Driving ability assessment system and driving ability assessment method

Abstract

A driving capability determination system (10) comprises: an acquisition unit (13) that acquires travel data of a vehicle; a first calculation unit (15) that calculates a first evaluation value indicating steering characteristics of a driver of the vehicle on the basis of the travel data acquired by the acquisition unit (13); and a second calculation unit (16) that calculates a second evaluation value indicating the steering characteristics of the driver of the vehicle on the basis of travel data in a first section from among the travel data acquired by the acquisition unit (13). The first calculation unit (15) calculates the first evaluation value on the basis of travel data in the first section and travel data in a second section different from the first section, from among the travel data acquired by the acquisition unit (13).

Description

[Technical field]

[0001] The present invention relates to a driving ability determination system and a driving ability determination method for determining the driving ability of a driver of a vehicle. [Background technology]

[0002] As this type of device, a device that measures a driver's safe driving ability is conventionally known (see, for example, Patent Document 1). In the device described in Patent Document 1, a load is intermittently applied to the driver by audio output to distribute the driver's attention, a steering entropy value that represents steering shake is calculated in a loaded state and an unloaded state, and the safe driving ability of the driver is evaluated based on the difference between the shake evaluation values ​​calculated in the loaded state and the unloaded state. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2014-174848 A Summary of the Invention [Problem to be solved by the invention]

[0004] However, the device described in Patent Document 1 requires imposing a load on the driver in order to evaluate the driver's safe driving ability, which impedes driving. [Means for solving the problem]

[0005] The driving ability determination system according to one aspect of the present invention is Includes steering angle information An acquisition unit for acquiring driving data; a section determination unit that determines whether a driving section per unit time is a high-load section in which a driving load on a driver of the vehicle is high or a no-load / low-load section other than the high-load section based on a time change in the steering angle included in the driving data acquired by the acquisition unit, and that determines whether the no-load / low-load section is a predetermined section in which a cognitive load on the driver of the vehicle is high; Driving data acquired by the acquisition unit Driving data for no-load and low-load sections a first calculation unit that calculates a first evaluation value that represents a steering characteristic of a driver of the vehicle based on the driving data acquired by the acquisition unit; Prescribed Based on the driving data for the section, Under cognitive loadA second calculation unit that calculates a second evaluation value that represents the steering characteristic of the driver of the vehicle. 。

[0006] Another aspect of the present invention is a method for determining driving ability, Includes steering angle information An acquisition step of acquiring driving data; a section determination unit that determines whether a driving section per unit time is a high-load section in which a driving load on a driver of the vehicle is high or a no-load / low-load section other than the high-load section based on a time change in the steering angle included in the driving data acquired in the acquisition step, and also determines whether the no-load / low-load section is a predetermined section in which a cognitive load on the driver of the vehicle is high; Driving data acquired in the acquisition step Driving data for no-load and low-load sections a first calculation step of calculating a first evaluation value representing a steering characteristic of a driver of the vehicle based on the driving data obtained in the acquisition step; Prescribed Based on the driving data for the section, Under cognitive load and a second calculation step of calculating a second evaluation value representing a steering characteristic of the driver of the vehicle. 。 Effect of the Invention

[0007] According to the present invention, driving ability can be determined without interfering with driving. [Brief description of the drawings]

[0008] [Figure 1] FIG. 2 is a diagram for explaining a driving section and an operating load. [Diagram 2] 1 is a block diagram illustrating a configuration of a main part of a driving ability determination system according to an embodiment of the present invention; [Diagram 3] 4A and 4B are diagrams for explaining fluctuations in the steering angle of a vehicle. [Figure 4] FIG. 13 is a diagram illustrating an example of a degree display of the degree of steering shake. [Diagram 5] 3 is a flowchart illustrating the flow of processing by the calculation unit in FIG. 2. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0009] Hereinafter, an embodiment of the present invention will be described with reference to Figs. 1 to 5. A driving ability determination system according to an embodiment of the present invention determines the driving ability of a driver of a vehicle. In general, a driver's driving behavior is composed of three elements: cognition, judgment, and operation. Of these elements, abilities related to "cognitive function," which is a person's intellectual function related to cognition and judgment, are known to gradually decline with age. When cognitive function declines, it becomes difficult to drive a vehicle safely.

