Driving ability assessment system and driving ability assessment method

Abstract

To determine operation ability without causing an operational issue.SOLUTION: An operation ability determination system 10 comprises: an information acquisition section 13 which acquires information on a surface of a road with a vehicle traveling thereon and steering angle data indicating a time series change in a steering angle of the vehicle; an unevenness determination section 14 which determines whether a level of unevenness of the surface of the road is equal to or less than a predetermined level on the basis of the information on the surface of the road acquired with the information acquisition section 13; and an evaluation value calculation section 16 which calculates an evaluation value indicating a steering characteristic of a driver on the basis of the steering angle data acquired with the information acquisition section 13. The evaluation value calculation section 16 calculates the evaluation value by making weight of first steering angle data, among the steering angle data acquired with the information acquisition section 13, during a period when the unevenness determination section 14 determines that the level of the unevenness of the surface of the road is equal to or less than the predetermined level larger than weight of second steering angle data during a period when the unevenness determination section 14 determines that the level of the unevenness of the surface of the road exceeds the predetermined level.SELECTED DRAWING: Figure 2

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 vehicle driver. [Background technology]

[0002] As this type of device, a device that measures a driver's safe driving ability is known (see, for example, Patent Document 1). The device described in Patent Document 1 intermittently applies a load to the driver by audio output to distribute attention, calculates steering entropy values ​​that represent steering deviations under load and no load conditions, and evaluates the driver's safe driving ability based on the difference between the deviation evaluation values ​​calculated under load and no load conditions.

[0003] By assessing the driving ability of elderly drivers and providing them with an opportunity to consider returning their driver's license or introducing driving assistance functions as necessary, we can improve road safety and contribute to the development of sustainable transportation systems. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Japanese Patent Application Laid-Open No. 2014-174848 Summary of the Invention [Problem to be solved by the invention]

[0005] 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]

[0006] A driving ability assessment system according to one aspect of the present invention includes an information acquisition unit that acquires steering angle data indicating changes in the steering angle of the vehicle over time along with information about the road surface on which the vehicle is traveling, an unevenness determination unit that determines whether the degree of road surface unevenness is equal to or less than a predetermined level based on the road surface information acquired by the information acquisition unit, and an evaluation value calculation unit that calculates an evaluation value representing the steering characteristics of the driver based on the steering angle data acquired by the information acquisition unit. The evaluation value calculation unit calculates the evaluation value by increasing the weight of first steering angle data during a period in which the unevenness determination unit determines that the degree of road surface unevenness is equal to or less than the predetermined level, among the steering angle data acquired by the information acquisition unit.

[0007] A driving ability assessment method according to another aspect of the present invention includes an information acquisition step of acquiring steering angle data indicating changes in the steering angle of the vehicle over time along with information about the surface of a road on which the vehicle is traveling, an unevenness determination step of determining whether the degree of road surface unevenness is equal to or less than a predetermined level based on the road surface information acquired in the information acquisition step, and an evaluation value calculation step of calculating an evaluation value representing the steering characteristics of the driver based on the steering angle data acquired in the information acquisition step. In the evaluation value calculation step, the evaluation value is calculated by giving a greater weight to first steering angle data, of the steering angle data acquired in the information acquisition step, during a period in which it is determined that the degree of road surface unevenness is equal to or less than the predetermined level in the unevenness determination step, than to a weight to second steering angle data during a period in which it is determined that the degree of road surface unevenness exceeds the predetermined level in the unevenness determination step. [Effects of the Invention]

[0008] According to the present invention, driving ability can be determined without interfering with driving. [Brief explanation of the drawings]

[0009] [Figure 1] FIG. 1 is a diagram for explaining a driving section and a driving load. [Figure 2]1 is a block diagram showing an example of a configuration of a main part of a driving ability determination system according to an embodiment of the present invention; [Figure 3] FIG. 3 is a diagram for explaining fluctuations in the steering angle of a vehicle. [Figure 4] FIG. 10 is a diagram illustrating an example of a degree display of the degree of steering shake. [Figure 5] 3 is a time chart for explaining road surface conditions that are taken into account by the evaluation value calculation unit of FIG. 2; [Figure 6] 3 is a flowchart showing an example of evaluation processing executed by the calculation unit of FIG. 2; [Figure 7] 3 is a flowchart showing an example of weighting processing executed by the calculation unit of FIG. 2; [Figure 8] 10 is a flowchart showing another example of the weighting process executed by the calculation unit of FIG. 2. DETAILED DESCRIPTION OF THE INVENTION

[0010] Hereinafter, an embodiment of the present invention will be described with reference to FIGS. 1 to 8. A driving ability determination system according to an embodiment of the present invention determines the driving ability of a vehicle driver. Generally, 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. Declining cognitive function makes it difficult to drive a vehicle safely. The driving ability related to cognitive function is determined based on driving data when the driver drives a vehicle, and safe driving can be supported by the driver and their family members by understanding the tendency of cognitive function decline.

