JP5691967B2 - Sleepiness prediction device - Google Patents

Description

  The present invention relates to a drowsiness prediction apparatus that predicts drowsiness of a driver while driving a vehicle, and more specifically, when a movement route of a vehicle is set, the current value of the drowsiness level of the driver detected during movement of the movement route is set. The present invention relates to a drowsiness prediction device that predicts drowsiness of a driver thereafter.

  Conventionally, various techniques for detecting a driver's sleepiness level (which takes a larger value as sleepiness becomes stronger) based on the driver's heart rate, facial expression, and the like have been proposed. As an application method of the drowsiness level detected by using such a technique, in a so-called car navigation device that guides the travel route of the vehicle to the destination, the arrival of the vehicle predicted to increase the drowsiness level of the driver It has been proposed to present the position as a drowsiness attention area (see, for example, Patent Document 1).

JP 2010-140358 A

  However, in the technique of Patent Document 1, it is assumed that the drowsiness level of the driver detected at any time increases at a similar rate along the time series. However, the actual drowsiness level does not increase depending only on the driving time, but the increase rate differs between driving on an expressway and driving on a general road, and the increase rate differs depending on the presence or absence of traffic. Therefore, in the technique described in Patent Document 1, the driver's awakening is caused by a sudden increase in the driver's drowsiness level due to a smoothly traveling vehicle entering a traffic jam location, or when the vehicle goes down from a highway to a general road. It is impossible to predict that the drowsiness level will decrease. Therefore, an object of the present invention is to provide a drowsiness prediction device that can predict a drowsiness state of a driver satisfactorily by referring to the form of a road constituting a travel route.

The drowsiness prediction device of the present invention, which has been made to achieve the above object, uses the current value of the drowsiness level that takes a larger value as drowsiness becomes stronger as the current value of drowsiness level as a drowsiness level current value. For a combination, a database that stores a parameter that expresses how much the driver's drowsiness level rises from the current value of the drowsiness level when the vehicle continues to travel on the road of the form, and a vehicle travel route Is set, road form acquisition means for acquiring the form of each road constituting the moving route, sleepiness level detection means for detecting the sleepiness level current value of the driver, and position detection for detecting the position of the vehicle And a position detected by the position detection means when the sleepiness level detection means detects the sleepiness level current value as a sleepiness detection position. The parameter corresponding to the road form after the drowsiness detection position among the road forms acquired by the road form acquisition means and the driver's sleepiness level current value detected by the sleepiness level detection means And drowsiness predicting means for predicting how far the driver's drowsiness level will increase when the vehicle continues to travel along the travel route by obtaining from the database.

In the drowsiness prediction apparatus of the present invention configured as described above, the database stores the number of distances that the driver keeps driving on the road of the form for each combination of the form of the road and the current value of the drowsiness level of the driver. A parameter that numerically represents whether the sleepiness level rises from the current value of the sleepiness level is stored in association with each other. And a road form acquisition means acquires the form of each road which comprises the movement route, when the movement route of a vehicle is set. The sleepiness level detection means detects the driver's sleepiness level current value, and the position detection means detects the position of the vehicle.

Therefore, the sleepiness prediction means relates to a road after the sleepiness detection position (the position of the vehicle when the sleepiness level detection means detects the sleepiness level current value) among the road forms acquired by the road form acquisition means. The parameter corresponding to the detected sleepiness level current value is acquired from the database. Then, by acquiring the parameter, the sleepiness prediction means predicts how long the driver continues to travel along the travel route, and the driver's sleepiness level increases . The drowsiness exhibited by the driver varies greatly depending on the form of the road that constitutes the travel route of the vehicle (for example, whether the road is an expressway or a general road). Therefore, in the present invention, the sleepiness prediction means refers to the form of each road constituting the travel route after the sleepiness detection position, and predicts sleepiness while moving along the travel route from the corresponding parameter. Therefore, in the present invention, it is possible to predict well how the sleepiness level of the driver changes from the sleepiness level current value.

Further, the present invention sets the value of the sleepiness level, which takes a larger value as sleepiness becomes stronger, as the sleepiness level current value as the current value of the sleepiness level. A database in which parameters related to predicted values are stored in association with each other, road form acquisition means for acquiring the form of each road constituting the movement route when the vehicle's movement route is set, and the driver's drowsiness level current value Drowsiness level detection means for detecting, position detection means for detecting the position of the vehicle, and the position detected by the position detection means when the drowsiness level detection means detects the drowsiness level current value as a sleepiness detection position, Of the road forms acquired by the road form acquisition means, those related to the road after the drowsiness detection position, and the drowsiness level detection Sleepiness prediction means for predicting sleepiness of a driver moving on the movement path after the sleepiness detection position by acquiring the parameter corresponding to the driver's sleepiness level current value detected by the stage from the database; An external environment acquisition means for acquiring an external environment including at least any one of traffic information relating to a road on the moving route after the sleepiness detection position , temperature, weather, or time; Driver information detection means for detecting the current value of physical condition as driver information, the database, for each combination of the external environment, the driver information, the road form and the sleepiness level current value, The parameters are stored in association with each other, and the drowsiness prediction unit is configured to store the external environment acquired by the external environment acquisition unit and the driver information. Driver information detected by the detecting means, information relating to the road after the drowsiness detection position among the road forms acquired by the road form acquiring means, and the present driver's sleepiness level detected by the sleepiness level detecting means the parameters corresponding to the value, by obtaining from the database may be one characterized by predicting drowsiness of the driver during movement of said movement path. In this case, the drowsiness prediction means matches the external environment acquired by the external environment acquisition means and the driver information detected by the driver information detection means (that is, the current value of the physical condition of the driver) with the above-described road form. And obtain the parameters corresponding to those combinations from the database. For this reason, the drowsiness prediction means can predict the drowsiness of the driver more accurately based on the acquired parameter.