[0010] Therefore, in this embodiment, the driving ability assessment system is configured as follows to assess the driving ability, particularly the driving ability related to cognitive function, based on driving data when the driver drives the vehicle, and to support safe driving by allowing the driver and his / her family to understand the tendency of cognitive function to decline.

[0011] FIG. 1 is a diagram for explaining the driving section and the driving load. As shown in FIG. 1, the driving section on which the vehicle travels can be classified into a no-load section such as a straight line where the driver is hardly burdened by the driving action, a high-load section such as an S-shaped curve, a crank, or parking where the driving load is large, and a low-load section in between. More specifically, the no-load section is a driving section where the driver is required to perform less steering per vehicle travel distance and the vehicle travel path has a simple shape, and the high-load section is a section where the driver is required to perform more steering per vehicle travel distance and the vehicle travel path has a complex shape. In such a high-load section, in addition to the high frequency of steering, the steering wheel needs to be operated in conjunction with the operation of the accelerator and brake, and a vehicle sense is also required, so high driving skills are required. In other words, the stability of driving in a high-load section is greatly affected by the driver's driving skills.

[0012] The low-load section includes driving sections such as right curves, left curves, lane changes, right turns, and left turns. Among these low-load sections, in a section where the vehicle crosses the oncoming lane at an intersection to change the traveling direction (a right-turn section in countries and regions where vehicles drive on the left side, and a left-turn section in countries and regions where vehicles drive on the right side; hereinafter, simply referred to as a "right-turn section"), when the driver recognizes the target trajectory of the vehicle, it is necessary to grasp the situation of the oncoming lane ahead while grasping the situation of the driving lane after the right turn. In this case, the driver's mental activity increases due to the occurrence of line-of-sight movement between the oncoming lane ahead and the driving lane after the right turn, and the driving load, especially the cognitive load related to cognition, becomes higher than in other low-load sections. For this reason, the driver's cognitive function has a large effect on the stability of driving in the right-turn section. By evaluating the stability of driving based on the driving data of such a right-turn section, the driving ability related to the driver's cognitive function can be determined.

[0013] Examples of driving sections where the driver's cognitive function affects driving stability include, in addition to right-turn sections, sections where many signs are installed and two-way traffic sections where the eye movement is set to be more than a predetermined amount, sections where traffic signals are installed, sections where the number of pedestrians is set to be more than a predetermined amount such as downtown areas, sections where blind spots during driving such as intersections with poor visibility are set to be more than a predetermined amount, and sections where multiple roads intersect. Therefore, by acquiring driving data for such sections in a manner that can be distinguished from other sections and evaluating the driving stability based on the driving data, it is also possible to determine the driving ability related to the driver's cognitive function. When time-series position information is acquired in addition to the vehicle's driving data, a specific driving section set in advance can be identified based on the position information.

[0014] FIG. 2 is a block diagram illustrating the main configuration of a driving ability determination system (hereinafter, referred to as the system) 10. As shown in FIG. 2, the system 10 is configured to include a computer having a calculation unit 11 such as a CPU, a storage unit 12 such as a ROM, a RAM, and the like, and peripheral circuits thereof. The calculation unit 11 has, as functional configurations, an information acquisition unit 13, a section determination unit 14, an α value calculation unit 15, an Hp value calculation unit 16, a cognitive function evaluation unit 17, and an information output unit 18. The storage unit 12 stores information such as a program executed by the calculation unit 11 and setting values. The system 10 may be configured as an on-board device mounted on a vehicle, or may be configured as a server device provided outside the vehicle.

[0015] The information acquisition unit 13 acquires driving data of the vehicle for each driver. For example, driving data during the elderly driver training course measured in a vehicle dedicated to the elderly driver training course, and driving data measured in a vehicle that the driver drives daily are acquired. The driving data includes at least information on the steering angle θ of the vehicle in time series. The driving data may include time series position information, etc. The information acquisition unit 13 may acquire information on the results of a cognitive function test during the elderly driver training course in addition to the driving data during the elderly driver training course.

