JP2018041138A - Driver's attention calling method and driver's attention calling device - Google Patents

Abstract

PROBLEM TO BE SOLVED: To call a driver's attention before a vehicle enters a right turn point and a left turn point or enters a branching-off point and a merging point, and then, to call the driver's attention in advance at the right turn point and the left turn point and the branching-off point and the merging point.SOLUTION: A driver's attention calling device 3 acquires a reference operation model calculated for each of a right turn point and a left turn point, and a branching-off point and a merging point from a server 7 by statistically processing vehicle information collected from a plurality of vehicles, and calculates a driver driving model for each of the right turn point and the left turn point and the branching-off point and the merging point by statistically processing the vehicle information collected for each driver. When the vehicle approaches the right turn point and the left turn point or the branching-off point and the merging point, the driver's attention calling device compares the reference driving model with the driver driving model, and when the device determines that attention calling is necessary, the device performs attention calling to the driver before the vehicle enters the right turn point and the left turn point or the branching-off point and the merging point.SELECTED DRAWING: Figure 1

Description

  The present invention relates to a driver alert method and a device for alerting a driver of a vehicle at a right / left turn point where the vehicle turns right and left and a branch / merging point where the vehicle branches or merges.

  Conventionally, Patent Document 1 discloses a driving evaluation device that evaluates a driving operation performed by a driver of a vehicle and informs the driver of the evaluation result. In this driving evaluation apparatus, the driving operation performed by the driver is evaluated in comparison with the evaluation standard, and when the evaluation result is notified to the driver, the notification is made in a different notification mode depending on the evaluation result.

JP-A-2015-141516

  However, in the conventional driving evaluation apparatus described above, the evaluation result is notified after the driver performs the driving operation. Therefore, for example, even if it is known that the driver's driving skill is low and the safety check is insufficient when turning right or left at the intersection, the driver is alerted before the vehicle enters the intersection. There was a problem that it was not possible.

  Therefore, the present invention has been proposed in view of the above-described circumstances, and an object thereof is to provide a driver alerting method and an apparatus thereof capable of alerting in advance at a right / left turn point and a branching / merging point. To do.

  In order to solve the above-described problem, a driver alert method and an apparatus thereof according to an aspect of the present invention are calculated for each right and left turn point and branch junction point by statistically processing vehicle information collected from a plurality of vehicles. The obtained reference operation model is acquired from the server. In addition, a driver driving model is calculated for each turning point and branching / merging point by statistically processing the vehicle information collected for each driver. When the vehicle approaches the right / left turn point or branch junction, the vehicle enters the right / left turn point or branch junction when it is determined that attention is required by comparing the reference driving model with the driver driving model. Alert the driver before.

  According to the present invention, it is possible to alert in advance at a right / left turn point where a vehicle turns right or left or a branch / merging point where a vehicle branches or merges.

FIG. 1 is a block diagram illustrating a configuration of a driver alert system including a driver alert device according to an embodiment of the present invention. FIG. 2 is a diagram for explaining a calculation method of the reference driving model and the driver driving model. FIG. 3 is a diagram for explaining the data structure of the reference operation model. FIG. 4 is a diagram for explaining the data structure of the driver driving model. FIG. 5 is a flowchart showing a processing procedure of an operation history recording process according to an embodiment of the present invention. FIG. 6 is a flowchart showing a processing procedure of a reference operation model calculation process according to an embodiment of the present invention. FIG. 7 is a flowchart showing a processing procedure of driver driving model calculation processing according to an embodiment of the present invention. FIG. 8 is a flowchart showing a processing procedure of driver alert processing according to an embodiment of the present invention.

  Hereinafter, an embodiment to which the present invention is applied will be described with reference to the drawings.

[Configuration of driver alert system]
FIG. 1 is a block diagram illustrating a configuration of a driver alert system including a driver alert device according to the present embodiment. As shown in FIG. 1, the driver alert system 1 according to this embodiment includes a vehicle 5 equipped with a driver alert device 3, a server 7, and a probe information database 9. 7 is connected via a communication network such as the Internet. The driver alert system 1 is a system that uses a probe car system that collects probe data from many vehicles and provides services.

  The vehicle 5 is a probe car that collects probe data, and can access the server 7 via a communication network by wireless communication. The vehicle 5 is equipped with a driver alert device 3, and further includes a GPS receiver 11, a camera 13, a speed sensor 15, a rudder angle sensor 17, an accelerator sensor 19, a brake switch 21, and a direction instruction. Device 23, navigation device 25, and vehicle control unit 27.