  Further, the drowsiness prediction means may predict a position on the moving route where the drowsiness level is predicted to rise. And in that case, you may further provide the display means which displays the said movement path | route on the map with the said position which the said drowsiness prediction means predicted. In that case, since the position on the moving route where the drowsiness level is predicted to rise is visually displayed on the map together with the moving route by the display means, the driver can be better alerted. This makes it easier to take measures to maintain an arousal state.

  Further, as described above, when the drowsiness prediction unit predicts the position where the drowsiness level is predicted to increase, the position detected by the position detection unit and the drowsiness prediction unit after the drowsiness prediction unit predicts the position. If the present value of the drowsiness level detected by the drowsiness level detection means does not increase until the predicted position coincides with the predicted position, it may further comprise drowsiness overcome notification means for informing the driver to that effect. . In this case, even if the drowsiness prediction means predicts that the driver's drowsiness level will increase at the position, the drowsiness level will be maintained even if the vehicle travels to that position and the position detected by the position detection means matches the position. When there is no increase, the sleepiness overcoming notification means is notified. Therefore, in this case, the driver can obtain a sense of accomplishment overcoming drowsiness, and can be motivated to prevent drowsiness.

  The road form acquisition means divides each road constituting the travel route into a plurality of preset segments to obtain the form for each segment, and the sleepiness prediction means constitutes the travel route. The sleepiness may be predicted by obtaining the parameters corresponding to the form of each segment of the road from the database. In this case, each road constituting the moving route is divided into segments, and the form and parameters are acquired for each segment, so the sleepiness prediction means can predict the driver's sleepiness state more accurately. it can.

  In addition, the form of the road includes whether the road is an expressway or a motorway, the radius of curvature of the road, the presence or absence of a tunnel on the road, the length of the tunnel on the road, the number of tunnels on the road Either the number of turns on the road, the number of traffic lights on the road, whether the road is in an urban area or a rural area, or the road is in a flat area or a mountain area It may be defined by one or any combination thereof.

  The road further comprises route setting means for storing road data relating to the position and form of the road, and setting a movement route of the vehicle to the destination based on the road data when a destination is instructed. The form acquisition means may acquire the form of each road constituting the movement route based on the road data when the movement route of the vehicle is set by the route setting means. The drowsiness prediction device of the present invention may execute the above-described processing on the vehicle movement route set outside the device, but includes route setting means for setting the vehicle movement route to the destination. When the process is performed on the movement route set in the setting unit, a series of processes from the setting of the movement route to the prediction of sleepiness can be performed collectively.

  In addition, the present invention may further include a road form detection unit that detects a form of a road on which the vehicle is running during driving of the vehicle, and a point in time when the sleepiness level detected by the sleepiness level detection unit is increased last time or The position detected by the position detecting means between the starting point and the rising point, starting from the time when the vehicle starts to travel, the rising point when the sleepiness level detected by the sleepiness level detecting means is further increased The parameter is calculated based on the travel distance of the vehicle corresponding to the change of the vehicle, the form detected by the road form detection means between the starting point and the rising point, and the starting point to the rising point Database updating means for storing in the database in association with the sleepiness level detected by the sleepiness level detection means. In this case, a parameter corresponding to the rise in sleepiness level detected by the sleepiness level detection means during actual driving is calculated, and the database is updated by the database update means with the parameter. The parameters calculated in this manner well reflect the circumstances specific to the driver, and the drowsiness predicting means can predict the drowsiness of the driver more accurately based on the parameters updated in this way.

  In this case, the database may store an initial value in advance as the parameter corresponding to each form and the sleepiness level current value, and the value of the parameter may be sequentially updated by the database update unit. In that case, for example, even when a road in a form in which the driver has never traveled by the vehicle, such as a driver who has never traveled by a vehicle on a highway, is included in the travel route, By using the initial value of the parameter, the drowsiness prediction means can predict the drowsiness of the driver satisfactorily.

It is a block diagram showing the structure of the drowsiness prediction apparatus to which this invention was applied. It is a flowchart showing the navigation process which a drowsiness prediction apparatus performs. It is a flowchart showing the all road pattern memory | storage process of a navigation process. It is a flowchart showing the present information acquisition process of a navigation process. It is a flowchart showing the external environment information acquisition process of a present information acquisition process. It is a flowchart showing the sleepiness induction area prediction process of a navigation process. It is explanatory drawing showing the database used by the sleepiness induction area prediction process. It is a flowchart showing the sleepiness induction area presentation process of a navigation process. It is explanatory drawing showing the example of a display of the sleepiness induction area of a sleepiness induction area presentation process. It is explanatory drawing showing the other example of a display of a sleepiness induction area. It is a flowchart showing the database update process which a drowsiness prediction apparatus performs. It is a flowchart showing the sleepiness overcoming point display process which a sleepiness prediction apparatus performs. It is explanatory drawing showing the example of a display of the sleepiness overcoming point display process.