[0016] The section determination unit 14 determines the driving section based on the driving data acquired by the information acquisition unit 13. More specifically, it determines whether the driving section per unit time is the no-load / low-load section or the high-load section in FIG. 1 based on the time change of the steering angle θ, and determines whether it is a right-turn section in the no-load / low-load section. The section determination unit 14 may determine the driving section per unit time based on the time change of the position information. Note that, when the information acquisition unit 13 acquires the driving data for each driving section, the section determination unit 14 does not need to determine the driving section.

[0017] FIG. 3 is a diagram for explaining fluctuations in the steering angle θ of a vehicle. When the vehicle is driven in a stable state, the steering is performed smoothly without any shaking, and the fluctuations in the steering angle θ are small. On the other hand, when the driving is unstable, the steering is shaken and the fluctuations in the steering angle θ are large. The α value calculation unit 15 calculates an α value, which is an evaluation value representing the characteristics of the steering by the driver of the vehicle, based on the driving data of the no-load / low-load section (for example, the driving data of the entire section) acquired by the information acquisition unit 13.

[0018] More specifically, as shown in FIG. 3, a predicted steering angle θp(n) at time point n is calculated by a second-order Taylor expansion centered on time point (n-1) based on actual steering angles θ(n-3), θ(n-2), and θ(n-1) at time points n-3, n-2, and n-1 immediately prior to a specific time point n. Since the predicted steering angle θp(n) is an estimated value assuming that steering was performed smoothly, if the actual steering was performed smoothly, it matches the actual steering angle θ(n), and if the actual steering was unstable, it deviates from the actual steering angle θ(n) depending on the degree of the unstableness. Such a degree of the unstableness can be expressed as a prediction error e(n) calculated by the following formula (i). e(n) = θ(n) - θp(n) (i)

[0019] FIG. 4 is a diagram illustrating an example of the frequency display of the degree of steering deviation, and shows an example of the frequency display of the prediction error e(n). The α value calculation unit 15 calculates the predicted steering angle θp(n) and the prediction error e(n) at each time point n based on the driving data of the no-load and low-load sections, and then calculates the 90th percentile value (α value) in the frequency distribution of the prediction error e(n) as shown by the solid line in FIG. 4. The smoother the steering is and the less the steering deviation is, the sharper the frequency distribution of the prediction error e(n) becomes centered on "0°" where there is no steering deviation, and the smaller the α value becomes. On the other hand, the more the steering deviation is, the broader the frequency distribution of the prediction error e(n) becomes, and the larger the α value becomes. By using the driving data of the no-load and low-load sections, excluding the high-load sections where there is a lot of steering and the influence of the driving skill on the steering deviation is large, the α value that represents the driver's steering deviation in a normal state can be appropriately calculated.

[0020] The Hp value calculation unit 16 calculates the Hp value, which represents the characteristics of steering by the driver of the vehicle, based on the α value calculated by the α value calculation unit 15 and the driving data of the right-turn section as a predetermined section among the no-load / low-load sections used to calculate the α value. More specifically, after calculating the predicted steering angle θp(n) and the prediction error e(n) at each time point n based on the driving data of the right-turn section, the frequency distribution of the prediction error e(n) as shown by the dashed line in Fig. 4 is divided into nine ranges P1 to P9 based on the α value. That is, based on the eight reference values ​​-5α, -2.5α, -α, -0.5α, 0.5α, α, 2.5α, 5α, it is divided into nine ranges P1 (up to -5α), P2 (-5α to -2.5α), P3 (-2.5α to -α), P4 (-α to -0.5α), P5 (-0.5α to 0.5α), P6 (0.5α to α), P7 (α to 2.5α), P8 (2.5α to 5α), and P9 (5α or more). Then, based on the proportions p1 to p9 of each range P1 to P9, the steering entropy value (Hp value) is calculated using the following formula (ii). Hp = -Σpi log9pi (ii)

[0021] The Hp value indicates the smoothness of steering, and the smaller the steering sway and the sharper the frequency distribution of the prediction error e(n), the smaller the value, and the larger the steering sway and the broader the frequency distribution of the prediction error e(n), the larger the value. By using driving data from a right-turn section where there is a lot of eye movement and the cognitive function is greatly affected by steering sway, it is possible to appropriately calculate the Hp value, which indicates the driver's steering sway when the cognitive load is greater than in normal conditions.

