspond to the current speed and target speed of the vehicle 30. Next, the determination unit 102 determines, for each driving method cluster acquired by the acquisition unit 101, an evaluation value corresponding to each of the selected multiple speed control parameter candidates. Next, the determination unit 102 weights the evaluation value for each determined driving method cluster according to the importance of the driving method cluster. Note that the determination unit 102 may weight the evaluation value obtained by multiplying the evaluation value for each determined driving method cluster by the number of occupants in the driving method cluster according to the importance of the driving method cluster. Finally, the determination unit 102 determines the speed control parameter with the highest total weighted evaluation value as the speed control parameter to be applied to the vehicle 30.

[0070] For example, in the above example, assume that there are two occupants, one in the time-focused cluster, and one in the safe driving cluster. Also, assume that the importance of the time-focused cluster is 1, and the importance of the safe driving cluster is 2. In this case, according to Equation 5, the sum of the evaluation values for each driving method cluster for speed control parameter A is 5 + 8 × 2 = 21. Also, the sum of the evaluation values for each driving method cluster for speed control parameter B is 9 + 2 × 2 = 13. Therefore, the determination unit 102 determines speed control parameter A as the speed control parameter to be applied to the vehicle 30. This makes it possible to determine the speed control parameter according to the importance of the driving method cluster.

[0071] When determining the speed control parameter that maximizes the evaluation value according to Equation 5, the determination unit 102 may ignore speed control parameters for which the evaluation values of at least some driving method clusters are less than a predetermined value without applying them to Equation 5. In other words, the determination unit 102 may determine, from among the multiple speed control parameters, the speed control parameter whose start speed and end speed correspond to the current speed and target speed of the vehicle 30 and whose total evaluation value corresponding to each of the multiple driving method clusters acquired by the acquisition unit 101 is equal to or greater than a predetermined value, as the speed control parameter to be applied to the vehicle 30.

[0072] Here, it is assumed that the predetermined value is set to "4." It is assumed that there are speed control parameters C and D whose start speed and end speed are 0 km / h and 40 km / h, respectively. Furthermore, m in Equation 5 c Assume that the importance of each driving method cluster is the same (for example, 1). Also, the evaluation values for the speed control parameter C are "5" and "6" for the time-focused cluster and the safe driving cluster, respectively. Also, the evaluation values for the speed control parameter D are "8" and "2" for the time-focused cluster and the safe driving cluster, respectively.

[0073] Because the evaluation value of the safe driving cluster for the speed control parameter D is 2, which is less than the predetermined value, the determination unit 102 ignores the speed control parameter D. Therefore, the determination unit 102 determines the speed control parameter C as the speed control parameter to be applied to the vehicle 30. This makes it possible to prevent a speed control parameter having an evaluation value less than the predetermined value in at least some driving method clusters from being selected.

[0074] In step S34, the control unit 103 performs control to accelerate or decelerate the vehicle 30 using the speed control parameters determined in the processing procedure of step S33.

[0075] In step S35, the control unit 103 ends the process if the autonomous driving is to be ended, and returns to the processing procedure of step S32 if the autonomous driving is not to be ended. After the autonomous driving is ended, the server 20 may collect time-series data and occupant evaluation values when the vehicle 30 actually travels, and update the collected data DB 200a, using a method similar to that of Fig. 5. The server 20 may also update the evaluation model using the updated collected data DB 200a, using a method similar to that of Fig. 7.

[0076] <<Second embodiment>> In the first embodiment, the start speed and the end speed are associated with the speed control parameter. Meanwhile, in the second embodiment, the speed change amount may be associated with the speed control parameter. For example, the speed change shown in FIG. 8 is an example of deceleration from 20 km / h to 0 km / h in T seconds. However, when decelerating by 20 km / h in T seconds, such as when decelerating from 60 km / h to 40 km / h in T seconds or when decelerating from 40 km / h to 20 km / h in T seconds, it is expected that the speed change will have a graph shape similar to that shown in FIG. 8 regardless of the start speed in km / h, and that the occupant's evaluation will also be similar. It is also expected that this will be the case not only when decelerating but also when accelerating.

