JP5045374B2 - Operating state determination device - Google Patents

Description

  The present invention relates to a driving state determination device and a driving support device.

  Conventionally, it has been proposed to determine an abnormal driving state such as a driver's snoozing driving.

  Patent Document 1 discloses a technique for calculating an estimated steering value of a driver during normal driving and determining abnormal driving based on the steepness of an error distribution between the actual steering amount and the estimated value.

  In Patent Document 2, the response delay time and the deviation amount of the driver are estimated using the steering amount, the vehicle speed, and the lateral movement of the vehicle, and the abnormal state is determined by comparing the response delay time and the deviation amount in the normal state. Technology is disclosed.

Patent Document 3 discloses a technique for calculating a behavior reference and a travel locus from a vehicle lateral momentum and a vehicle speed, and determining abnormal driving based on a difference between the behavior reference and the travel locus.
JP-A-11-227491 Japanese Patent Laid-Open No. 5-85221 Japanese Patent Laid-Open No. 2001-167397

  However, the techniques of Patent Documents 1 to 3 have a problem that the road shape that can be determined is limited. Specifically, the technique of Patent Document 1 obtains a steering estimated value from a steering amount that changes from moment to moment, and the steering pattern generally increases depending on the road shape. For example, a straight line, a right curve, a left gentle curve, an S-shape, and the like have a steering pattern corresponding to each. Therefore, since the estimation accuracy of the steering estimation value greatly depends on the road shape, there is a problem that the abnormality determination accuracy also greatly depends on the road shape.

  The techniques of Patent Documents 2 and 3 calculate the behavior standard from the vehicle behavior and the vehicle speed, but do not consider the relationship between the estimated behavior standard and the road shape. Therefore, when the estimated behavior standard and the road shape are different, the abnormality determination accuracy decreases. For example, when the road shape is S-shaped, if the behavior criterion is calculated as a straight line, and the traveling locus is also a straight line, there is a problem that it is determined that the driving is normally an abnormal operation but a normal operation. In addition, when the road shape is a straight line, the behavior criterion is calculated to be S-shaped, and when the travel locus is a straight line, there is a problem that it is normally determined to be an abnormal operation although it is a normal operation.

The present invention has been proposed in order to solve the above problems, and an object thereof is to provide an operating condition determining equipment capable of determining an operating condition with high accuracy.

Invention in which the operating condition determining apparatus according to claim 1, a steering angle detecting means for detecting a steering angle by steering of the driver, as the road shape of the traveling, the predetermined distance from the vehicle and the front position of a predetermined distance from the vehicle Road shape detection means for detecting a deviation from the lane position ahead, steering angle detected by the steering angle detection means at a predetermined time after the start of driving, and detection by the road shape detection means at a predetermined time after the start of driving The storage means for storing the data of the set with the deviation as data during normal operation, and the data of the set stored in the storage means are divided into a plurality of groups according to the deviation, and the average steering angle for each group A standard deviation of the value and the steering angle is calculated, and a range in which the average value + the standard deviation is an upper limit and the average value−the standard deviation is a lower limit is defined as a normal steering region and the normal steering range. A table area was an abnormal steering area other than the operation state determination table generating means for generating a driving state determination table for determining an operating condition of the driver, the steering angle detecting means after the start of the operation the predetermined time period elapses Based on the combination of the steering angle detected by the vehicle and the deviation detected by the road shape detection means after the predetermined time has elapsed from the start of driving , and the driving condition determination table created by the driving condition determination table creator And driving state determination means for determining the driving state of the driver.

  The driving state determination device according to the present invention can determine the driving state with high accuracy by determining the driving state of the driver based on the steering amount and the road shape.

  Hereinafter, preferred embodiments of the present invention will be described in detail with reference to the drawings.