[0022] The cognitive function evaluation unit 17 evaluates the cognitive function of the driver of the vehicle based on the Hp value calculated by the Hp value calculation unit 16. That is, by continuously monitoring the Hp value, which indicates the steering shake under a cognitive load, the cognitive function of the driver can be evaluated as being in a declining trend. For example, if the Hp value calculated for each course based on the driving data in a course for the elderly that is periodically conducted is in an increasing trend, it is evaluated that the cognitive function is in a declining trend. The score of the cognitive function test in the course for the elderly may be taken into consideration. A similar evaluation may be performed based on the Hp value that is periodically calculated based on the driving data of daily driving.

[0023] The information output unit 18 transmits the evaluation result by the cognitive function evaluation unit 17 to a user terminal of the driver himself / herself or a family member. For example, a notification can be sent to a pre-registered email address. In this case, the notification can prompt the driver himself / herself or a family member to consider returning the driver's license or replacing the vehicle with one that has enhanced driving support functions. Since objective information based on driving data is provided, the driver himself / herself can easily accept the current state of his / her own cognitive function and can consider appropriate measures at an early stage.

[0024] 5 is a flowchart illustrating the flow of processing by the calculation unit 11 of the system 10. The processing shown in this flowchart is executed, for example, every time driving data during an elderly person training course is input to the system 10. First, in step S1, time-series driving data is acquired. Next, in step S2, the driving section for each unit time is determined. Next, in step S3, driving data for a period determined to be a high load section in step S2 is excluded from the driving data acquired in step S1, and the process proceeds to step S4 to calculate an α value. The latest α value calculated in step S4 is stored in the memory unit 12 and updated.

[0025] Next, in step S5, the driving data for the period determined to be a right-turn section in step S2 is extracted from the driving data acquired in step S1, and the process proceeds to step S6, where the Hp value is calculated based on the latest α value stored in the storage unit 12. The latest Hp value calculated in step S6 is stored and accumulated in the storage unit 12. Next, in step S7, the latest Hp value stored in the storage unit 12 is compared with past Hp values ​​to determine the driving ability related to the driver's cognitive function. Next, in step S8, the evaluation result of step S7 is sent to a pre-registered email address, and the process ends.

[0026] In this way, since the evaluation is performed based on daily driving data such as driving data during the elderly driver's training course, the driving ability of the driver of the vehicle can be determined without impeding driving (step S1). In addition, by excluding high-stress sections where the influence of driving skills on steering shake is large, the α value representing the driver's steering shake in a normal state can be calculated with high accuracy (steps S2 to S4). Furthermore, by using the driving data of the section where the influence of cognitive function on steering shake is large, the Hp value representing the driver's steering shake in a state where cognitive load is applied compared to a normal state can be calculated with high accuracy (steps S2, S5 to S6). In addition, the driver's cognitive function is automatically evaluated based on the driving data, and the evaluation result is notified to the driver and his / her family, so that the burden of watching over the elderly driver who drives the vehicle can be reduced for family members who live apart from him / her (steps S1 to S8).

[0027] According to this embodiment, the following advantageous effects can be obtained. (1) The system 10 includes an information acquisition unit 13 that acquires vehicle driving data, an α value calculation unit 15 that calculates an α value representing the steering characteristics of the vehicle driver based on the driving data acquired by the information acquisition unit 13, and an Hp value calculation unit 16 that calculates an Hp value representing the steering characteristics of the vehicle driver based on driving data in a predetermined section (e.g., a right-turn section) of the driving data acquired by the information acquisition unit 13 (FIG. 2). The α value calculation unit 15 calculates the α value based on driving data in the predetermined section of the driving data acquired by the information acquisition unit 13 and driving data in a no-load / low-load section (e.g., a straight section, a curve section, a lane-changing section, a left-turn section) different from the predetermined section.

[0028] This makes it possible to calculate the α value and Hp value, which are indicators for judging a driver's driving ability, based on everyday driving data, such as driving data from an elderly driver's driving course, so that driving ability can be judged without interfering with driving.