[0077] Therefore, the server 20 may perform the following processing steps in the processing procedure of Fig. 7. Note that, points that are not particularly mentioned may be the same as those described in the first embodiment.

[0078] In step S20, the generation unit 202 acquires time-series data from the collected data DB 200a and generates a speed control parameter from the acquired time-series data. At this time, the generation unit 202 converts the acquired time-series data into time-series data when accelerating from 0 km or time-series data when decelerating to 0 km by subtracting the lowest speed value from each of the multiple data included in the acquired time-series data. For example, assume that the acquired time-series data includes seven pieces of data: (time, speed) = (0 seconds, 20 km / h), (1 second, 25 km / h), (2 seconds, 30 km / h), (3 seconds, 40 km / h), (4 seconds, 45 km / h), (5 seconds, 48 km / h), and (6 seconds, 50 km / h). In this case, the lowest speed data is 20 km / h, so the generation unit 202 subtracts 20 km / h from each of the seven pieces of data to convert the acquired time series data into seven pieces of data: (time, speed) = (0 seconds, 0 km / h), (1 second, 5 km / h), (2 seconds, 10 km / h), (3 seconds, 20 km / h), (4 seconds, 25 km / h), (5 seconds, 28 km / h), (6 seconds, 30 km / h).

[0079] Next, the generating unit 202 calculates the constants a, b, c, and d that best fit the converted time series data using equation (2).

[0080] Next, the generation unit 202 subtracts the speed in the first data from the speed in the last data of the seven data included in the time series data (i.e., the speed of 30 km at 6 seconds), and stores this value as the speed change amount in the speed control parameter DB 200b together with the calculated constant.

[0081] In this modification, the "speed control parameters" in the speed control parameter DB 200b include "speed change amounts and constant values of 1 or more applied to functions" instead of "start speed, end speed, and constant values of 1 or more applied to functions." In the example of time-series data above, the speed control parameters store +30 km / h as the speed change amount. If the time-series data indicates a deceleration pattern (i.e., braking), a negative value, such as -20 km / h, will be stored as the speed change amount.

[0082] According to the modified example described above, the generation unit 202 calculates constants for all time-series data stored in the collected data DB 200a and stores the constants together with the speed change amount in the speed control parameter DB 200b. In this modified example, it is desirable to collect multiple pieces of time-series data of vehicle speed that represent driving operations performed by a professional driver or the like, at least for each speed change amount used in autonomous driving. As a result, the speed control parameter DB 200b stores multiple speed control parameters for each speed change amount.

[0083] The server 20 may also perform the following processing steps in the processing procedure of Fig. 10. Note that the points not specifically mentioned may be the same as those explained above.

[0084] In step S33, the control unit 103 determines a target speed of the vehicle 30. Subsequently, the determination unit 102 determines a speed control parameter to be used for accelerating or decelerating the vehicle 30, based on the driving method cluster acquired in the processing procedure of step S30. For example, the determination unit 102 may determine, as the speed control parameter to be applied to the vehicle 30, from among the multiple speed control parameters stored in the speed control parameter DB 100a, a speed control parameter whose speed change amount corresponds to a value obtained by subtracting the current speed from the target speed of the vehicle 30 and whose evaluation value corresponding to the driving method cluster acquired by the acquisition unit 101 is the highest.

[0085] For example, suppose that the control unit 103 determines to decelerate the vehicle 30, which is traveling at 40 km / h, to 20 km / h. The driving style cluster for the occupant or cargo is a time-focused cluster. The evaluation value is determined using a trained model. In this case, the determination unit 102 refers to the speed control parameter DB 100a and acquires multiple speed control parameters for which the speed change amount is −20 km / h. The determination unit 102 then inputs parameters p(a, b, c, d) included in each of the acquired speed control parameters into a trained model corresponding to the time-focused cluster, thereby acquiring an evaluation value for each of the acquired speed control parameters. The determination unit 102 then determines the parameter p(a, b, c, d) with the highest acquired evaluation value as the speed control parameter to be applied to the vehicle 30.

