Information processing device

Abstract

This technology provides an objective evaluation of the difficulty level of a target route by considering various routes with similar attributes to the target route. [Solution] The information processing device calculates the difficulty level of a predetermined route, one or more processors determine the attributes of the predetermined route, acquire information on multiple routes similar to the determined attributes, calculate a first probability distribution showing the overall occurrence trend of the values ​​indicated by one or more first indicators related to geographical features across multiple routes based on the acquired information on multiple routes, and calculate the difficulty level of the predetermined route based on the position in the first probability distribution of the values ​​indicated by one or more first indicators at predetermined points or predetermined sections included in the predetermined route.

Description

[Technical Field]

[0001] This disclosure relates to an information processing device, and more particularly to an information processing device for calculating the difficulty level of a predetermined route. [Background technology]

[0002] Technologies for evaluating the difficulty of a vehicle's travel route have been known for some time.

[0003] For example, Patent Document 1 discloses a navigation device comprising: a map information recording unit that records map information; a route search unit that searches for a route to a destination specified by the driver using the map information; a corner extraction unit that extracts corners in the searched route; a corner difficulty estimation unit that estimates the difficulty of the extracted corners based on the driver's skill; a route difficulty evaluation unit that evaluates the difficulty of the route based on the estimated corner difficulty; and a display unit that displays the difficulty of the searched route and the evaluated route. Patent Document 1 also discloses that the standard deviation of the difficulty of each corner is calculated, and if a candidate route includes corners that exceed the range of the standard deviation, it is evaluated as a more difficult route than a candidate route that does not include such corners. [Prior art documents] [Patent Documents]

[0004] [Patent Document 1] Japanese Patent Publication No. 2015-169612 [Overview of the project] [Problems that the invention aims to solve]

[0005] In the conventional technology disclosed in Patent Document 1, even if the corner difficulty of a candidate route is not high compared to the corner difficulty of various similar routes, if the corner difficulty of the candidate route falls outside the range of standard deviation, it is evaluated as a difficult route even if the driving operation is not actually that difficult.

[0006] In light of these circumstances, the purpose of this disclosure is to provide a technology for objectively evaluating the difficulty of a target route by considering various routes that have similar attributes to the target route. [Means for solving the problem]

[0007] An information processing apparatus according to one embodiment of the present disclosure is an information processing apparatus for calculating the difficulty level of a predetermined route, comprising one or more processors and one or more memories connected to the one or more processors in a communicative manner, wherein the one or more processors determine the attributes of the predetermined route, acquire information on a plurality of routes similar to the determined attributes, calculate a first probability distribution showing the tendency of the values ​​indicated by one or more first indicators relating to geographical features to appear across the plurality of routes based on the acquired information on the plurality of routes, and calculate the difficulty level of the predetermined route based on the position in the first probability distribution of the values ​​indicated by one or more first indicators at a predetermined point or predetermined section included in the predetermined route. [Effects of the Invention]

[0008] According to one embodiment of this disclosure, the difficulty level of a target route can be objectively evaluated by considering various routes that have similar attributes to the target route. [Brief explanation of the drawing]

[0009] [Figure 1] This is a schematic diagram showing an example of a system configuration to which the information processing device according to the first embodiment of this disclosure can be applied. [Figure 2] This is a schematic diagram showing an example configuration of a vehicle capable of communicating with an information processing device according to the first embodiment of this disclosure. [Figure 3] This is a block diagram showing an example configuration of an information processing device according to the first embodiment of the present disclosure. [Figure 4] This diagram illustrates the multiple paths considered when calculating difficulty. [Figure 5]This diagram illustrates a predetermined path used to calculate difficulty. [Figure 6] This is a diagram explaining the difficulty levels. [Figure 7] This is a flowchart illustrating an example of the operation of an information processing device according to the first embodiment of this disclosure. [Figure 8] Figure 7 is a flowchart that provides a detailed explanation of the difficulty calculation process, which is one of the operational examples shown. [Figure 9] This is a flowchart illustrating an example of the operation of an information processing device according to the second embodiment of this disclosure. [Modes for carrying out the invention]

[0010] Preferred embodiments of this disclosure will be described in detail below with reference to the attached drawings. In this specification and the drawings, components having substantially the same functional configuration are denoted by the same reference numerals, and redundant descriptions will be omitted.

[0011] <1. First Embodiment> (1-1. System) Referring to Figure 1, the system 1000 comprises a vehicle 10, a terminal device 20, and an information processing device 30. The vehicle 10, the terminal device 20, and the information processing device 30 can communicate with each other via a publicly known or arbitrary network 40 such as the Internet. However, in this disclosure, the terminal device 20 is not an essential component and can be omitted as appropriate.

[0012] Vehicle 10 is, for example, an automobile equipped with an internal combustion engine such as a gasoline engine or a diesel engine. However, vehicle 10 is not limited to this, and may also be, for example, an electric vehicle equipped with a drive motor. Examples of electric vehicles include BEV (Battery Electric Vehicle), HEV (Hybrid Electric Vehicle), PHEV (Plug-in Hybrid Electric Vehicle), and FCEV (Fuel Cell Electric Vehicle).

[0013] The terminal device 20 is, for example, a mobile device such as a smartphone, mobile phone, tablet, or wearable device.

[0014] The information processing device 30 is a computer such as a server belonging to a cloud computing system or other computing system. However, this disclosure is not limited thereto, and the information processing device 30 may be mounted on the vehicle 10.

[0015] (1-2. Vehicles) Referring to Figure 2, the vehicle 10 is configured as a four-wheeled vehicle that transmits the drive torque output from the drive source 1 to the wheels. The combination of drive wheels and the drive method are not particularly limited, and the vehicle 10 may be a front-wheel drive vehicle, a rear-wheel drive vehicle, or a four-wheel drive vehicle. Furthermore, if the vehicle 10 is configured as an electric vehicle, it may be an electric vehicle equipped with a drive motor corresponding to each wheel.

[0016] The vehicle 10 includes, as equipment used for driving control, at least a power source 1, an electric steering device 2, brake devices 3LF, 3RF, 3LR, 3RR (hereinafter collectively referred to as "brake device 3" unless otherwise specified), and a vehicle control device 4.

[0017] The drive source 1 outputs drive torque which is transmitted to the front wheel drive shaft 6F via a transmission (not shown) and a differential mechanism 5. The drive of the drive source 1 and the transmission is controlled by a vehicle control device 4.

[0018] The electric steering system 2 is mounted on the front wheel drive shaft 6F. The electric steering system 2 includes an electric motor (not shown) and a gear mechanism (not shown), and adjusts the steering angle of the front wheels by being controlled by the vehicle control device 4. The vehicle control device 4 controls the electric steering system 2 based on the steering angle of the steering wheel 7 made by the driver. When the vehicle 10 is configured to perform automatic driving control, the vehicle control device 4 controls the electric steering system 2 based on the steering angle of the steering wheel 7 made by the driver during manual driving. On the other hand, during automatic driving, the vehicle control device 4 controls the electric steering system 2 based on a steering angle or steering angular velocity that is appropriately set by known or arbitrary automatic driving technology.

[0019] Brake units 3LF, 3RF, 3LR, and 3RR apply braking force to their respective wheels. Brake unit 3 may be, for example, a hydraulic brake system. In this case, the hydraulic pressure supplied to each brake unit 3 is adjusted by controlling the drive of the hydraulic unit 8 by the vehicle control device 4. When the vehicle 10 is configured as an electric vehicle, brake unit 3 is used in conjunction with regenerative braking by the drive motor.

