Driving index output device

Abstract

To provide a driving index output device capable of outputting a driving index such as an accident risk.SOLUTION: In a driving index output device 1, a surrounding environment detection unit 5 acquires a driving environment of a vehicle; a speed sense detection unit 8 acquires a sense of speed when there is no other vehicle in front of the vehicle; and an inter-vehicle time detection unit 7 acquires an inter-vehicle time of a driver statistically obtained from an inter-vehicle distance when another vehicle is in front and a traveling speed of the driver's own vehicle. Then, a coping distance detection unit 9 calculates a coping distance by multiplying the statistical value of the traveling speed and the statistical value of the inter-vehicle time as driving indexes.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present invention relates to a driving index output device that outputs a driving index of a driver. [Background technology]

[0002] Conventionally, driving indicators such as a driver's accident risk, safe driving evaluation, and driving characteristic evaluation have been determined by detecting sudden braking while driving. However, this method does not detect accident risk in situations that do not involve sudden braking.

[0003] Patent Document 1 describes that a preceding vehicle speed fluctuation estimation unit 106b estimates the speed fluctuation of the preceding vehicle, and judges the psychological state of the driver only when it is estimated that the preceding vehicle is traveling stably. In judging the psychological state, a traveling scene determination unit c determines whether the traveling scene of the host vehicle is an "acceleration scene," a "steady traveling scene," or a "deceleration scene," and a psychological state determination unit 106a executes processing according to the determined traveling scene to judge the psychological state of the driver.

[0004] Patent document 2 describes that the driver psychology assessment means 31 assesses the driver's psychological state based on a comparison between the driving state of the vehicle when there is a preceding vehicle and the driving state of the vehicle when there is no preceding vehicle.

[0005] Patent document 3 describes that an input system 10 inputs the actual inter-vehicle distance maintained between the driver and other vehicles during actual driving into a judgment control system 30 in correspondence with the vehicle speed at that time, and that the judgment control system 30 reads out from a data management system 20 a basic inter-vehicle distance that serves as the basis for psychological judgment in correspondence with the vehicle speed obtained by the input system 10, compares the actual inter-vehicle distance input from the input system 10 with the basic inter-vehicle distance read out from the data management system 20, and judges the driver's psychological state based on the difference in the inter-vehicle distance. [Prior art documents] [Patent documents]

[0006] [Patent Document 1] Japanese Patent Application Laid-Open No. 2005-230381 [Patent Document 2] Japanese Patent Application Laid-Open No. 2007-133673 [Patent Document 3] Japanese Patent Application Laid-Open No. 2003-51097 Summary of the Invention [Problem to be solved by the invention]

[0007] Patent Documents 1 to 3 only go so far as to determine the psychological state of the driver, but do not go so far as to output a driving index that indicates the resulting accident risk.

[0008] One example of a problem to be solved by the present invention is to provide a driving index output device that can output a driving index such as an accident risk. [Means for solving the problem]

[0009] In order to solve the above problem, the invention described in claim 1 is characterized by comprising a driving environment acquisition unit that acquires the driving environment of the vehicle, a driving speed information acquisition unit that acquires statistical values of the driver's driving speed based on a statistically obtained relationship between the driving environment and speed when there are no other vehicles ahead, a vehicle-to-vehicle time information acquisition unit that acquires statistical values of the driver's vehicle-to-vehicle time obtained statistically from the vehicle-to-vehicle distance when there are other vehicles ahead and the vehicle's driving speed, and an output unit that outputs a manageable distance based on the vehicle-to-vehicle speed statistical value and the vehicle-to-vehicle time statistical value as a driving index for the driver.

[0010] The invention described in claim 7 is a driving index output method executed by a driving index output device that outputs a driver's driving index, characterized by comprising: a driving environment acquisition step of acquiring the driving environment of a vehicle; a driving speed information acquisition step of acquiring a statistical value of the driver's driving speed based on a statistically obtained relationship between the driving environment and speed when there is no other vehicle ahead; a vehicle-to-vehicle time information acquisition step of acquiring a statistical value of the driver's inter-vehicle time statistically obtained from the inter-vehicle distance when there is another vehicle ahead and the vehicle's traveling speed; and an output step of outputting an manageable distance based on the statistical value of the traveling speed and the statistical value of the inter-vehicle time as the driver's driving index.

[0011] The invention as set forth in claim 8 is characterized in that the driving index output method as set forth in claim 7 is executed by a computer.