[0011] Figure 1 is a diagram explaining the relationship between driving sections and driving load. As shown in Figure 1, the driving load imposed on a driver due to driving behavior varies depending on the driving section, such as road shape. For example, driving on S-curves or winding roads, or parking in a parking space, increases the driving load. In other words, driving load increases on driving sections where the driver is required to make many steering maneuvers per unit of vehicle movement and the vehicle's driving trajectory has a complex shape. In this case, high driving skills are required, as steering is required in coordination with accelerator and brake operations, and vehicle sense is also required. In such driving sections (high-load sections), the driver's driving skills have a significant impact on driving stability.

[0012] On the other hand, there is almost no driving load when driving on a straight road. In other words, there is almost no steering required from the driver per unit of vehicle movement, and the vehicle's driving trajectory is extremely simple, so there is almost no driving load. In such driving sections (no-load sections), the driver's driving skill has almost no effect on driving stability.

[0013] Driving loads fall somewhere in between these two levels when driving on curved roads, changing lanes on multi-lane roads, turning right or left at intersections, etc. Even in these driving sections (low load sections), the driver's driving skill does not have much of an impact on driving stability.

[0014] However, even in no-load or low-load sections, for example, when driving on a single-lane highway (two-way traffic section) with no central divider, the driver needs to recognize the conditions of the vehicle's own lane and the oncoming lane. In this case, the driver's mental activity increases as the driver's gaze shifts between the vehicle's own lane and the oncoming lane, increasing the cognitive load (hereinafter referred to as "cognitive load"). The cognitive load also increases because gaze shifts are required in sections with multiple lanes with heavy traffic, sections with many signs and traffic signals, sections with many pedestrians such as in busy areas, sections with many blind spots such as curved roads with poor visibility or intersections, and sections where multiple roads intersect.

[0015] Furthermore, when making a turn at an intersection to change the direction of travel of the vehicle by crossing the oncoming lane (a right turn in countries and regions where vehicles drive on the left side of the road, and a left turn in countries and regions where vehicles drive on the right side of the road; hereinafter simply referred to as a "right turn"), the driver needs to grasp the situation of the oncoming lane ahead while also grasping the situation of the lane ahead after the right turn in order to recognize the target trajectory of the vehicle. In this case too, the driver's line of sight shifts between the oncoming lane ahead and the lane ahead after the right turn, increasing the cognitive load.

[0016] In a driving section where cognitive load is high (hereinafter referred to as a "specific section"), the state of the driver's cognitive function affects the driving stability. By acquiring driving data for the specific section in a manner that allows it to be distinguished from other sections and evaluating the driving stability based on the driving data, it is possible to determine the driving ability related to the driver's cognitive function. For example, time-series location information of the vehicle can be acquired, and based on the acquired location information, it is possible to identify the driving data for the specific section that is preset in the map information.

[0017] However, when the road surface on which the vehicle is traveling is highly uneven and lateral acceleration (acceleration in the width direction or up and down direction of the vehicle, hereinafter referred to as "lateral acceleration") acts on the vehicle in the traveling direction, the driver's steering becomes unstable, making it difficult to evaluate the driver's own driving stability based on the traveling data. Therefore, in this embodiment, the driving ability assessment system is configured as follows so that driving ability related to cognitive function can be appropriately assessed by changing the way the traveling data is handled depending on the condition of the road surface on which the vehicle is traveling.

[0018] FIG. 2 is a block diagram showing an example of the configuration of the main components of a driving ability assessment system (hereinafter referred to as the system) 10. As shown in FIG. 2, the system 10 includes a computer having a calculation unit 11 such as a CPU, a storage unit 12 such as a ROM and a RAM, and peripheral circuits thereof. The calculation unit 11 functions as an information acquisition unit 13, an unevenness determination unit 14, a load determination unit 15, an evaluation value calculation unit 16, a cognitive function assessment unit 17, and an information output unit 18. The system 10 may be configured as an in-vehicle device mounted on a vehicle, as a server device or the like provided outside the vehicle, or as a combination of an in-vehicle device and an external server device or the like.

[0019] The memory unit 12 stores road map information along with information such as programs executed by the calculation unit 11 and setting values. The road map information includes information such as road position information, road curvature and width, and information on whether the road is paved with asphalt or the like or an unpaved road such as a gravel road. Unpaved roads also include forest roads, farm roads, and footpaths.

[0020] The information acquisition unit 13 acquires time-series vehicle driving data for each pre-registered driver. For example, it acquires driving data measured on a pre-registered vehicle that each driver drives daily. The driving data includes at least information on the road surface on which the vehicle is traveling and time-series steering angle data that indicates changes in the steering angle of the steering wheel (steering wheel) by the driver. The driving data also includes time-series position information of the vehicle.

[0021] The road surface information acquired by the information acquisition unit 13 is, for example, information on the degree of unevenness of the road surface on the road around the vehicle, detected by a sensor (external sensor) mounted on the vehicle. For example, from a vehicle equipped with a camera having an imaging element such as a CCD or CMOS and capturing images of the surroundings of the vehicle including the road surface, image information of the road surface detected (captured) by the camera can be acquired as road surface information.