  The server 7 is a probe server installed in the data center of the probe car system, and collects probe data from many vehicles and stores it in the probe information database 9. In particular, the server 7 collects vehicle information from many vehicles, and calculates a reference driving model for each right-left turn point and branch junction point by statistically processing the collected vehicle information. The right / left turn point is a point where the vehicle turns right / left, and includes not only an intersection but also an entrance / exit point from a roadway to a parking lot or the like. A branching / merging point is a point where a vehicle branches or merges like an interchange or a junction. Further, the vehicle information includes information such as the vehicle speed, steering angle, accelerator opening, brake timing, position information by GPS (Global Positioning System), images outside and inside the vehicle, and the operation state of the direction indicator.

  The reference driving model is data that defines a reference value for driving operation necessary for safely driving the vehicle at a right / left turn point and a branch / merging point. As shown in FIG. 2, the standard driving model collects driving operations performed by a large number of drivers at specific right and left turn points and branching / merging points as vehicle information, and statistically processes the collected vehicle information. Calculated. Therefore, the reference operation model is data that defines safety standards for each of the right and left turn points and branch junction points, and can be used as a threshold value for determining whether or not the vehicle is safe. In addition, the reference operation model may be calculated for each time zone after calculating for each right / left turn point and branch junction point.

  In the reference driving model, as shown in FIG. 3, reference values for safe driving operations are set for the vehicle speed, steering angle, accelerator opening, brake timing, driver's head rotation angle, and the like. . The reference driving model calculation method shown in FIG. 3 may be, for example, collecting vehicle speed information when passing an intersection, calculating an average value, and setting the average value as a reference value. In addition to this, for each driving operation such as a steering angle and an accelerator opening, an average value is set as a reference value, and these reference values are collected to form a reference driving model. However, the reference value calculation method may be obtained by other methods, for example, the average value may be calculated using only highly safe driver data.

  The probe information database 9 accumulates the probe data collected by the server 7 and stores vehicle information necessary for calculating the reference operation model and the calculated reference operation model.

  The GPS receiver 11 receives information on the latitude, longitude, and altitude of the host vehicle from the satellite. The camera 13 includes an out-of-vehicle camera that images the surroundings of the host vehicle and an in-vehicle camera that images the cabin of the host vehicle, and acquires an image of the surroundings of the host vehicle and an image of passengers in the cabin. The speed sensor 15 measures the vehicle speed of the host vehicle. The steering angle sensor 17 detects the steering angle of the host vehicle. The accelerator sensor 19 detects the accelerator opening. The brake switch 21 outputs on / off of the brake. The direction indicator 23 outputs the operating state of the direction indicator. The navigation device 25 stores map information electronically, detects the position of the host vehicle, and calculates a guidance route to the destination. The vehicle control unit 27 is an ECU (Electrical Control Unit) that acquires information from each sensor and controls the host vehicle.

  The driver alert device 3 is a controller that alerts the driver of the vehicle at a right / left turn point and a branch / merging point. The driver alerting device 3 obtains a reference driving model from the server 7, and calculates a driver driving model for each right / left turn point and branching / merging point by statistically processing the vehicle information collected for each driver. Then, when the vehicle 5 approaches the right / left turn point or branch junction point, the vehicle enters the right / left turn point or branch junction point when the reference driving model and the driver driving model are compared and it is determined that attention is required. Alert the driver before starting. The driver alerting device 3 includes a driving history recording unit 31, an information acquisition unit 33, a driver driving model calculation unit 35, an alerting determination unit 37, and an alerting execution unit 39. However, although this embodiment demonstrates the case where the driver alerting apparatus 3 is mounted in the vehicle 5, you may install the driver alerting apparatus 3 in the server 7. FIG.

  The driving history recording unit 31 collects probe data from each sensor mounted on the vehicle and uploads it to the server 7. In particular, the driving history recording unit 31 collects, as vehicle information, information such as vehicle speed, steering angle, accelerator opening, brake timing, GPS position information, images outside and inside the vehicle, and operation status of the direction indicator. To do.

  The information acquisition unit 33 communicates with the server 7 via the communication network, and acquires the vehicle information stored in the probe information database 9 and the reference driving model calculated by the server 7. In particular, when acquiring a reference driving model, the position of the host vehicle is determined from position information obtained by GPS, and an intersection or branching junction where the host vehicle passes next is detected to acquire a reference driving model at that point. To do.