[Overall configuration of sleepiness prediction device]
Next, embodiments of the present invention will be described with reference to the drawings. FIG. 1 is a block diagram showing the configuration of a drowsiness prediction device 10 to which the present invention is applied together with peripheral devices. In addition, you may comprise the drowsiness prediction apparatus by which the whole including a peripheral device was integrated as a system. The drowsiness prediction device 10 is configured as a processing device mounted on a vehicle including a CPU, a ROM, a RAM, and the like, and as shown in FIG. 1, a drowsiness induction area prediction unit 11 that predicts a sleepiness induction area on a planned travel route. And a storage unit 12 composed of a hard disk or the like storing various data such as a database used for the prediction.

  The sleepiness prediction device 10 is connected to a navigation device (navigation) 1 mounted on the vehicle so that information can be input to the sleepiness induction area prediction unit 11. The navigation device 1 stores the position (latitude and longitude) and shape of the road in units of segments (for example, equally spaced segments or so-called VICS links (registered trademark)), and the destination is indicated. Sometimes, the travel route of the vehicle to the destination is searched, and guidance is performed while the position of the vehicle is detected by the GPS receiver provided by itself.

  Also connected to the drowsiness prediction device 10 are various biological sensors 2 for detecting various biological information such as heart rate and body temperature of the driver, such as sensors and thermo cameras installed on the steering wheel and seat, via the physical condition determination unit 3. A camera 4 that is installed on a steering column (not shown) and captures a face image of a driver traveling in the vehicle is also connected via a sleepiness level determination unit 5. The physical condition determination unit 3 is configured as a processing device including a CPU, a ROM, and a RAM, and determines the physical condition of the driver in three stages: good, normal, and abnormal based on various biological information detected by the various biological sensors 2. The drowsiness level determination unit 5 is configured as a processing device including a CPU, a ROM, and a RAM, and based on the driver's face image photographed via the camera 4, the driver's drowsiness level is classified into 6 levels (0 to 5). The larger the number, the stronger the sleepiness.

  Furthermore, an external environment sensor 6 that acquires an external environment is connected to the sleepiness prediction apparatus 10 via an external environment determination unit 7. The external environment sensor 6 includes a plurality of sensors such as a rain sensor, a temperature / humidity sensor, and a clock mounted on the vehicle. The external environment determination unit 7 is configured as a processing device including a CPU, a ROM, and a RAM. judge.

[Details of the navigation process]
Next, a navigation process executed by the sleepiness induction area prediction unit 11 in cooperation with the navigation device 1 will be described. FIG. 2 is a flowchart showing the main routine of the navigation process. This process is performed by a program stored in the ROM by the CPU constituting the sleepiness induction area prediction unit 11 when the driver gets into the vehicle and instructs the navigation apparatus 1 to perform route guidance in the sleepiness induction area prediction mode. It is executed based on.

  As shown in FIG. 2, in this process, a process for displaying a message for the driver to input a destination on the screen by sending a signal to the navigation device 1 in S1 (S represents a step: the same applies hereinafter). Is made. When the driver inputs the destination with the voice or displayed button in response to the message, a well-known route search is executed by the processing unit including the CPU, ROM, and RAM provided in the navigation device 1, and the driver plans to pass When the route (movement route) is determined, the data of the scheduled route is returned to the sleepiness induction area prediction unit 11. The drowsiness induction area prediction unit 11 executes the next all road pattern storage process (S3) by receiving the data of the planned travel route in S2 following S1.

  FIG. 3 is a flowchart showing in detail the all road pattern storage process of S3. This process determines the road pattern for each equally spaced distance (segment) for the planned travel route for which the determination result has been received in S2, and determines the road pattern of all segments on the planned travel route and the road pattern switching unit. This is a process of storing the raised flag in the storage unit 12.

  As shown in FIG. 3, in this process, first, in S31, the planned travel route determined in S2 is classified into road segments (for example, high-speed automobile national roads or automobile-only roads, etc.) for each equal distance (segment). The combination of whether the road is a local area or an urban area) is obtained from the navigation information (information stored in the database of the navigation device 1). Next, in S32, the terrain (for example, whether it is a flat part or a mountain part) is acquired from the navigation information for each segment for which the road classification is acquired in S31. Next, in S33, the road shape (for example, whether the tunnel is a straight line or a curve) is acquired from the navigation information for each segment for which the road classification is acquired in S31. If the road shape is a curve, the radius of curvature is also acquired. In subsequent S34, the set of road segment / terrain / road shape information acquired in S31 to S33 is stored in the storage unit 12 as a road pattern of each segment.

  In S35, a flag is set in the road pattern switching section stored in S34, and all the flags are stored in the storage section 12 together with the data of the planned travel route and the road pattern, and the process proceeds to S4 in FIG. To do.