[0012] The invention as set forth in claim 9 is characterized in that the driving index output program as set forth in claim 8 is stored. [Brief explanation of the drawings]

[0013] [Figure 1] 1 is a functional configuration diagram of a driving index output device according to a first embodiment of the present invention. [Figure 2] 2 is a flowchart of data collection and learning operations relating to statistical data and learning data of the driving indicator output device shown in FIG. 1. [Figure 3] 2 is a flowchart of a risk detection operation of the driving index output device shown in FIG. [Figure 4] 1 is a graph showing the results of a hypothetical running experiment conducted by the present inventors. [Figure 5] This is the result of further analysis of group (a) shown in FIG. [Figure 6] This is the result of further analysis of group (b) shown in Figure 4. [Figure 7] 10 is a flowchart of a risk detection operation of a driving index output device according to a second embodiment of the present invention. [Figure 8]FIG. 10 is a functional configuration diagram of a driving index output device according to a third embodiment of the present invention. [Figure 9] 9 is a graph illustrating a driver's psychology method in the driving index output device shown in FIG. 8. [Figure 10] 9 is a graph illustrating a driver's psychology method in the driving index output device shown in FIG. 8. DETAILED DESCRIPTION OF THE INVENTION

[0014] A driving index output device according to one embodiment of the present invention will be described below. In the driving index output device according to one embodiment of the present invention, a driving environment acquisition unit acquires the driving environment of the vehicle, a driving speed information acquisition unit acquires a statistical value of the driver's driving speed based on a statistically obtained relationship between the driving environment and the speed when there is no other vehicle ahead, and a time gap information acquisition unit acquires a statistical value of the driver's time gap calculated statistically from the inter-vehicle distance and the driving speed of the vehicle when there is another vehicle ahead. Then, an output unit outputs a driving index of the driver based on the statistical value of the driving speed and the statistical value of the time gap. In this way, it is possible to output a driving index based on the acquired statistical value. Furthermore, there is no need to determine the driver's psychological state when outputting a driving index.

[0015] The output unit may also output, as the driving index, an actionable distance calculated by multiplying the statistical value of the traveling speed and the statistical value of the time headway. In this way, a value calculated based on these statistical values can be output as the driving index.

[0016] The output unit may also determine and output the driver's accident risk as a driving index based on the manageable distance. In this way, specific information such as the accident risk can be output.

[0017] Furthermore, the output unit may determine that there is an accident risk when the manageable distance is equal to or less than the first reference value. In this way, it is possible to determine whether there is an accident risk according to the manageable distance.

[0018] The output unit may also output information related to the driver's psychological state as a driving index, thereby detecting changes in the driver's psychological state and issuing a warning to the driver.

[0019] The vehicle may further include a sudden braking detection unit that detects sudden braking of the vehicle, and the output unit may output a driving index of the driver based on the statistical value of the sense of speed and the statistical value of the inter-vehicle time when the number of sudden brakings detected by the sudden braking detection unit is equal to or less than a second reference value. In this way, a driving index can be output when sudden braking is not detected, and an accident risk can be reliably determined when sudden braking is not detected.

[0020] Furthermore, a driving index output method according to one embodiment of the present invention includes a driving environment acquisition step of acquiring the driving environment of the vehicle, a driving speed information acquisition step of acquiring a statistical value of the driver's driving speed based on a statistically obtained relationship between the driving environment and the speed when there is no other vehicle ahead, and a time gap information acquisition step of acquiring a statistical value of the driver's time gap calculated statistically from the inter-vehicle distance and the driving speed of the vehicle when there is another vehicle ahead.Then, an output step of the driving index of the driver is based on the statistical value of the driving speed and the statistical value of the time gap.In this way, the driving index can be output based on the acquired statistical values.In addition, there is no need to determine the driver's psychological state when outputting the driving index.

[0021] Furthermore, the above-described driving index output method is executed by a computer, whereby the driving index can be output based on the acquired statistical values using the computer.

[0022] The driving index output program may be stored in a computer-readable storage medium. In this way, the program can be distributed as a standalone program in addition to being incorporated into a device, and version upgrades can be easily performed. [Example]

[0023] A driving index output device according to a first embodiment of the present invention will be described with reference to FIGS. 1 to 6. As shown in FIG. 1, the driving index output device 1 according to this embodiment includes a sudden braking detection unit 2, an inter-vehicle distance detection unit 3, a traveling speed detection unit 4, a surrounding environment detection unit 5, an object approach detection unit 6, an inter-vehicle time detection unit 7, a sense of speed detection unit 8, an actionable distance detection unit 9, an accident risk detection unit 10, statistical data D1, statistical data D2, map data D3, learning data D4, and accident risk statistical data D5. The configuration shown in FIG. 1 may be configured as hardware or as a computer program (driving index output program). When configured as a computer program, the program may be stored in a storage medium such as a hard disk or a USB memory.