[0020] The vehicle control device 4 includes at least one or more ECUs (Electronic Control Units) that control the drive of the power source 1, the electric steering system 2, and the brake system 3. The vehicle control device 4 also includes one or more ECUs that control the drive of various other devices mounted on the vehicle 10 besides the power source 1, the electric steering system 2, and the brake system 3. The vehicle control device 4 may be appropriately separated and provided for each controlled object.

[0021] In addition, the vehicle 10 includes an ambient environment sensor 11, a vehicle status sensor 12, a position detection sensor 13, a communication device 14, a navigation device 15, and a notification device 16.

[0022] The ambient environment sensor 11 includes at least forward-facing cameras 11L and 11R. The forward-facing cameras 11L and 11R capture images of the area in front of the vehicle 10 and generate image data. The forward-facing cameras 11L and 11R are equipped with image sensors such as CCD (Charged Coupled Devices) or CMOS (Complementary Metal Oxide Semiconductor), and transmit the generated image data to the information processing device 30 via the communication device 14. In Figure 2, the forward-facing cameras 11L and 11R are stereo cameras including a pair of left and right cameras, but they may be monocular cameras. In addition, the ambient environment sensor 11 may include a rear-facing camera in addition to the forward-facing cameras 11L and 11R. Furthermore, the ambient environment sensor 11 may include one or more distance measuring sensors, such as radar sensors like LiDAR (Light Detection And Ranging) or millimeter-wave radar, and ultrasonic sensors.

[0023] The vehicle state sensor 12 includes at least one sensor that detects the state of the vehicle 10 resulting from the driver's operation of the vehicle 10. The vehicle state sensor 12 may include, for example, an accelerator position sensor, a brake stroke sensor, or a steering angle sensor. The vehicle state sensor 12 may also include, for example, a vehicle speed sensor, an acceleration sensor, or an angular velocity sensor. The vehicle state sensor 12 transmits the detection result to the information processing device 30 via the communication device 14.

[0024] The position detection sensor 13 may include a GNSS (Global Navigation Satellite System) sensor. The GNSS sensor receives satellite signals from positioning satellites such as GPS (Global Positioning System) satellites. The position detection sensor 13 transmits the vehicle's position information, which is included in the received satellite signals, to the information processing device 30 via the communication device 14. In addition to the GPS sensor, the position detection sensor 13 may also include an antenna that receives satellite signals from other satellite systems that determine the vehicle's position.

[0025] The communication device 14 includes at least one communication interface. As the communication interface, for example, an interface compatible with mobile communication standards such as 4G (4th Generation) or 5G (5th Generation) standards, or a LAN (Local Area Network) standard, can be used. The communication device 14 transmits the detection results of the ambient environment sensor 11, the vehicle condition sensor 12, and the position detection sensor 13 to the information processing device 30 via the network 40. The communication device 14 also receives various information necessary for controlling the vehicle 10 from the information processing device 30 via the network 40.

[0026] The navigation device 15 searches for a route to guide the vehicle 10 from its current location to its destination, based on map information. The navigation device 15 includes a display unit such as an LCD (Liquid Crystal Display) or an organic EL (Electro Luminescence) display, and can output various information to the driver. The navigation device 15 also includes an operation unit such as buttons or a touch panel, and can accept input operations from the driver.

[0027] The notification device 16 notifies the driver of the vehicle 10 of various information through image display, text display, or audio output. The notification device 16 may be integrated with the navigation device 15, integrated with the instrument panel, or it may be a HUD (Head Up Display) that displays on the front windshield of the vehicle 10.

[0028] (1-3. Information Processing Devices) Referring to Figure 3, the information processing device 30 according to the first embodiment will be described in detail.

[0029] (1-3-1. Example Configuration) The information processing device 30 functions as a device that calculates the difficulty level of a predetermined path by having one or more processors, such as CPUs (Central Processing Units), execute a computer program. The computer program is a computer program that causes the processor to execute the operations that the information processing device 30 should perform, as described later. The computer program executed by the processor may be recorded on a recording medium that functions as a memory unit 32, as described later, or on a recording medium built into the information processing device 30 or on any external recording medium that can be attached to the information processing device 30.

[0030] The recording medium for storing computer programs may include magnetic media such as hard disks, floppy disks, and magnetic tapes; optical recording media such as CD-ROMs, DVDs, and Blu-ray®; magneto-optical media such as floppy disks; memory elements such as RAM and ROM; flash memory such as USB memory and SSDs; and other media capable of storing programs.

[0031] The information processing device 30 comprises at least a processing unit 31, a storage unit 32, and a communication unit 33.

[0032] The processing unit 31 comprises one or more processors such as a CPU and various peripheral components. Part or all of the processing unit 31 may consist of updatable components such as firmware, or it may be a program module that is executed by instructions from the CPU or the like.

[0033] The memory unit 32 is composed of one or more memory elements such as RAM or ROM that are connected to the processing unit 31 in a communicative manner. However, the type and number of memory units 32 are not particularly limited. The memory unit 32 stores information such as computer programs executed by the processing unit 31, various parameters used in arithmetic processing, detection data, and calculation results.

[0034] The communication unit 33 is composed of one or more communication interfaces that are connected to the processing unit 31 in a communicative manner. Examples of communication interfaces include interfaces that are compatible with mobile communication standards such as 4G or 5G standards, or LAN standards. The communication unit 33 can communicate with the vehicle 10 and the terminal device 20 via the network 40. If the information processing device 30 is mounted on the vehicle 10, some or all of the functions of the communication unit 33 may be incorporated into the communication device 14 of the vehicle 10.

[0035] (1-3-2. Functional configuration of the processing unit) The functional configuration of the processing unit 31 of the information processing device 30 will now be described. The processing unit 31 comprises an attribute determination unit 311, a route information acquisition unit 312, a probability distribution calculation unit 313, a difficulty calculation unit 314, a driving information acquisition unit 315, a driving skill evaluation unit 316, and a presentation processing unit 317. Each of these units is a function realized by the execution of a computer program by one or more processors such as a CPU. However, some or all of these units may be configured using analog circuits.

[0036] (Attribute determination section) The attribute determination unit 311 determines the attributes of a predetermined route R0. Specifically, the storage unit 32 may store information on various routes, including the predetermined route R0, and attribute information for each route, in pre-associated locations. The attribute determination unit 311 may determine the attributes of the predetermined route R0 by referring to the storage unit 32, identifying the predetermined route R0 from among the various routes, and identifying the attributes associated with the identified route. Note that the route information (hereinafter abbreviated as "route information") may include arbitrary information for identifying the location of the route on a map. Examples of such information include the latitude, longitude, and altitude of the route, but this disclosure is not limited to these, and may also include, for example, satellite image data including the route. Furthermore, the attribute information may include information on one or more attributes among attributes indicating whether or not it is an urban area, whether or not it is a mountainous area, and whether or not it is a highway.

[0037] However, the attributes used in this disclosure are not limited to the attributes described above, and may be any attributes that can be set based on the region, type, or design speed of the road. For example, the attribute determination unit 311 may determine whether the attribute of a given route R0 is an expressway or an expressway. If the attribute determination unit 311 determines that the attribute of a given route R0 is an expressway or an expressway, it may further determine whether the attribute of a given route R0 is in a mountainous area or a flat area. If the attribute determination unit 311 does not determine that the attribute of a given route R0 is an expressway or an expressway, it may further determine whether the attribute of a given route R0 is a national road, a prefectural road, or a municipal road, and further determine whether it is in a mountainous area or a flat area.