[First Embodiment]
FIG. 1 is a block diagram showing the configuration of the driving support apparatus according to the first embodiment of the present invention. The driving support device is mounted on a vehicle (hereinafter referred to as “own vehicle”), and includes a front camera 1 that images a road ahead of the vehicle, a lane recognition unit 2 that recognizes a lane on the road surface, and a deviation. A deviation calculating unit 3 for calculating, a steering angle sensor 4 for detecting a steering angle, an abnormal state determining unit 5 for determining whether or not the current steering is abnormal, and a buzzer 6 for generating an alarm sound are provided. Yes.

  The front camera 1 generates a road image in front of the vehicle. The lane recognition unit 2 recognizes the lane position of the road based on the road image generated by the front camera 1.

  Specifically, the lane recognition unit 2 first extracts lane marking candidate points from the road image. Here, binarization using the fact that the lane marking portion has higher brightness than the road surface, edge extraction, template matching considering the shape of the lane marking, spoke filter, and the like are performed. Next, the lane recognition unit 2 estimates the most probable lane position from the extracted lane marking candidate points. That is, the lane recognition unit 2 divides a parameter space composed of five parameters into small areas, and projects each area on the camera imaging surface based on a predetermined formula. Then, the lane recognition unit 2 calculates the sum of the lane marking candidate points in the area projected on the imaging surface. The value of each of the five parameters when the sum is maximized is obtained.

  The lane recognition unit 2 is described in “Study on improvement of robustness in lane detection”, Takahashi et al., IEICE Technical Report vol. 98, no. 334 (1998) is used, but other lane recognition techniques may of course be used.

  Based on the road image generated by the front camera 1 and the lane position recognized by the lane recognition unit 2, the deviation calculation unit 3 determines the future position and target of the vehicle at a distance L [m] ahead of the vehicle. The deviation ε from the course position is calculated.

  FIG. 2 is a diagram showing the relationship between the future position of the vehicle and the target course position. The future position of the host vehicle is a front position that is a distance L from the host vehicle. The target course position is the center position of the lane recognized by the lane recognition unit 2. Note that L is a distance that the driver is usually gazing at, and in this embodiment, L = 100 [m].

  Further, as shown in FIG. 2, the deviation ε represents how much the road shape on which the vehicle travels is bent with respect to a straight line. If the road shape is a straight line, the deviation ε is zero. The larger the curvature, the larger the value.

  The steering angle sensor 4 detects a steering angle σ according to the driver's steering operation. The abnormal state determination unit 5 stores a determination table for determining whether the current steering is normal or abnormal.

  FIG. 3 is a diagram illustrating a determination table. The determination table defines an area indicating normal steering or abnormal steering by a combination of the deviation ε calculated by the deviation calculator 3 and the steering angle σ detected by the steering angle sensor 4.

  That is, the abnormal state determination unit 5 refers to the determination table, and when the region representing the combination of the deviation ε calculated by the deviation calculation unit 3 and the steering angle σ detected by the steering angle sensor 4 is “normal”. It is determined that the steering is normal, and when the region representing the combination is “abnormal”, it is determined that the steering is abnormal.

  In the present embodiment, the abnormal state determination unit 5 determines that the abnormal state is in an abnormal state when the abnormal steering per unit time reaches a certain time (for example, the abnormal steering per minute is 10 seconds or more).

  FIG. 4A shows the relationship between the deviation ε and the steering angle σ during normal operation, and FIG. The thick line indicates the boundary between normal operation and abnormal operation. As shown in the figure, during normal operation, the position of the deviation ε and the steering angle σ are almost in the normal steering region, but often in the abnormal region during dozing operation.

  The buzzer 6 outputs a buzzer sound when the abnormal state determination unit 5 determines that the steering is abnormal. This gives a warning to the driver.

  As described above, the driving support apparatus according to the first embodiment uses the deviation ε and the steering angle θ according to the road shape, thereby obtaining the relationship between the road shape and steering during normal driving or abnormal driving. As a result, it is possible to determine with high accuracy whether the driver is operating normally or abnormally. Furthermore, when it is determined that the driver is operating abnormally, the driving support device can prevent an accident caused by the abnormal driving of the driver by performing an alarm operation.

