Driving evaluation system, driving evaluation method, and computer program
The driving evaluation system addresses low driver acceptance by calculating deviations in individual driving behavior over time, providing personalized and effective unsafe driving alerts.
Patent Information
- Application Number
- JP2022036018
- Authority / Receiving Office
- JP · JP
- Patent Type
- Patents
- Current Assignee / Owner
- Filing Date
- 2022-03-09
- Publication Date
- 2025-10-02
- Estimated Expiration
- 2042-03-09
AI Technical Summary
Existing driving evaluation systems fail to account for individual driving behavior variations over time, leading to low driver acceptance and rejection of guidance and assistance control due to poorly evaluated unusual driving behaviors.
A driving evaluation system that calculates deviations in driving behavior characteristics over time using moving averages, comparing current driving to historical norms to identify unsafe driving, and provides personalized evaluation results.
Enhances driver acceptance of evaluation results by using individual driving data, reducing annoyance from guidance and assistance control, and effectively identifying unsafe driving patterns.
Smart Images

Figure 0007748310000009 
Figure 0007748310000010 
Figure 0007748310000011
Abstract
Description
[Technical Field]
[0001] The present invention relates to a technique for evaluating driving. [Background technology]
[0002] There are known technologies that collect data such as vehicle speed and acceleration, and use the data to evaluate individual driving and perform driving assistance control. For example, Patent Document 1 describes a technology in which an on-board device generates characteristic information based on driving behavior data and transmits it to a center, and the center obtains an evaluation value by comparing the accumulated characteristic information with the received characteristic information, and determines that the driving of the vehicle is anomalous if the cumulative value of the obtained evaluation value is large.
[0003] For example, Patent Document 2 describes a method of accumulating vehicle state quantities of multiple vehicles in a management center server, calculating a target vehicle state quantity for the host vehicle based on the degree of deviation of the host vehicle's vehicle state quantity from the average value, and executing driving assistance control for the host vehicle with respect to the target vehicle state quantity as well. For example, Patent Document 3 describes a method of estimating the vehicle's next traffic situation from current position information and map information, and presenting advice information if the driver's driving skill level evaluated in a similar traffic situation is low. For example, Patent Document 4 describes a method of estimating the driver's state from the driver's past driving history, and controlling the content of a notification to the driver based on the estimated driver's state. [Prior art documents] [Patent documents]
[0004] [Patent Document 1] Japanese Patent Application Publication No. 2018-10407 [Patent Document 2] Japanese Patent Application Laid-Open No. 2017-191502 [Patent Document 3] Japanese Patent Application Laid-Open No. 2009-222746 [Patent Document 4] Japanese Patent Application Laid-Open No. 2012-118951 Summary of the Invention [Problem to be solved by the invention]
[0005] Here, driving behavior characteristics such as speed and acceleration vary from driver to driver. In the technologies described in Patent Documents 1 and 2, individual driving behavior is evaluated using data collected from the general public, resulting in low driver acceptance of the evaluation results. Drivers may find guidance and driving assistance control based on the evaluation results annoying and reject the system itself. Even when a driver is driving with utmost care, an operation error or a sudden increase in speed or acceleration, in other words, an unusual driving behavior characteristic, may occur. In this regard, the technologies described in Patent Documents 1, 3, and 4 do not take into consideration the evaluation of changes in driving behavior characteristics over time. As a result, unexpectedly occurring unusual driving behavior characteristics are evaluated poorly, resulting in drivers finding guidance and driving assistance control based on the evaluation results annoying and rejecting the system itself.
[0006] The present invention has been made to solve at least part of the above-mentioned problems, and aims to provide a driving evaluation system that can present evaluation results that are easily accepted by drivers. [Means for solving the problem]
[0007] The present invention has been made to solve at least part of the above-mentioned problems, and can be realized in the following form: A driving evaluation system, comprising: an acquisition unit that acquires host vehicle information including host vehicle position information indicating the position of the host vehicle and driving behavior characteristics of the host vehicle at the position; an accumulation unit that accumulates the acquired host vehicle information in a storage unit; an evaluation unit that calculates a deviation of the current driving from normal driving using a change over time in the driving behavior characteristics in the accumulated host vehicle information, thereby evaluating whether the current driving is transitioning to unsafe driving that is less safe than the normal driving; and an output control unit that outputs the evaluation result by the evaluation unit, ,beforeA deviation value of the current driving with respect to the normal driving is calculated as an index representing the deviation, thereby evaluating whether the current driving is transitioning to the unsafe driving. The deviation value Rt is calculated by the following formula (1): k Calculate TIFF0007748310000001.tif12170 In the formula (1), xm k is a value representing the current driving, calculated by a moving average of the driving behavior features included in the subject vehicle information for the past w1 (w1 is a natural number) times going back from the present, and μ k is a value representing the normal driving, calculated by a moving average of the driving behavior characteristics included in the subject vehicle information for the past w2 (w2 is a natural number) times, going back from the present, and σ k is the standard deviation of the kth accumulated value for the past specified number of times, and k is a variable (natural number) that represents the number of times processing is performed. ,Driving evaluation system. a storage unit that stores the acquired vehicle information in a memory unit; an evaluation unit that uses changes over time in the driving behavior characteristics included in the stored vehicle information to calculate a deviation of the current driving from normal driving, thereby evaluating whether the current driving is transitioning to unsafe driving that is less safe than the normal driving; and an output control unit that outputs the evaluation result by the evaluation unit, wherein the evaluation unit determines the current driving as a moving average of the driving behavior characteristics included in the vehicle information for the past w1 (w1 is a natural number) times acquired going back across days from the present, and determines the normal driving as a moving average of the driving behavior characteristics included in the vehicle information for the past w2 (w2 is a natural number) times acquired going back across days from the present.