[0024] The sudden braking detection unit 2 detects sudden braking based on a signal indicating the acceleration of the vehicle being driven by the target driver, detected by the acceleration sensor 21. For example, sudden braking is detected when the detected acceleration is equal to or greater than a predetermined threshold. The detected sudden braking is output to be compiled into statistical data D1.

[0025] The inter-vehicle distance detection unit 3 acquires data indicating the distance to an object in front of the vehicle being driven by the target driver, for example, as measured by the object positioning sensor 22, and detects that distance as the inter-vehicle distance.

[0026] The traveling speed detection unit 4 acquires the traveling speed of the vehicle being driven by the target driver, which is detected by the speed sensor 23 .

[0027] The surrounding environment detection unit 5 detects the surrounding environment of the location where the vehicle being driven by the driver is located based on the image data of the surroundings of the vehicle being driven by the driver acquired by the image acquisition sensor 24 and the map data D3. Examples of the surrounding environment include the time of day, weather, the environment related to the road being driven (road type, number of lanes, road width, whether the road is curved, etc.), and the surrounding conditions of the road (urban or suburban, etc.). In other words, the surrounding environment detection unit 5 functions as a driving environment acquisition unit that acquires the driving environment of the vehicle.

[0028] The object approach detection unit 6 detects whether an object (vehicle ahead) is approaching or not based on the inter-vehicle distance detected by the inter-vehicle distance detection unit 3 and the traveling speed detected by the traveling speed detection unit 4. In this embodiment, for example, when the traveling speed is 10 km / h or more and an object is detected at a distance of less than 200 m ahead, it is detected that an object is approaching. In other words, it detects whether or not the vehicle is traveling with a vehicle ahead of the vehicle.

[0029] When the object approach detection unit 6 detects the approach of an object, the inter-vehicle time detection unit 7 calculates the inter-vehicle time from the inter-vehicle distance detected by the inter-vehicle distance detection unit 3 and the traveling speed detected by the traveling speed detection unit 4, and outputs the calculated time to be compiled into statistical data D2. When detecting an accident risk, the inter-vehicle time detection unit 7 obtains the inter-vehicle time from the statistical data D2 and outputs it to the manageable distance detection unit 9. In other words, the inter-vehicle time detection unit 7 functions as an inter-vehicle time information acquisition unit that obtains statistical values of the driver's inter-vehicle time, which are statistically calculated from the inter-vehicle distance when there is another vehicle ahead and the traveling speed of the vehicle itself.

[0030] When the object approach detection unit 6 does not detect the approach of an object, the sense of speed detection unit 8 outputs the traveling speed detected by the traveling speed detection unit 4 and the surrounding environment detected by the surrounding environment detection unit 5 to the learning data D4 for machine learning. When detecting an accident risk, the sense of speed detection unit 8 outputs the sense of speed obtained by outputting the surrounding environment to the learning data D4, that is, the sense of speed output by the learning model, to the manageable distance detection unit 9.

[0031] Here, the sense of speed is a statistical value of the driver's driving speed based on the statistically obtained relationship between the driving environment (surrounding environment) and speed, and can be calculated by multiple regression analysis using, for example, the following model formula: In formula (1), V is the sense of speed, E is the surrounding environment such as the time of day and road width, and α is a parameter.

number

[0032] That is, the sense of speed detection unit 8 functions as a driving speed information acquisition unit that acquires statistical values of the driver's driving speed based on the relationship between the surrounding environment (driving environment) and speed obtained statistically when there are no other vehicles ahead.

[0033] The manageable distance detection unit 9 calculates the manageable distance from the inter-vehicle time output from the inter-vehicle time detection unit 7 and the sense of speed output from the sense of speed detection unit 8, and outputs the calculated manageable distance to the accident risk detection unit 10. The manageable distance is calculated by multiplying the inter-vehicle time and the sense of speed.

[0034] The accident risk detection unit 10 detects (determines) the accident risk of the target driver based on the manageable distance calculated by the manageable distance detection unit 9 and statistical data acquired from the accident risk statistical data D5. Furthermore, when the sudden braking detection unit 2 detects sudden braking a predetermined number of times or more, the accident risk detection unit 10 detects (determines) the accident risk of the target driver based on the sudden braking detection result and the statistical data D1. Furthermore, the accident risk detection unit 10 outputs the manageable distance calculated by the manageable distance detection unit 9 to be compiled into the accident risk statistical data D5.

[0035] That is, the manageable distance detection unit 9 and the accident risk detection unit 10 function as an output unit that outputs a driving index of the driver based on the statistical value of the traveling speed and the statistical value of the inter-vehicle time.