  The driver driving model calculation unit 35 calculates a driver driving model for each right / left turn point and branching / merging point by statistically processing the vehicle information collected for each driver. As shown in FIG. 2, the driver driving model is calculated by collecting driving operations performed by a specific driver as specific vehicle information at specific right and left turn points and branching / merging points, and statistically processing the collected vehicle information. be able to. The driver driving model has the same configuration as the reference driving model. As shown in FIG. 4, the driver driving model has a specific driving speed, steering angle, accelerator opening, brake timing, driver's head rotation angle, etc. A statistical value obtained by statistically processing a driver's operation is set. The driver driving model calculation method shown in FIG. 4 may be, for example, collecting vehicle speed information when passing an intersection, calculating an average value, and setting the average value as a statistical value. In addition, the average value is obtained as a statistical value for each driving operation such as the steering angle and the accelerator opening, and these statistical values are collected to obtain a driver driving model. However, the statistical value is not an average value and may be obtained by other methods. In addition, the driver driving model may be calculated for each time zone after calculating for each right / left turn point and branch / merging point.

  When the vehicle 5 approaches a right or left turn point or branch junction point, the attention determination unit 37 compares the reference driving model with the driver driving model to determine whether or not attention is required. For example, when the vehicle speed of the driver driving model is faster than the vehicle speed of the reference driving model, it is determined that alerting is necessary. For items other than the vehicle speed, it is determined whether it is necessary to call attention in the same manner.

  When the alerting determination unit 37 determines that alerting is necessary, the alerting execution unit 39 executes alerting before the host vehicle enters the right / left turn point and branch junction. As a method of calling attention, a voice message for calling attention to the driver may be sent, or a warning message may be displayed on the display.

  The driver alert device 3 includes a general-purpose electronic circuit including a microcomputer, a microprocessor, and a CPU, and peripheral devices such as a memory. And by operating a specific program, it operates as the driving history recording unit 31, the information acquisition unit 33, the driver driving model calculation unit 35, the alert determination unit 37, and the alert execution unit 39 described above. Each function of the driver alert device 3 can be implemented by one or a plurality of processing circuits. The processing circuit includes a programmed processing device such as, for example, a processing device including an electrical circuit, and an application specific integrated circuit (ASIC) or conventional circuit arranged to perform the functions described in the embodiments. It also includes devices such as parts.

[Operation history recording procedure]
Next, the procedure of the driving history recording process by the driver alerting device 3 according to the present embodiment will be described with reference to the flowchart of FIG. The operation history recording process shown in FIG. 5 is a process executed by all probe cars. Therefore, the driving history recording unit 31 is provided in all probe cars.

  As shown in FIG. 5, first, in step S101, the driving history recording unit 31 determines whether or not the ignition switch is turned on and the vehicle starts driving. When the vehicle has not started driving, the driving history recording process according to the present embodiment is terminated, and when the vehicle has started driving, the process proceeds to step S103.

  In step S103, the driving history recording unit 31 detects the operating state of the direction indicator 23 of the vehicle 5 and determines whether or not the direction indicator 23 has been operated. When the direction indicator 23 is not operating, the operating state of the direction indicator 23 is continuously monitored, and when the direction indicator 23 is operating, the process proceeds to step S105.

  In step S <b> 105, the driving history recording unit 31 acquires position information from the GPS receiver 11 and acquires the speed of the vehicle from the speed sensor 15. Also, the time when the data was acquired is recorded. Thereby, the driving history recording unit 31 can acquire the position information and the vehicle speed when the direction indicator 23 is operated and the vehicle turns right or left or branches and merges.

  In step S <b> 107, the driving history recording unit 31 acquires the vehicle steering angle from the steering angle sensor 17, acquires the accelerator opening from the accelerator sensor 19, and acquires the brake timing from the brake switch 21. Also, the time when the data was acquired is recorded. Thereby, the driving history recording unit 31 can acquire the steering angle, the accelerator opening, and the brake timing of the vehicle when the direction indicator 23 operates and the vehicle turns right or left or branches and merges.

  In step S <b> 109, the driving history recording unit 31 acquires images outside the vehicle and inside the vehicle from the camera 13. Also, the time when the data was acquired is recorded. As a result, the driving history recording unit 31 can acquire images of the outside of the vehicle and the interior of the vehicle when the direction indicator 23 is activated and the vehicle turns right or left or merges.