[0008] (1) According to one aspect of the present invention, there is provided a driving evaluation system including: an acquisition unit that acquires host vehicle information including host vehicle position information indicating the position of the host vehicle and driving behavior characteristics of the host vehicle at the position; an accumulation unit that accumulates the acquired host vehicle information in a storage unit; an evaluation unit that uses a time-dependent change in the driving behavior characteristics in the accumulated host vehicle information to calculate a deviation of the current driving from normal driving, thereby evaluating whether the current driving is transitioning to unsafe driving that is less safe than the normal driving; and an output control unit that outputs the evaluation result by the evaluation unit.
[0009] According to this configuration, the evaluation unit evaluates the current driving of an individual driver using driving behavior features from the vehicle information stored in the storage unit. Here, the driving behavior features used for the evaluation are information about the vehicle (in other words, information about the individual driver). Therefore, compared to when driving is evaluated using data collected from the general public, the driver's acceptance of the evaluation results is higher, reducing the risk that the driver will find guidance and driving assistance control based on the evaluation results annoying. Furthermore, according to this configuration, the evaluation unit uses changes in the driving behavior features over time to calculate the deviation of the current driving from normal driving, thereby evaluating whether the current driving is shifting toward unsafe driving, which is less safe than normal driving. This reduces the risk of receiving a negative evaluation for unusual driving behavior features that occur unexpectedly due to operational errors or the situation at the time. As a result, this configuration provides a driving evaluation system that can present evaluation results that are easily accepted by the driver.
[0010] (2) In the driving evaluation system of the above type, the evaluation unit may use a moving average of the driving behavior characteristics to determine the current driving and the normal driving, and calculate a deviation value of the current driving relative to the normal driving, which is an index representing the deviation, to evaluate whether the current driving is transitioning to the unsafe driving. According to this configuration, the evaluation unit can easily evaluate the current driving using the change in driving behavior characteristics over time by obtaining the current driving and the normal driving using the moving average of the driving behavior characteristics. In addition, the evaluation unit can obtain a stable evaluation result that is standardized by the variability of the normal driving by using the deviation value of the current driving from the normal driving as an index representing the deviation.
[0011] (3) In the driving evaluation system of the above type, the evaluation unit may use a moving average of the driving behavior characteristics to determine the current driving and the normal driving, and calculate a deviation rate of the current driving from the normal driving, which is an index representing the deviation, to evaluate whether the current driving is transitioning to the unsafe driving. According to this configuration, the evaluation unit can easily evaluate the current driving using the change over time of the driving behavior characteristics by obtaining the current driving and the normal driving using the moving average of the driving behavior characteristics. Further, as an index representing the deviation, the evaluation unit can obtain a clear evaluation result based on the normal driving by using the deviation rate of the current driving from the normal driving.
[0012] (4) In the driving evaluation system of the above aspect, the evaluation unit may use, as the current driving, the moving average of the driving behavior characteristics included in the own vehicle information for the past w1 (w1 is a natural number) times retroactively from the present, and use, as the normal driving, the moving average of the driving behavior characteristics included in the own vehicle information for the past w2 (w2 is a natural number) times retroactively from the present. According to this configuration, since the evaluation unit uses, as the current driving, the moving average of the driving behavior characteristics for the past w1 times retroactively from the present and uses, as the normal driving, the moving average of the driving behavior characteristics for the past w2 times retroactively from the present, it is possible to obtain the smoothed current driving and normal driving.
[0013] (5) In the driving evaluation system of the above aspect, the evaluation unit may make at least one of the value of w1 and the value of w2 changeable within a range satisfying w1 < w2. According to this configuration, since the evaluation unit makes at least one of the value of w1 and the value of w2 changeable within a range satisfying w1 < w2 it is possible to change the degree of smoothing of the current driving and the normal driving. For example, by increasing the value of w1, it is possible to evaluate the current driving captured from a long-term perspective, while by decreasing the value of w1, it is possible to evaluate the current driving captured from a short-term perspective. Also, for example, by increasing the value of w2, it is possible to evaluate the current driving based on the normal driving captured from a long-term perspective, while by decreasing the value of w2, it is possible to evaluate the current driving based on the (recent) normal driving captured from a short-term perspective.
[0014] (6) In the driving evaluation system of the above form, the driving behavior characteristics may be at least one of the speed of the vehicle, the acceleration of the vehicle, the average speed of the vehicle in a specified section, the maximum deceleration of the vehicle in a specified section, and the minimum speed of the vehicle in a specified section. According to this configuration, evaluation can be performed using at least one of the following driving behavior characteristics: the speed of the vehicle, the acceleration of the vehicle, the average speed of the vehicle in a specified section, the maximum deceleration of the vehicle in a specified section, and the minimum speed of the vehicle in a specified section.
[0015] (7) In the driving evaluation system of the above form, the storage unit may store the vehicle information at a predetermined specific location in the memory unit, and may not store the vehicle information at a location other than the specific location in the memory unit. According to this configuration, the storage unit stores vehicle information at predetermined specific points in the storage unit, but does not store vehicle information at points other than the specific points. Therefore, by setting the specific points as points (e.g., the location of a stop line, the location of a railroad crossing, etc.) where significant changes in driving behavior characteristics (e.g., speed, acceleration, average section speed, maximum deceleration) are expected, or points where the vehicle passes relatively frequently (e.g., any point on the driver's commute route, etc.), the storage unit can efficiently collect and store vehicle information. Furthermore, compared to storing vehicle information without limiting it to specific points (e.g., periodically storing vehicle information), the amount of data stored in the storage unit can be reduced, and the processing load on the processing device can be reduced.