[0086] Here, if the vehicle 30 is a bus or a taxi with multiple occupants, it is assumed that each occupant will have a different driving style cluster. In this case, the determination unit 102 may determine, from among the multiple speed control parameters, a speed control parameter that corresponds to a value obtained by subtracting the current speed from the target speed of the vehicle 30 and that has the highest total of evaluation values corresponding to each of the multiple driving style clusters acquired by the acquisition unit 101, as the speed control parameter to be applied to the vehicle 30.

[0087] For example, suppose the control unit 103 decides to accelerate the stopped vehicle 30 to 40 km / h. Also, suppose there are two occupants, one in the time-focused cluster and one in the safe driving cluster. Also, suppose the evaluation value is determined using an evaluation model. In this case, the determination unit 102 refers to the speed control parameter DB 100a and acquires multiple speed control parameters whose speed change amount is +40 km / h. Next, the determination unit 102 inputs parameters p (a, b, c, d) included in each acquired speed control parameter into an evaluation model corresponding to the time-focused cluster and an evaluation model corresponding to the safe driving cluster, thereby acquiring an evaluation value for the time-focused cluster and an evaluation value for the safe driving cluster for each acquired speed control parameter.

[0088] Next, the determining unit 102 determines the speed control parameters that maximize the evaluation value according to Equation 5.

[0089] According to Equation 5, n c That is, the determination unit 102 may determine, as the speed control parameter to be applied to the vehicle 30, a speed control parameter that corresponds to a speed change amount obtained by subtracting the current speed of the vehicle 30 from the target speed of the vehicle 30 and that has the highest total of evaluation values obtained by multiplying the evaluation values corresponding to each of the driving method clusters acquired by the acquisition unit 101 by the number of occupants in the driving method cluster.

[0090] Furthermore, according to Equation 5, m c is multiplied by the evaluation value. A different value may be set for the importance for each driving method cluster. When determining the speed control parameters, the determination unit 102 may weight the evaluation values based on the importance of the driving method cluster. First, the determination unit 102 selects, from among the multiple speed control parameters, multiple speed control parameter candidates whose speed change amount corresponds to the value obtained by subtracting the current speed of the vehicle 30 from the target speed of the vehicle 30. Next, the determination unit 102 determines an evaluation value corresponding to each of the selected multiple speed control parameter candidates for each driving method cluster acquired by the acquisition unit 101. Next, the determination unit 102 weights the evaluation value for each determined driving method cluster according to the importance of the driving method cluster. Note that the determination unit 102 may weight the evaluation value obtained by multiplying the evaluation value for each determined driving method cluster by the number of occupants in the driving method cluster according to the importance of the driving method cluster. Finally, the determination unit 102 determines the speed control parameter with the highest total weighted evaluation value as the speed control parameter to be applied to the vehicle 30.

[0091] When determining the speed control parameter that maximizes the evaluation value according to Equation 5, the determination unit 102 may ignore speed control parameters for which the evaluation values of at least some driving method clusters are less than a predetermined value, without applying them to Equation 5. That is, the determination unit 102 may determine, from among the multiple speed control parameters, the speed control parameter that maximizes the speed change amount corresponding to the value obtained by subtracting the current speed of the vehicle 30 from the target speed of the vehicle 30 and that maximizes the sum of evaluation values for the multiple driving method clusters acquired by the acquisition unit 101 that are equal to or greater than a predetermined value, as the speed control parameter to be applied to the vehicle 30. In step S34, the control unit 103 controls the vehicle 30 to accelerate or decelerate using the speed control parameter determined in the processing procedure of step S33. For example, assume that the control unit 103 determines in the processing procedure of step S32 to decelerate the vehicle 30 from 40 km / h to 20 km / h. In this case, in the processing procedure of step S33, one speed control parameter with a speed change amount of −20 km / h is selected. Therefore, the control unit 103 decelerates the vehicle 30 traveling at 40 km / h to 20 km / h so as to follow the graph shape of the function f indicated by the selected speed control parameters.