[0036] The statistical data D1 compiles sudden braking detected by the sudden braking detection unit 2. The statistical data D2 compiles inter-vehicle time detected by the inter-vehicle time detection unit 7. In other words, the statistical data D2 is a statistical value of the driver's inter-vehicle time, statistically calculated from the inter-vehicle distance when there is another vehicle ahead and the traveling speed of the vehicle itself. The map data D3 may be the same data as that installed in navigation devices, autonomous vehicles, etc., and includes information such as nodes, links, the number of lanes, and road width.

[0037] The learning data D4 is a learning model that is trained using the speed and surrounding environment output from the sense of speed detection unit 8 as training data. That is, the learning data D4 is a statistical value of the driver's driving speed based on the relationship between the driving environment and the speed statistically obtained when there are no other vehicles ahead. The accident risk statistical data D5 is calculated and set as a threshold value for detecting an accident risk by the accident risk detection unit 10. Furthermore, the statistical data D1, the statistical data D2, the map data D3, the learning data D4, and the accident risk statistical data D5 may be provided on an external server or the like, or may be included in the driving indicator output device 1 itself.

[0038] Furthermore, the statistical data D1, statistical data D2, and learning data D4 are aggregated and learned for each driver. For the accident risk statistical data D5, a threshold is calculated based on the collected data of all drivers. Note that the storage location of the statistical data D1, statistical data D2, map data D3, learning data D4, and accident risk statistical data D5 is not limited to within the device, and some or all of the data may be stored on a server, etc. Furthermore, the statistical data D1, statistical data D2, and learning data D4 may be statistically and learning processed for each individual driver, or may be statistically and learning processed by modeling drivers with similar driving tendencies.

[0039] The acceleration sensor 21 is a well-known sensor that detects the acceleration of an object (a vehicle in this embodiment) on which the sensor is installed, and the type is not limited, and may be a semiconductor type, an optical type, or the like. The object positioning sensor 22 is a sensor that measures the distance to an object (an object in front of the vehicle in this embodiment), and a distance measurement sensor such as LiDAR (Light Detection and Ranging) can be used. The speed sensor 23 is a well-known sensor that detects the moving speed of the object (a vehicle in this embodiment) on which the sensor is installed, and a vehicle speed pulse or the like provided on the vehicle may be used. The image acquisition sensor 24 is a sensor that can capture images of the surroundings of the vehicle, and an on-board camera can be used.

[0040] Next, the operation of the driving index output device 1 configured as described above will be described with reference to Fig. 2 to Fig. 4. Fig. 2 is a flowchart of data collection and machine learning operations related to the statistical data D2 and the learning data D4. When executing this flowchart, the driving index output device 1 may be mounted on a vehicle, or may be installed outside the vehicle and acquire detection results and the like of each sensor from the vehicle via a network or the like.

[0041] 2, first, the traveling speed detection unit 4 determines whether the vehicle driven by the target driver is traveling at a speed exceeding the slow traveling speed (step S11), and if the vehicle is traveling at a speed below the slow traveling speed, this step is repeated until the vehicle is traveling at a speed exceeding the slow traveling speed (step S11: NO). Here, the slow traveling speed is a speed at which the vehicle can be stopped immediately, and may be set to, for example, 10 km / h.

[0042] If the vehicle driven by the target driver is traveling at a speed exceeding the creep speed (step S11: YES), a risk detection flow described below is executed (ON) (step S12), and the object approach detection unit 6 determines whether or not there is an obstacle ahead (step S13) based on the distance to the obstacle ahead detected by the inter-vehicle distance detection unit 3. The object approach detection unit 6 determines that there is an obstacle ahead when it detects an object within a predetermined distance.

[0043] If it is determined that there is an obstacle ahead (step S13: Yes), the inter-vehicle time detection unit 7 collects inter-vehicle times (step S14). This collection is performed for each driver. The collected inter-vehicle times are compiled and analyzed in statistical data D2. Specifically, for example, the average value of the compiled inter-vehicle times is calculated and used to calculate the actionable distance in the object approach detection unit 6.

[0044] On the other hand, if it is determined that there is no obstacle ahead (step S13: NO), the sense of speed detection unit 8 collects statistical data that is the basis for the sense of speed (step S15). This collection is performed for each driver. In this step, as described above, the sense of speed detection unit 8 collects training data D4 based on the traveling speed and the surrounding environment.

[0045] Then, it is determined whether or not the vehicle has finished traveling (step S16), and if so, the flow chart is terminated, and if not, the process returns to step S11. Whether or not the vehicle has finished traveling may be determined, for example, based on the traveling speed or whether the ignition switch has been turned off.

[0046] In this way, the driving indicator output device 1 can collect data and perform machine learning on the statistical data D2 and the learning data D4.