[0022] In this case, the degree of road surface unevenness can be estimated by processing the road surface image information acquired by the information acquisition unit 13, detecting road surface unevenness, and estimating the area, density, and depth or height of the detected unevenness. Note that road surface unevenness includes not only certain unevenness caused by gravel laid on the road, but also depressions in the road surface, scattered objects on the road, ruts caused by snowfall, and the like.

[0023] The information acquisition unit 13 may acquire information on the depth of depressions or height of protrusions on the road surface around the vehicle as road surface information from a vehicle equipped with a lidar or radar that measures the distance to objects such as vehicles and obstacles around the vehicle.

[0024] The road surface information acquired by the information acquisition unit 13 may be information on the lateral acceleration acting on the vehicle detected by an acceleration sensor (lateral G sensor) mounted on the vehicle. Generally, the greater the degree of road surface roughness, the greater the lateral acceleration acting on the vehicle. Therefore, based on the acquired lateral acceleration information, it is possible to estimate the degree of road surface roughness on the road on which the vehicle is traveling. In addition, by comparing the magnitude of the lateral acceleration acting on the vehicle with a predetermined threshold, it is also possible to determine whether the degree of road surface roughness is equal to or less than a predetermined level.

[0025] The road surface information acquired by the information acquisition unit 13 may be road surface information of a road corresponding to the vehicle's position information, which is included in pre-stored road map information. In this case, the information acquisition unit 13 acquires information (position information) about the vehicle's current position detected by a positioning sensor mounted on the vehicle. By comparing the acquired vehicle position information with the road position information in the road map information stored in the storage unit 12, it is possible to identify the road on which the vehicle is traveling and determine whether the road on which the vehicle is traveling is a paved road or an unpaved road that is predetermined in the road map information.

[0026] The driving data is transmitted from the vehicle to the system 10 at a predetermined interval via, for example, a TCU (telematics control unit) mounted on the vehicle. The information acquisition unit 13 acquires the driving data transmitted from pre-registered vehicles as time-series driving data for each pre-registered driver. The time-series driving data for each driver acquired by the information acquisition unit 13 is stored in the storage unit 12.

[0027] The unevenness determination unit 14 determines whether the degree of unevenness of the road surface is equal to or less than a predetermined level based on the road surface information stored in the memory unit 12. More specifically, when the road surface information is image information of the road surface, the unevenness of the road surface is first detected by processing the image information of the road surface, and the depth or height of the detected unevenness is estimated. Next, the estimated depth or height of the unevenness is compared with a predetermined threshold, and if the depth or height is equal to or less than the threshold, the unevenness of the road surface is determined to be equal to or less than the predetermined level. The unevenness determination unit 14 may estimate the area and density of the unevenness detected by image processing, and estimate the degree of unevenness taking these into consideration.

[0028] When the road surface information is information about the depth of depressions or the height of protrusions on the road surface around the vehicle, the unevenness determination unit 14 compares the depth or height of the unevenness with a predetermined threshold value to determine whether the degree of unevenness of the road surface is below a predetermined level.

[0029] If the road surface information is information about the lateral acceleration acting on the vehicle, the unevenness determination unit 14 compares the magnitude of the lateral acceleration with a predetermined threshold, and if the magnitude is less than the threshold, determines that the degree of unevenness of the road surface is less than a predetermined level.

[0030] When the road surface information is vehicle position information, the unevenness determination unit 14 first identifies the road on which the vehicle is traveling by comparing the vehicle position information with the road position information in the road map information. Next, it determines whether the identified road is a paved road or an unpaved road that is predetermined in the road map information, and if it is an unpaved road, it determines that the degree of unevenness of the road surface exceeds a predetermined level.

[0031] When multiple types of information, such as information on the lateral acceleration acting on the vehicle and vehicle position information, are acquired by the information acquisition unit 13 as road surface information at the same time and stored in the memory unit 12, the unevenness determination unit 14 can perform the above determinations in combination. That is, if the road identified based on the position information is an unpaved road, it is determined that the degree of road surface unevenness exceeds a predetermined level, while if it is a paved road, it is further determined based on the lateral acceleration information whether the degree of road surface unevenness is equal to or less than a predetermined level. In this case, even if the road identified based on the position information is an unpaved road, if the magnitude of the lateral acceleration exceeds a threshold, it is determined that the degree of road surface unevenness exceeds a predetermined level.

[0032] The load determination unit 15 determines whether a predetermined cognitive load is acting on the driver for each unit time based on the driving data stored in the storage unit 12. More specifically, the load determination unit 15 determines whether the driving section for each unit time is a no-load section or a low-load section (no-load / low-load section) or a high-load section in FIG. 1 based on time-series position information of the vehicle. Furthermore, the load determination unit 15 determines whether the driving section for each unit time is a specific section among the no-load / low-load sections that is preset in the map information.

[0033] The evaluation value calculation unit 16 calculates an α value representing the average steering characteristics of an individual driver and an Hp value representing the steering characteristics of the driver when the cognitive load is increased, based on the steering angle data stored in the storage unit 12. More specifically, the evaluation value calculation unit 16 calculates the α value based on the steering angle data for a period during which the load determination unit 15 determines that the vehicle is traveling in a no-load / low-load section. The evaluation value calculation unit 16 also calculates the Hp value based on the calculated α value and the steering angle data for a period during which the load determination unit 15 determines that the vehicle is traveling in a specific section.