[0092] <<Third Embodiment>> In the first and second embodiments described above, the in-vehicle device 10 determines the speed control parameters to be applied to the vehicle 30 in accordance with the driving method cluster of the occupant or the load, but in the third embodiment, the server 20 may determine the speed control parameters to be applied to the vehicle 30. Points not specifically mentioned may be the same as those in the first and second embodiments.

[0093] FIG. 11 is a diagram showing an example of a functional block configuration of an in-vehicle device 10 according to the third embodiment. FIG. 12 is a diagram showing an example of a functional block configuration of a server 20 according to the third embodiment. As shown in FIG. 12, the server 20 may include a determination unit 204. As shown in FIG. 11, the in-vehicle device 10 may not include the determination unit 102, speed control parameter DB 100a, and evaluation model 100b that are present in FIG. 3. Other points that are not particularly mentioned are the same as those in FIGS. 3 and 4, and therefore description thereof will be omitted.

[0094] 13 is a sequence diagram showing the processing procedure between the in-vehicle device 10 and the server 20 according to the third embodiment. The processing procedure in FIG. 13 is executed in steps S33 and S34 in the processing procedure in FIG.

[0095] In step S100, the communication processing unit 104 transmits information about the current speed of the vehicle 30, the target speed, and the driving style clusters of the occupants or cargo to the server 20. If the vehicle 30 has multiple occupants, the communication processing unit 104 transmits the driving style clusters for each occupant to the server 20.

[0096] In step S101, the determination unit 204 of the server 20 determines the speed control parameters to be applied to the vehicle 30 by a processing procedure similar to the processing procedure of step S34 in the processing procedure of FIG.

[0097] In step S102, the communication processing unit 201 of the server 20 transmits the determined speed control parameters to be applied to the vehicle 30 to the in-vehicle device 10. The control unit 103 of the in-vehicle device 10 performs automatic control of the vehicle 30 using the speed control parameters received from the server 20.

[0098] <Summary> According to the above-described embodiments, a driving style cluster related to occupants or cargo is defined, and speed control parameters are determined based on the driving style cluster. This makes it possible to realize speed control according to the cluster of occupants, etc. Furthermore, since the driver performs the driving operation himself, he can predict the occurrence of sudden braking and sudden acceleration. However, since sudden braking and sudden acceleration seem to occur suddenly to occupants other than the driver, the discomfort caused by sudden braking and sudden acceleration is greater than that felt by the driver. According to each embodiment, speed control according to the cluster of occupants is realized, thereby reducing the discomfort felt by occupants, including those other than the driver, and providing a comfortable ride for occupants. Furthermore, the technology according to each embodiment can contribute to the achievement of Goal 9 of the Sustainable Development Goals (SDGs), "Build resilient infrastructure, promote inclusive and sustainable development, and promote industrial and technological innovation."

[0099] The above-described embodiments are intended to facilitate understanding of the present invention and are not intended to limit the present invention. The flowcharts, sequences, elements included in the embodiments, and their arrangements, materials, conditions, shapes, sizes, etc. are not limited to those illustrated and can be modified as appropriate. Furthermore, configurations shown in different embodiments can be partially substituted or combined with each other. [Explanation of symbols]

[0100] 1...Autonomous driving system, 10...In-vehicle device, 11...Processor, 12...Storage device, 13...Communication IF, 14...Input device, 15...Output device, 20...Server, 30...Vehicle, 100...Storage unit, 100a...Speed control parameter DB, 100b...Evaluation model, 101...Acquisition unit, 102...Determination unit, 103...Control unit, 104...Communication processing unit, 200...Storage unit, 200a...Collected data DB, 200b...Speed control parameter DB, 200c...Evaluation model, 201...Communication processing unit, 202...Generation unit, 203...Collecting unit, 204...Determination unit

Claims

1. An acquisition unit that acquires, from among a plurality of clusters related to driving methods, a cluster of driving methods according to the preferences of passengers other than the driver who are riding in the vehicle or a cluster of driving methods according to the characteristics of cargo in the vehicle; a determination unit that determines a speed control parameter that defines a speed change of the vehicle based on the cluster acquired by the acquisition unit; a control unit that controls the speed of the vehicle in accordance with the acceleration / deceleration pattern represented by the speed control parameter determined by the determination unit; and the speed control parameters include a plurality of speed control parameters for each combination of a start speed and an end speed used when controlling the speed of the vehicle from a current speed to a target speed, the determination unit determines, from among the plurality of speed control parameters, a speed control parameter whose start speed and end speed correspond to the current speed and target speed of the vehicle and whose evaluation value corresponding to the cluster acquired by the acquisition unit is the highest, as the speed control parameter to be applied to the vehicle. Information processing device.