[0016] The present invention can be realized in various forms, for example, in the form of an information processing device, a traffic behavior evaluation device, a judgment device, an information provision device, a monitoring device, a recording device, a method executed in an information processing device to realize the functions of each of these devices, a system including each of these devices, a computer program to realize the functions of each of these devices and systems, a server device for distributing the computer program, a non-transitory storage medium on which the computer program is stored, etc. [Brief explanation of the drawings]
[0017] [Figure 1] 1 is a schematic diagram of a driving evaluation system according to an embodiment of the present invention; [Figure 2] 10 is a flowchart illustrating an example of a procedure for an evaluation process. [Figure 3] FIG. 2 is an explanatory diagram showing an example of host vehicle information; [Figure 4] FIG. 10 is a diagram illustrating a moving average. [Figure 5] FIG. 10 is a diagram illustrating output of an evaluation result. [Figure 6] FIG. 10 is a schematic diagram of a driving evaluation system according to a second embodiment. DETAILED DESCRIPTION OF THE INVENTION
[0018] First Embodiment Fig. 1 is a schematic diagram of a driving evaluation system 1 according to one embodiment of the present invention. The driving evaluation system 1 is a system that evaluates the current driving of a driver P of a vehicle 90 using changes over time in the driving behavior characteristics of the driver P himself / herself. Here, "driving behavior characteristics" refers to any index that represents the characteristics of driving behavior, and examples of driving behavior characteristics include speed, acceleration, and average speed for a section. At least one of the maximum deceleration, the maximum section speed, and the minimum section speed can be used. In the following example, a case where "speed" is used as the driving behavior feature will be illustrated. As described above, the driving evaluation system 1 of this embodiment performs evaluation using changes over time in the driving behavior features of the driver P of the vehicle 90 himself, and therefore can present evaluation results that are more likely to be accepted by the driver P.
[0019] In the example of FIG. 1, the driving evaluation system 1 is mounted on a vehicle 90, and includes an information processing device 10, a GPS receiver 30, and an information presentation device 40.
[0020] The information processing device 10 includes a CPU 11, a storage unit 12, and a ROM / RAM (not shown), and these units are interconnected via a bus. The information processing device 10 may be implemented as a personal computer or an electronic control unit (ECU). The CPU 11 controls the units of the information processing device 10 by loading a computer program stored in the ROM into the RAM and executing the program. The CPU 11 also functions as an acquisition unit 111, a storage unit 112, an evaluation unit 113, and an output control unit 114.
[0021] The acquisition unit 111 acquires the subject vehicle information in an evaluation process described later. Here, the "subject vehicle information" includes location information (e.g., latitude and longitude) indicating the location of the subject vehicle 90 and driving behavior characteristics of the subject vehicle 90 at the location (e.g., at least one of speed, acceleration, average section speed, and maximum deceleration; in this embodiment, acceleration). The subject vehicle information may also include accompanying information that accompanies the location information and driving behavior characteristics. The accompanying information may include, for example, the date and time when the location information and driving behavior characteristics were acquired, information for identifying the specific point where the location information and driving behavior characteristics were acquired, and the external environment (e.g., season, weather, temperature, etc.) when the location information and driving behavior characteristics were acquired.
[0022] The accumulation unit 112 accumulates the host vehicle information acquired by the acquisition unit 111 in the host vehicle information 121 of the storage unit 12 in the evaluation process described below.
[0023] In the evaluation process described below, the evaluation unit 113 uses the time-dependent changes in driving behavior characteristics in the vehicle information 121 stored in the memory unit 12 to calculate the deviation of the current driving from normal driving, thereby evaluating whether the current driving is transitioning to unsafe driving that is less safe than normal driving. Here, "current driving" does not mean the driver P's driving "at the moment," but rather means smoothed current driving. Therefore, the current driving can also be said to be the driver P's recent driving. Furthermore, "normal driving" means the driver P's smoothed normal driving.
[0024] In the evaluation process described below, the output control unit 114 causes the information presentation device 40 to output the evaluation result by the evaluation unit 113. In this way, the acquisition unit 111, the accumulation unit 112, the evaluation unit 113, and the output control unit 114 cooperate to execute the evaluation process described below. Details of the process will be described later.
[0025] The storage unit 12 is configured with a flash memory, a memory card, a hard disk, etc. The storage unit 12 stores vehicle information 121 and specific location information 122. The vehicle information 121 is vehicle information accumulated by the accumulation unit 112 through an evaluation process described later.
[0026] The specific point information 122 stores information (for example, latitude and longitude) for identifying specific points used in the evaluation process described later. Here, a "specific point" refers to a point where a large change in driving behavior characteristics is expected, or a point where the vehicle 90 passes through relatively frequently. Specifically, the specific point information 122 stores information (latitude and longitude) for identifying points corresponding to at least one of the following a1 to a3: (a1) Point where a large change in driving behavior characteristics is expected: A point where a stop line is set on a road. The point where it was hit. (a2) A point where a large change in driving behavior characteristics is expected: a temporary stop position at a railroad crossing. (a3) A point that is passed by the vehicle 90 relatively frequently: any point on a road that the driver P frequently travels (for example, a commute route connecting home and work, or a route calculated from the movement history of the vehicle 90).
[0027] The GPS receiver 30 is installed inside the vehicle interior 91 of the vehicle 90. The GPS receiver 30 receives radio waves transmitted from artificial satellites that make up the GPS (Global Positioning System), and acquires the latitude and longitude that represent the current position of the vehicle 90.
[0028] The information presentation device 40 is installed on a dashboard 93 provided below a windshield 92 of the vehicle 90. The information presentation device 40 is a display device (monitor) incorporating a display for outputting images and a speaker for outputting sounds. The information presentation device 40 may be configured with only a display or only a speaker. In addition, in the above-described configuration, instead of the information processing device 10, the GPS receiver 30, and the information presentation device 40, an in-vehicle device that includes all of these functions, a smartphone, a robot, or the like may be used.
[0029] 2 is a flowchart showing an example of the procedure of the evaluation process. The evaluation process is a process of accumulating vehicle information of the vehicle 90 and evaluating the current driving of the vehicle 90 by the driver P. The evaluation process is started at any trigger. For example, the evaluation process may be started when the engine of the vehicle 90 is started, when the information processing device 10 is powered on, when the driver P issues a start instruction, or the like.