  In step S111, the driving history recording unit 31 determines whether or not the ignition switch is turned off and the vehicle has finished driving. When the vehicle has not finished driving, the process returns to step S103, and when the vehicle has finished driving, the driving history recording process according to the present embodiment is finished. Thereafter, the operation history recording unit 31 uploads the acquired data to the server 7. As a communication method, communication using a wireless communication network such as a mobile phone, WiFi, DSRC, or power line communication may be used, or recording on a removable recording medium such as a flash memory and via a terminal with another communication function. You may upload.

[Standard operation model calculation processing procedure]
Next, the procedure of the reference operation model calculation process by the server 7 will be described with reference to the flowchart of FIG. In step S <b> 201, the server 7 acquires vehicle information data collected from many vehicles from the probe information database 9.

  In step S203, the server 7 determines whether or not a reference operation model has been created. Since the reference operation model is created for each right / left turn point and branch / merging point, it is determined whether a reference operation model has been created for each right / left turn point and branch / merging point. If the reference operation model has not been created, the process proceeds to step S205. If the reference operation model has been created, the process proceeds to step S207.

  In step S205, the server 7 performs a statistical process on vehicle information collected from many vehicles, thereby calculating a reference operation model for each right / left turn point and branch / merging point. As a calculation method of the reference driving model, an average value of each data of vehicle information is calculated. That is, the average value of the vehicle speed, the average value of the steering angle, the average value of the accelerator opening, and the average value of the brake timing are calculated. Further, the image of the passenger compartment image is processed to detect the rotation angle of the driver's head, and the average value of the rotation angle of the driver's head is also calculated. Further, instead of simply calculating the average value, the average value may be calculated using vehicle information of a highly safe driver. Highly safe drivers include, for example, drivers with low frequency of sudden braking operations, drivers with low speeds, and drivers with a large head rotation angle on the assumption that visual safety has been sufficiently confirmed. Etc. In this case, for example, the drivers are arranged in the order of the frequency of sudden braking operations, the drivers within a predetermined range are extracted from the lowest level, and the average value is calculated using only the extracted driver data. In addition, an intermediate value may be used instead of the average value. Further, the reference operation model may be calculated for each time zone. When the reference operation model is calculated in this way, the reference operation model calculation process according to the present embodiment is terminated.

  In step S207, the server 7 determines whether or not the reference operation model needs to be changed. When new vehicle information is collected, for example, when the total number of data changes, or when data extracted as a driver with a low speed or a driver with a large rotation angle of the head changes, the server 7 Determines that the reference operation model needs to be changed. If it is determined that there is no need to change the reference operation model, the reference operation model calculation process according to the present embodiment is terminated. If it is determined that the reference operation model needs to be changed, the process proceeds to step S209. .

  In step S209, the server 7 updates the reference operation model using new data. As a method of updating, the reference operation model may be recalculated using new data using the same method as the reference operation model calculation method performed in step S205. When the reference operation model is updated in this way, the reference operation model calculation process according to the present embodiment is terminated. Thereafter, the calculated reference operation model is stored in the probe information database 9.

[Driver driving model calculation process procedure]
Next, the procedure of the driver driving model calculation process by the driver alerting device 3 according to the present embodiment will be described with reference to the flowchart of FIG. However, in this embodiment, the case where the driver driving model is calculated by the driver alerting device 3 mounted on the vehicle 5 will be described. However, the driver alerting device 3 is installed in the server 7 and the driver driving model is installed in the server 7. May be calculated.

  In step S <b> 301, the information acquisition unit 33 acquires vehicle information of the driver of the host vehicle from the server 7.

  In step S303, the driver driving model calculation unit 35 determines whether or not a driver driving model has been created. Since the driver driving model is created for each right / left turn point and branch / merging point, it is determined whether or not a driver driving model has been created for each right / left turn point and branch / merging point. If a driver driving model has not been created, the process proceeds to step S305. If a driver driving model has been created, the process proceeds to step S307.

  In step S305, the driver driving model calculation unit 35 calculates a driver driving model for each right / left turn point and branch / merging point by statistically processing the vehicle information of the driver of the host vehicle. The driver driving model may be calculated by the same method as the reference driving model. That is, the average value of each data of the vehicle information may be calculated. For example, the average value of the vehicle speed, the average value of the steering angle, the average value of the accelerator opening, and the average value of the brake timing are calculated. Further, the image of the passenger compartment image is processed to detect the rotation angle of the driver's head, and the average value of the rotation angle of the driver's head is also calculated. In addition, an intermediate value may be used instead of the average value. Further, a driver driving model may be calculated for each time zone. When the driver driving model is thus calculated, the driver driving model calculating process according to the present embodiment is terminated.