[Second Embodiment]
FIG. 5 is a block diagram showing the configuration of the driving support apparatus according to the second embodiment of the present invention. In addition, while attaching | subjecting the same code | symbol to the site | part same as 1st Embodiment, the detailed code | symbol is abbreviate | omitted and it mainly demonstrates a different point from 1st Embodiment.

  The driving assistance apparatus according to the second embodiment is obtained by adding a normal steering accumulation unit 7 to the configuration of the first embodiment shown in FIG. The normal steering accumulation unit 7 accumulates data of a set of the deviation ε and the steering angle σ for 5 minutes after the start of operation as data during normal operation. The reason for driving to doze is that it is often after 5 minutes from the start of driving. The data accumulation time is not limited to “5 minutes” after the start of operation, but may be other time.

  On the other hand, the abnormal state determination unit 5 does not store the determination table shown in FIG. 3 immediately after the start of operation, and determines that it is in a normal state for 5 minutes after the start of operation. Then, the abnormal state determination unit 5 creates a determination table using the data stored in the normal steering storage unit 7 for 5 minutes from the start of operation, and is normal operation using this determination table after 5 minutes from the start of operation. Or abnormal operation. The determination table is created as follows.

  The abnormal state determination unit 5 divides the data stored in the normal steering storage unit 7 into n groups according to the value of the deviation ε (for example, n = 5). Next, the abnormal state determination unit 5 calculates the average σm and the standard deviation σs of the steering angles σ of each set, sets the region included in σm ± 3 · σs as the normal steering region, and abnormally the other regions The steering area. The normal steering region is not limited to σm ± 3 · σs, and may be another region set using the average σm and the standard deviation σs.

  FIG. 6 is a diagram showing a state in which the data accumulated in the normal steering accumulation unit 7 is divided into five groups according to the value of the deviation ε. Note that the right end and left end pairs in FIG. 6 are excluded, and upper and lower limits indicating the normal steering region are set in the other five sets.

  As described above, the driving support apparatus according to the second embodiment creates a determination table using a set of data of the deviation ε and the steering angle σ accumulated after the start of driving, and based on this determination table, normal operation is performed. Since it is determined whether the operation or the abnormal operation is performed, the normal operation or the abnormal operation can be determined with high accuracy according to the operation characteristics of each driver.

  In the second embodiment, the abnormal state determination unit 5 determines the normal steering region based on the average and the standard deviation, but the present invention is not limited to this. For example, the abnormal state determination unit 5 represents the data accumulated in the normal steering accumulation unit 7 as a mixed normal distribution, and sets the region above a certain value of the obtained mixed normal distribution as a normal steering region, and the region below the certain value as a normal steering region. It may be an abnormal steering area.

[Third Embodiment]
FIG. 7 is a block diagram showing the configuration of the driving support apparatus according to the third embodiment of the present invention. In addition, while attaching | subjecting the same code | symbol to the site | part same as 1st Embodiment, the detailed code | symbol is abbreviate | omitted and it mainly demonstrates a different point from 1st Embodiment.

  The driving support apparatus according to the third embodiment automatically sets the distance L that the driver is normally gazing at. The configuration of the first embodiment shown in FIG. A detection unit 9 is added.

  The face camera 8 captures the face of the driver and generates a face image. The line-of-sight detection unit 9 detects the line of sight of the driver based on the face image generated by the face camera 8. Specifically, the line-of-sight detection unit 9 cuts out the left eye region from the face image for each frame, and extracts the center positions of the eyes and pupils as eye feature points. Then, the line-of-sight detection unit 9 calculates the position of the eyes relative to the face (the left and right direction and the up and down direction) of the face as a value representing the eye direction from these feature points. In this embodiment, the line-of-sight detection unit 9 is “detecting the line of sight of a driver while driving a car”, Sakaguchi et al., IEICE Technical Report PRU, vol. 95, no. 44 (1995) is used, but other line-of-sight detection techniques may of course be used.