[0034] 3 is a diagram for explaining fluctuations in the steering angle θ of a vehicle. When the vehicle is being driven stably, the steering is smooth and stable, resulting in small fluctuations in the steering angle θ. On the other hand, when the vehicle is being driven unstable, the steering becomes unstable and the fluctuations in the steering angle θ become large.

[0035] More specifically, as shown in FIG. 3, a predicted steering angle θp(n) at time point n is calculated by second-order Taylor expansion centered on time point (n-1) based on the actual steering angles θ(n-3), θ(n-2), and θ(n-1) at time points n-3, n-2, and n-1 immediately preceding the specific time point n. Since the predicted steering angle θp(n) is an estimated value assuming smooth steering, if the actual steering is smooth, it will match the actual steering angle θ(n), but if the actual steering is unstable, it will deviate from the actual steering angle θ(n) depending on the degree of the unstable steering. The degree of such unstable steering can be expressed as a prediction error e(n) calculated by the following equation (i): e(n)=θ(n)-θp(n) (i)

[0036] FIG. 4 is a diagram illustrating an example of a frequency display of the degree of steering error, showing an example of the frequency display of the prediction error e(n). The evaluation value calculation unit 16 calculates the predicted steering angle θp(n) and prediction error e(n) at each time point n based on the steering angle data in the no-load and low-load sections, and calculates the 90th percentile value (α value) of the frequency distribution of the prediction error e(n) as shown by the solid line. The smoother the steering and the less the steering error, the sharper the frequency distribution of the prediction error e(n) will be centered around "0°," where there is no steering error, and the smaller the α value will be. On the other hand, the more the steering error, the broader the frequency distribution of the prediction error e(n) will be and the larger the α value will be.

[0037] By using steering angle data from no-load and low-load sections, excluding high-load sections where there is a lot of steering and driving skill has a large effect on steering error, it is possible to properly calculate the α value, which represents the driver's average steering error.

[0038] Furthermore, the evaluation value calculation unit 16 calculates the Hp value based on the calculated α value and the steering angle data for the specific section. More specifically, the evaluation value calculation unit 16 calculates the predicted steering angle θp(n) and prediction error e(n) for each time point n based on the steering angle data for the specific section, and divides the frequency distribution of the prediction error e(n) as indicated by the dashed line into nine ranges P1 to P9 based on the α value. That is, based on eight reference values ​​-5α, -2.5α, -α, -0.5α, 0.5α, α, 2.5α, and 5α, the nine ranges are divided into P1 (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 higher). Then, based on the proportions p1 to p9 of the ranges P1 to P9, the steering entropy value (Hp value) is calculated by the following formula (ii). Hp=-Σpi·log9pi ···(ii)

[0039] The Hp value represents the smoothness of steering, and the smaller the steering error and the sharper the frequency distribution of the prediction error e(n), the smaller the value, and the larger the steering error and the broader the frequency distribution of the prediction error e(n).By using steering angle data from specific sections where there is a lot of eye movement and the cognitive function is greatly affected by steering error, it is possible to appropriately calculate the Hp value, which represents the driver's steering error when the cognitive load is higher than usual.

[0040] FIG. 5 is a time chart for explaining the road surface conditions considered by evaluation value calculation unit 16, and shows the determination results of road surface conditions by unevenness determination unit 14. As shown in FIG. 5, among the steering angle data acquired by information acquisition unit 13 and stored in storage unit 12, steering angle data for a period (~t1, t2~) during which unevenness determination unit 14 has determined that the degree of road surface unevenness is equal to or less than a predetermined level will be referred to as "first steering angle data." Furthermore, steering angle data for a period (t1 to t2) during which unevenness determination unit 14 has determined that the degree of road surface unevenness exceeds the predetermined level will be referred to as "second steering angle data." Note that in FIG. 5, a road surface condition in which the degree of unevenness is equal to or less than the predetermined level is shown as "good," and a road surface condition in which the degree of unevenness exceeds the predetermined level is shown as "poor."

[0041] (Evaluation value weighting) The evaluation value calculation unit 16 performs weighting so that the weight of the first steering angle data is greater than the weight of the second steering angle data, and then calculates the Hp value, or the α value and the Hp value. More specifically, the evaluation value calculation unit 16 calculates the α value without weighting, and calculates the Hp value after weighting. Alternatively, the evaluation value calculation unit 16 performs weighting and then calculates the α value, and then calculates the Hp value after weighting.

[0042] When the α value is calculated without weighting and only the Hp value is calculated after weighting, the determination of the road surface condition by the unevenness determination unit 14 may be performed only on the driving data for the period determined by the load determination unit 15 as being during driving on a specific section. In this case, the calculation load on the unevenness determination unit 14 can be reduced as necessary.