[0047] Next, the risk detection operation (driving index output method) in this embodiment will be described with reference to the flowchart in FIG. 3. The flowchart shown in FIG. 3 illustrates the operation when analysis is performed after the actual driving has ended. Therefore, while driving, the results detected by the acceleration sensor 21, object position sensor 22, speed sensor 23, and image acquisition sensor 24 are recorded as a log. Then, the driving index output device 1 reads the recorded log and executes the following steps. Therefore, when executing this flowchart, the driving index output device 1 does not need to be installed in the vehicle.

[0048] First, the inter-vehicle time detection unit 7 acquires inter-vehicle time data from the statistical data D2 of the driver who is the subject of accident risk assessment (step S21), and the sense of speed detection unit 8 acquires sense of speed data from the learning data D4 of the driver who is the subject of accident risk assessment (step S22). This statistical data of sense of speed indicates the sense of speed V calculated by equation (1). Note that steps S21 and S22 may be performed in reverse order.

[0049] After acquiring the inter-vehicle time and sense of speed, the accident risk detection unit 10 determines whether or not there is a risk (step S23). In this step, first, the manageable distance detection unit 9 calculates the manageable distance based on the acquired inter-vehicle time and sense of speed, and determines whether or not there is a risk based on the calculated manageable distance and a threshold value (first reference value) acquired from the accident risk statistical data D5.

[0050] A method for determining whether or not there is a risk will be described with reference to Figures 4 to 6. Figures 4 to 6 show the results of a virtual driving experiment conducted by the present inventors using a driving simulator.

[0051] First, we will explain the experimental conditions. For the experiment, a virtual experimental environment was created using a vehicle-like cockpit and driving simulator software. A road environment measuring 0.6 km in length and 1.3 km in width was created in the virtual space. Building objects were generated with reference to map data so that only the size was close to reality, in order to eliminate the influence of the visual saliency of each building. Multiple sedan-type vehicles were placed on the road, and they were set to be relocated if they went outside a certain range, with the driving vehicle at the center.

[0052] The time and weather were varied to evaluate the effects of differences in visibility. The experiment began at 8:00 a.m. on a winter day, with time advancing every 15 minutes for two days. The weather conditions, including rain intensity, precipitation, and visibility, were randomly varied. To simulate the risk of an elderly pedestrian (walking speed 4.6 km / h) suddenly crossing the road, multiple triggers were installed on the road. When a pedestrian passed by, there was a 70% chance that a pedestrian would appear 150 meters ahead. When the pedestrian was within 50 meters of a pedestrian in the same lane or 100 meters of a pedestrian in the opposite lane, there was a 70% chance that a pedestrian would suddenly appear 0.6 seconds later. The subjects were 22 men in their 20s to 50s. The experiment lasted a total of 25 minutes, consisting of a 5-minute warm-up run, a 5-minute break, and a 15-minute main run.

[0053] The results of the experiment conducted under these conditions are shown in Figure 4. In Figure 4, the vertical axis shows the number of sudden decelerations (0.3G or more), and the horizontal axis shows the number of collisions (regardless of whether the driver was at fault or not). When the results in Figure 4 were divided into two groups, (a) with seven or more sudden decelerations and (b) with less than seven sudden decelerations, it was found that in group (a), a strong correlation was observed between accidents and sudden decelerations (sudden braking). It was also found that in group (b), a weak correlation was observed between the number of collisions and the number of collisions.

[0054] It was found that in group (a), the number of sudden decelerations had a linear relationship with the number of contacts, as shown in Figure 5. Furthermore, in group (b), when the number of sudden decelerations was below a certain level, it was found that it was possible to separate the relationship into those shown by logistic regression, as shown in Figure 6.

[0055] According to Figure 6, under the conditions of the above-mentioned experiment, when the actionable distance is approximately 45 m or less, the presence or absence of contact becomes "1," and it is clear that the risk of an accident increases. Therefore, it was found that by calculating the actionable distance, it is possible to determine the risk of an accident even when sudden braking is rare.

[0056] Therefore, in this embodiment, a threshold value of the actionable distance for determining whether or not an accident risk is detected when the number of times sudden braking is detected is stored as accident risk statistical data D5 for each surrounding environment and location. The accident risk detection unit 10 reads the threshold value of the actionable distance from the accident risk statistical data D5 and determines the accident risk. In other words, if the calculated actionable distance is less than the threshold value, it is determined that there is an accident risk, and if it is greater than or equal to the threshold value, it is determined that there is no accident risk.