  In S4, the current information, that is, the current driver's physical condition and sleepiness level, the acquisition of the current road pattern, and the acquisition process of the current external environment information are executed. FIG. 4 is a flowchart showing the current information acquisition process in detail. As shown in FIG. 4, in this process, first, in S <b> 41, an operation is instructed to the above-described various biological information sensors 2, thereby acquiring biological information such as the body temperature and heartbeat of the driver. In subsequent S42, the physical condition (good, normal, or abnormal) of the driver determined by the physical condition determination unit 3 based on the biological information acquired by the biological information sensor 2 is read.

  In S <b> 43, when the operation is instructed to the camera 4, the driver's face image is acquired by the camera 4. In subsequent S44, the driver's current sleepiness level determined by the sleepiness level determination unit 5 in six steps based on the driver's face image captured (acquired) by the camera 4 is read. For the determination of the drowsiness level, a well-known method using changes in the driver's facial expression, eyelid opening, number of blinks, or the like can be applied. Alternatively, the drowsiness level may be determined using both the driver biometric information acquired in S41 and the driver face image acquired in S43. The sleepiness level is classified into a plurality of levels (for example, 6 levels) at regular intervals from the awake state to the dozing state. The sleepiness level may be classified into two levels, but is preferably classified into at least three levels.

  In S45, the current location of the vehicle is acquired via the GPS receiver included in the navigation device 1, and the road pattern of the currently traveling segment on the planned route on which the determination result is received in S2 is stored in S3 in S3. It is called from the road pattern memorized in In subsequent S46, external environment information acquisition processing for acquiring external environment information such as a rainfall state, external temperature humidity, and time is executed via the external environment sensor 6. FIG. 5 is a flowchart showing in detail the external environment information acquisition process.

  As shown in FIG. 5, in this process, an operation is instructed to the external environment sensor 6 in S461, so that the current rainfall state and external temperature / humidity are acquired. In the subsequent S462, the current weather (for example, clear, cloudy, rain, snow, etc.) is determined via the external environment determination unit 7 from the information on the rainfall state and the external temperature and humidity acquired in S461. In S463, the current time is acquired from a clock which is one of the external environment sensors 6. Note that the time may be acquired from the navigation device 1 in S463.

  In subsequent S464, the current time zone (for example, 8:00 to 12: 00/12: 00 to 16:00) is determined from the time acquired in S463. In S465, traffic congestion information on the current scheduled route is acquired from a road traffic information processing unit (for example, a processing unit related to VICS (registered trademark)) of the navigation device 1. In S466, the current weather determined in S462, the current time zone information determined in S464, and the set of traffic jam information acquired in S465 are stored in the storage unit 12 as current external environment information. Stored, and the process proceeds to S47 in FIG.

  In S47, the physical condition of the driver determined in S42, the current sleepiness level of the driver determined in S44, the current road pattern called in S45, and the current external environment information stored in S46 are “current It is stored in the storage unit 12 as a data set of “information”, and the process proceeds to S5 in FIG. In addition, as the current external environment information, a continuous travel distance (or time) during which the vehicle continuously travels may be additionally used.

  In S5, the drowsiness induction area prediction process is executed as follows, and the drowsiness induction area presentation process is executed in S6 based on the prediction result. FIG. 6 is a flowchart showing in detail the sleepiness induction area prediction process of S5.

  As shown in FIG. 6, in this process, in S51, it is determined whether or not “current information” is already stored in the storage unit 12 in S47 described above. If “current information” is already stored in the storage unit 12, that is, if the vehicle is traveling (S51: Y), the process proceeds to S52, where “current information” newly stored is stored. The existing “current information” is compared. At this time, each item of sleepiness level, road pattern (for example, road classification, topography, road shape) and each item of external environment information (for example, weather, time zone, traffic jam situation) are compared. .

  In subsequent S53, it is determined whether or not there is a difference between at least one item among the items compared in S52. If there is a difference in at least one item (S53: Y), the process proceeds to S54, and the driver's drowsiness level, the running road pattern, or the external environment information is changed from the previous information. , Flag f is set to 1. On the other hand, if there is no difference in any of the items (S53: N), the process proceeds to S55, and the driver's sleepiness level, the running road pattern, and the external environment information are changed from the immediately preceding information. Assuming that there is no flag, after the flag f is reset to 0, the process proceeds to the sleepiness induction area presenting process of S6 (see FIG. 2). If it is determined in S51 that the existing “current information” does not exist (S51: N), that is, if the vehicle is immediately after departure, the process directly proceeds from S51 to S54.

  When the flag f is set to 1 in S54, in the following S56, the road pattern switching flag stored in the storage unit 12 in S3 is present in the traveling direction of the vehicle on the planned travel route, and the current location of the vehicle It is determined whether or not there is a traffic jam between the nearest flag and the current location. Note that the presence or absence of traffic jams is determined by reading the latest information from the road traffic information processing unit of the navigation device 1 as in S465 described above. In subsequent S57, a data set that matches the “current information” and the traffic jam presence / absence information determined in S56 is extracted from the database stored in advance in the storage unit 12.

  That is, in the database stored in the storage unit 12 in advance, as illustrated in FIG. 7, for example, how long the vehicle travels for a combination of weather / time zone / physical condition / road pattern / congestion (Continuation distance) A data set in which how sleepiness level transitions (sleepiness level transition) is associated is stored for each combination. In S57, the most recent “current information” and the presence / absence information on the traffic jam determined in S56 and the sleepiness level before the transition are extracted from the various combinations of the databases.