[0043] (Weighting of alpha value - weighting of frequency) When the evaluation value calculation unit 16 calculates the α value after weighting, first, based on the first steering angle data for the period determined by the load determination unit 15 to be in the no-load / low-load section, the predicted steering angle θp1(n) and the prediction error e1(n) are calculated. Also, based on the second steering angle data for the same period, the predicted steering angle θp2(n) and the prediction error e2(n) are calculated. Next, the frequency of the prediction error e1(n) (the frequency distribution shown by the solid line in FIG. 4) is multiplied by the weighting coefficient W1 (0 < W1, for example, W1 = 1), and the frequency of the prediction error e2(n) is multiplied by the weighting coefficient W2 (0 ≤ W2 < W1, for example, W2 = 0), and these are added together. The evaluation value calculation unit 16 calculates the 90th percentile value in the frequency distribution of the weighted and added prediction error (W1e1(n) + W2e2(n)) as the α value.

[0044] (Weighting of Hp value - Weighting to frequency -) When the evaluation value calculation unit 16 calculates the Hp value after weighting, first, based on the first steering angle data for the period determined by the load determination unit 15 to be in the specific section, the predicted steering angle θp1(n) and the prediction error e1(n) are calculated. Also, based on the second steering angle data for the same period, the predicted steering angle θp2(n) and the prediction error e2(n) are calculated. Next, the frequency of the prediction error e1(n) (the frequency distribution shown by the dashed line in FIG. 4) is multiplied by the weighting coefficient W1 (0 < W1, for example, W1 = 1), and the frequency of the prediction error e2(n) is multiplied by the weighting coefficient W2 (0 ≤ W2 < W1, for example, W2 = 0), and these are added together. The evaluation value calculation unit 16 divides the frequency distribution of the weighted and added prediction error (W1e1(n) + W2e2(n)) into ranges P1 to P9 based on the α value, and calculates the Hp value according to formula (ii) based on the ratios p1 to p9 of each range P1 to P9.

[0045] (Weighting of Hp value - Direct weighting -) When calculating the Hp value after weighting, the evaluation value calculation unit 16 may calculate the Hp1 value based on the first steering angle data and the Hp2 value based on the second steering angle data, and multiply the calculated Hp1 value and Hp2 value by the weight coefficients W1 and W2, respectively. More specifically, the evaluation value calculation unit 16 calculates the predicted steering angle θp1(n), the prediction error e1(n), and the Hp1 value based on the first steering angle data during the period determined by the load determination unit 15 to be traveling in the specific section. Also, based on the second steering angle data for the same period, the predicted steering angle θp2(n), the prediction error e2(n), and the Hp2 value are calculated. The evaluation value calculation unit 16 multiplies the Hp1 value by the weight coefficient W1 (0 < W1, for example, W1 = 1), multiplies the Hp2 value by the weight coefficient W2 (0 ≤ W2 < W1, for example, W2 = 0), and calculates the sum of these values (W1Hp1 + W2Hp2) as the Hp value.

[0046] The cognitive function evaluation unit 17 evaluates the driver's cognitive function based on the Hp value calculated by the evaluation value calculation unit 16. That is, by continuously monitoring the Hp value representing the steering deviation when the cognitive load increases, the decreasing trend of the driver's cognitive function can be evaluated. For example, if the Hp value calculated regularly (e.g., monthly) based on the driving data of daily driving shows an increasing trend, it is evaluated that the cognitive function has a decreasing trend.

[0047] The information output unit 18 transmits the evaluation result by the cognitive function evaluation unit 17 to a user terminal such as the driver himself or his family. For example, a notification can be sent to a pre-registered email address. In this case, based on the notification, the driver himself or his family can consider returning the driver's license or replacing the vehicle with a vehicle equipped with a more advanced driving support function. Since objective information based on driving data is provided, it is easier for the driver himself to accept the current situation of his cognitive function and can consider appropriate countermeasures at an early stage.

[0048] FIG. 6 is a flowchart showing an example of an evaluation process executed by the calculation unit 11 of the system 10. The process shown in this flowchart is executed, for example, periodically. First, in step S1, the driving data stored in the memory unit 12 is read. Next, in step S2, based on the driving data read in step S1, it is determined whether the road surface condition of the road during driving per unit time is good or poor. Next, in step S3, based on the driving data read in step S1, it is determined whether the driving section per unit time is a no-load / low-load section or a high-load section. Furthermore, based on the driving data of the no-load / low-load section, it is determined whether the driving section per unit time is a specific section.

[0049] Next, in step S4, an α value is calculated based on steering angle data during the period determined in step S3 to be traveling in a no-load / low-load section. Next, in step S5, an Hp value is calculated based on the α value calculated in step S4 and steering angle data during the period determined in step S3 to be traveling in a specific section. The latest Hp value calculated in step S5 is stored and accumulated in memory unit 12. Next, in step S6, the latest Hp value stored in memory unit 12 is compared with past Hp values ​​to determine the driver's driving ability related to cognitive function. Next, in step S7, the evaluation result of step S6 is sent to a pre-registered email address, and the process ends.

[0050] In this way, the α value and Hp value, which are indices for determining a driver's driving ability, can be calculated based only on daily driving data, so that driving ability can be determined without interfering with driving (steps S1 to S5). In addition, the cognitive function of the driver is automatically evaluated based only on daily driving data, and the evaluation results are notified to the driver and his / her family, so the burden on family members living far away from the elderly driver can be reduced (steps S1 to S7).