  The deviation calculation unit 3 uses the driver's line of sight detected by the line-of-sight detection unit 9 to calculate the distance between the point at which the driver is gazing and the position of the vehicle, and sets the value as the distance L described above. And the deviation calculating part 3 calculates deviation (epsilon) using this distance L. FIG.

  As described above, the driving support device according to the third embodiment sets the distance to the point at which the driver is gazing as L, and thus considers the point at which the driver is actually gazing and the steering state. Since the driving state is determined, the driving state can be determined with high accuracy, and driving support such as an alarm operation can be performed.

[Fourth Embodiment]
FIG. 8 is a block diagram showing the configuration of the driving support apparatus according to the fourth embodiment of the present invention. In addition, while attaching | subjecting the same code | symbol to the site | part same as 1st Embodiment, the detailed code | symbol is abbreviate | omitted and it mainly demonstrates a different point from 1st Embodiment.

  The driving support apparatus according to the fourth embodiment is obtained by adding a rear camera 1A, a storage unit 10, a vehicle speed sensor 11, and a yaw angle sensor 12 to the configuration of the first embodiment shown in FIG. In addition, the front camera 1 is arrange | positioned so that 1 A of rear cameras may image the back of a vehicle.

  The accumulation unit 10 accumulates the recognition result of the lane recognition unit 2. The vehicle speed sensor 11 detects a vehicle speed that is the speed of the host vehicle. The yaw angle sensor 12 detects a yaw angle that is a rotation angle around the yaw axis of the host vehicle.

  The lane recognition unit 2 recognizes the lane position behind the vehicle based on the road image generated by the rear camera 1A. The accumulation unit 10 accumulates the road image generated by the rear camera 1A and the recognition result of the lane recognition unit 2.

  Based on the vehicle speed detected by the vehicle speed sensor 11 and the yaw angle detected by the yaw angle sensor 12, the deviation calculation unit 3 calculates the vehicle position P before traveling from the current position N by a distance (L + L1). However, L1 is the distance from the front end of the vehicle in the traveling direction to the lane position recognized by the rear camera 1A.

  FIG. 9 is a diagram showing the current position N and the vehicle position P before traveling a distance (L + L1) therefrom. Next, the deviation calculation unit 3 calculates a position A ahead of the distance L from the vehicle position P, calculates a current lane center position B, and calculates a deviation ε of the distance between the positions A and B.

  As described above, the driving support apparatus according to the fourth embodiment can determine the driving state based on the road shape behind the host vehicle and the steering amount, and can perform driving support such as an alarm operation.

  Note that L is a preset distance as in the first embodiment, but a forward distance that the driver is gazing at may be used as in the second embodiment.

[Fifth Embodiment]
FIG. 10 is a block diagram showing the configuration of the driving support apparatus according to the fifth embodiment of the present invention. In addition, while attaching | subjecting the same code | symbol to the site | part same as 1st Embodiment, the detailed code | symbol is abbreviate | omitted and it mainly demonstrates a different point from 1st Embodiment.

  The driving support apparatus according to the fifth embodiment includes a GPS sensor 21 and a map database 22 instead of the front camera 1 and the lane recognition unit 2 of the first embodiment shown in FIG.

  The GPS sensor 21 detects the latitude and longitude of the vehicle. The map database 22 outputs map data representing the road shape around the vehicle based on the latitude and longitude detected by the GPS sensor 21.

  Based on the latitude and longitude detected by the GPS sensor 21 and the map data obtained from the map database 22, the deviation calculation unit 3 calculates the curve radius R of the currently traveling road.