[0038] (Route information acquisition unit) The route information acquisition unit 312 identifies multiple routes R whose attributes are similar to those of a predetermined route R0 determined by the attribute determination unit 311. i (wherein i is a natural number and is an index for identifying each path.) The path information acquisition unit 312 obtains information about multiple paths R whose attributes are similar to the attributes of a predetermined path R0 determined by the attribute determination unit 311 by referring to the storage unit 32. i Identify the information of multiple routes R similar to a given route R0. i This will be selected. For example, if a given route R0 mainly passes through an urban area, then multiple routes R that mainly pass through the urban area will be selected. i This will be selected. Also, if a given route R0 mainly passes through a mountainous area, then multiple routes R that mainly pass through the mountainous area will be selected. i This will be selected. Also, if a given route R0 is mainly a highway, then multiple routes R that are mainly highways will be selected. i This will be selected. Also, for example, multiple routes R with attributes similar to the attributes of a given route R0. i This is the distance of the section corresponding to a specific attribute within a given path R0 and each path R i The route may also be one in which the distance of the section corresponding to the specific attribute matches a certain value or more.

[0039] (Probability distribution calculation unit) The probability distribution calculation unit 313 calculates a value indicated by one or more first indicators related to geographical features based on information on a plurality of routes R acquired by the route information acquisition unit 312. i Further, the probability distribution calculation unit 313 calculates a first probability distribution indicating the appearance tendency of the values indicated by the one or more first indicators in the entirety of the plurality of routes R acquired by the route information acquisition unit 312. i The first indicator related to geographical features is an arbitrary indicator that reflects the geographical features of the road and affects driving operations such as the accelerator operation, brake operation, or steering operation by the driver of the vehicle 10.

[0040] Specifically, the first indicator is an indicator related to the shape of the road, such as the road gradient, curve shape, or road width, at a predetermined point P or a predetermined section S included in each of the plurality of routes R. i Here, i is a natural number and is an index for identifying each point or each section. i The predetermined point P may be an arbitrary point sequentially selected from a plurality of points set at a predetermined interval from the start point to the end point of each route. i Further, the predetermined section S may be an interval between any two adjacent points sequentially selected from such a plurality of points. i The predetermined point P may be an arbitrary point sequentially selected from a plurality of points set at a predetermined interval from the start point to the end point of each route. i The predetermined section S may be an interval between any two adjacent points sequentially selected from such a plurality of points.

[0041] An example of the first indicator, relating to the shape of the road, is one or more of the following indicators: longitudinal gradient, transverse gradient, curvature, change in curvature, curve length, road width, curve direction, visual distance, and curve continuity. The longitudinal gradient is the change in elevation in the direction of travel of the road and can be calculated using the latitude, longitude, and elevation of the road. The longitudinal gradient affects the forward visibility from the vehicle 10 and affects the change in vehicle speed due to inertia. The transverse gradient is the change in elevation in the width direction of the road and can be calculated using the latitude, longitude, and elevation of the road. The transverse gradient affects the difficulty of turning the vehicle 10. The curvature can be calculated using the latitude and longitude of the road and affects the difficulty of turning the vehicle 10 at high speeds. The change in curvature can be calculated using the latitude and longitude of the road and affects the increase or decrease in the amount of driving maneuvers performed by the driver. The curve length can be calculated using the latitude and longitude of the road and affects the time it takes for the driver to perform driving maneuvers. The curve direction can be calculated using the road's latitude and longitude, and affects the forward visibility from vehicle 10 and how to react to oncoming vehicles. The road width can be calculated using the road's latitude and longitude, but satellite imagery may be used, or a road database used in a navigation system may be used. The road width affects the margin of error for driver mistakes. The sight distance can be calculated using the road's longitude and latitude, satellite imagery, and a road database, and affects the forward visibility from vehicle 10 due to obstructions such as trees or guardrails. The sight distance can be appropriately calculated using a tangent line drawn from the center of the road to the obstruction, etc. The curve continuity can be calculated using the road's longitude and latitude, and may be the distance between curves, or a combination of the above-mentioned indicators.

[0042] Here, the memory unit 32 has multiple paths R i Map information containing at least each of the routes is stored in advance. The probability distribution calculation unit 313 calculates the number of routes R i For each of these, map information is obtained from the memory unit 32, and the route R is identified by the obtained map information. iBased on the shape of the road in the area, the value indicated by one or more first indicators may be calculated. Furthermore, for each of the one or more first indicators, the probability distribution calculation unit 313 calculates multiple paths R of the value indicated by the one or more first indicators calculated in this way. i A first probability distribution showing the overall tendency of occurrence may be calculated.

[0043] Referring to Figure 4, multiple paths R have attributes similar to the attributes of a given path R0. i There are a total of k such paths R i The calculation of the first probability distribution will be explained in detail using the example where there are a total of p curve intervals and a total of n first indicators. In this case, the probability distribution calculation unit 313 calculates the k paths R i The first probability distribution may be calculated by determining the probability density function for each of the n first indicators from the road shapes of a total of p curved sections included in (1≦i≦k), for example, by maximum likelihood estimation. Below, the curvature change C e Using this as an example, we will explain the maximum likelihood estimation method in detail.

[0044] First, the probability distribution calculation unit 313 calculates location P i Curvature e i And, section S i (That is, point P) i and point P i+1 Curve length d (the section between) i,i+1 and, e i+1 and e i The difference (absolute value) from d i,i+1 The interval S divided by i The rate of change of curvature at and are calculated. Here, the probability distribution calculation unit 313 calculates this curvature e i , curve length d i,i+1 Furthermore, in calculating the rate of curvature change, the latitude and longitude of the route are converted to a plane orthogonal coordinate system by using the map information stored in the memory unit 32. Here, the radius of the circle fitted to the three continuous data points is the radius of curvature, and its reciprocal is the curvature. The rate of curvature change is the change in curvature per unit length, and is the value obtained by dividing the change in curvature by the curve length.

[0045] Next, the probability distribution calculation unit 313 calculates the curvature e mentioned above. i , curve length d i,i+1 And the curvature change C is defined by equation (1) below, using the rate of curvature change and the curvature change C. e The following is calculated. Note that the longer the curve length, the smaller the radius of curvature, and the larger the rate of change of curvature, the more difficult it tends to be for the driver to operate the accelerator, brake, and steering, and the rate of change of curvature C is defined by equation (1) below. e This reflects these trends.

[0046]

number

[0047] However, as can be understood from equation (1) above, perfect simple curves where the argument is 0 are excluded, and special cases such as spiral curves where the denominator is 1 or less are also excluded.

[0048] The probability distribution calculation unit 313 calculates k paths R i For all p curve intervals included in (1≦i≦k), the curvature change C defined by equation (1) above is defined. e The curvature change C calculated by the probability distribution calculation unit 313 is stored in the memory unit 32. e The population consists of k paths R0 whose attributes are similar to those of a given path R0. i This results in a dataset (so-called big data) that reflects information from all curve segments included in (1≦i≦k).

[0049] Next, the probability distribution calculation unit 313 refers to the memory unit 32 and calculates the curvature change C e A population is collected, and assuming that the collected population follows a predetermined probability distribution, the parameters of its probability density function are calculated using the maximum likelihood estimation method. The predetermined probability distribution is not particularly limited, but may be a normal distribution, standard normal distribution, beta distribution, or gamma distribution, and can be appropriately selected depending on the characteristics of the data. Equations (2) to (5) below represent the curvature change C. eThis example shows a maximum likelihood estimation method for parameters α and β in a beta distribution, assuming that the population follows a beta distribution.