[0051] 7 is a flowchart showing an example of weighting processing executed by the calculation unit 11 of the system 10, in which the frequency of prediction error is multiplied by a weighting coefficient in the process of calculating the evaluation values ​​(α value, Hp value). The processing shown in this flowchart is executed in steps S4 and / or S5 of FIG.

[0052] (Weighting of alpha value - weighting of frequency) When the frequency of the prediction error is multiplied by a weighting factor in the process of calculating the α value, the process shown in this flowchart is executed in step S4 of FIG. 6. As shown in FIG. 7, first, in step S10, a predicted steering angle θp1(n) is calculated based on the first steering angle data for the period determined in step S3 to be traveling in the no-load / low-load section, and a prediction error e1(n) is calculated. Also, a predicted steering angle θp2(n) is calculated based on the second steering angle data for the same period, and a prediction error e2(n) is calculated. Next, in step S11, the frequency of the prediction error e1(n) calculated in step S10 is multiplied by a weighting factor W1, and the frequency of the prediction error e2(n) calculated in step S10 is multiplied by a weighting factor W2. Next, in step S12, the weighted frequencies W1e1(n) and W2e2(n) calculated in step S11 are added together. In this case, in step S4 of FIG. 6, the 90th percentile value in the frequency distribution of the weighted and summed prediction errors (W1e1(n)+W2e2(n)) calculated in step S12 is calculated as the α value.

[0053] (Weighting of Hp values ​​- Weighting of frequency -) When the frequency of the prediction error is multiplied by a weighting factor in the process of calculating the Hp value, the process shown in this flowchart is executed in step S5 of FIG. 6. As shown in FIG. 7, first, in step S10, a predicted steering angle θp1(n) is calculated based on first steering angle data for the period determined in step S3 to be traveling through a specific section, and a prediction error e1(n) is calculated. Also, a predicted steering angle θp2(n) is calculated based on second steering angle data for the same period, and a prediction error e2(n) is calculated. Next, in step S11, the frequency of the prediction error e1(n) calculated in step S10 is multiplied by a weighting factor W1, and the frequency of the prediction error e2(n) calculated in step S10 is multiplied by a weighting factor W2. Next, in step S12, the weighted frequencies W1e1(n) and W2e2(n) calculated in step S11 are added together. In this case, in step S5 of FIG. 6, the Hp value is calculated based on the frequency distribution of the weighted and summed prediction errors (W1e1(n)+W2e2(n)) summed in step S12 and the α value calculated in step S4 of FIG. 6.

[0054] (Hp value weighting - direct weighting) FIG. 8 is a flowchart showing another example of the weighting process executed by the calculation unit 11 of the system 10. This is a variation of the flowchart of FIG. 6 in which the evaluation value (Hp value) is directly multiplied by a weighting coefficient. Steps S1 to S4, S6, and S7 in FIG. 8 are similar to steps S1 to S4, S6, and S7 in FIG. 6, and therefore will not be described here. As shown in FIG. 8, in step S5A, a predicted steering angle θp1(n), a prediction error e1(n), and an Hp1 value are calculated based on the α value calculated in step S4 and the first steering angle data for the period determined in step S3 to be traveling through the specific section. Furthermore, a predicted steering angle θp2(n), a prediction error e2(n), and an Hp2 value are calculated based on the second steering angle data for the same period. Next, in step S5B, the Hp1 value calculated in step S5A is multiplied by a weighting coefficient W1, and the Hp2 value calculated in step S5A is multiplied by a weighting coefficient W2. Next, in step S5C, the weighted Hp1 and Hp2 values ​​calculated in step S5B are summed to calculate the Hp value (W1Hp1+W2Hp2).

[0055] When the road surface on which the vehicle is traveling is highly uneven and in poor condition, the lateral acceleration acting on the vehicle increases, disrupting the driver's steering, making it difficult to evaluate the driver's driving stability based on the steering angle data. On the other hand, when the vehicle is traveling on a road with a low level of road surface unevenness and in good condition, the lateral acceleration acting on the vehicle is small and has little effect on the driver's steering, making it possible to appropriately evaluate the driver's driving stability based on the steering angle data. By actively using the first steering angle data obtained when traveling on a road with a good road surface, i.e., by assigning a weight to the first steering angle data greater than that to the second steering angle data, the evaluation value can be calculated, thereby enabling an accurate determination of driving ability (steps S11 and S5B).

[0056] For example, when the first steering angle data is actively used to calculate the Hp value, it is possible to evaluate the steering characteristics of the driver when the cognitive load increases while driving on a road with good road surface conditions. In this case, the accuracy of the Hp value, which is periodically calculated and accumulated, is improved, so the cognitive function of the driver can be evaluated with high accuracy. Furthermore, when the first steering angle data is also actively used to calculate the α value, it is possible to evaluate the steering characteristics of the driver while driving on a road with good road surface conditions, and the accuracy of the α value is improved, so the cognitive function of the driver can be evaluated with even higher accuracy.