  FIG. 11 is a diagram showing the curve radius R and the deviation ε. Next, the deviation calculation unit 3 assumes that the rotation angle during travel of the distance L is θ,

より、次のように偏差εを算出できる。

Thus, the deviation ε can be calculated as follows.

  As the rotation angle θ, a detection result from a yaw angle sensor (not shown) may be used. Further, L is a preset distance as in the first embodiment, but a forward distance that the driver is gazing at as in the second embodiment may be used.

  As described above, the driving support apparatus according to the fifth embodiment drives based on the curve radius R of the road that is currently running as the road shape and the rotation angle of the vehicle during the distance L as the steering amount. The state can be determined, and driving assistance such as alarm operation can be performed.

[Sixth Embodiment]
The driving support apparatus according to the sixth embodiment measures the driving characteristics of the driver particularly at the time of a curve or a left / right turn, and optimizes driving support and alarm presentation according to individual differences and road conditions.

  FIG. 12 is a diagram illustrating a state where the vehicle is traveling on a road having a curvature such as a curve. When traveling on a curved road, it is known that the driver determines the steering amount as shown in Expression (1) based on the future position of the vehicle and the deviation of the road shape. (Basic automotive engineering, Masato Kondo, Yokendo, 1965).

ここでｈは操舵ゲイン、δは操舵量である。

Here, h is a steering gain, and δ is a steering amount.

  FIG. 13 is a diagram showing the relationship between the steering gain and the speed at the time of turning (hereinafter referred to as “turning speed”). The relationship between the steering gain and the turning speed shown in FIG. 13 is already known (four-wheel active steering vehicle with model following type sliding mode control, Hiraoka et al., Automotive Engineering Society, 2003), as shown in Equation (2) expressed.

  Here, V is a turning speed, and λ is a driver steering characteristic which is a parameter that varies depending on the driver.

  Thus, it is considered that the driver is steering according to the law determined based on the road shape and the vehicle speed during normal driving (when not drinking, sleeping, looking aside). Therefore, the driving support apparatus according to the sixth embodiment monitors the relationship between the driver's steering, the road shape, and the vehicle speed, and determines the time when it deviates from this law as abnormal driving.

  FIG. 14 is a block diagram showing the configuration of the driving support apparatus according to the sixth embodiment of the present invention. The driving support apparatus includes an acceleration sensor 21 that generates a signal corresponding to the longitudinal acceleration, a vehicle speed sensor 22 that generates a signal corresponding to the vehicle speed, a front camera 23 that captures a road ahead of the vehicle, and a steering angle. A steering angle sensor 24 that generates a signal and a calculation device 30 that performs a calculation for driving support.

  The arithmetic device 30 includes an acceleration detection unit 31 that detects longitudinal acceleration based on a signal from the acceleration sensor 21, a speed detection unit 32 that detects a speed (vehicle speed) based on a signal from the vehicle speed sensor 22, and a front A road shape detection unit 33 that detects a road shape based on an image from the camera 23 and a steering amount detection unit 34 that detects a steering amount based on a signal from the steering angle sensor 24 are provided.

  Furthermore, the arithmetic unit 30 includes a vehicle state prediction unit 35 that predicts the vehicle state, a steering characteristic calculation unit 36 that calculates the steering characteristics, and a steering characteristic storage unit 37 that stores the calculated steering characteristics. .

  The driving support apparatus configured as described above calculates driver steering characteristics by performing the following processing.

  The road shape detection unit 33 detects the road shape (particularly the center position of the travel lane) by performing predetermined image processing on the image from the front camera 23.

  Based on the acceleration a detected by the acceleration detection unit 31 and the speed V detected by the speed detection unit 32, the vehicle state prediction unit 35 determines the vehicle position (in front of the host vehicle) after t seconds according to Equation (3). ) D) is calculated.

  Furthermore, the vehicle state prediction unit 35 includes a target position after t seconds in the center position of the travel lane detected by the road shape detection unit 33, a vehicle position after t seconds obtained by the equation (3), The deviation ε is calculated. Note that the method for deriving the deviation ε is not limited to this, and for example, the method described in the first embodiment may be used.