2. An acquisition unit that acquires, from among a plurality of clusters related to driving methods, a cluster of driving methods according to the preferences of passengers other than the driver who are riding in the vehicle or a cluster of driving methods according to the characteristics of cargo in the vehicle; a determination unit that determines a speed control parameter that defines a speed change of the vehicle based on the cluster acquired by the acquisition unit; a control unit that controls the speed of the vehicle in accordance with the acceleration / deceleration pattern represented by the speed control parameter determined by the determination unit; and the speed control parameters include a plurality of speed control parameters for each combination of a start speed and an end speed used when controlling the speed of the vehicle from a current speed to a target speed, the clusters acquired by the acquisition unit include a cluster for each occupant riding in the vehicle; the determination unit determines, from among the plurality of speed control parameters, a speed control parameter whose start speed and end speed correspond to the current speed and target speed of the vehicle and which has the highest total of evaluation values corresponding to each of the clusters for each occupant acquired by the acquisition unit, as the speed control parameter to be applied to the vehicle. Information processing device.

3. The determination unit selecting, from the plurality of speed control parameters, a plurality of speed control parameter candidates whose start speed and end speed correspond to the current speed and target speed of the vehicle; determining an evaluation value corresponding to each of the selected plurality of speed control parameter candidates for each of the clusters acquired by the acquisition unit; weighting the evaluation values for each cluster in accordance with the importance of the cluster, and determining the speed control parameter that gives the highest total weighted evaluation value as the speed control parameter to be applied to the vehicle; The information processing device according to claim 2 .

4. An acquisition unit that acquires, from among a plurality of clusters related to driving methods, a cluster of driving methods according to the preferences of occupants other than the driver who rides in the vehicle or a cluster of driving methods according to the characteristics of cargo in the vehicle; a determination unit that determines a speed control parameter that defines a speed change of the vehicle based on the cluster acquired by the acquisition unit; a control unit that controls the speed of the vehicle in accordance with the acceleration / deceleration pattern represented by the speed control parameter determined by the determination unit; and the speed control parameters include a plurality of speed control parameters for each speed change amount, the determination unit determines, from among the plurality of speed control parameters, a speed control parameter whose speed change amount corresponds to a value obtained by subtracting a current speed of the vehicle from a target speed of the vehicle and whose evaluation value corresponding to the cluster acquired by the acquisition unit is the highest, as a speed control parameter to be applied to the vehicle. Information processing device.

5. An acquisition unit that acquires, from among a plurality of clusters related to driving methods, a cluster of driving methods according to the preferences of passengers other than the driver who are riding in the vehicle or a cluster of driving methods according to the characteristics of cargo in the vehicle; a determination unit that determines a speed control parameter that defines a speed change of the vehicle based on the cluster acquired by the acquisition unit; a control unit that controls the speed of the vehicle in accordance with the acceleration / deceleration pattern represented by the speed control parameter determined by the determination unit; and the speed control parameters include a plurality of speed control parameters for each speed change amount, the clusters acquired by the acquisition unit include a cluster for each occupant riding in the vehicle; the determination unit determines, from among the plurality of speed control parameters, a speed control parameter whose speed change amount corresponds to a value obtained by subtracting a current speed of the vehicle from a target speed of the vehicle and whose total of evaluation values corresponding to each of the clusters for each occupant acquired by the acquisition unit is the highest, as the speed control parameter to be applied to the vehicle. Information processing device.