  The items shown in Table 1 below are prepared as the items of weather, time zone, physical condition, road pattern, and traffic jam. Further, as for the continuation distance and sleepiness level transition, data is updated while the vehicle is traveling by a database update process described later, but appropriate values are set as initial values for each combination. Further, in the road pattern of Table 1, the rural / urban areas are classified with a view of landscape rather than the terrain, and the flat / mountainous areas are classified with emphasis on terrain such as undulations.

  In S57, if the item of traffic jam is different between the “current information” and the determination result of S56, for example, even if “current information” is “congested: no”, it is determined that “congested: present” in S56. If so, the data sets of “congestion: present” and “congestion: none” are extracted. In subsequent S58, only the data set from the current sleepiness level until the sleepiness level rises by a predetermined level (for example, one stage) (becomes sleepy) is extracted from the data set extracted in S57. In S59, an average value (average distance) of the continuation distance is calculated for the data set extracted in S58. When there are a plurality of data sets with different traffic jam items, the average distance is calculated for each jam traffic item (presence / absence). Similarly, when the number of data sets extracted in S58 is one, the average value calculation process (S59) is executed.

  In subsequent S510, the average distance calculated in S59 is compared with the distance between the current position and the road pattern switching flag that exists in the traveling direction and is closest to the current position. If the average distance calculated in S59 is longer than the distance between the current pattern and the road pattern switching flag closest to the current position in the traveling direction, the drowsiness induction area prediction process (S5) ends and the process Shifts to the drowsiness induction area presentation processing of S6 (see FIG. 2).

  On the other hand, when the average distance calculated in S59 is closest to the current location and is shorter than the distance between the road pattern switching flag in the traveling direction and the current location (S510: Y), the process proceeds to S511. . In S511, the average distance calculated in S59 is stored in the storage unit 12 as a continuous travel distance threshold, and the process proceeds to the sleepiness induction area presentation process in S6 (see FIG. 2).

  In calculating the average distance in S59, even if “congestion: none” in the “current information”, if it is determined in S56 that “congestion: present”, the continuation distance stored in the database is calculated. The average distance may be calculated by multiplying the congestion coefficient (k) calculated by comparing the average values.

  FIG. 8 is a flowchart showing in detail the drowsiness induction area presentation process in S6 (see FIG. 2). This process is a process of presenting the sleepiness induction area on the planned travel route on the screen of the navigation device 1 as described below. As shown in FIG. 8, in this process, first, in S61, it is determined whether or not the flag f stored in the storage unit 12 is set to 1. If f = 0 (S61: N), this drowsiness induction area presentation process is terminated as it is, and the process proceeds to S7 (see FIG. 2). If f = 1 (S61: Y), the process continues. The process proceeds to S62.

  In S62, it is determined whether or not the sleepiness induction area is already displayed on the planned travel route displayed on the navigation device 1. If the sleepiness induction area is already displayed (S62: Y), after the display of the sleepiness induction area is erased in S63, the sleepiness induction area is not displayed yet (S62: N). ), The process proceeds to S64. In S63, the display color may be changed to a transparent color or the color may be changed without deleting the display. In addition, the driver may freely select the display number of past sleepiness induction areas.

  In S64, it is announced by voice that the sleepiness induction area is displayed. The announcement content may be changed according to the number of times the sleepiness induction area is presented. For example, when the sleepiness induction area is presented for the first time after the start of driving, the “sleepiness induction area has been displayed”, and when the already presented sleepiness induction area is changed, “the sleepiness induction area has been changed. It may be ” The announcement may use sound or music in addition to voice.

  In S65, the segment including the continuous travel distance threshold stored in the storage unit 12 in S511 when the current location is the base point is used as a sleepiness induction area on the planned travel route displayed on the screen of the navigation device 1. Is displayed. In S66, the history set as the sleepiness induction area is stored in the segment information in the storage unit 12 regarding the segment displayed as the sleepiness induction area, and the process proceeds to S7 (see FIG. 2). In addition, by storing the segment information in this way (S66), in the above-described announcement (S64), it is possible to make an announcement reflecting whether or not the sleepiness induction area has changed and the magnitude and direction of the change. it can. Further, S66 may be omitted.

  FIG. 9 is an explanatory diagram illustrating a display example of the drowsiness induction area executed in S65. In the example shown in FIG. 9, the road pattern changes to I, II, III while the vehicle moves through the segments A, B,. Currently, the vehicle is driving on the first segment of road pattern II with the driver's drowsiness level of 1, and the segment that includes the continuous mileage threshold is changed from the fourth segment of road pattern II to the third segment. When changed (S61: Y), the highlight display (not shown) for the fourth segment is deleted, and the third segment is highlighted as the sleepiness induction area.