[0057] Returning to the explanation of Fig. 3, if the result of determining whether there is a risk in step S23 is that there is no risk (step S23: no), the accident risk detection unit 10 outputs information indicating that the driving was safe and records this in a recording device or the like (not shown) (step S24). On the other hand, if the result of determining whether there is a risk in step S23 is that there is a risk (step S23: yes), the accident risk detection unit 10 outputs information indicating that the driving was high-risk and records this in a recording device or the like (step S25).

[0058] Although the flowchart in Fig. 3 does not take into consideration the detection of sudden braking, it may be executed when the number of times sudden braking is detected is small. For example, a threshold value (second reference value) may be set for the number of times sudden braking is detected, and the flowchart may be executed when the number is equal to or less than the threshold value. The threshold value is not limited to seven times as in the above experiment, and may be changed as appropriate.

[0059] In addition, although the present embodiment outputs the presence or absence of an accident risk as a driving index, the manageable distance may be output as a driving index. In this case, the presence or absence of an accident risk may be determined by another device or the like.

[0060] Furthermore, the flowchart shown in Figure 3 judges the accident risk for a single drive, but it is also possible to compare the manageable distances obtained from logs of multiple drives on the same route and output a driving index indicating whether the risk has worsened or improved.

[0061] According to this embodiment, in the driving index output device 1, the surrounding environment detection unit 5 acquires the vehicle's driving environment, the sense of speed detection unit 8 acquires the sense of speed when there are no other vehicles ahead, and the inter-vehicle time detection unit 7 acquires the driver's inter-vehicle time statistically calculated from the inter-vehicle distance when there are other vehicles ahead and the driving speed of the vehicle. Then, the manageable distance detection unit 9 multiplies the sense of speed and the inter-vehicle time to calculate the manageable distance as a driving index. In this way, the manageable distance calculated based on machine learning and statistical values such as the acquired sense of speed and inter-vehicle time can be output as a driving index. Furthermore, there is no need to determine the driver's psychological state when outputting the driving index.

[0062] Furthermore, the accident risk detection unit 10 determines and outputs the accident risk of the driver based on the manageable distance as a driving index. In this way, it is possible to output specific information such as the accident risk.

[0063] Furthermore, the accident risk detection unit 10 determines that there is an accident risk when the manageable distance is equal to or less than a predetermined threshold. In this way, it is possible to determine whether or not there is an accident risk depending on the manageable distance.

[0064] In addition, the threshold value of the distance that can be handled for determining the risk of an accident varies depending on the surrounding environment and location. In this way, the risk of an accident can be determined using a threshold value appropriate for the location where the vehicle is traveling.

[0065] Furthermore, the driving index output device 1 includes a sudden braking detection unit 2 that detects sudden braking of the vehicle, and the accident risk detection unit 10 outputs the driver's accident risk based on the sense of speed and inter-vehicle time when the number of sudden brakings detected by the sudden braking detection unit 2 is equal to or less than a predetermined threshold. In this way, a driving index such as an accident risk can be output when sudden braking is infrequent, and it is possible to reliably determine the potential accident risk when sudden braking is infrequent. [Example]

[0066] A driving index output device according to a second embodiment of the present invention will be described with reference to Fig. 7. The same parts as those in the first embodiment described above are denoted by the same reference numerals and description thereof will be omitted.

[0067] This embodiment has the same configuration as that shown in Fig. 1. However, this embodiment differs in the risk detection operation. In this embodiment, the presence or absence of a risk is determined using inter-vehicle time and traveling speed acquired (detected) in real time. Fig. 7 shows a flowchart of the risk detection operation according to this embodiment.

[0068] First, in step S31, the object approach detection unit 6 determines whether or not there is an obstacle ahead based on the distance to the obstacle ahead (e.g., a vehicle ahead) detected by the inter-vehicle distance detection unit 3. This step is basically the same as step S13 described above.

[0069] If it is determined that there is an obstacle ahead (step S31: Yes), the inter-vehicle time detection unit 7 acquires the inter-vehicle time based on the inter-vehicle distance detected by the inter-vehicle distance detection unit 3 and the traveling speed detected by the traveling speed detection unit 4 (step S32). Then, the speed sense detection unit 8 acquires the sense of speed from the learning data D4 according to the surrounding environment (step S33).

[0070] Then, the manageable distance detection unit 9 calculates the manageable distance from the inter-vehicle time acquired in step S32 and the sense of speed acquired in step S33, and determines whether or not there is a risk based on the calculated manageable distance and a threshold value acquired from the accident risk statistical data D5 (step S36). In other words, the presence or absence of a risk is determined based on the inter-vehicle time acquired in real time.