  The steering characteristic calculation unit 36 uses the speed V detected by the speed detection unit 32, the deviation e predicted by the vehicle state prediction unit 35, and the steering amount δ detected by the steering amount detection unit 34. The driver steering characteristic λ is calculated as follows.

  Equation (5) is derived from Equations (1) and (2).

  The steering characteristic storage unit 37 sequentially stores the values calculated by the steering characteristic calculation unit 36, and stores the converged value as a driver steering characteristic λ unique to the driver. The driver steering characteristic λ is a parameter that does not depend on the speed. For this reason, the driving assistance device can use, for example, the driver steering characteristic λ learned by the vehicle passing through the intersection at a low speed for detecting an abnormality on the high-speed curve.

[Seventh Embodiment]
FIG. 15 is a block diagram illustrating a configuration of the driving support apparatus according to the seventh embodiment. The above-described driving support device is obtained by adding an appropriate steering prediction unit 38 that calculates an appropriate steering amount and a steering abnormality determination unit 39 that determines whether steering is abnormal to the configuration shown in FIG.

The appropriate steering prediction unit 38 uses the speed V detected by the speed detection unit 32, the deviation e predicted by the vehicle state prediction unit 35, and the driver steering characteristic λ stored in the steering characteristic storage unit 37 as a result of learning. The appropriate steering amount δ ^* is calculated according to the equation (6).

Here, the driver steering characteristic λ stored in the steering characteristic storage unit 37 has a certain distribution, and the appropriate steering amount δ ^* obtained from the driver steering characteristic λ also has a certain distribution.

Steering abnormality determination unit 39 determines whether the steering amount detected by the steering amount detecting section 34 [delta] is within the proper steering amount [delta] ^* of distribution (e.g., the proper steering amount [delta] ^* in the standard deviation), is within When it is not, it is determined as “normal operation”.

As described above, the driving support apparatus according to the seventh embodiment learns the driver steering characteristic λ that does not depend on the speed of the vehicle, and calculates the appropriate steering amount δ ^* based on the driver steering characteristic λ. Then, the driving support device determines whether or not the driver is operating abnormally based on whether or not the steering amount δ of the driver is within the distribution of the appropriate steering amount δ ^* , thereby determining the individual steering characteristics of the driver. Accordingly, it can be determined whether or not the vehicle is operating abnormally.

  In addition, the above-described driving support device uses the driver steering characteristic λ that does not depend on the speed of the vehicle, so that even if the driving environment constantly changes, whether or not it is abnormal driving without being affected by it. Can be determined.

[Eighth Embodiment]
FIG. 16 is a block diagram showing the configuration of the driving support apparatus according to the eighth embodiment of the present invention. The driving assistance device is obtained by adding an alarm device 41 and a steering assistance device 42 to the configuration shown in FIG.

  The warning device 41 outputs a warning sound indicating that there is a risk of lane departure, for example, when the steering abnormality determination unit 39 determines that the vehicle is operating abnormally. As a result, the driver can know in advance that an accident is likely to occur.

Further, since the steering assist device 42 knows the difference between the appropriate steering amount δ ^* and the steering amount δ from the determination process of the steering abnormality determination unit 39, the steering angle is adjusted so that the steering amount δ approaches the appropriate steering amount δ ^*. Control and perform steering interventions. Thereby, a dangerous state can be forcibly avoided.

[Ninth Embodiment]
FIG. 17 is a block diagram illustrating a configuration of the driving support apparatus according to the ninth embodiment. The driving support device is obtained by removing the steering abnormality determination unit 39 from the configuration shown in FIG. 15 and adding an automatic driving device 43 instead.

The automatic driving device 43 automatically controls the steering so that the appropriate steering amount δ ^* calculated by the appropriate steering prediction unit 38 is obtained. As a result, automatic driving is possible even on curved roads.