6. The determination unit selecting, from the plurality of speed control parameters, a plurality of speed control parameter candidates whose speed change amount corresponds to a value obtained by subtracting a current speed from a target speed of the vehicle; determining an evaluation value corresponding to each of the selected plurality of speed control parameter candidates for each of the clusters acquired by the acquisition unit; weighting the evaluation values for each cluster in accordance with the importance of the cluster, and determining the speed control parameter that gives the highest total weighted evaluation value as the speed control parameter to be applied to the vehicle; The information processing device according to claim 5 .

7. the determination unit determines an evaluation value by inputting the speed control parameter into a predetermined evaluation model. The information processing device according to any one of claims 1 to 6.

8. The evaluation model is a trained model generated by training a machine learning model. The information processing device according to claim 7 .

9. An acquisition unit that acquires, from among a plurality of clusters related to driving methods, a cluster of driving methods according to the preferences of passengers other than the driver who are riding in the vehicle or a cluster of driving methods according to the characteristics of cargo in the vehicle; a determination unit that determines a speed control parameter that defines a speed change of the vehicle based on the cluster acquired by the acquisition unit; a control unit that controls the speed of the vehicle in accordance with the acceleration / deceleration pattern represented by the speed control parameter determined by the determination unit; and the speed control parameters include a plurality of speed control parameters for each combination of a start speed and an end speed used when controlling the speed of the vehicle from a current speed to a target speed, the determination unit determines, from among the plurality of speed control parameters, a speed control parameter whose start speed and end speed correspond to the current speed and target speed of the vehicle and whose evaluation value corresponding to the cluster acquired by the acquisition unit is the highest, as the speed control parameter to be applied to the vehicle. vehicle.

10. An acquisition unit that acquires, from among a plurality of clusters related to driving methods, a cluster of driving methods according to the preferences of passengers other than the driver who are riding in the vehicle or a cluster of driving methods according to the characteristics of cargo in the vehicle; a determination unit that determines a speed control parameter that defines a speed change of the vehicle based on the cluster acquired by the acquisition unit; a control unit that controls the speed of the vehicle in accordance with the acceleration / deceleration pattern represented by the speed control parameter determined by the determination unit; and the speed control parameters include a plurality of speed control parameters for each combination of a start speed and an end speed used when controlling the speed of the vehicle from a current speed to a target speed, the clusters acquired by the acquisition unit include a cluster for each occupant riding in the vehicle; the determination unit determines, from among the plurality of speed control parameters, a speed control parameter whose start speed and end speed correspond to the current speed and target speed of the vehicle and which has the highest total of evaluation values corresponding to each of the clusters for each occupant acquired by the acquisition unit, as the speed control parameter to be applied to the vehicle. vehicle.

11. An acquisition unit that acquires, from among a plurality of clusters related to driving methods, a cluster of driving methods according to the preferences of passengers other than the driver who are riding in the vehicle or a cluster of driving methods according to the characteristics of cargo in the vehicle; a determination unit that determines a speed control parameter that defines a speed change of the vehicle based on the cluster acquired by the acquisition unit; a control unit that controls the speed of the vehicle in accordance with the acceleration / deceleration pattern represented by the speed control parameter determined by the determination unit; and the speed control parameters include a plurality of speed control parameters for each speed change amount, the determination unit determines, from among the plurality of speed control parameters, a speed control parameter whose speed change amount corresponds to a value obtained by subtracting a current speed of the vehicle from a target speed of the vehicle and whose evaluation value corresponding to the cluster acquired by the acquisition unit is the highest, as a speed control parameter to be applied to the vehicle. vehicle.

12. An acquisition unit that acquires, from among a plurality of clusters related to driving methods, a cluster of driving methods according to the preferences of passengers other than the driver who are riding in the vehicle or a cluster of driving methods according to the characteristics of cargo in the vehicle; a determination unit that determines a speed control parameter that defines a speed change of the vehicle based on the cluster acquired by the acquisition unit; a control unit that controls the speed of the vehicle in accordance with the acceleration / deceleration pattern represented by the speed control parameter determined by the determination unit; and the speed control parameters include a plurality of speed control parameters for each speed change amount, the clusters acquired by the acquisition unit include a cluster for each occupant riding in the vehicle; the determination unit determines, from among the plurality of speed control parameters, a speed control parameter whose speed change amount corresponds to a value obtained by subtracting a current speed of the vehicle from a target speed of the vehicle and whose total of evaluation values corresponding to each of the clusters for each occupant acquired by the acquisition unit is the highest, as the speed control parameter to be applied to the vehicle. vehicle.