[0030] In step S10, the acquisition unit 111 acquires current location information from the GPS receiver 30 and sets it as host vehicle location information. The acquisition unit 111 may correct the current location information acquired from the GPS receiver 30 using map information pre-stored in the storage unit 12. The execution order of step S10 and step S12 described next may be reversed, or they may be executed in parallel (simultaneously). Steps S10 and S12 correspond to the "step of acquiring host vehicle information."
[0031] In step S12, the acquisition unit 111 acquires driving behavior features. The driving behavior features can be acquired by various methods, such as the following methods b1 to b5. (b1) When speed is used as a driving behavior feature, the acquisition unit 111 may acquire the speed (vehicle speed) measured by a speedometer mounted on the vehicle 90, or may calculate the speed using the current position information, the position information acquired one time ago, and the elapsed time between them. (b2) When acceleration is used as a driving behavior feature, the acquisition unit 111 may acquire acceleration measured by an accelerometer mounted on the vehicle 90, or may calculate acceleration by calculation from the speed acquired by the above-mentioned means. (b3) When the section average speed is used as the driving behavior feature, the acquisition unit 111 can calculate the average speed from the speeds acquired in a specified section (specifically, for example, a range of a certain distance before and after an arbitrary point as the base point), and use the calculated average speed as the section average speed. (b4) When the maximum deceleration is used as the driving behavior feature, the acquisition unit 111 can select the maximum acceleration (deceleration) from the accelerations (decelerations) acquired in a predetermined section (specifically, for example, a range of a certain distance before and after an arbitrary point as the base point) and set the selected acceleration as the maximum deceleration. (b5) When the minimum section speed is used as the driving behavior feature, the acquisition unit 111 determines the minimum speed from the speeds acquired in a predetermined section (specifically, for example, a range of a certain distance before and after an arbitrary point as a reference point), and sets the determined minimum speed as the minimum section speed. do.
[0032] In step S14, the accumulation unit 112 accumulates the vehicle position information of the specific point and the driving behavior characteristics in the vehicle information 121 of the storage unit 12. Specifically, the accumulation unit 112 first compares the vehicle position information acquired in step S10 with the specific point information 122 in the storage unit 12 to determine whether the position indicated by the vehicle position information acquired in step S10 (i.e., the position of the vehicle 90) is within a predetermined error range from the specific point (a1 to a3). At this time, the accumulation unit 112 may use information indicating the traveling direction (e.g., a vector) to determine the traveling direction of the vehicle 90. If the position indicated by the vehicle position information is within the specific point (including within the error range), the accumulation unit 112 accumulates the date and time when step S10 was performed, the vehicle position information acquired in step S10, and the driving behavior characteristics acquired in step S12 in the vehicle information 121 in association with each other. If the position indicated by the vehicle position information is not at a specific location, the storage unit 112 moves the process to the next step without storing the vehicle information (vehicle position information and driving behavior characteristics). Note that step S14 corresponds to "the step of storing the vehicle information in the storage unit."
[0033] FIG. 3 is an explanatory diagram showing an example of the host vehicle information 121. As a result of repeating the processes of steps S10 to S14, data such as that shown in FIG. 3 is accumulated in the host vehicle information 121. In the illustrated example, the host vehicle information 121 accumulates an acquisition date and time, host vehicle position information, and driving behavior characteristics in association with each other. "X" in FIG. 3 is an arbitrary character string. Entry E1 of the host vehicle information 121 stores the acquisition date and time, host vehicle position information, and driving behavior characteristics of information acquired at a specific point A. Entry E2 of the host vehicle information 121 stores the acquisition date and time, host vehicle position information, and driving behavior characteristics of information acquired at another specific point B. Entry E6 stores the acquisition date and time, host vehicle position information, and driving behavior characteristics of information acquired at the same specific point A as entry E1 but at a different date and time from entry E1. In this way, the vehicle information 121 accumulates a history representing the driving behavior characteristics of the vehicle 90 (in other words, the driver P himself / herself) together with the vehicle position information and accompanying information (acquisition date and time in the illustrated example).
[0034] Note that step S14 in FIG. 2 (storing data in the vehicle information 121) may be executed sequentially together with steps S10 and S12 as the vehicle 90 moves, or may be executed at any timing on a data set that has been stored in RAM or the like as a result of repeated execution of steps S10 and S12 alone.
[0035] In step S16, the evaluation unit 113 determines whether a predetermined evaluation trigger has occurred. The evaluation trigger can be any of the following triggers c1 to c4, for example. If the evaluation trigger has occurred (step S16: YES), the evaluation unit 113 transitions the process to step S18. On the other hand, if the evaluation trigger has not occurred (step S16: NO), the evaluation unit 113 transitions the process to step S10 and continues accumulating the host vehicle information. (c1) When starting to drive the vehicle 90: for example, when starting the engine of the vehicle 90. (c2) When driving of the vehicle 90 is completed: for example, when the destination is reached, or when the speed of the vehicle 90 has been zero for a predetermined period of time. (c3) When the driver P has time to spare: For example, when the speed of the vehicle 90 remains constant for a predetermined period of time. (c4) When an evaluation instruction operation by the driver P is detected.
[0036] In step S18 of FIG. 2, the evaluation unit 113 evaluates the driving behavior of the vehicle 90 (i.e., the driver P) using the vehicle information 121. Specifically, the evaluation unit 113 calculates the deviation value Rt of the current driving with respect to normal driving using the following equation (1): k Here, "k" and "i" are variables (natural numbers) that represent the number of times of processing. k is a value that represents the current operation, and μ in Eq. (1) k is a value that represents normal operation. σ in Equation (1) k is the kth This is the standard deviation of the accumulated values over the past w2 times. Note that step S18 corresponds to the "evaluation step."