  Note that the present invention is not limited to the above-described embodiment, and it is needless to say that the present invention can also be applied to a design modified within the scope of the claims. For example, the driving support devices of the first to fifth embodiments perform a warning operation by generating a buzzer sound when abnormal driving is detected, but it is also possible to perform driving intervention such as braking control instead. is there.

  In addition, the driving assistance devices according to the sixth to ninth embodiments detect the acceleration via the acceleration sensor 21, but instead, the acceleration detected by time differentiation of the speed detected via the vehicle speed sensor 22 is obtained. It may be detected.

It is a block diagram which shows the structure of the driving assistance apparatus which concerns on the 1st Embodiment of this invention. It is a figure which shows the relationship between the future position of the own vehicle, and a target course position. It is a figure which shows the determination table. (A) is a figure which shows the relationship between deviation (epsilon) and steering angle (sigma) at the time of normal driving | operating, and (B) at the time of dozing operation. It is a block diagram which shows the structure of the driving assistance apparatus which concerns on the 2nd Embodiment of this invention. It is a figure which shows the state which divided | segmented the data accumulate | stored in the normal steering accumulation | storage part 7 into 5 sets according to the value of deviation (epsilon). It is a block diagram which shows the structure of the driving assistance device which concerns on the 3rd Embodiment of this invention. It is a block diagram which shows the structure of the driving assistance device which concerns on the 4th Embodiment of this invention. It is a figure which shows the vehicle position P before driving | running | working the present position N and distance (L + L1) from it. It is a block diagram which shows the structure of the driving assistance device which concerns on the 5th Embodiment of this invention. It is a figure which shows curve radius R and deviation (epsilon). It is a figure which shows the state which the vehicle is drive | working the road with curvatures, such as a curve. It is a figure which shows the relationship between a steering gain and turning speed. It is a block diagram which shows the structure of the driving assistance device which concerns on the 6th Embodiment of this invention. It is a block diagram which shows the structure of the driving assistance device which concerns on the 7th Embodiment of this invention. It is a block diagram which shows the structure of the driving assistance device which concerns on the 8th Embodiment of this invention. It is a block diagram which shows the structure of the driving assistance device which concerns on the 9th Embodiment of this invention.

Explanation of symbols

DESCRIPTION OF SYMBOLS 1 Front camera 2 Lane recognition part 3 Deviation calculation part 4 Steering angle sensor 5 Abnormal state determination part 6 Buzzer 7 Normal steering accumulating part 8 Face camera 9 Line of sight detection part 10 Accumulation part 11 Vehicle speed sensor 12 Yaw angle sensor

Claims (1)

A steering angle detecting means for detecting a steering angle by the driver of the steering wheel operation,
Road shape detection means for detecting a deviation between a front position at a predetermined distance from the vehicle and a lane position ahead of the predetermined distance from the vehicle as a running road shape;
Data of a set of a steering angle detected by the steering angle detection means at a predetermined time after the start of driving and a deviation detected by the road shape detection means at a predetermined time after the start of driving is stored as data during normal driving. Storage means ;
The set of data stored in the storage means is divided into a plurality of groups according to the deviation, an average value of the steering angle and a standard deviation of the steering angle are calculated for each group, and the average value + the standard deviation is an upper limit. A driving state determination table for determining a driving state of the driver using a table in which a range in which the average value minus the standard deviation is a lower limit is a normal steering region and a region other than the normal steering region is an abnormal steering region Operating state determination table creation means to create as,
Steering angle detected by the steering angle detecting means after a lapse of the predetermined time from the start of operation, and a combination of the detected deviation by the road shape detection means after the lapse of the predetermined time from the start of operation, creates the driving state determination table A driving state determination unit that determines the driving state of the driver based on the driving state determination table created by the unit;
An operating state determination device comprising:

Images