[0050]

number

[0051]

number

[0052]

number

[0053]

number

[0054] In equations (2) through (5) above, α and β are shape parameters in the β distribution. Equation (2) above expresses the curvature change C, given α and β. e This is the probability density function of the curvature change C. Equation (3) above is given by the curvature change C. e This is the likelihood function given the observed data. Equation (4) above is the log-likelihood function.

[0055] (Difficulty calculation section) The difficulty calculation unit 314 calculates a predetermined point P included in a predetermined route R0. i or a predetermined section S i The difficulty of a predetermined route R0 is calculated based on the position of the value indicated by one or more first indicators in a first probability distribution. i These may be multiple points set sequentially at predetermined intervals from the start to the end of a predetermined route R0. i This could be the section between two adjacent points among the multiple points in question.

[0056] Specifically, the difficulty calculation unit 314 calculates k paths R for each of the n first indicators shown in Figure 4.i The population mean μ and standard deviation σ of the first index may be calculated from the estimation parameters in the maximum likelihood estimation method used when calculating the first probability distribution from the information of a total of p curve intervals included in (1≦i≦k). For example, the curvature change C included in the first index. e In this case, the difficulty calculation unit 314 may calculate the mean μ defined by equation (6) and the standard deviation σ defined by equation (7) below, which are obtained from the estimated parameters defined by equation (5) above.

[0057]

number

[0058]

number

[0059] On the other hand, the difficulty calculation unit 314 calculates for each of the one or more first indicators the location P included in the predetermined route R0. i or section S i The value indicated by the first indicator may be calculated for each step. i " or "S i In this context, "i" is an index used to identify each point or section from the starting point to the ending point, and it changes sequentially from the starting point to the ending point. Then, the difficulty calculation unit 314 calculates point P based on the position of the value indicated by the first index in the population of the first index. i or section S i The difficulty level of a predetermined route R0 may be calculated for each instance. Specifically, the difficulty level calculation unit 314 obtains map information including the predetermined route R0 shown in Figure 5 by referring to the storage unit 32. The difficulty level calculation unit 314 also determines the location P included in the predetermined route R0 identified by the acquired map information. i or section S i Based on the shape of the road at point P i or section S i The value indicated by n first indicators may be calculated for each point P. ior section S i For each of the n first indicators, based on the degree of deviation of the value shown by the first indicator from the population mean μ and standard deviation σ of the first indicator, point P i or section S i The difficulty level of each predetermined path R0 may be calculated. As will be described in more detail later with reference to Figure 6, the position of each of the n first indicators in the first probability distribution is identified using the degree of deviation. However, this disclosure is not limited to calculating difficulty levels considering curved sections as shown in Figure 5, but can also cover calculating difficulty levels considering straight sections.

[0060] In the example shown in Figure 6, values ​​greater than or equal to 0 and less than (mean μ - standard deviation σ) are classified as Level 1 (Lv1), values ​​greater than or equal to (mean μ - standard deviation σ) and less than mean μ are classified as Level 2 (Lv2), values ​​greater than or equal to mean μ and less than (mean μ + standard deviation σ) are classified as Level 3 (Lv3), and values ​​greater than or equal to (mean μ + standard deviation σ) and 1 or less are classified as Level 4 (Lv4). Here, the difficulty level increases as the level increases. In this way, the difficulty calculation unit 314 calculates the location P included in the predetermined route R0. i or section S i For each of the n first indicators, the difficulty of a given path R0 can be calculated based on the position of each of the corresponding populations. For example, the curvature change C e If the value of a parameter is small enough that it rarely appears overall, but appears frequently on a given path R0, then that path R0 is considered a difficult path.

[0061] The difficulty calculation unit 314 calculates the point P included in the predetermined route R0. i or section S i The difficulty level of a given path R0 may be calculated by summarizing the difficulty levels along the path from its start to its end. For example, the difficulty level of the given path R0 as a whole may be calculated by considering the level of curvature change, the level of visibility, or the level of curve continuity, and the overall difficulty level may be calculated by summarizing these levels.

[0062] (Driving information acquisition unit) The driving information acquisition unit 315 acquires information from a predetermined point P included in a predetermined route R0. i or a predetermined section S i The system acquires information on the driving operations performed by the driver of the vehicle 10. Specifically, the driving information acquisition unit 315 acquires the detection results of the vehicle state sensor 12 and the position detection sensor 13 of the vehicle 10 from the vehicle 10 via the communication unit 33 each time a predetermined time (for example, the calculation cycle of various sensors) has elapsed since the vehicle 10 started.

[0063] Information on driving operations may include the driver's adjustment of the acceleration / deceleration rate of the vehicle 10 or steering correction operations, and may be stored in the storage unit 32 together with the position information of the vehicle 10 at the time the driving operation was performed by the driver. "Correction operation" means turning the steering wheel from one direction to another and then turning the steering wheel back from the other direction to the first direction within a predetermined time. Acceleration / deceleration adjustment operations can be identified by known or arbitrary methods from the detection values ​​of the vehicle speed sensor and acceleration sensor included in the vehicle state sensor 12 of the vehicle 10. Steering correction operations can be identified by known or arbitrary methods from the detection value of the steering angle sensor included in the vehicle state sensor 12 of the vehicle 10. The position of the vehicle 10 can be identified by known or arbitrary methods from the detection value of the position detection sensor 13 of the vehicle 10. However, the information on driving operations in this disclosure is not limited to these, and may include any information that can be identified by known or arbitrary methods from the detection values ​​of various sensors included in the vehicle state sensor 12 of the vehicle 10. Furthermore, instead of the detection values ​​of the various sensors included in the vehicle condition sensor 12 of the vehicle 10, the detection values ​​of various sensors such as acceleration sensors, angular velocity sensors, or position detection sensors included in a terminal device 20 such as a smartphone held by the driver may be used.

[0064] (Driving Skills Evaluation Department) The driving skills evaluation unit 316 evaluates a predetermined point P included in a predetermined route R0 based on the difficulty level calculated by the difficulty level calculation unit 314 and the driving operation information acquired by the driving information acquisition unit 315. i or a predetermined section S iEvaluate the driving skills of the driver. Specifically, the driving skill evaluation unit 316 determines that, even though the difficulty level of a point P i or a section S i included in a predetermined route R0 is low, the driving skill of the driver is lower as the number of acceleration and deceleration adjustment operations of the vehicle 10 by the driver at the point P i or the section S i is greater than a reference value. On the other hand, the driving skill evaluation unit 316 determines that, even though the difficulty level of a point P i or a section S i included in the predetermined route R0 is high, the driving skill of the driver is higher as the number of acceleration and deceleration adjustment operations of the vehicle 10 by the driver at the point P i or the section S i is less than the reference value. Further, the driving skill evaluation unit 316 determines that, even though the difficulty level of a point P i or a section S i included in the predetermined route R0 is low, the driving skill of the driver is lower as the number of steering operation correction operations by the driver at the point P i or the section S i is greater. Also, the driving skill evaluation unit 316 determines that, even though the difficulty level of a point P i or a section S i included in the predetermined route R0 is high, the driving skill of the driver is higher as the number of steering operation correction operations by the driver at the point P i or the section S i is less. Note that the evaluation of the driving skill may be an evaluation using a continuous value such as a score, but the present disclosure is not limited thereto, and may be a multi-stage evaluation such as "beginner", "intermediate", and "advanced".

[0065] Among the driving routes of the vehicle 10 by the driver who is the evaluation target of the driving skill, which is an example of the predetermined route R0, the driving skill evaluation unit 316 determines a point P j or a section S jIdentify and perform the following processes. However, j is a natural number and is an index for identifying a point or section among a plurality of points or sections where the evaluation value of the driving skill is less than a predetermined reference value. That is, the driving skill evaluation unit 316 identifies information on the driving operation of a model driver and the identified point P j or section S j It may identify the difference between the driver's driving operation and the driving operation of the model driver at.