[0071] If it is determined that there is no risk as a result of determining whether there is a risk in step S36 (step S36: NO), the flowchart ends. Alternatively, the process may return to step S31. On the other hand, if it is determined that there is a risk as a result of determining whether there is a risk in step S36 (step S36: YES), the accident risk detection unit 10 notifies the driver of a guide such as a caution or warning (step S37). Specifically, the accident risk detection unit 10 generates and outputs information for notifying the driver of a guide such as a caution or warning or a break. Examples of output destinations include display means and audio output means for notifying the driver of a guide such as a caution or warning or a break.

[0072] On the other hand, if it is determined that there is no obstacle ahead (step S31: NO), the sense of speed detection unit 8 acquires the traveling speed detected by the traveling speed detection unit 4 (step S34). Then, the inter-vehicle time detection unit 7 acquires the inter-vehicle time from the statistical data D2 (step S35). Then, the manageable distance detection unit 9 calculates the manageable distance from the traveling speed acquired in step S34 and the inter-vehicle time acquired in step S35, and determines whether there is a risk based on the calculated manageable distance and a threshold acquired from the accident risk statistical data D5 (step S36). In other words, the presence or absence of a risk is determined based on the traveling speed acquired in real time.

[0073] According to this embodiment, the risk of an accident is determined based on the time gap and driving speed obtained in real time, so if the situation changes during driving such that the distance that can be handled becomes shorter, a warning can be issued quickly, and an accident can be avoided.

[0074] In the second embodiment, the accident risk is determined based on the inter-vehicle time and traveling speed obtained in real time, but the driving index output device 1 does not necessarily have to be mounted on the vehicle. The driving index output device 1 may be located outside the vehicle, and may be configured to obtain information detected by each sensor of the vehicle in real time, determine the accident risk in real time, and send the information to the vehicle.

[0075] In addition, in the second embodiment, by determining the accident risk in real time and storing a log of the detection results of each sensor, it is possible to also determine the accident risk after driving, as in the first embodiment. [Example]

[0076] A driving index output device according to a third embodiment of the present invention will be described with reference to Figures 8 to 10. Note that the same parts as those in the first embodiment described above are given the same reference numerals and description thereof will be omitted.

[0077] In this embodiment, the psychological state of the driver is determined from the statistical value of the traveling speed (learned data D4) and the statistical value of the inter-vehicle time (statistical data D2).

[0078] The functional configuration of this embodiment is shown in Fig. 8. The configuration shown in Fig. 8 differs from the configuration shown in Fig. 1 in that data from the time inter-vehicle detection unit 7 and the sense of speed detection unit 8 are each directly input to the accident risk detection unit 10. That is, data on the time inter-vehicle time (statistical values of the time inter-vehicle) is input from the time inter-vehicle detection unit 7, and data on the sense of speed (statistical values of the time inter-vehicle) is input from the sense of speed detection unit 8. The accident risk detection unit 10 then determines the psychological state of the driver based on these data and issues a risk warning according to the determination result.

[0079] A method for determining a driver's psychological state according to this embodiment will be described with reference to Figs. 9 and 10. Fig. 9 is a graph analyzing data obtained as a result of the experiment described in the first embodiment. In the graph of Fig. 9, the vertical axis represents the statistical value of driving speed, i.e., the inverse of the sense of speed, and the horizontal axis represents the statistical value of inter-vehicle time. In the graph of Fig. 9, points plotted with x marks represent subjects who did not have contact, and points plotted with o marks represent subjects who had contact. Furthermore, points surrounded by □ represent subjects who had contact and whose number of sudden braking attempts was below the threshold (7 times).

[0080] According to Figure 9, the area surrounded by lines L1 and L2 has many drivers who have not made contact with other vehicles, and it is considered that the drivers are in a psychological state (calm state) where they can drive safely. Also, in areas other than the area surrounded by lines L1 and L2, if the value of the inverse of the sense of speed is small and the value of the inter-vehicle distance is small, it is considered that the drivers tend to drive fast and the inter-vehicle distance is short, so the psychological state is considered to be hurrying. Also, if the value of the inverse of the sense of speed is not small and the value of the inter-vehicle distance is small, it is considered that the drivers do not tend to drive fast but the inter-vehicle distance is short, so the psychological state is considered to be a decline in concentration. Also, if the value of the inverse of the sense of speed is not small and the value of the inter-vehicle distance is not small, it is considered that the drivers do not tend to drive fast and the inter-vehicle distance is not short, so the psychological state is considered to be anxiety.

