JPH05319134A - Asleep driving detecting device - Google Patents

Abstract

PURPOSE:To detect asleep driving by a driver by providing a fuzzy inference part to infer degree of awakening of the driver based on membership functions respectively corresponding to a running operation detecting part and a steering operation detecting part. CONSTITUTION:When vehicle speed exceeds a contain value, steering angle data based on the detected result of a steering angle sensor 9 are accumulated in a memory 14. The format of control rule is stored in the memory 14, and because respective fuzzy variable grades computed against the control rule are fitted for it, the class of degree of awakening as a necessary quantity is obtained. When the necessary quantity of degree of awakening is obtained, it is displayed on an indicator 15. By looking at the display the driver can grasp the driving condition of himself.

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a doze driving detection device for detecting a driver's dozing driving.

[0002]

2. Description of the Related Art An automobile has various operating means such as a steering wheel, an accelerator pedal, a brake pedal, a shift lever, a winker lever, a wiper switch, a lighting switch, and a steering wheel which can be operated by a driver.
When the number of operations of these operating means is reduced, driving becomes monotonous and the driver may start to fall asleep.

Therefore, conventionally, as shown in Japanese Patent Laid-Open No. 58-105844, the elapsed time during driving is counted, and when a certain time has elapsed without any operation, an alarm is issued to prevent drowsiness. There is something.

Further, as disclosed in Japanese Patent Application Laid-Open No. 58-175094, when a certain period of time elapses while the number of operations is less than a predetermined value, numerical data "1" is added and the added value is obtained. Some of them issue an alarm to prevent falling asleep when the value is reached.

[0005]

However, in the above-mentioned method, it is difficult to catch the continuous change of the driver's condition because the monotony of the driving is judged by sampling every fixed time.

The present invention takes the above circumstances into consideration,
Its purpose is to be able to accurately detect the driver's drowsiness while considering the continuous change of the driver's state from the start of driving to the present.

[0007]

The doze driving detection apparatus of the present invention has an integrating means for accumulating a constant value at every predetermined time during the operation of the vehicle to obtain a monotonicity, and various operating means except steering. When the operation is performed, a driving operation detection unit having subtraction means for correcting a monotonicity by subtracting a weighting value set in advance corresponding to the operation from the integrated value of the integrating unit, and the steering within a fixed time. A steering operation detecting section having at least one of a steering speed detecting means for obtaining an average value of steering speeds of the respective steerings and a steering number detecting means for obtaining the number of times of steering of the steering within a predetermined time, and the driving operation detection. And a fuzzy inference unit that estimates the awakening degree of the driver based on the membership functions corresponding to the steering operation detecting unit and the steering operation detecting unit.

[0008]

In the driving operation detecting portion, a constant value is integrated at predetermined time intervals during driving of the vehicle to obtain monotonicity. When various operating means other than the steering wheel are operated, the weighting value preset corresponding to the operation is subtracted from the integrated value, and the monotonicity is corrected. The steering operation detection unit detects at least one of the average value of the steering speed and the number of times of steering.

Membership functions corresponding to the driving operation detecting section and the steering operation detecting section are prepared, and the awakening degree of the driver is estimated by fuzzy inference based on the respective membership functions. This arousal level is an index for drowsy driving.

[0010]

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS An embodiment of the present invention will be described below with reference to the drawings. In FIG. 1, reference numeral 1 is a control unit, which includes a microcomputer and its peripheral circuits.

The control unit 1 includes a vehicle speed sensor 2, a brake operation detection unit 3, an exhaust detection unit 4, a shift operation detection unit 5, a winker operation detection unit 6, and a wiper for detecting operations of various operation units of the automobile. The operation detection unit 7, the illumination operation detection unit 8, and the steering angle sensor 9 are connected.