[0066] Specifically, in the storage unit 32, there may be stored in advance information on the driving operation of a model driver set according to the difficulty level in the first probability distribution calculated using information on a plurality of routes R i whose attributes are similar to the attributes of the driving route of the vehicle 10 by the driver. Here, the model driver set according to the difficulty level may mean a driver having a standard driving skill or a skilled driving skill required to safely drive the vehicle 10 at a point or section indicating the difficulty level. The driving skill evaluation unit 316, in the same manner as the method described above, based on the position of the value indicated by the first index at a point P j or section S j where the evaluation value of the driving skill is less than a predetermined reference value, in the first probability distribution, may calculate the difficulty level of the point P j or section S j And the driving skill evaluation unit 316 may identify the difference between the driver's driving operation and the driving operation of the model driver by referring to the storage unit 32 and identifying the information on the driving operation of the model driver appropriately set according to the calculated difficulty level. Note that the difference in the driving operation is not particularly limited, but may be, for example, the timing difference in the driving operations between the driver and the model driver, or the trajectory difference of the vehicle 10 between the driver and the model driver.

[0067] (Presentation processing unit) The presentation processing unit 317 is a predetermined point P included in the driving route of the vehicle 10 by the driver who is the evaluation target of the driving skill, which is an example of a predetermined route R0 i or a predetermined section S iIn this process, the difficulty level of the driving operation calculated by the difficulty level calculation unit 314 is associated with the driving operation performed by the driver, as acquired by the driving information acquisition unit 315, and presented to the driver. Specifically, the presentation processing unit 317 may, for example, after the driver has finished driving the vehicle 10, generate feedback information that associates the difficulty level and the driving operation as described above, and that can be recognized by the driver via the notification device 16 of the vehicle 10, and transmit it to the vehicle 10 via the communication unit 33. Here, the feedback information is (i) a point P in the driving route of the vehicle 10 where the evaluation value of the driving skill falls below a predetermined standard value. j or section S i (ii) Information on location P j or section S i The difficulty level and (iii) location P j or section S i This may include information on the driving operations actually performed by the driver. This allows the driver to determine if their driving skills were poor at point P. j or section S i Multiple paths R with similar difficulty levels i This allows for an objective assessment of the difficulty level compared to other factors. Furthermore, drivers are assessed as having low driving skills at point P. j or section S i This allows drivers to reflect on their own driving actions. Therefore, drivers can efficiently improve their driving skills by reflecting on their own driving actions not only in relation to map information, but also in relation to objective difficulty levels considering various routes similar to the one they drove.

[0068] If the difference between the driver's driving operations and the exemplary driver's driving operations is identified as described above, the presentation processing unit 317 may perform a process to present the identified difference in driving operations to the driver. In this case, the feedback information described above may include information to make the driver aware of, for example, the timing difference in the driving operations between the driver and the exemplary driver or the difference in the trajectory of the vehicle 10. Furthermore, the feedback information may include, for example, the timing difference in the driving operations between the driver and the exemplary driver or the difference in the trajectory of the vehicle 10, presented as a still image or video (animation, etc.) at point Pj or section S i The information may be superimposed on a map and made visible to the driver via the notification device 16 of the vehicle 10. This allows the driver to see the location P where their driving skills were evaluated as low. j or section S j Since you can also learn the driving techniques of exemplary drivers, you can improve your driving skills even more efficiently.

[0069] The presentation processing unit 317 may perform the process of presenting the driver with advice information according to the driver's driving type. The driving type can be identified by the driving skill evaluation unit 316 based on the driver's driving operation information acquired by the driving information acquisition unit 315. For example, the driving type may be identified as safe, passive, or sporty based on the vehicle speed, acceleration, or jerk of the vehicle 10. In this case, the above-mentioned feedback information may include arbitrary advice information to improve the driver's driving skills according to whether the driving type is safe, passive, or sporty.

[0070] Alternatively, instead of sending the notification device 16 of the vehicle 10, the feedback information may be sent to a terminal device 20, such as a smartphone, carried by the driver. In this case, the driver can understand the feedback information via the display of the terminal device 20.

[0071] (1-3-3. Examples of information processing device operation) Referring to Figure 7, an example of the operation of the information processing device 30 according to the first embodiment will be explained in accordance with the flowchart.

[0072] For simplicity, the first indicator used below is the change in curvature C. e The following example illustrates the case where the vehicle 10 adopts a predetermined route R0, which is a guided route from the current location to the destination specified by the driver of the vehicle 10 via the navigation device 15. However, the operation examples of the information processing device 30 are not limited to this, and the first indicator is the curvature change C. e Instead, or change of curvature Ce In addition, the various first indicators mentioned above can be adopted as appropriate.

[0073] In step S10, the vehicle 10 begins to travel along a guided route from its current location to its destination, as specified by the driver via the navigation device 15. The process then proceeds to step S11.

[0074] In step S11, the driving information acquisition unit 315 of the processing unit 31 acquires point P included in the driving route of the vehicle 10 corresponding to a predetermined route R0 (hereinafter simply referred to as "driving route"). i or section S i The system acquires information on the driver's driving operations each time. The driving information acquisition unit 315 then stores the acquired driving operation information at point P i or section S i The location information is associated with the data and stored in the memory unit 32. Note that the process in step S11 is performed from the time the vehicle 10 departs from its current location until it arrives at its destination.

[0075] In step S12, the attribute determination unit 311 of the processing unit 31 determines the attributes of the travel route by referring to the storage unit 32 in the manner described above. The process then proceeds to step S13.

[0076] In step S13, the route information acquisition unit 312 of the processing unit 31 refers to the storage unit 32 and finds k routes R whose attributes are similar to the attributes determined in step S12. i The information for (1 ≤ i ≤ k) is obtained. Then the process proceeds to step S14.

[0077] In step S14, the probability distribution calculation unit 313 of the processing unit 31 calculates the k paths R obtained in step S13. i Based on the information (1≦i≦k), the curvature change C corresponds to the first index. e (Hereafter, simply referred to as "curvature change C") e It is written as ". ) calculates. Specifically, the probability distribution calculation unit 313 calculates k paths R iFor all p curve intervals included in (1≦i≦k), the curvature change C defined by equation (1) above is defined. e The process then proceeds to step S15.

[0078] In step S15, the probability distribution calculation unit 313 of the processing unit 31 calculates the curvature change C calculated in step S14. e k paths R of the value indicated by i A first probability distribution is calculated that shows the overall tendency of occurrence for (1≦i≦k). Specifically, the probability distribution calculation unit 313 calculates the curvature change C as described above. e Assuming that the population follows, for example, a beta distribution, the first probability distribution is calculated by determining the parameters of its probability density function using the maximum likelihood estimation method. The process then proceeds to step S16.

[0079] In step S16, the difficulty calculation unit 314 of the processing unit 31 calculates the point P included in the travel route using the method described above. i or section S i Curvature change C e The process then proceeds to step S17.

[0080] In step S17, the difficulty calculation unit 314 of the processing unit 31 calculates the curvature change C calculated in step S16. e Based on the position in the first probability distribution calculated in step S15, point P i or section S i The difficulty level of the route is calculated for each point. Then, the difficulty level calculation unit 314 assigns the calculated difficulty level to point P i or section S i The information is stored in the memory unit 32 in association with the information.