[0057] According to this embodiment, the following effects can be achieved. (1) The system 10 includes an information acquisition unit 13 that acquires steering angle data indicating changes in the steering angle of the vehicle over time along with information on the road surface of the road on which the vehicle is traveling, an unevenness determination unit 14 that determines whether the degree of unevenness of the road surface is equal to or less than a predetermined level based on the road surface information acquired by the information acquisition unit 13, and an evaluation value calculation unit 16 that calculates an evaluation value representing the steering characteristics of the driver based on the steering angle data acquired by the information acquisition unit 13 (Figure 2).

[0058] The evaluation value calculation unit 16 calculates the evaluation value by increasing the weight of the first steering angle data during a period in which the unevenness determination unit 14 determines that the degree of unevenness of the road surface is below a predetermined level, among the steering angle data acquired by the information acquisition unit 13, compared to the weight of the second steering angle data during a period in which the unevenness determination unit 14 determines that the degree of unevenness of the road surface exceeds the predetermined level.

[0059] In this way, by calculating an evaluation value that serves as an index for determining the driving ability of a driver based on daily driving data, the driving ability of the driver can be determined without interfering with driving. In addition, by actively using the first steering angle data obtained while the vehicle is traveling on a road with a good road surface condition, where the road surface is small in unevenness and the lateral acceleration acting on the vehicle has little effect on the steering of the driver, the driving ability can be determined with high accuracy.

[0060] (2) The road surface information is information on the depth or height of road surface irregularities detected by a sensor mounted on the vehicle. When the depth or height of the irregularities is equal to or less than a threshold, the irregularity determination unit 14 determines that the degree of road surface irregularity is equal to or less than a predetermined level. This makes it possible to accurately determine whether the road surface condition is good or bad.

[0061] (3) The road surface information is information on the lateral acceleration acting on the vehicle detected by a sensor mounted on the vehicle. When the magnitude of the lateral acceleration is equal to or less than a threshold, the unevenness determination unit 14 determines that the degree of road surface unevenness is equal to or less than a predetermined level. This makes it possible to easily and accurately determine whether the road surface condition is good or bad.

[0062] (4) The road surface information is information about the road surface corresponding to the vehicle's position information, which is included in pre-stored road map information. When the road on which the vehicle is traveling is unpaved, the unevenness determination unit 14 determines that the degree of unevenness of the road surface exceeds a predetermined level. This makes it possible to easily determine whether the road surface condition is good or bad.

[0063] (5) The system 10 further includes a load determination unit 15 that determines whether or not a predetermined cognitive load is acting on the driver based on the steering angle data acquired by the information acquisition unit 13 (FIG. 2). The evaluation value calculation unit 16 calculates an α value that represents the average steering characteristics of the driver based on the steering angle data acquired by the information acquisition unit 13, and calculates an Hp value that represents the steering characteristics of the driver when the predetermined cognitive load is acting based on the calculated α value and the steering angle data acquired by the information acquisition unit 13, the steering angle data for a period during which the load determination unit 15 determines that the predetermined cognitive load is acting.

[0064] The evaluation value calculation unit 16 calculates the α value without weighting either the first steering angle data or the second steering angle data, while calculating the Hp value by weighting the first steering angle data more heavily than the second steering angle data. In this way, by actively using the first steering angle data obtained when the cognitive load increases while driving on a road with good road surface conditions, the Hp value can be accurately calculated, and the driver's cognitive function can be accurately evaluated. Furthermore, because the steering angle data used to calculate the α value is used regardless of the road surface conditions, ensuring a sufficient amount of data allows the α value, which represents the driver's average steering characteristics, to be appropriately calculated.

[0065] (6) The evaluation value calculation unit 16 calculates the α value by weighting the first steering angle data more heavily than the second steering angle data, and calculates the Hp value by weighting the first steering angle data more heavily than the second steering angle data. For example, when a sufficient amount of data is available, the α value can be accurately calculated and the driver's cognitive function can be accurately evaluated by actively using the first steering angle data obtained when the cognitive load increases while driving on a road with a good road surface.

[0066] In the above embodiment, an example has been described in which the α value is calculated based on the steering angle data when the vehicle is traveling in a no-load / low-load section, and the Hp value is calculated based on the steering angle data when the vehicle is traveling in a specific section, but the evaluation value calculation unit is not limited to this.The evaluation value calculation unit may be any unit that calculates an evaluation value that represents the steering characteristics of each driver based on the steering angle data for each driver.

[0067] Although the present invention has been described above as a driving ability determination system, it can also be used as a driving ability determination method. That is, the driving ability determination method includes an information acquisition step S1 for acquiring information on the road surface on which the vehicle is traveling as well as steering angle data showing changes in the steering angle of the vehicle over time, an unevenness determination step S2 for determining whether the degree of unevenness of the road surface is equal to or less than a predetermined level based on the road surface information acquired in the information acquisition step S1, and evaluation value calculation steps S4, S5, S10 to S12, and S5A to A5C for calculating an evaluation value representing the steering characteristics of the driver based on the steering angle data acquired in the information acquisition step S1 (FIGS. 6 to 8). In the evaluation value calculation steps S4, S5, S10 to S12, and S5A to A5C, the evaluation value is calculated by increasing the weight of the first steering angle data during the period in which the degree of road surface unevenness is determined to be below a predetermined level in the unevenness determination step S2, among the steering angle data acquired in the information acquisition step S1, compared to the weight of the second steering angle data during the period in which the degree of road surface unevenness is determined to exceed the predetermined level in the unevenness determination step S2.