  FIG. 10 is an explanatory diagram illustrating a display example of the sleepiness induction area when the above-described congestion coefficient (k) is used. In FIG. 10, it is assumed that a traffic jam occurs at a location indicated by a thick line. In this way, when the traffic situation has changed (for example, changed to traffic jam) in the middle of the planned traffic route, the item of traffic jam is determined by the “current information” stored in the storage unit 12 and the determination result of S56 described above. May be different. In such a case, as shown in FIG. 10, a continuous travel distance threshold L corresponding to “congestion: none” and a continuous travel distance threshold M corresponding to “congestion: present” are expressed as a traffic congestion coefficient (k). , The segment including the continuous travel distance threshold is highlighted as the sleepiness induction area, with the continuous travel distance threshold being M + k × (LM). The traffic congestion coefficient (k) may be determined by dividing the data into two parts according to the presence or absence of traffic congestion and comparing the respective average duration distances in a data set group other than the traffic congestion information in the database.

  Returning to FIG. 2, when the drowsiness induction area presentation process in S6 ends, it is determined in S7 whether or not the vehicle is traveling. When the vehicle is traveling (S7: Y), the process proceeds to S4 described above, and the processes of S4 to S7 are repeatedly executed at predetermined time intervals. Whether or not the vehicle is running is determined by using vehicle speed sensors, acceleration sensors, steering and pedal operation information, and the like mounted on the vehicle. On the other hand, when the vehicle is not traveling, that is, when the vehicle stops (S7: N), the process proceeds to S8. In S8, the “current information” stored in the storage unit 12 is deleted, and all of the navigation processing ends.

  Note that the determination in S7 may be made by determining whether or not the destination has been reached via the navigation device 1. In that case, even when the vehicle stops on the route to the destination, an affirmative determination is made in S7, and the processes in S4 to S7 are repeatedly executed at predetermined time intervals. And when it arrives at the destination (S7: N), a process transfers to S8.

[Database update processing]
Next, a database update process for updating the aforementioned database in the storage unit 12 while the vehicle is running will be described. FIG. 11 is a flowchart showing database update processing. Note that this processing is performed by the CPU of the drowsiness induction area prediction unit 11 in the program stored in the ROM while the guidance is performed by the navigation device 1 regardless of whether the guidance is based on the navigation processing described above. This process is executed based on the above.

  As shown in FIG. 11, in this process, first, in S81, the camera 4 is instructed to shoot the face image of the running driver, and in S82, the driver's face image taken by the camera 4 is also displayed. At the same time, the sleepiness level of the driver determined by the sleepiness level determination unit 5 in 6 stages is read. In subsequent S83, it is determined whether or not there is a change in the current sleepiness level as compared with the previous sleepiness level. If there is no change (S83: N), the process proceeds to S81 described above.

  On the other hand, when there is a change in the sleepiness level of the driver (S83: Y), the process proceeds to S84. In S84, the road pattern having the highest appearance rate is acquired from the navigation device 1 among the road patterns of the segments on which the vehicle has traveled until the driver's drowsiness level changes. Then, the road pattern, the continuous travel distance of the road pattern acquired from the navigation device 1 and the presence / absence of traffic congestion during travel, and the biosensor 2 and the external environment sensor 6 during travel are acquired. The physical condition, external environment, and time zone of the driver are stored in the database of the storage unit 12 as a set together with the transition information of the sleepiness level. In S85, it is determined whether or not the vehicle is traveling. If the vehicle is traveling (S85: Y), the process proceeds to S81 described above. If the vehicle is not traveling (S85: N), the process is performed. Exit once.

  In S84, the position of the vehicle at the time when the processing is performed is stored at least in preparation for the case where an affirmative determination is made in S83 and the process proceeds to S84. Further, as described above, the database of the storage unit 12 stores the continuation distance and the sleepiness level transition in association with various combinations of weather, road pattern, etc., but first a data set is created in S84. If the data set has been set, the data set created in S84 is overwritten on the data set as the initial value. When a data set is created for the same combination of road patterns and the like after the second time, the data set may be overwritten or additionally written in the database together with a time stamp. In the latter case, in S59 described above, instead of taking an average, a data set having the latest time stamp may be extracted.

[Effects of Embodiments and Modifications]
As described above, in the above-described embodiment, the storage unit 12 determines the drowsiness level when the vehicle continuously travels (continuation distance) for the combination of weather, time zone, physical condition, road pattern, and traffic jam. It has a database that stores how it transitions (drowsiness level transition) in association with each other. And since the drowsiness induction area prediction unit 11 predicts the drowsiness induction area using the database, the sleepiness induction area is improved by reflecting the weather, the time zone, the physical condition of the driver, the road pattern, the presence or absence of traffic, and the like. Can be predicted. In addition, since the prediction result is displayed on the screen of the navigation device 1 as illustrated in FIG. 9, the driver can be better alerted, and the driver can take measures to maintain the awake state. It becomes easy.

  Moreover, since the data set memorize | stored in the database of the memory | storage part 12 is sequentially updated to the data according to the driver by the database update process of FIG. 11, a sleepiness induction area can be estimated still more correctly. The database items may include the number of right / left turn points and the number of traffic lights as road patterns. In this case, the sleepiness induction area can be predicted more accurately.

  In the embodiment, the database in the storage unit 12 corresponds to the database, and the navigation device 1 corresponds to the route setting unit. Of the processes executed by the drowsiness induction area prediction unit 11, S3 is the road form acquisition means, S43 and S44 are the drowsiness level detection means, and among the processes of S45, the vehicle is connected via the GPS receiver of the navigation device 1. The process of acquiring the current location is the position detection means, S5 and S6 are drowsiness prediction means, S46 is the external environment acquisition means, S41 and S42 are driver information detection means, S65 is the display means, The process for acquiring the road pattern corresponds to the road form detection means, and the other processes in S84 correspond to the database update means.