13. A step in which an information processing device relating to driving methods acquires, from a plurality of clusters, a cluster of driving methods according to the preferences of occupants other than the driver riding in the vehicle or a cluster of driving methods according to the characteristics of cargo in the vehicle; an information processing device determining a speed control parameter that defines a speed change of the vehicle based on the acquired cluster; an information processing device controlling the speed of the vehicle in accordance with an acceleration / deceleration pattern represented by the determined speed control parameter; Including, the speed control parameters include a plurality of speed control parameters for each combination of a start speed and an end speed used when controlling the speed of the vehicle from a current speed to a target speed, the determining step determines, from among the plurality of speed control parameters, a speed control parameter whose start speed and end speed correspond to the current speed and target speed of the vehicle and whose evaluation value corresponding to the acquired cluster is the highest, as the speed control parameter to be applied to the vehicle; Information processing methods.

14. A step in which an information processing device relating to driving methods acquires, from a plurality of clusters, a cluster of driving methods according to the preferences of occupants other than the driver riding in the vehicle or a cluster of driving methods according to the characteristics of cargo in the vehicle; an information processing device determining a speed control parameter that defines a speed change of the vehicle based on the acquired cluster; an information processing device controlling the speed of the vehicle in accordance with an acceleration / deceleration pattern represented by the determined speed control parameter; Including, the speed control parameters include a plurality of speed control parameters for each combination of a start speed and an end speed used when controlling the speed of the vehicle from a current speed to a target speed, the clusters acquired in the acquiring step include a cluster for each of the occupants riding in the vehicle; the determining step determines, from among the plurality of speed control parameters, a speed control parameter whose start speed and end speed correspond to the current speed and target speed of the vehicle and which has the highest total of evaluation values corresponding to each of the acquired clusters for each occupant, as the speed control parameter to be applied to the vehicle; Information processing methods.

15. A step in which an information processing device relating to driving methods acquires, from a plurality of clusters, a cluster of driving methods according to the preferences of occupants other than the driver riding in the vehicle or a cluster of driving methods according to the characteristics of cargo in the vehicle; an information processing device determining a speed control parameter that defines a speed change of the vehicle based on the acquired cluster; an information processing device controlling the speed of the vehicle in accordance with an acceleration / deceleration pattern represented by the determined speed control parameter; Including, the speed control parameters include a plurality of speed control parameters for each speed change amount, the determining step determines, from among the plurality of speed control parameters, a speed control parameter whose speed change amount corresponds to a value obtained by subtracting a current speed of the vehicle from a target speed of the vehicle and whose evaluation value corresponding to the acquired cluster is the highest, as the speed control parameter to be applied to the vehicle; Information processing methods.

16. A step in which an information processing device relating to driving methods acquires, from a plurality of clusters, a cluster of driving methods according to the preferences of occupants other than the driver riding in the vehicle or a cluster of driving methods according to the characteristics of cargo in the vehicle; an information processing device determining a speed control parameter that defines a speed change of the vehicle based on the acquired cluster; an information processing device controlling the speed of the vehicle in accordance with an acceleration / deceleration pattern represented by the determined speed control parameter; Including, the speed control parameters include a plurality of speed control parameters for each speed change amount, the clusters acquired in the acquiring step include a cluster for each of the occupants riding in the vehicle; the determining step determines, from among the plurality of speed control parameters, a speed control parameter whose speed change amount corresponds to a value obtained by subtracting a current speed of the vehicle from a target speed of the vehicle and whose total of evaluation values corresponding to each of the clusters for each occupant acquired in the acquiring step is the highest, as the speed control parameter to be applied to the vehicle; Information processing methods.

Images