  In step S307, the driver driving model calculation unit 35 determines whether or not the driver driving model needs to be changed. When new vehicle information is collected due to driving by the driver of the host vehicle, the driver driving model calculation unit 35 determines that the driver driving model needs to be changed. If it is determined that there is no need to change the driver driving model, the driver driving model calculation process according to the present embodiment is terminated. If it is determined that the driver driving model needs to be changed, the process proceeds to step S309. .

  In step S309, the driver driving model calculation unit 35 updates the driver driving model using new data. As an updating method, the driver driving model may be recalculated with new data using the same method as the driver driving model calculating method performed in step S305. Thereby, the driver driving model calculation unit 35 learns the driving operation performed by the driver. When the driver driving model is updated in this way, the driver driving model calculation process according to the present embodiment is terminated. Thereafter, the calculated driver driving model may be uploaded to the server 7 and stored in the probe information database 9, or may be stored in the memory or the like of the driver alerting device 3.

[Procedure for driver alert processing]
Next, the procedure of the driver alert process by the driver alert device 3 according to the present embodiment will be described with reference to the flowchart of FIG. The driver alert process of this embodiment starts when the ignition switch of the vehicle is turned on.

  In step S401, the information acquisition unit 33 determines whether or not the vehicle has approached a right / left turn point or a branching / merging point by moving. The right / left turn point is a point where the vehicle turns right or left, and includes not only an intersection but also an entrance / exit point from a roadway to a parking lot or the like. A branch / merging point is a point where the vehicle branches or merges like an interchange or a junction. Here, the right / left turn point and branch junction where the approach is determined are points where the host vehicle actually turns right / left or branch, and does not include intersections that simply pass and do not involve right / left turn or branch junction. Therefore, the determination method of whether the right / left turn point or the branching / merging point has approached is determined by whether or not the direction indicator 23 has been operated. In addition, when the route guidance to the destination is performed by the navigation device 25, it is determined that the right / left turn point or the branch / merging point approaches when the right / left turn or branch / merging route guidance is performed. And if it is not approaching the right / left turn point or branch junction, it will continue to determine the approach to the right / left turn point or branch junction, and if it is approaching the right / left turn point or branch junction, The process proceeds to S403.

  In step S403, the information acquisition unit 33 acquires the reference driving model and the driver driving model when the right / left turn point or the branching / merging point approaches. At this time, the information acquisition unit 33 detects the position of the host vehicle from the position information obtained by GPS, determines the right / left turn point or branch junction where the host vehicle approaches, and determines the reference driving model and the driver driving model at that point. get.

  In step S405, the attention determination unit 37 compares the reference driving model acquired in step S403 with the driver driving model to determine whether or not it is necessary to alert the driver. That is, the alert determination unit 37 determines whether or not the driver driving model calculated based on the driving operation of the driver satisfies the safety standard defined by the reference driving model. It is determined that alerting is necessary. For example, when the vehicle speed of the driver driving model is faster than the vehicle speed of the reference driving model, it is determined that alerting is necessary. Further, when the rotation angle of the driver's head of the driver driving model is smaller than the rotation angle of the reference driving model, it is determined that the safety check by visual inspection is insufficient and that it is necessary to call attention. In addition, for items such as the steering angle, the accelerator opening, and the brake timing, it is determined whether or not the driver driving model satisfies the safety standard defined by the reference driving model. If it is determined that attention is required, the process proceeds to step S407. If it is determined that attention is not required, the process proceeds to step S409.

  In step S407, the alert execution unit 39 executes alert to the driver before the own vehicle enters the right / left turn point or branch junction. As a method of calling attention, there are a voice message output and a warning message display. In this way, when the vehicle speed is higher than the safety standards specified in the standard driving model at a specific intersection or when safety confirmation is insufficient, warning is made in advance, so the right / left turn point or branch junction Alerts can be made in advance at the point.

  In step S409, the driving history recording unit 31 detects a driving operation by the driver when the host vehicle passes a right / left turn point or a branch / merging point, and obtains vehicle information such as a vehicle speed and a rotation angle of the driver's head. get. The acquired data is uploaded to the server 7. At this time, the driver driving model calculation unit 35 updates the driver driving model based on the newly acquired vehicle information.