The vehicle speed sensor 2 detects the vehicle speed V of the vehicle. The brake operation detecting means 3 detects the operation of the brake pedal. The exhaust detection unit 4 detects the operation of the exhaust brake switch. Shift operation detection means 5
Detects the operation of the transmission shift lever. The winker operation detecting means 6 detects the operation of the winker lever. The wiper operation detecting means 7 detects the operation of the wiper switch. The illumination operation detection means 8 detects the operation of the illumination switch. The steering angle sensor 9 detects the steering angle Q of the steering.

Further, a timer 10, a counter 11, a counter 12, a wake-up means 13, a memory 14, and a display 15 are connected to the control unit 1. The awakening means 13 includes a plurality of awakening devices 13a, 13b, 13 having different strengths of awakening action.
It consists of c and 13d. The awakening device 13a emits a smell or a weak wind during operation, and has the weakest awakening action. The awakening device 13b emits light or strong wind during operation,
The awakening action is stronger than that of the awakening device 13a. The awakening device 13c emits sound or vibration during operation, and has a stronger awakening action than the awakening device 13b. The awakening device 13d emits a smell, a light,
It emits a combination of wind, sound, and vibration, or emits an electrical shock, and has the strongest arousal effect. The timer 10 is used to count various times during operation and control cycle time.

The memory 14 is a storage means for storing a weighted value n _i (i = 1, 2, ...) For the operation of each operation means, and the weighted value n _i is associated with each operation means in advance. Remembered. In addition, the memory 14 also stores various setting value data.

The weighting value n _i is determined in consideration of the fact that the monotonous feeling resolved by the execution of an operation differs depending on the type of operation. For example, turn signal lever operation for changing lanes, "1" as a weighting value n _i is set. Braking operation for stopping or deceleration, "2.5" is set as the weighting value n _i since large eliminated amount of monotonousness. In other words, the turn signal lever 1
Each operation is detected as the number of operations "1" as it is, but one operation of the brake is detected as the number of operations "2.5". Similarly for other operations, the weighting value n considering the monotonicity elimination amount is set. on the other hand,
The control unit 1 includes a reference value setting unit, a driving operation detection unit, a steering operation detection unit, a fuzzy inference unit, and a notification unit. First, the reference value setting unit works for an initial operation for a fixed time from the start of operation, and includes the following functional means (1) to (8). (1) A means for setting a fixed time t _s1 from the start of operation as the initial operation. (2) when at least one, except for steering of the various operating means but which is operated, reading means weighting value n _i from the memory 13 corresponding to the operation means.

(3) A means for adding the weighted values n _i read out by the counter 11 (n = Σn _i ) and holding the added value n as the total operation number No during the initial operation. Here, the addition of the weighting values n _i is a countermeasure against a case where a plurality of operating means are operated simultaneously, although it seems that the actual occurrence rate is low.

(4) When the steering angle Q detected by the steering angle sensor 9 exceeds a predetermined threshold level, it is judged as one steering, and the counter 12 is incremented by "1" for each steering. Means for adding and obtaining the steering frequency M, and sequentially storing the steering frequency M every 30 seconds in the memory 14. (5) Based on the steering angle Q detected by the steering angle sensor 9,
A means for obtaining a steering speed (deg / sec) for each steering and sequentially storing it in the memory 14. (6) A means for obtaining the average value d of the stored steering speeds at the end of the initial operation. (7) A means for obtaining a predetermined deviation (= difference between the upper quadrant position and the lower quadrant position) e of each stored steering speed at the end of the initial operation.

(8) At the end of the initial operation, the total number of operations N
o, the number of steering times M, the average value d of the respective steering speeds, and the predetermined deviation e of the respective steering speeds as reference values, respectively.
Means to store in. Further, the driving operation detection unit works after the initial driving has elapsed, and includes the following functional means (1) to (8). (1) Driving time t ₂ by timer 10 and awakening degree determination time t
₃ , and the counting of the non-operation time t4 is started. (2) Integration means for calculating a monotonicity T by integrating a constant value To with the counter 11 every 1/10 second, which is the control cycle time.