[0037] FIG. 4 is a diagram illustrating the moving average. As shown in equation (2), the current driving time xm k is calculated using the moving average of the driving behavior feature x. Specifically, the current driving behavior feature xm k is calculated by the moving average of the driving behavior feature x included in the vehicle information 121 for the past w1 (w1 is a natural number) times going back from the present. For example, when w1=3, the current driving xm k is calculated from the moving average of the driving behavior feature x included in the vehicle information 121 for the past three times going back from the present (Figure 4: values within the bold frame range).
[0038] As shown in equation (3), normal operation μ k is calculated using the moving average of the driving behavior feature x. Specifically, normal driving μ k is calculated by the moving average of the driving behavior feature x included in the vehicle information 121 for the past w2 (w2 is a natural number) times going back from the present. For example, when w2=10, the normal driving μ k is calculated from the moving average of the driving behavior feature x included in the vehicle information 121 for the past 10 times going back from the present (Figure 4: values within the dashed frame range).
[0039]
number
number
number
[0040] The evaluation unit 113 calculates the deviation value Rt k By comparing the value of Rt with a predetermined threshold (for example, a deviation value of 50), it is evaluated whether the current driving is transitioning to unsafe driving, which is less safe than normal driving. k can be said to be an index that shows the deviation of current operation from normal operation.
[0041] Note that the evaluation unit 113 may use the following formula (4) instead of formula (1) to obtain the deviation rate Rd of the current operation from the normal operation k to obtain. xm in formula (4) k , μ k are as described in formulas (2) and (3). The evaluation unit 113 compares the value of the deviation rate Rd k obtained by formula (4) with a predetermined threshold value (for example, the deviation rate "0") to evaluate whether the current operation is about to shift to an unsafe operation with lower safety compared to the normal operation. That is, the deviation rate Rd k can be said to be an index representing the deviation of the current operation from the normal operation, similar to the deviation value Rt k .
[0042]
Number
[0043] Note that the evaluation unit 113 may use both the deviation value Rt k [[ID=z6]]and the deviation rate Rd k to evaluate whether the current operation is about to shift to an unsafe operation with lower safety compared to the normal operation. Also, when the evaluation unit 113 adopts two or more pieces of information (for example, speed and acceleration) exemplified in b1 to b5 above as driving behavior characteristics, the deviation value Rt k and / or the deviation rate Rd k obtained using speed, and the deviation value Rt k and / or the deviation rate Rd k obtained using acceleration, can be used in combination to evaluate whether the current operation is about to shift to an unsafe operation with lower safety compared to the normal operation.
[0044] Note that the evaluation unit 113 may be able to change the value of w1 and the value of w2 used in formulas (2) and (3) within the range satisfying w1 < w2. This change may be executable by the administrator of the driving evaluation system 1 or may be executable by the driver P.
[0045] 2, the output control unit 114 refers to the evaluation result by the evaluation unit 113 and determines whether or not there are signs of unsafe driving (in other words, whether or not the current driving is transitioning to unsafe driving). If there are signs of unsafe driving (step S20: Yes), the output control unit 114 transitions the process to step S22. On the other hand, if there are no signs of unsafe driving (step S20: No), the output control unit 114 transitions the process to step S10 and continues to accumulate the host vehicle information.
[0046] FIG. 5 is a diagram illustrating the output of the evaluation result. In step S22 of FIG. 2, the output control unit 114 generates information (presentation information) for presenting the evaluation result to the driver P. In step S24, the output control unit 114 causes the information presentation device 40 to output the presentation information. As a result, as shown in FIG. 5, the presentation information indicating the evaluation result is presented to the driver P. For example, in Example 1 of FIG. 5, an image and / or audio output of a warning message stating, "You've been speeding a bit recently" is displayed. Example 1 is a warning message related to a recent trend, so it can be output regardless of the current position of the vehicle 90. For example, in Example 2 of FIG. 5, an image and / or audio output of a warning message stating, "There will be a lot of speeding up ahead." Example 2 is a warning message related to a specific location, so it is output when the vehicle approaches a predetermined distance before the location where speeding is determined to be frequent. The image display may include the display of text or an icon. Steps S22 and S24 correspond to a "process of outputting the evaluation result."
[0047] The output control unit 114 may cause the information presentation device 40 to output the evaluation result by the evaluation unit 113, regardless of whether or not there are signs of unsafe driving. In this case, step S20 in FIG. 2 is omitted. In this case, the output control unit 114 may adopt, as the presentation information, content such as "The deviation value (deviation rate) of your recent driving is XX" or content such as "Thank you for always driving safely." Furthermore, the output control unit 114 may cause the information presentation device 40 to output the transition of the evaluation result by the evaluation unit 113 (transition of the deviation value or deviation rate).
[0048] As explained above, according to the driving evaluation system 1 of the first embodiment, the evaluation unit 113 of the information processing device 10 evaluates the current driving of the individual driver P using the driving behavior features of the own vehicle information 121 stored in the storage unit 12. Here, the driving behavior features used for the evaluation are information on the own vehicle 90 (in other words, information on the individual driver P), so compared to when driving is evaluated using data widely collected from the general public, the driver P is more likely to accept the evaluation results, and it is possible to reduce the risk that the driver P will find guidance and driving assistance control based on the evaluation results annoying. Furthermore, according to the driving evaluation system 1 of the first embodiment, the evaluation unit 113 uses changes over time in the driving behavior features to evaluate the current driving xm k Normal operation μ k Deviation Rt k ,Rd k By calculating the , we evaluate whether the current driving is shifting to unsafe driving, which is less safe than normal driving. As a result, the driving evaluation system 1 of the first embodiment can provide a driving evaluation system that can present evaluation results that are likely to be accepted by the driver.