[0081] 9, it was found that many subjects had contact in the area of decreased concentration and the number of sudden braking attempts was below the threshold. In other words, it was found that it is possible to detect a psychological state of decreased concentration when the number of sudden braking attempts is low. The accident risk detection unit 10, for example, stores the graph shown in FIG. 9 in the accident risk statistical data D5, and determines the psychological state or change in psychological state using the above-mentioned method based on the data obtained from the inter-vehicle time detection unit 7 and the sense of speed detection unit 8 and the data corresponding to the graph obtained from the accident risk statistical data D5, and outputs information indicating the determination result.

[0082] In this embodiment, for example, as shown in FIG. 10, if a subject that was in the area indicating safety at the start of driving moves to an area indicating a decrease in concentration due to, for example, a change in inter-vehicle time, it is determined that concentration is decreasing and a warning is given to the driver. FIG. 10 shows an example in which a subject that was in the ST position at the start of driving moves to the SP position as driving continues. In this case, the subject has moved from the area indicating safety to an area indicating a decrease in concentration, and information indicating a change in psychological state can be output. As in the second embodiment, the output destination can be a display means or audio output means that issues a warning or caution.

[0083] According to this embodiment, the accident risk detection unit 10 outputs information related to the psychological state of the driver as a driving index, and is therefore able to detect changes in the psychological state of the driver and issue a warning to the driver, etc. Furthermore, since the psychological state can be determined, an appropriate warning can be issued to the driver by issuing a notification, etc., according to the psychological state.

[0084] Furthermore, in the above three embodiments, the accident risk may not be judged only after the end of driving or during driving, but may be judged only in a specific section (such as only expressways).

[0085] Furthermore, the present invention is not limited to the above-described embodiments. That is, a person skilled in the art can implement various modifications in accordance with conventionally known knowledge without departing from the gist of the present invention. As long as such modifications still include the driving indicator output device of the present invention, they are of course included in the scope of the present invention. [Explanation of symbols]

[0086] 1. Driving indicator output device 2. Sudden braking detection unit 3. Vehicle distance detection unit 4. Travel speed detection unit 5 Surrounding environment detection unit (driving environment acquisition unit) 6. Object approach detection unit 7. Inter-vehicle time detection unit (inter-vehicle time information acquisition unit) 8 Speed detection unit (driving speed information acquisition unit) 9. Handling distance detection unit (output unit) 10 Accident risk detection unit (output unit) D1 Statistics D2 Statistics D3 map data D4 Training data D5 Accident Risk Statistics Data

Claims

1. a driving environment acquisition unit that acquires the driving environment of the vehicle; a traveling speed information acquisition unit that acquires a statistical value of the driver's traveling speed based on a statistically obtained relationship between the traveling environment and the speed when there is no other vehicle ahead; a vehicle-to-vehicle time information acquisition unit that acquires a statistical value of the driver's vehicle-to-vehicle time obtained statistically from the vehicle-to-vehicle distance when there is another vehicle ahead and the traveling speed of the vehicle; an output unit that outputs an actionable distance based on the statistical value of the traveling speed and the statistical value of the inter-vehicle time as a driving index of the driver; A driving index output device comprising:

2. The driving index output device according to claim 1, wherein the output unit outputs the manageable distance calculated by multiplying the statistical value of the traveling speed by the statistical value of the inter-vehicle time as the driving index.

3. The driving index output device according to claim 2 , wherein the output unit determines an accident risk of the driver based on the manageable distance and outputs the determined accident risk as the driving index.

4. The driving index output device according to claim 3 , wherein the output unit determines that there is an accident risk when the manageable distance is equal to or less than a first reference value.

5. The driving index output device according to claim 1 , wherein the output unit outputs information related to the driver's psychological state as the driving index.

6. further comprising a sudden braking detection unit that detects sudden braking of the vehicle; 6. The driving index output device according to claim 1, wherein the output unit outputs a driving index of the driver based on the statistical value of the traveling speed and the statistical value of the inter-vehicle time when the number of sudden brakings detected by the sudden braking detection unit is equal to or less than a second reference value.

7. A driving index output method executed by a driving index output device that outputs a driving index of a driver, a driving environment acquisition step of acquiring a driving environment of a vehicle; a traveling speed information acquisition step of acquiring a statistical value of the driver's traveling speed based on a statistically obtained relationship between the traveling environment and the speed when there is no other vehicle ahead; a vehicle-to-vehicle time information acquisition step of acquiring a statistical value of the driver's vehicle-to-vehicle time obtained statistically from the vehicle-to-vehicle distance when there is another vehicle ahead and the traveling speed of the vehicle; an output step of outputting an manageable distance based on the statistical value of the traveling speed and the statistical value of the inter-vehicle time as a driving index of the driver; A driving index output method comprising:

8. A driving index output program for causing a computer to execute the driving index output method according to claim 7.

9. A computer-readable storage medium storing the driving indicator output program according to claim 8.

Images