[0029] (2) The predetermined section is at least one of a section set as having more than a predetermined amount of eye movement while driving, a section with traffic lights, a section set as having more pedestrians than a predetermined amount, a section set as having more than a predetermined amount of blind spots while driving, and a section where multiple roads intersect. By using driving data from such sections where cognitive function is greatly affected by steering shake, it is possible to accurately calculate the Hp value, which represents the driver's steering shake under a cognitive load compared to a normal state, and to accurately determine the driving ability related to cognitive function.

[0030] (3) The specified section and the no-load / low-load section different from the specified section are driving sections that do not involve S-curve driving, crank driving, or parking driving (Fig. 1). In high-load sections involving these types of driving, steering is frequent, the steering wheel needs to be operated in conjunction with the accelerator and brake operations, and vehicle sense is also required, so that driving skills have a greater influence on steering error than cognitive functions. By excluding driving data from such high-load sections, it is possible to accurately calculate the α value, which represents the driver's steering error under normal conditions.

[0031] (4) The specified section is a section where the vehicle crosses the oncoming lane at an intersection to change its direction of travel, and is a right-turn section in countries and regions where vehicles are driven on the left side of the road (Figure 1). In a right-turn section, when recognizing the target trajectory of the vehicle, the driver's line of sight moves between the oncoming lane ahead and the lane to which the driver has turned right, which increases the driver's mental activity and increases the driver's cognitive load, resulting in greater steering sway compared to other driving sections. By using the driving data of such a right-turn section, it is possible to accurately calculate the Hp value, which represents the driver's steering sway under a cognitive load compared to a normal state.

[0032] (5) The system 10 further includes a cognitive function evaluation unit 17 that evaluates the cognitive function of the driver of the vehicle based on the Hp value calculated by the Hp value calculation unit 16 (FIG. 2). For example, the driving data of the individual driver is periodically acquired, such as at each senior citizen training course, to calculate the Hp value, and if an upward trend in the Hp value is observed, it can be evaluated that the cognitive function is declining. By continuously monitoring changes in cognitive function using daily driving data in this way, it is possible to grasp the tendency of cognitive function to decline early on, before a specific event such as an accident occurs. In addition, by grasping the tendency of cognitive function to decline at an early stage, it is possible to review the entire life other than driving the vehicle, leading to the maintenance and recovery of cognitive function.

[0033] (6) The system 10 further includes an information output unit 18 that outputs the evaluation results by the cognitive function evaluation unit 17 (FIG. 2). For example, a notification can be sent to the email address of the driver or a family member that has been registered in advance. In this case, the notification can prompt the driver to consider returning his / her driver's license or switching to a vehicle with enhanced driving support functions. In this way, objective information based on driving data is provided, making it easier for the driver to accept the current state of his / her cognitive function and to consider appropriate measures at an early stage.

[0034] In the above embodiment, an example of continuously monitoring the driving data of a specific driver has been described, but the method of determining the driving ability of a vehicle driver is not limited to this. For example, the driving ability related to cognitive function may be determined by comparing the driving ability with a predetermined reference value, such as the average value of multiple drivers who have taken an elderly driver training course.

[0035] Although the present invention has been described above as a driving ability determination system, the present invention can also be used as a driving ability determination method. That is, the driving ability determination method includes driving data acquisition steps S1 to S3 for acquiring vehicle driving data, an α value calculation step S4 for calculating an α value representing the steering characteristics of the vehicle driver based on the driving data acquired in the driving data acquisition steps S1 to S3, and an Hp value calculation step S5 to S6 for calculating an Hp value representing the steering characteristics of the vehicle driver based on the driving data in a predetermined section among the driving data acquired in the driving data acquisition step S1 (FIG. 5). In the α value calculation step S4, the α value is calculated based on the driving data in the predetermined section and the driving data in a no-load / low-load section different from the predetermined section among the driving data acquired in the driving data acquisition steps S1 to S3.