  In step S411, the driving history recording unit 31 determines whether the ignition switch is turned off and the vehicle has finished driving. When the vehicle has not finished driving, the process returns to step S401, and when the vehicle has finished driving, the driver alert processing according to the present embodiment is finished.

[Effect of the embodiment]
As described above in detail, in the driver alert device 3 according to the present embodiment, when the vehicle approaches a right / left turn point or a branching / merging point, the reference driving model and the driver driving model are compared. When it is determined that alerting is necessary, alerting is given to the driver before the vehicle enters the right / left turn point or branch junction. As a result, it is possible to call attention in advance at a right / left turn point or a branching / merging point.

  Further, the driver alerting device 3 according to the present embodiment determines that the vehicle has approached a right / left turn point or a branch / merging point when the direction indicator of the vehicle is activated. Accordingly, the timing at which the vehicle turns right or left or branches and joins can be reliably detected, so that the driver can be alerted before the vehicle enters the right or left turn or branch and junction.

  Furthermore, the driver alerting device 3 according to the present embodiment determines that the vehicle has approached the right / left turn point or the branch merge point when the navigation device guides the right / left turn or branch merge point. Thereby, since the timing at which the vehicle turns right or left or branches and joins can be predicted in advance, it is possible to alert the driver before the vehicle enters the right or left turn or branch and join point.

  Further, the driver alert device 3 according to the present embodiment calculates a reference driving model by statistically processing the vehicle information of the driver with high safety. Thereby, the safety | security in the right-and-left turn point and a branch merge point can be improved.

  Furthermore, the driver alert device 3 according to the present embodiment includes the rotation angle of the driver's head in the reference driving model and the driver driving model. Thereby, since the presence or absence of the safety check by a driver | operator's visual observation can be confirmed, the safety | security in the right-and-left turn point and a branch merge point can be improved.

  The above-described embodiment is an example of the present invention. For this reason, the present invention is not limited to the above-described embodiment, and even if it is a form other than this embodiment, as long as it does not depart from the technical idea of the present invention, it depends on the design and the like. Of course, various modifications are possible.

DESCRIPTION OF SYMBOLS 1 Driver alert system 3 Driver alert device 5 Vehicle 7 Server 9 Probe information database 11 GPS receiver 13 Camera 15 Speed sensor 17 Rudder angle sensor 19 Accelerator sensor 21 Brake switch 23 Direction indicator 25 Navigation device 27 Vehicle control part 31 Driving history recording unit 33 Information acquisition unit 35 Driver driving model calculation unit 37 Attention determination unit 39 Attention execution unit

Claims (6)

A driver alerting method in which the controller alerts the driver of the vehicle at a right / left turn point where the vehicle turns right and left and a branch / merging point where the vehicle branches or merges,
The controller is
By obtaining from the server a reference driving model calculated for each of the right and left turn points and the branch and merge points by statistically processing vehicle information collected from a plurality of vehicles,
A driver driving model is calculated for each of the right / left turn points and the branch / merge points by statistically processing the vehicle information collected for each driver,
When the vehicle approaches the right / left turn point or the branch / merge point, the vehicle compares the reference driving model with the driver's driving model and determines that an alert is required. A driver alert method characterized by alerting the driver before entering the point.   2. The driver alert method according to claim 1, wherein when the direction indicator of the vehicle is activated, the controller determines that the vehicle has approached the right / left turn point or the branch / merging point.   3. The controller according to claim 1, wherein the controller determines that the vehicle has approached the right / left turn point or the branch / merging point when the navigation device guides a right / left turn or branch / merging point. 4. Driver alert method.   4. The driver alert method according to claim 1, wherein the reference driving model is calculated by statistically processing vehicle information of a driver with high safety.   5. The driver alerting method according to claim 1, wherein the reference driving model and the driver driving model include a rotation angle of a driver's head. A driver alert device that alerts a driver of a vehicle at a right / left turn point where the vehicle turns right and left and a branch / merging point where the vehicle branches or merges,
By obtaining from the server a reference driving model calculated for each of the right and left turn points and the branch and merge points by statistically processing vehicle information collected from a plurality of vehicles,
A driver driving model is calculated for each of the right / left turn points and the branch / merge points by statistically processing the vehicle information collected for each driver,
When the vehicle approaches the right / left turn point or the branch / merge point, the vehicle compares the reference driving model with the driver's driving model and determines that an alert is required. A driver alert device that alerts a driver before entering a spot.

Images