[0081] Now, with reference to Figure 8, the difficulty calculation process in step S17 will be explained in detail. In this example of operation, the difficulty calculation unit 314 of the processing unit 31 calculates the curvature change C e Point P relative to the population mean μ and standard deviation σ i or section S i Curvature change C eBased on the degree of deviation, point P i or section S i The difficulty level of each route is calculated. Note that the curvature change C e The population mean μ and standard deviation σ can be calculated from the estimation parameters in the maximum likelihood estimation method, as described above.

[0082] Specifically, in step S17-1, the difficulty calculation unit 314 of the processing unit 31 calculates the curvature change C e Determine whether the curvature change C is between (mean μ + standard deviation σ) and 1. e If (mean μ + standard deviation σ) is greater than or equal to 1 (step S17-1: YES), the process proceeds to step S17-2. Meanwhile, the curvature change C e If the value is not greater than or equal to (mean μ + standard deviation σ) and less than or equal to 1 (step S17-1: NO), the process proceeds to step S17-3.

[0083] In step S17-2, the difficulty calculation unit 314 of the processing unit 31 calculates point P i or section S i The difficulty level of the route is determined to be level 4. After that, the difficulty calculation process is completed, and the process proceeds to step S18 in Figure 7.

[0084] In step S17-3, the difficulty calculation unit 314 of the processing unit 31 calculates the curvature change C e Determine whether the curvature change C is greater than or equal to the mean μ and less than (mean μ + standard deviation σ). e If the value is greater than or equal to the mean μ and less than (mean μ + standard deviation σ) (step S17-3: YES), the process proceeds to step S17-4. Meanwhile, the curvature change C e If the value is not greater than or equal to the mean μ and less than (mean μ + standard deviation σ) (step S17-3: NO), the process proceeds to step S17-5.

[0085] In step S17-4, the difficulty calculation unit 314 of the processing unit 31 calculates point P i or section S iThe difficulty level of the route is determined to be level 3. After that, the difficulty calculation process is completed, and the process proceeds to step S18 in Figure 7.

[0086] In step S17-5, the difficulty calculation unit 314 of the processing unit 31 calculates the curvature change C e Determine whether the curvature change C is greater than or equal to (mean μ - standard deviation σ) and less than the mean μ. e If the value is greater than or equal to (mean μ - standard deviation σ) but less than the mean μ (step S17-5: YES), the process proceeds to step S17-6. Meanwhile, the curvature change C e If the result is greater than or equal to (mean μ - standard deviation σ) and not less than the mean μ (step S17-5: NO), the process proceeds to step S17-7.

[0087] In step S17-6, the difficulty calculation unit 314 of the processing unit 31 calculates point P i or section S i The difficulty level of the route is determined to be level 2. After that, the difficulty calculation process is completed, and the process proceeds to step S18 in Figure 7.

[0088] In step S17-7, the difficulty calculation unit 314 of the processing unit 31 calculates point P i or section S i The difficulty level of the route is determined to be level 1. After that, the difficulty calculation process is completed, and the process proceeds to step S18 in Figure 7.

[0089] Furthermore, the difficulty calculation unit 314 of the processing unit 31 calculates point P included in the travel route. i or section S i It is preferable to repeat the process described in steps S17-1 to S17-7 for each section of the route, from the starting point to the ending point. This allows for the comprehensive calculation of the difficulty level of each curved section included in the route.

[0090] Returning to Figure 7, in step S18, the driving skill evaluation unit 316 of the processing unit 31 evaluates point P included in the driving route based on the difficulty level calculated in step S17 and the driving operation information acquired in step S11. i or section S i The driver's driving skills are evaluated each time. As mentioned above, the driving skills evaluation unit 316 evaluates the driving skills at point P where the evaluation value of the driving skills falls below a predetermined standard value. j or section S j The differences between the driver's driving operations and those of a model driver may be identified. The process then proceeds to step S19.

[0091] In step S19, the presentation processing unit 317 of the processing unit 31 processes the evaluation results of driving skills in step S18 to be fed back to the driver. As described above, the presentation processing unit 317 processes the points P where the driving skill evaluation value falls below a predetermined standard value. j or section S j The driver may be given feedback, for example, using still images or videos (animations, etc.), regarding the differences between the driver's driving actions and those of a model driver. After that, the process ends.

[0092] (1-4. Summary) As described above, the information processing device 30 according to the first embodiment is a device for calculating the difficulty of a predetermined route R0. In particular, the processing unit 31 of the information processing device 30 determines the attributes of the predetermined route R0. Then, the processing unit 31 determines a plurality of routes R similar to the determined attributes. i The processing unit 31 then obtains information on the multiple paths R. i Based on the information, multiple paths R of values ​​indicated by one or more first indicators regarding geographical features i The first probability distribution showing the overall tendency of occurrence is calculated. Then, the processing unit 31 calculates the location P included in the predetermined path R0. i or section S i The difficulty of a given path R0 is calculated based on the position of the value indicated by one or more first indicators in a first probability distribution.

[0093] According to this configuration, multiple paths R have attributes similar to a given path R0. i Since the population of the first indicator regarding geographical features in the region is considered, the difficulty of a given route R0 can be objectively calculated. This means that, for example, even if a given route R0 alone is difficult, multiple routes with similar attributes to the given route R0 can be considered. i If the overall difficulty level is low, the difficulty level of the given route R0 will be calculated as low. Therefore, by considering various routes with similar attributes to the target route, the difficulty level of the target route can be objectively evaluated. As a result, by using such difficulty levels to evaluate a driver's driving skills, the driver's driving skills can be objectively assessed.

[0094] <2. Second Embodiment> The information processing device 30 according to the second embodiment of this disclosure will now be described. Hereinafter, the differences between the information processing device 30 according to this embodiment and the first embodiment will be mainly described.

[0095] (2-1. Example of Information Processing Device Configuration) (Probability distribution calculation unit) The probability distribution calculation unit 313 calculates a plurality of paths R whose attributes are similar to the attributes of a predetermined path R0 determined by the attribute determination unit 311, in the same manner as in the first embodiment. i Based on the information, the values ​​indicated by one or more second indicators regarding road surface conditions are calculated. Here, the second indicator is an arbitrary indicator that reflects the road surface conditions and affects driving operations such as acceleration, braking, or steering by the driver. The values ​​indicated by the second indicator include multiple paths R. i Each of these includes a predetermined point P i or a predetermined section S iThe values ​​may also relate to the shape of the road surface, such as the degree of unevenness or rutting. The probability distribution calculation unit 313 can calculate the value indicated by the second index by applying known or arbitrary image recognition processing to image data or satellite image data captured by the surrounding environment sensor 11 of the vehicle 10 or another vehicle, which is stored in advance in the storage unit 32.

[0096] The probability distribution calculation unit 313 calculates the value indicated by one or more second indicators calculated by the method described above, and then calculates the multiple paths R obtained by the path information acquisition unit 312. i A second probability distribution showing the overall occurrence trend is calculated. Specifically, the probability distribution calculation unit 313 calculates k paths R in the same manner as in the first embodiment. i The second probability distribution may be calculated by calculating the probability density function for each of m (where m is the same as n) second indicators from the road surface shape in (1≦i≦k) using the same method as for the first indicator. For example, the degree of rutting D may be used for the second indicator. w If this is included, the probability distribution calculation unit 313 calculates k paths R whose attributes are similar to the attributes of a predetermined path R0. i Degree of rutting D in (1≦i≦k) w The degree of rutting D corresponds to the data set that reflects the information. w We calculate the second probability distribution that the population follows.