[0049] Furthermore, according to the driving evaluation system 1 of the first embodiment, the evaluation unit 113 of the information processing device 10 calculates the current driving speed xm using a moving average of the driving behavior features. k and normal operation μ k By calculating the above, it is possible to easily realize evaluation of the current driving using the change over time of the driving behavior characteristics. Furthermore, according to the formula (1), the evaluation unit 113 uses the current driving characteristic xm as an index representing the deviation. k Normal operation μ k Standard deviation Rt k By using the formula (4), it is possible to obtain an evaluation result with less fluctuation, which is standardized by the variation of normal driving. Also, according to the formula (4), the evaluation unit 113 uses the current driving xm as an index representing the deviation. k Normal operation μ k Deviation rate Rd kBy using this, a clear evaluation result based on normal driving can be obtained. Also, since both the deviation value and the divergence rate are standardized values, an evaluation result with less influence from differences in the absolute values of speed and acceleration due to the driver or location can be obtained.
[0050] Furthermore, according to the driving evaluation system 1 of the first embodiment, the evaluation unit 113 of the information processing device 10 sets the moving average of the driving behavior characteristics for the past w1 times retrospectively as the current driving xm k and sets the moving average of the driving behavior characteristics for the past w2 times retrospectively as the normal driving μ k Therefore, the smoothed current driving and normal driving can be obtained.
[0051] Furthermore, according to the driving evaluation system 1 of the first embodiment, the evaluation unit 113 of the information processing device 10 can change at least one of the value of w1 and the value of w2 within the range that satisfies w1 < w2, so that the current driving xm k and the normal driving μ k The degree of smoothing between can be changed. For example, by increasing the value of w1, the current driving captured from a long-term perspective can be evaluated, while by decreasing the value of w1, the current driving captured from a short-term perspective can be evaluated. Also, for example, by increasing the value of w2, the current driving can be evaluated based on the normal driving captured from a long-term perspective, while by decreasing the value of w2, the current driving can be evaluated based on the (recent) normal driving captured from a short-term perspective.
[0052] Furthermore, according to the driving evaluation system 1 of the first embodiment, as the driving behavior characteristics, an evaluation using at least one of the speed of the host vehicle 90, the acceleration of the host vehicle 90, the section average speed of the host vehicle 90 in a predetermined section, and the maximum deceleration of the host vehicle 90 in a predetermined section can be realized.
[0053] Furthermore, according to the driving evaluation system 1 of the first embodiment, the accumulation unit 112 of the information processing device 10 accumulates in the storage unit 12 the host vehicle information at specific points predetermined in the specific point information 122, but does not accumulate in the storage unit 12 the host vehicle information at points other than the specific points. Therefore, by setting the specific points to the points described in a1 to a3, specifically, points where large changes in driving behavior characteristics (e.g., speed, acceleration, average section speed, maximum deceleration) are expected (e.g., the position of a stop line, the position of a railroad crossing, etc.), or points where the host vehicle 90 passes relatively frequently (e.g., any point on the driver P's commute route, etc.), the accumulation unit 112 can efficiently collect and accumulate the host vehicle information. Furthermore, compared to accumulating host vehicle information without limiting it to specific points (e.g., accumulating host vehicle information periodically), the amount of data accumulated in the storage unit 12 (the amount of data of the host vehicle information 121) can be reduced, and the processing load on the information processing device 10 can be reduced.
[0054] Second Embodiment 6 is a schematic diagram of a driving evaluation system 1A of the second embodiment. The driving evaluation system 1A is configured with an information processing device 10A mounted on the vehicle 90 shown in FIG. 1 and a server 20 connected via a network. Note that in FIG. 6, the GPS receiver 10A shown in FIG. 1 is The machine 30, the information presentation device 40, the vehicle 90, and the driver P are not shown. In the driving evaluation system 1A of the second embodiment, the driving behavior evaluation (FIG. 2: step S18) and the process of generating and displaying presentation information (steps S20 to S24) are executed by the server 20.
[0055] The information processing device 10A has a CPU 11A instead of the CPU 11 in the configuration described in the first embodiment. The CPU 11A does not have the evaluation unit 113 and output control unit 114 described in the first embodiment, but has a communication unit 115. The communication unit 115 executes the evaluation process described in Fig. 2 by communicating with the server 20 connected via a network. Details will be described later.
[0056] The server 20A includes a CPU 21, a storage unit 22, and a ROM / RAM (not shown), and these units are interconnected via a bus. The CPU 21 controls the units of the server 20 by loading a computer program stored in the ROM into the RAM and executing it. The CPU 21 also functions as an evaluation unit 213, an output control unit 214, and a communication unit 215. The processing in the evaluation unit 213 is similar to that of the evaluation unit 113 of the information processing device 10 described in the first embodiment. The processing in the output control unit 214 is similar to that of the output control unit 114 of the information processing device 10 described in the first embodiment. The communication unit 215 executes the evaluation process described in FIG. 2 by communicating with the information processing device 10A connected via a network. Details will be described later.
[0057] 2, the communication unit 115 of the information processing device 10A determines whether or not a predetermined evaluation trigger (c1 to c4) has occurred. If an evaluation trigger has occurred (step S16: YES), the communication unit 115 transmits an evaluation request and the host vehicle information 121 stored in the storage unit 12 to the server 20. On the other hand, if an evaluation trigger has not occurred (step S16: NO), the communication unit 115 transitions the process to step S10 and continues storing the host vehicle information.
[0058] The evaluation unit 213 of the server 20 that has received the evaluation request executes step S18 of the evaluation process in FIG. 2. Thereafter, the output control unit 214 of the server 20 executes steps S20 to S24 of the evaluation process in FIG. 2. Specifically, in step S20, if there are signs of unsafe driving (step S20: Yes), the output control unit 214 transitions the process to step S22. On the other hand, if there are no signs of unsafe driving (step S20: No), the output control unit 214 responds to the information processing device 10A with only the evaluation result and ends the process. This evaluation result can be in any form, and for example, it may respond that there are no signs of unsafe driving, and the deviation value Rt calculated in step S18 k and deviation rate Rd kThe communication unit 115 that has received the response from the server 20 may or may not output the evaluation result included in the response to the information presentation device 40.