[0036] The above description is merely an example, and the present invention is not limited to the above-mentioned embodiment and modifications, as long as the features of the present invention are not impaired. The above-mentioned embodiment and one or more modifications can be arbitrarily combined, and modifications can be combined with each other. [Explanation of symbols]

[0037] 10 Driving ability judgment system (system), 11 Calculation unit, 12 Memory unit, 13 Information acquisition unit, 14 Section judgment unit, 15 α value calculation unit, 16 Hp value calculation unit, 17 Cognitive function evaluation unit, 18 Information output unit

Claims

1. An acquisition unit that acquires driving data including information on a steering angle of a vehicle; a section determination unit that determines whether a driving section per unit time is a high-load section in which a driving load on a driver of the vehicle is high or a no-load / low-load section other than the high-load section based on a time change of the steering angle included in the driving data acquired by the acquisition unit, and that determines whether the no-load / low-load section is a predetermined section in which a cognitive load on the driver of the vehicle is high; a first calculation unit that calculates a first evaluation value that represents a steering shake of a driver of the vehicle based on the driving data in the no-load / low-load section among the driving data acquired by the acquisition unit; A driving ability assessment system comprising: a second calculation unit that calculates a second evaluation value that represents the steering shake of the driver of the vehicle under cognitive load based on the driving data for the specified section among the driving data acquired by the acquisition unit.

2. The driving ability determination system according to claim 1, A driving ability assessment system characterized in that the specified section is at least one of a section set as having more than a specified amount of eye movement while driving, a section where traffic lights are installed, a section set as having more pedestrians than a specified amount, a section set as having more than a specified amount of blind spots while driving, and a section where multiple roads intersect.

3. The driving ability determination system according to claim 1 or 2, A driving ability determination system, wherein the no-load / low-load section is a driving section that does not include S-curve driving, crank driving, or parking driving.

4. In the driving ability determination system according to any one of claims 1 to 3, A driving ability determination system, wherein the predetermined section is a section where the vehicle changes direction by crossing an oncoming lane at an intersection.

5. The driving ability determination system according to claim 4, A driving ability assessment system, wherein the predetermined section is a right turn section.

6. In the driving ability determination system according to any one of claims 1 to 5, A driving ability determination system further comprising an evaluation unit that evaluates the cognitive function of the driver of the vehicle based on the second evaluation value calculated by the second calculation unit.

7. 7. The driving ability determination system according to claim 6, The driving ability determination system further comprises an output unit that outputs an evaluation result by the evaluation unit.

8. An acquisition step of acquiring driving data including information on a steering angle of a vehicle; a section determination unit that determines whether a driving section per unit time is a high-load section in which a driving load on a driver of the vehicle is high or a no-load / low-load section other than the high-load section based on a time change of the steering angle included in the driving data acquired in the acquisition step, and determines whether the no-load / low-load section is a predetermined section in which a cognitive load on the driver of the vehicle is high; a first calculation step of calculating a first evaluation value representing a steering shake of a driver of the vehicle based on the driving data in the no-load / low-load section among the driving data acquired in the acquisition step; A driving ability assessment method comprising: a second calculation step of calculating a second evaluation value representing the steering shake of the driver of the vehicle under cognitive load based on the driving data for the specified section among the driving data acquired in the acquisition step.

9. 9. The driving ability determination method according to claim 8, A method for determining driving ability, characterized in that the specified section is at least one of a section set as having more than a specified amount of eye movement while driving, a section where traffic lights are installed, a section set as having more pedestrians than a specified amount, a section set as having more than a specified amount of blind spots while driving, and a section where multiple roads intersect.

10. The driving ability determination method according to claim 8 or 9, A driving ability determination method, characterized in that the no-load / low-load section is a driving section that does not include S-curve driving, crank driving, or parking driving.

11. The driving ability determination method according to any one of claims 8 to 10, A driving ability determination method, characterized in that the specified section is a section where the vehicle changes direction by crossing an oncoming lane at an intersection.

12. The driving ability determination method according to claim 11, A driving ability determination method, wherein the predetermined section is a right turn section.

13. The driving ability determination method according to any one of claims 8 to 12, A driving ability determination method, further comprising an evaluation step of evaluating the cognitive function of the driver of the vehicle based on the second evaluation value calculated in the second calculation step.

14. The driving ability determination method according to claim 13, The driving ability determination method further comprising an output step of outputting an evaluation result in the evaluation step.

Images