  Further, the present invention is not limited to the above-described embodiment, and can be implemented in various forms without departing from the gist of the present invention. For example, instead of or in parallel with the display of the sleepiness induction area described above (S65), the driver may be warned when the current location approaches within a predetermined distance from the sleepiness induction area.

  Also, if the driver's drowsiness level has not increased when reaching the sleepiness induction area, it is considered that the driver has overcome drowsiness through self-help efforts (suppressing the increase in drowsiness). May be given to the driver. In this case, the sleepiness overcoming point is displayed on the screen of the navigation device 1 and notified to the driver. The display can give the driver a sense of accomplishment and encourage motivation to prevent drowsiness.

  FIG. 12 is a flowchart showing drowsiness overcome point display processing (corresponding to drowsiness overcome notification means) that enables such processing. This process is executed based on a program stored in the ROM by the CPU constituting the drowsiness induction area prediction unit 11 in parallel with the above-described navigation process, and is performed at predetermined time intervals (or for one segment of the vehicle). Repeated every time is run).

  As shown in FIG. 12, in this process, first, segment information of the current location is acquired from the storage unit 12 in S91. That is, information on whether or not the segment at the current location is a segment that has been stored as a sleepiness induction area in S66 in the past is acquired. In subsequent S92, it is determined whether or not there is a history displayed as the sleepiness induction area in the segment information acquired in S91, and if there is a history displayed as the sleepiness induction area in the segment of the current location (S92: Y), The process proceeds to S93. Note that this history is limited to the history from the time point when the destination is set in S1 and the traveling is started.

  In S93, it is determined whether or not the current sleepiness level is equal to or lower than a predetermined level. When the current sleepiness level is equal to or lower than the predetermined level (S93: Y), the process proceeds to S94, the sleepiness overcoming point is displayed on the screen of the navigation device 1, and the process ends.

  For example, as illustrated in FIG. 13A, the vehicle is running on the first segment of the road pattern II and the third segment of the road pattern II is the drowsiness induction area as in the example of FIG. Is displayed. Then, as illustrated in FIG. 13B, when the sleepiness level is 0 when the segment displayed as the sleepiness induction area is reached (S92: Y, S93: Y), For example, 1 pt is displayed (S94). The drowsiness overcoming points may be added, for example, as 1 pt (points) when drowsiness is overcome for each one of the drowsiness induction areas.

  On the other hand, when the segment of the current location is a segment without a history that has been displayed as a sleepiness induction area in the past (S92: N), or when the current sleepiness level is not less than a predetermined level (S93: N), this sleepiness The overcoming point display process ends as it is.

  In the above embodiment, alerting is performed by displaying the drowsiness-inducing area. However, not only alerting but also a safe route that does not make you sleepy, while driving to the driver via the navigation device 1 You may suggest. Furthermore, in the above embodiment, the continuation distance is stored in the database as a parameter, but various other forms can be considered as the parameter. For example, the fatigue level accumulated every time 1 km is traveled (may be a sleepiness level classified into several tens of stages) is stored in the database as a parameter, and the sleepiness induction area is estimated by integrating the fatigue level. Also good. In this case, the fatigue level is gradually accumulated even when the road pattern changes, and drowsiness can be predicted. Accordingly, the drowsiness induction area ahead of the road pattern switching flag can also be predicted.

  Furthermore, in the said embodiment, although the drowsiness prediction apparatus 10 was connected to the navigation apparatus 1 from the beginning, you may add to a general navigation apparatus later. In that case, it may be impossible to work on the screen of the navigation device because it is a retrofit, but even in that case, if the following control is performed by providing a speaker or the like, This completes the process. For example, it may be possible to control such as issuing a message prompting a break such as “Would you like to take a break soon?” When the vehicle reaches the drowsiness induction area.

  Still further, the travel route of the vehicle referred to in the present invention is not necessarily searched by the navigation device. For example, the moving route may be set manually such as “1. Turn right at the intersection of XX, turn left at the intersection of 2.xx. Even in this case, if the drowsiness prediction apparatus includes navigation information, drowsiness prediction can be performed in the same manner as in the above embodiment. In the database update process of FIG. 11, the road pattern is acquired from the navigation device 1, but the road pattern may be acquired from the steering operation amount, the accelerator operation amount and speed, the information on the ETC onboard equipment, and the like. Furthermore, the roads that make up the travel route do not need to be subdivided as in the VICS link. For example, when the form of the road is only a large classification such as a highway, a main local road, and other general roads, The unit from the joining point to the leaving point of the travel route to the road may be a unit.