[0068] The above description is merely an example, and the present invention is not limited to the above-described embodiment and modifications as long as the features of the present invention are not impaired. One or more of the above-described embodiment and modifications can be arbitrarily combined, and modifications can also be combined with each other. [Explanation of symbols]

[0069] 10 driving ability determination system (system), 11 calculation unit, 12 memory unit, 13 information acquisition unit, 14 unevenness determination unit, 15 load determination unit, 16 evaluation value calculation unit, 17 cognitive function evaluation unit, 18 information output unit

Claims

1. an information acquisition unit that acquires steering angle data indicating a change in the steering angle of the vehicle over time, together with information about the road surface on which the vehicle is traveling; an unevenness determination unit that determines whether the degree of unevenness of the road surface is equal to or less than a predetermined level based on the road surface information acquired by the information acquisition unit; an evaluation value calculation unit that calculates an evaluation value representing a steering characteristic of a driver based on the steering angle data acquired by the information acquisition unit, A driving ability determination system characterized in that the evaluation value calculation unit calculates the evaluation value by increasing the weight of first steering angle data during a period in which the unevenness determination unit determines that the degree of unevenness of the road surface is below the predetermined level, among the steering angle data acquired by the information acquisition unit, compared to the weight of second steering angle data during a period in which the unevenness determination unit determines that the degree of unevenness of the road surface exceeds the predetermined level.

2. 2. The driving ability determination system according to claim 1, the road surface information is information on the depth or height of unevenness of the road surface detected by a sensor mounted on the vehicle; The driving ability determination system is characterized in that the unevenness determination unit determines that the degree of unevenness of the road surface is equal to or less than the predetermined degree when the depth or height of the unevenness is equal to or less than a threshold value.

3. 2. The driving ability determination system according to claim 1, the road surface information is information on lateral acceleration acting on the vehicle detected by a sensor mounted on the vehicle; The driving ability determination system is characterized in that the roughness determination unit determines that the degree of roughness of the road surface is equal to or less than the predetermined degree when the magnitude of the lateral acceleration is equal to or less than a threshold value.

4. In the driving ability determination system according to any one of claims 1 to 3, the road surface information is information about the road surface of a road that corresponds to the vehicle position information and is included in pre-stored road map information; The driving ability determination system is characterized in that the unevenness determination unit determines that the degree of unevenness of the road surface exceeds the predetermined degree when the road on which the vehicle is traveling is an unpaved road.

5. 2. The driving ability determination system according to claim 1, a load determination unit that determines whether a predetermined load is acting on the driver based on the steering angle data acquired by the information acquisition unit, the evaluation value calculation unit calculates a first evaluation value representing an average steering characteristic of the driver based on the steering angle data acquired by the information acquisition unit, and calculates a second evaluation value representing the steering characteristic of the driver when the predetermined load is applied based on the calculated first evaluation value and steering angle data acquired by the information acquisition unit for a period during which the load determination unit determines that the predetermined load is applied; A driving ability assessment system characterized in that the evaluation value calculation unit calculates the first evaluation value without weighting either the first steering angle data or the second steering angle data, while calculating the second evaluation value by weighting the first steering angle data more than the weighting of the second steering angle data.

6. 2. The driving ability determination system according to claim 1, a load determination unit that determines whether a predetermined load is acting on the driver based on the steering angle data acquired by the information acquisition unit, the evaluation value calculation unit calculates a first evaluation value representing an average steering characteristic of the driver based on the steering angle data acquired by the information acquisition unit, and calculates a second evaluation value representing the steering characteristic of the driver when the predetermined load is applied based on the calculated first evaluation value and steering angle data acquired by the information acquisition unit for a period during which the load determination unit determines that the predetermined load is applied; The driving ability assessment system is characterized in that the evaluation value calculation unit calculates the first evaluation value by making the weight of the first steering angle data greater than the weight of the second steering angle data, and calculates the second evaluation value by making the weight of the first steering angle data greater than the weight of the second steering angle data.

7. Each of the methods is executed by a computer. an information acquisition step of acquiring steering angle data indicating a change in the steering angle of the vehicle over time together with information about the road surface on which the vehicle is traveling; an unevenness determination step of determining whether or not the degree of unevenness of the road surface is equal to or less than a predetermined level based on the information about the road surface acquired in the information acquisition step; an evaluation value calculation step of calculating an evaluation value representing a steering characteristic of a driver based on the steering angle data acquired in the information acquisition step, A driving ability assessment method characterized in that in the evaluation value calculation step, the evaluation value is calculated by increasing the weight of first steering angle data during a period in which the degree of road surface unevenness is determined to be below the predetermined level in the unevenness determination step, among the steering angle data acquired in the information acquisition step, compared to the weight of second steering angle data during a period in which the degree of road surface unevenness is determined to exceed the predetermined level in the unevenness determination step.

Images