[0097] (Difficulty calculation section) The difficulty calculation unit 314 calculates (i) a predetermined point P included in a predetermined route R0. i or a predetermined section S i (ii) the position in the first probability distribution of the value indicated by one or more first indicators in (ii) a predetermined point P included in a predetermined path R0. i or a predetermined section S i Based on the position in the second probability distribution of the value indicated by one or more second indicators in a given path R0, a predetermined point P is included in the given path R0. i or a predetermined section S i Calculate the difficulty level.

[0098] Specifically, with respect to the first indicator, the difficulty calculation unit 314 calculates point P included in the predetermined route R0 in the same manner as in the first embodiment. i or section S i For each of the n first indicators in the given set, the degree of deviation of the value indicated by the first indicator from the population mean μ and standard deviation σ of the first indicator (hereinafter sometimes referred to as the "first deviation") may be calculated.

[0099] On the other hand, with respect to the second indicator, the difficulty calculation unit 314 calculates the location P included in the predetermined route R0. i or section S i Based on the road surface conditions at point P, i or section S i The difficulty calculation unit 314 may calculate the values ​​indicated by m second indicators at point P. Furthermore, the difficulty calculation unit 314 may perform known or arbitrary image recognition processing on image data captured by the vehicle's surrounding environment sensor 11 each time a predetermined time (e.g., the calculation cycle of various sensors) has elapsed since the vehicle 10 started, and calculate the values ​​indicated by the second indicators. Additionally or alternatively, the difficulty calculation unit 314 may calculate the values ​​indicated by the second indicators from the acceleration and angular velocity of the vehicle 10 included in the detection results of the vehicle's vehicle state sensor 12 each time a predetermined time has elapsed since the vehicle 10 started. Furthermore, the difficulty calculation unit 314 may supplementarily use satellite image data or the like pre-stored in the storage unit 32 when calculating the values ​​indicated by the second indicators. However, this disclosure is not limited to these, and instead of the detection values ​​of various sensors included in the vehicle's surrounding environment sensor 11 or vehicle state sensor 12, detection values ​​of various sensors included in a terminal device 20 such as a smartphone held by the driver may be used. Also, the difficulty calculation unit 314 may use the following methods: i or section S i For each of the m second indicators in the system, the degree of deviation of the value indicated by the second indicator from the population mean μ and standard deviation σ of the second indicator (hereinafter sometimes referred to as the "second deviation") may be calculated. In addition, the difficulty calculation unit 314 may, in calculating the second deviation, appropriately use the estimation parameters in the maximum likelihood estimation method used when calculating the second probability distribution, similar to the first embodiment.

[0100] As described above, the difficulty calculation unit 314 calculates the point P included in the predetermined route R0. i or section S i For each step, we may calculate n first deviations for n first indicators and m second deviations for m second indicators.

[0101] The difficulty calculation unit 314 calculates point P included in the predetermined route R0. i or section S i For each point, by summing n first deviations and m second deviations, the location P included in the predetermined path R0 can be determined. i or section S i The difficulty level may be calculated for each of the n first indicators and m second indicators. For example, for each of the n first indicators and m second indicators, values ​​between 0 and (mean μ - standard deviation σ) may be classified as Level 1, values ​​between (mean μ - standard deviation σ) and mean μ may be classified as Level 2, values ​​between mean μ and (mean μ + standard deviation σ) may be classified as Level 3, and values ​​between (mean μ + standard deviation σ) and 1 may be classified as Level 4. In this case, the difficulty level calculation unit 314 calculates the level of the n first indicators and the level of the m second indicators by taking the arithmetic mean or weighted mean, etc., and then calculates the level of point P i or section S i The difficulty level may be calculated for each location. However, this disclosure is not limited thereto, and the difficulty level calculation unit 314 further subdivides the level of each of the n first indicators using the levels of the m second indicators, thereby calculating the difficulty level for location P i or section S i You can calculate the difficulty level for each individual challenge.

[0102] (Driving Skills Evaluation Department) The driving skills evaluation unit 316, in the same manner as in the first embodiment, uses the difficulty level calculated by the difficulty level calculation unit 314 and the driving operation information acquired by the driving information acquisition unit 315, in the same manner as in the first embodiment, to determine point P included in the predetermined route R0. i or section S i To evaluate the driving skills of drivers in this context.

[0103] (2-2. Examples of information processing device operation) Referring to Figure 9, an example of the operation of the information processing device 30 according to the second embodiment will be explained in accordance with the flowchart.

[0104] For simplicity, the first indicator used below is the change in curvature C. e We adopted the second indicator, the degree of rutting D w The following example illustrates the case where the vehicle 10 adopts a predetermined route R0, which is a guided route from the current location to the destination specified by the driver of the vehicle 10 via the navigation device 15. However, the operation examples of the information processing device 30 are not limited to this, and the first indicator could be, for example, the curvature change C. e Instead of or change of curvature C e In addition, the various first indicators mentioned above can be adopted, and as a second indicator, for example, the degree of rutting D w Instead of or degree of rutting D w In addition, the various second indicators mentioned above can be adopted.

[0105] In step S20, the vehicle 10 begins to travel along the guided route from its current location to its destination, as specified by the driver via the navigation device 15. The process then proceeds to steps S21-1 and S21-2. The processes in steps S21-1 and S21-2 are carried out in parallel from the time the vehicle 10 leaves its current location until it arrives at its destination.

[0106] In step S21-1, the driving information acquisition unit 315 of the processing unit 31 acquires point P included in the driving route of the vehicle 10 corresponding to a predetermined route R0 (hereinafter simply referred to as "driving route"). i or section S i The system acquires information on the driver's driving operations each time. The driving information acquisition unit 315 then stores the acquired driving operation information at point P i or section S i The location information is associated with the data and stored in the memory unit 32.

[0107] In step S21-2, the difficulty calculation unit 314 of the processing unit 31 acquires image data captured by the surrounding environment sensor 11 of the vehicle 10 via the communication unit 33 from the vehicle 10 each time a predetermined amount of time has elapsed since the vehicle 10 started moving. The difficulty calculation unit 314 then stores the acquired image data in the storage unit 32, associating it with the location information of the point where it was acquired.

[0108] In step S22, the attribute determination unit 311 of the processing unit 31 determines the attributes of the travel route in the same manner as in the first embodiment. The process then proceeds to step S23.

[0109] In step S23, the route information acquisition unit 312 of the processing unit 31, in the same manner as in the first embodiment, finds k routes R whose attributes are similar to the attribute determined in step S22. i The information for (1 ≤ i ≤ k) is obtained. Then the process proceeds to step S24.

[0110] In step S24, the probability distribution calculation unit 313 of the processing unit 31 calculates the k paths R obtained in step S23. i Based on the information (1≦i≦k), the degree of rutting is D. w Specifically, the probability distribution calculation unit 313 calculates k paths R by applying known or arbitrary image recognition processing to image data captured by the surrounding environment sensor 11 of the vehicle 10 or other vehicles, or satellite image data, which are stored in advance in the storage unit 32. i The degree of rutting included in (1≦i≦k) D w The probability distribution calculation unit 313 calculates the curvature change C in the same manner as in the first embodiment. e The process then proceeds to step S25.

[0111] In step S25, the probability distribution calculation unit 313 of the processing unit 31 calculates the degree of rutting D calculated in step S24. w k paths R iA second probability distribution is calculated that shows the overall tendency of occurrence for (1≦i≦k). Specifically, the probability distribution calculation unit 313 calculates the degree of rutting D as described above. w Assuming that the population follows, for example, a β distribution, the parameters of its probability density function are calculated using the maximum likelihood estimation method to calculate the second probability distribution. The probability distribution calculation unit 313 calculates the curvature change C in the same manner as in the first embodiment. e The first probability distribution for is also calculated. The process then proceeds to step S26.