[0059] In step S22 of the evaluation process in FIG. 2, the output control unit 214 of the server 20 generates information (presentation information) for presenting the evaluation result to the driver P. Thereafter, the output control unit 214 of the server 20 responds to the information processing device 10A with the evaluation result and the generated presentation information, and ends the process. This evaluation result can be in any form, and may be a response that "there are signs of unsafe driving," and the deviation value Rt calculated in step S18 k and deviation rate Rd k The response may be the presentation information itself, or may be omitted (if omitted, the response from the server 20 will be only the presentation information). Upon receiving the response from the server 20, the communication unit 115 causes the information presentation device 40 to output the presentation information included in the response.
[0060] As described above, the configuration of the driving evaluation system 1A can be modified in various ways, and at least some of the functional units described in the first embodiment can be realized by an external server 20. 6 shows an example in which the functions of the evaluation unit 213 and the output control unit 214 are realized by the server 20. However, other functions may also be realized by the server 20. For example, the host vehicle information 121 and the specific location information 122 of the information processing device 10A may be stored in the storage unit 22 of the server 20. In this case, the host vehicle information 121 further stores information for identifying the host vehicle 90 (or information for identifying the driver P) in association with the information described in FIG.
[0061] In this way, the driving evaluation system 1A of the second embodiment can also achieve the same effects as those of the first embodiment. Furthermore, the driving evaluation system 1A of the second embodiment can reduce the processing load of the information processing device 10A.
[0062] <Modification of this embodiment> The present invention is not limited to the above-described embodiment, and can be embodied in various forms without departing from the spirit of the present invention. For example, a part of the configuration realized by hardware may be replaced by software, and conversely, a part of the configuration realized by software may be replaced by hardware. In addition, for example, the following modifications are also possible.
[0063] [Variation 1] In the above-described embodiments, the configurations of the driving evaluation systems 1 and 1A have been exemplified. However, as explained in the second embodiment, the configuration of the driving evaluation system 1 can be any configuration. For example, the driving evaluation system 1 may be configured by an in-vehicle device, smartphone, robot, or the like that has all of the functions of the information processing device 10, the GPS receiver 30, and the information presentation device 40. For example, the function of the storage unit 112 may be realized by the server 20.
[0064] [Variation 2] In the above embodiment, the evaluation process (FIG. 2) has been described using an example of a processing procedure. However, these processing procedures can be modified in various ways, and the processing content of each step may be added / omitted / modified, and the execution order of the steps (procedures) may be changed.
[0065] For example, in step S14, the storage unit 112 may store the vehicle information (vehicle position information, driving behavior characteristics, and accompanying information) in the vehicle information 121 in every processing cycle, regardless of whether the vehicle is a specific location or not. In this case, the specific location information 122 described in FIG. 1 can be omitted.
[0066] For example, in step S18, the evaluation unit 113 may use an index different from the above-described formulas (1) to (4) to calculate the deviation of the current driving from normal driving. For example, the deviation of the current driving from normal driving may be calculated using a neural network that receives as input a change over time in the driving behavior characteristics of the vehicle 90 (in other words, the history of the driving behavior characteristics of the vehicle 90) and outputs the deviation of the current driving from normal driving. Furthermore, the above-described formulas (1) to (4) or the neural network may output an evaluation result that further takes into account accompanying information (e.g., the date and time, location information, and the external environment when the driving behavior characteristics were acquired: season, weather, temperature, etc.). In this way, the deviation of the current driving from normal driving can be calculated taking into account conditions that are likely to cause differences in driving behavior characteristics (e.g., daytime or sunny days, versus nighttime or rainy days, etc.), thereby further improving the evaluation accuracy.
[0067] For example, indices other than the speed, acceleration, average section speed, maximum deceleration, and minimum section speed described in b1 to b5 above may be used as driving behavior features. In this case, for example, the speed exceeding the speed limit or the presence or absence of sudden deceleration may be used as driving behavior features. Sudden deceleration can be determined when G-forces exceeding a predetermined standard G (e.g., 0.25 G) are applied.
[0068] For example, in the above specific example, w1 = 3 and w2 = 10 were used as examples, but these can be changed as desired. For example, if w1 = 1, it is possible to evaluate the current driving. Also, the smoothing range can be expanded to w1 = 10. The same applies to w2. For example, in the above specific example, 50 was used as the threshold for detecting signs of a transition to unsafe driving for the deviation value and 0 as the deviation rate. However, the level of unsafety can be set by changing these thresholds. Furthermore, the thresholds may be dynamically changed when an unsafe state continues for a certain period of time or when the threshold is frequently crossed. This can reduce the detection of unnecessary unsafe states.
[0069] [Variation 3] The features of the first and second embodiments and the first and second modifications can be combined as appropriate. For example, the features described in the first and second modifications may be adopted in the configuration of the second embodiment (the configuration using the server 20).