DESCRIPTION OF SYMBOLS 1 ... Navigation apparatus 2 ... Biosensor 3 ... Physical condition determination part 4 ... Camera 5 ... Drowsiness level determination part 6 ... External environment sensor 7 ... External environment determination part 10 ... Drowsiness prediction apparatus 11 ... Drowsiness induction area prediction part 12 ... Memory | storage Part

Claims (10)

The current value of the sleepiness level, which takes a larger value as sleepiness becomes stronger, is the current value of sleepiness level, and the distance between the road form and the driver's current sleepiness level is the distance between the road form and the driver. If it continues, a database that stores a parameter that expresses numerically whether the sleepiness level of the driver will rise from the current value of the sleepiness level , and
Road form acquisition means for acquiring the form of each road constituting the movement route when the movement route of the vehicle is set;
Drowsiness level detection means for detecting the drowsiness level current value of the driver;
Position detecting means for detecting the position of the vehicle;
The position detected by the position detecting unit when the drowsiness level detecting unit detects the current value of drowsiness level is defined as the drowsiness detection position, and after the drowsiness detection position in the road form acquired by the road form acquisition unit. By acquiring from the database the parameters corresponding to the road and the driver's drowsiness level current value detected by the drowsiness level detection means, the vehicle continues to travel for a distance along the travel route. And a drowsiness prediction means for predicting whether the drowsiness level of the driver is increased ,
A drowsiness prediction device characterized by comprising: Corresponds to the parameter related to the predicted value of the driver's sleepiness level for the combination of the road form and the driver's sleepiness level current value, with the current value of the sleepiness level taking a larger value as sleepiness becomes stronger. With the database stored and attached,
Road form acquisition means for acquiring the form of each road constituting the movement route when the movement route of the vehicle is set;
Drowsiness level detection means for detecting the drowsiness level current value of the driver;
Position detecting means for detecting the position of the vehicle;
The position detected by the position detecting unit when the drowsiness level detecting unit detects the current value of drowsiness level is defined as the drowsiness detection position, and after the drowsiness detection position in the road form acquired by the road form acquisition unit. By acquiring the parameter corresponding to the road and the driver's sleepiness level current value detected by the sleepiness level detection means from the database, the travel route after the sleepiness detection position is moving Sleepiness prediction means for predicting driver drowsiness;
An external environment acquisition means for acquiring an external environment including at least one of air temperature, weather, time, or traffic jam information related to a road on the moving route after the drowsiness detection position;
Driver information detecting means for detecting the current value of the physical condition of the driver as driver information;
With
The database stores the parameter in association with each combination of the external environment, the driver information, the road form, and the sleepiness level current value,
The sleepiness prediction means includes the external environment acquired by the external environment acquisition means, the driver information detected by the driver information detection means, and the sleepiness detection position among the road forms acquired by the road form acquisition means. By acquiring the parameter corresponding to the current value of the drowsiness level detected by the drowsiness level detection means detected by the drowsiness level detection unit from the database, the drowsiness of the driver moving along the movement route is obtained. sleepiness prediction apparatus characterized by predicting. The sleepiness prediction means, sleepiness prediction apparatus according to claim 1 or 2, characterized in that predicting the position on the movement path which the drowsiness levels are expected to rise. Display means for displaying the movement path on the map together with the position predicted by the sleepiness prediction means;
The sleepiness prediction apparatus according to claim 3 , further comprising: The drowsiness level detected by the drowsiness level detection unit between the time when the drowsiness prediction unit predicts the position and the position detected by the position detection unit coincides with the position predicted by the drowsiness prediction unit. If the value did not rise, a drowsiness overcome notification means to notify the driver to that effect,
Further sleepiness prediction apparatus according to claim 3 or 4, characterized in that it comprises. The road form acquisition means divides each road constituting the travel route into a plurality of preset segments to acquire the form for each segment,
The sleepiness prediction means, by obtaining respectively the parameters corresponding to the form of each segment of the road constituting the moving path from the database, any claim 1-5, characterized in that predicting the sleepiness The drowsiness prediction apparatus according to claim 1. The form of the road is whether the road is an expressway or an automobile-only road, the radius of curvature of the road, the presence or absence of a tunnel on the road, the length of the tunnel on the road, the number of tunnels on the road, The number of right / left turn points on the road, the number of traffic lights on the road, whether the road is in an urban area or a rural area, or whether the road is in a flat area or a mountain area Or the drowsiness prediction device according to any one of claims 1 to 6 , wherein the sleepiness prediction device is defined by any combination. Route setting means for storing road data relating to the position and form of the road and setting a movement route of the vehicle to the destination based on the road data when a destination is instructed,
In addition,
The road form acquisition means acquires the form of each road constituting the movement route based on the road data when the movement route of the vehicle is set by the route setting means. The drowsiness prediction device according to any one of 7 . Furthermore,
Road form detecting means for detecting the form of the road on which the vehicle is running during driving of the vehicle;
The starting point is the time when the drowsiness level detected by the drowsiness level detection means last rises or the time when the vehicle starts to travel, the time when the drowsiness level detected by the drowsiness level detection means further rises, and the starting point. The parameter is calculated based on the travel distance of the vehicle corresponding to the change in the position detected by the position detection unit from the starting point to the rising point, and the parameter is calculated between the starting point and the rising point. Database updating means for storing in the database in association with the sleepiness level detected by the sleepiness level detection means between the form detected by the road form detection means and the rising point to the rising point;
The drowsiness prediction apparatus according to any one of claims 1 to 8 , further comprising: Said database, said previously stores the initial value as the parameter corresponding to the respective embodiments and the sleepiness level current value, according to claim 9, characterized in that the value of the parameter is sequentially updated by the database update means The drowsiness prediction apparatus described in 1.