[0112] In step S26, the difficulty calculation unit 314 of the processing unit 31 performs known or arbitrary image recognition processing on the image data acquired in step S21-2, thereby determining the location P included in the travel route. i or section S i Each time, the degree of rutting is D w The difficulty level calculation unit 314 calculates the point P included in the travel route, in the same manner as in the first embodiment. i or section S i Curvature change C e The process then proceeds to step S27.

[0113] In step S27, the difficulty calculation unit 314 of the processing unit 31 calculates (i) the curvature change C calculated in step S26. e (ii) the position in the first probability distribution calculated in step S25, and the degree of rutting D calculated in step S26. w Based on the position in the second probability distribution calculated in step S25, point P i or section S i The difficulty level of the driving route is calculated for each step. Specifically, the difficulty level calculation unit 314 calculates the curvature change C using the same method as in the first embodiment. e Using the population mean μ and standard deviation σ for the relevant point P in the travel route, i or section S i Curvature change C e The level (levels 1 to 4) related to this is determined. Furthermore, the difficulty calculation unit 314 determines the degree of rutting D using the same method as in the first embodiment.w Using the population mean μ and standard deviation σ for the relevant point P in the travel route, i or section S i Each time, the degree of rutting is D w The level (levels 1 to 4) related to the curvature change C is determined. Then, the difficulty calculation unit 314 determines the level (levels 1 to 4) related to the curvature change C e Level and degree of rutting D w By taking the arithmetic mean or weighted mean of the levels at point P, i or section S i The difficulty level of the route is calculated for each point. Then, the difficulty level calculation unit 314 assigns the calculated difficulty level to point P i or section S i The information is stored in the memory unit 32 in association with the information. After that, the process proceeds to step S28.

[0114] In step S28, the driving skill evaluation unit 316 of the processing unit 31 evaluates point P included in the driving route, based on the difficulty level calculated in step S27 and the driving operation information acquired in step S21-1, in the same manner as in the first embodiment. i or section S i The driver's driving skills are evaluated each time. The process then proceeds to step S29.

[0115] In step S29, the presentation processing unit 317 of the processing unit 31 processes the evaluation results of driving skills in step S28 and provides feedback to the driver in the same manner as in the first embodiment. After that, the process ends.

[0116] (2-3. Summary) As described above, the information processing device 30 according to the second embodiment is a device for calculating the difficulty level of a predetermined route R0. In particular, the processing unit 31 of the information processing device 30 determines the attributes of the predetermined route R0. The processing unit 31 then determines a plurality of routes R similar to the determined attributes. i The processing unit 31 then obtains information on the multiple paths R. i Based on the information, the values ​​shown by one or more first indicators regarding geographical features, for multiple paths R iThe first probability distribution showing the overall occurrence trend is calculated. The processing unit 31 also calculates the multiple paths R obtained. i Based on the information, multiple paths R of the value indicated by one or more second indicators regarding road surface conditions i A second probability distribution showing the overall tendency of occurrence is calculated. Then, the processing unit 31 calculates (i) a point P included in a predetermined path R0. i or section S i (ii) the position in the first probability distribution of the value indicated by one or more first indicators in (ii) and point P included in the predetermined path R0. i or section S i The difficulty of a given path R0 is calculated based on the position of the value indicated by one or more second indicators in a second probability distribution.

[0117] According to this configuration, multiple paths R have attributes similar to a given path R0. i In addition to the population of the first indicator concerning geographical features, the population of the second indicator concerning road surface conditions is also considered, so the difficulty of a given route R0 can be objectively calculated by taking into account information that cannot be obtained from map information alone. In the second embodiment as well, even if the difficulty of a given route R0 is high when viewed alone, multiple routes R0 with similar attributes to the given route R0 can be considered. i If the overall difficulty level is low, the difficulty level of the given route R0 will be calculated as low. Therefore, by considering various routes with similar attributes to the target route, the difficulty level of the target route can be objectively evaluated. As a result, by using such difficulty levels to evaluate a driver's driving skills, the driver's driving skills can be objectively assessed.

[0118] While preferred embodiments of the present disclosure have been described in detail above with reference to the attached drawings, the present disclosure is not limited to such examples. It is clear to any person with ordinary skill in the art to which the present disclosure belongs that various modifications or alterations can be conceived within the scope of the technical idea described in the claims, and these will naturally also be understood to fall within the technical scope of the present disclosure. For example, the functions, etc., included in each component or step, etc., can be rearranged in a logically consistent manner, and multiple components or steps, etc., can be combined into one or divided into two.

[0119] Furthermore, the technology disclosed herein can also be realized as a vehicle 10 equipped with the information processing device 30 described in the above-described embodiment, an information processing method executed by the information processing device 30, a computer program that causes a computer to function as the above-described information processing device 30, and a non-temporary tangible recording medium on which the computer program is recorded. [Explanation of symbols]

[0120] 10: Vehicle, 30: Information processing device, 31: Processing unit, 32: Memory unit, 33: Communication unit, 311: Attribute determination unit, 312: Route information acquisition unit, 313: Probability distribution calculation unit, 314: Difficulty calculation unit, 315: Driving information acquisition unit, 316: Driving skill evaluation unit, 317: Presentation processing unit

Claims

1. An information processing device for calculating the difficulty level of a predetermined route, It comprises one or more processors and one or more memories connected to the one or more processors in a communicative manner, The aforementioned one or more processors Determine the attributes of the predetermined route, Obtain information on multiple routes similar to the determined attribute, Based on the acquired information of the multiple routes, a first probability distribution is calculated that shows the tendency for the values ​​indicated by one or more first indicators relating to geographical characteristics to appear across the multiple routes as a whole. The difficulty level of the predetermined route is calculated based on the position in the first probability distribution of the value indicated by one or more first indicators at a predetermined point or predetermined section included in the predetermined route. Information processing device.

2. The aforementioned predetermined route is the route taken by the vehicle driven by the driver whose driving skills are to be evaluated, The aforementioned one or more processors Based on the position of the value indicated by one or more of the first indicators in the first probability distribution, the difficulty level at the predetermined point or predetermined section is calculated. Information on the driver's driving operations at the predetermined location or section is acquired. Based on the calculated difficulty level and the acquired driving operation information, the driver's driving skills at the predetermined point or predetermined section are evaluated. The information processing apparatus according to claim 1.

3. The aforementioned one or more processors Based on the acquired information of the multiple routes, a second probability distribution is further calculated that shows the tendency for the values ​​indicated by one or more second indicators related to road surface conditions to appear across the multiple routes as a whole. The difficulty level of the predetermined route is calculated based on the position in the first probability distribution of the value indicated by one or more first indicators at the predetermined location or predetermined section, and the position in the second probability distribution of the value indicated by one or more second indicators at the predetermined location or predetermined section. The information processing apparatus according to claim 1.

4. The aforementioned predetermined route is the route taken by the vehicle driven by the driver whose driving skills are to be evaluated, The aforementioned one or more processors Based on the position in the first probability distribution of the value indicated by one or more first indicators and the position in the second probability distribution of the value indicated by one or more second indicators, the difficulty level at the predetermined point or predetermined section is calculated. Information on the driver's driving operations at the predetermined location or section is acquired. Based on the calculated difficulty level and the acquired driving operation information, the driver's driving skills at the predetermined point or predetermined section are evaluated. The information processing apparatus according to claim 3.

5. The aforementioned one or more processors The difficulty level of the driving operation at the predetermined point or section and the driving operation performed by the driver are presented to the driver in correspondence. The information processing apparatus according to claim 2 or 4.

Images