[0070] This aspect has been described above based on embodiments and modifications. However, the above-described embodiments are intended to facilitate understanding of this aspect and are not intended to limit this aspect. This aspect may be modified or improved without departing from the spirit and scope of the claims, and equivalents thereof are included in this aspect. Furthermore, if a technical feature is not described as essential in this specification, it may be deleted as appropriate. [Explanation of symbols]
[0071] 1,1A... Driving evaluation system 10, 10A...Information processing equipment 11,11A...CPU 12...Storage section 20, 20A...Server 21...CPU 22...Storage section 30...GPS receiver 40...Information presentation device 90...Own vehicle 91...Inside the vehicle 92...Windshield 93…Dashboard 111…Acquisition Department 112...Storage section 113...Evaluation Department 114...Output control unit 115…Communications Department 121...Vehicle information 122...Specific location information 213...Evaluation Department 214...Output control unit 215…Communications Department
Claims
1. A driving evaluation system, an acquisition unit that acquires vehicle information including vehicle position information indicating the position of the vehicle and driving behavior characteristics of the vehicle at the position; a storage unit that stores the acquired vehicle information in a storage unit; an evaluation unit that calculates a deviation of a current driving behavior from a normal driving behavior using a time-dependent change in the driving behavior characteristics of the stored host vehicle information, and evaluates whether the current driving behavior is transitioning to an unsafe driving behavior that is less safe than the normal driving behavior; an output control unit that outputs an evaluation result by the evaluation unit; Equipped with The evaluation unit a deviation value of the current driving with respect to the normal driving, the deviation value being an index representing the deviation, to evaluate whether the current driving is transitioning to the unsafe driving; Rt k , which indicates the deviation value, is calculated using the following formula (1): In the formula (1), xm k is a value representing the current driving, and is calculated by taking a moving average of the driving behavior characteristics included in the subject vehicle information for the past w1 (w1 is a natural number) times going back from the present, μ k is a value representing the normal driving, and is calculated by taking a moving average of the driving behavior features included in the subject vehicle information for the past w2 (w2 is a natural number) times going back from the present, σ k is the standard deviation of the k-th accumulated value over a predetermined number of times in the past, k is a variable (natural number) representing the number of processing times in the driving evaluation system.
2. The driving evaluation system according to claim 1, The evaluation unit, in addition to the deviation value, further calculates a deviation rate of the current driving from the normal driving, which is an index representing the deviation, thereby evaluating whether the current driving is transitioning to unsafe driving.
3. A driving evaluation system, an acquisition unit that acquires vehicle information including vehicle position information indicating the position of the vehicle and driving behavior characteristics of the vehicle at the position; a storage unit that stores the acquired vehicle information in a storage unit; an evaluation unit that calculates a deviation of a current driving behavior from a normal driving behavior using a time-dependent change in the driving behavior characteristics of the stored host vehicle information, and evaluates whether the current driving behavior is transitioning to an unsafe driving behavior that is less safe than the normal driving behavior; an output control unit that outputs an evaluation result by the evaluation unit; Equipped with The evaluation unit The current driving is determined as a moving average of the driving behavior characteristics included in the vehicle information for the past w1 (w1 is a natural number) times acquired going back across days from the present, A driving evaluation system in which the normal driving is determined as a moving average of the driving behavior characteristics included in the vehicle information for the past w2 (w2 is a natural number) times obtained by going back across days from the present.
4. The driving evaluation system according to claim 3, The driving evaluation system, wherein the evaluation unit is capable of changing at least one of the value of w1 and the value of w2 within a range that satisfies w1<w2.
5. A driving evaluation system according to any one of claims 1 to 4, A driving evaluation system, wherein the driving behavior characteristics are at least one of the speed of the vehicle, the acceleration of the vehicle, the average section speed of the vehicle in a specified section, the maximum deceleration of the vehicle in a specified section, and the minimum section speed of the vehicle in a specified section.
6. A driving evaluation system according to any one of claims 1 to 5, A driving evaluation system in which the accumulation unit accumulates the vehicle information at a predetermined specific point in the storage unit, and does not accumulate the vehicle information at a point other than the specific point in the storage unit.
7. A method for evaluating driving, comprising: acquiring host vehicle information including host vehicle position information indicating the position of the host vehicle and driving behavior characteristics of the host vehicle at the position; storing the acquired vehicle information in a storage unit; a step of evaluating whether the current driving is transitioning to unsafe driving, which is less safe than the normal driving, by calculating a deviation of the current driving from normal driving using a change over time in the driving behavior characteristics of the accumulated vehicle information; outputting the results of the evaluation; Run In the evaluating step, a deviation value of the current driving with respect to the normal driving, the deviation value being an index representing the deviation, to evaluate whether the current driving is transitioning to the unsafe driving; Rt k , which indicates the deviation value, is calculated using the following formula (1): In the formula (1), xm k is a value representing the current driving, and is calculated by taking a moving average of the driving behavior characteristics included in the subject vehicle information for the past w1 (w1 is a natural number) times going back from the present, μ k is a value representing the normal driving, and is calculated by taking a moving average of the driving behavior features included in the subject vehicle information for the past w2 (w2 is a natural number) times going back from the present, σ k is the standard deviation of the k-th accumulated value over a predetermined number of times in the past, In this method, k is a variable (a natural number) representing the number of times processing is performed.
8. A computer program for executing the program on an information processing device, a function of acquiring vehicle information including vehicle position information indicating the position of the vehicle and driving behavior characteristics of the vehicle at the position; a function of storing the acquired vehicle information in a storage unit; a function of calculating a deviation of the current driving from normal driving using a time-dependent change in the driving behavior characteristics of the stored subject vehicle information, and thereby evaluating whether the current driving is transitioning to unsafe driving that is less safe than the normal driving; a function of outputting the results of the evaluation; Execute The function to be evaluated is a deviation value of the current driving with respect to the normal driving, the deviation value being an index representing the deviation, to evaluate whether the current driving is transitioning to the unsafe driving; Rt k , which indicates the deviation value, is calculated using the following formula (1): In the formula (1), xm k is a value representing the current driving, and is calculated by taking a moving average of the driving behavior characteristics included in the subject vehicle information for the past w1 (w1 is a natural number) times going back from the present, μ k is a value representing the normal driving, and is calculated by taking a moving average of the driving behavior features included in the subject vehicle information for the past w2 (w2 is a natural number) times going back from the present, σ k is the standard deviation of the k-th accumulated value over a predetermined number of times in the past, k is a variable (natural number) that represents the number of processing times in a computer program.
Citation Information
Patent Citations
Driving advice device
JP2009222746A
On-vehicle device and driving support system
JP2012118951A
Drive assistance apparatus for vehicle and drive assistance method for vehicle
JP2013030188A
Drive support system
JP2017191502A
Driving support system
JP2018010407A