(3) A means for reading out the weighting value n _i corresponding to the operating means from the memory 13 when at least one of the various operating means except the steering wheel is operated. Here, the addition of the weighting values n _i is a countermeasure against a case where a plurality of operating means are operated simultaneously, although it seems that the actual occurrence rate is low. (4) Means for adding the weighted value n _i read out by the counter 11 (n = Σn _i ) and holding the added value n as the total number of operations N after the initial operation. (5) Time elapsed between each operation during operation by dividing the operation time t ₂ by the total number of operations N (= no operation time)
Means for obtaining the average value [= t ₂ / N] of (6) By multiplying the average value over time by the above-mentioned constant value To, the monotonicity increase amount [= (t ₂
/ N) · To].

(7) The weighting value n is added to the monotonicity increase amount.
By multiplying (= added value of n _i ), the monotonicity elimination amount [= (t ₂ / N) · To · n] based on the current operation
Means for seeking. (8) Subtraction means for correcting the monotonicity T by subtracting the integrated value of the counter 11 by the monotonicity elimination amount. The steering operation detection unit works after the initial driving, and the following (1) to
The functional means of (3) is provided. (1) Means for accumulating steering angle data based on the detection result of the steering angle sensor 9 in the memory 14. (2) Part 3 based on the latest steering angle data for 30 seconds
Steering speed detecting means for obtaining an average value of steering speeds of respective steerings in 0 second. (3) Part 3 based on the latest steering angle data for 30 seconds
Steering number detecting means for obtaining the number of steering in 0 seconds. The fuzzy reasoning unit works after the initial operation, and has the following functional means (1). (1) The driver's arousal level is estimated based on the membership functions corresponding to the driving operation detecting unit and the steering operation detecting unit. The notification unit works after the initial operation has elapsed, and the following (1)
It is equipped with the functional means of. (1) Awakening devices 13a, 13b, 13c, depending on the arousal level
Means for selectively activating 13d. Next, the operation of the above configuration will be described with reference to the flowcharts of FIGS. 2, 3, and 4. When the ignition switch is turned on and the engine is started, the control unit 1 starts the system,
The vehicle speed V detected by the vehicle speed sensor 2 is monitored (step 101).
). When the vehicle speed V exceeds a certain value V ₁ (Y in step 101)
ES), the timer 10 starts counting the initial operation time t ₁ (seconds) (step 102). The constant value V ₁ is set to a value of 60 km to 70 km, for example, on the assumption that the driver easily feels monotonous. While driving, various operations are performed by the driver, and the following types are available.

Operation of the accelerator pedal. Brake pedal operation. Exhaust brake switch operation. Shift lever operation. Operation of the blinker lever. Operation of the wiper switch. Lighting switch operation. Steering operation, etc.

When at least one of these operations other than the steering operation is executed (step 103)
YES), the weighting value n _i predetermined for the operating means is read from the memory 14 (step 104).

The weighted values n _i read out are added by the counter 11 in consideration of the case of simultaneous operation (step 105).
), The added value n is held as the total number of operations No. during the initial operation (step 106). n = Σn _i No = No + n

When the steering wheel is operated, the steering angle Q is detected by the steering angle sensor 9. When this steering angle Q exceeds a predetermined threshold level, it is determined that the steering is one steering.

When there is steering (YES in step 107), the counter 12 is incremented by "1" for each steering to obtain the number of steering times M (step 108), and the number of steering times M every 30 seconds is stored in the memory 14. Sequentially stored. M = M + n At the same time, the steering speed (deg / sec) for each steering is obtained based on the detected steering angle Q (step 109), which is sequentially stored in the memory 14. When the initial operation time t ₁ exceeds a constant value t _s1 (for example, 20 minutes) (step 11
0), and then the initial operation ends.

At the end of this initial operation, each steering speed stored in the memory 14 is read out, the average value d of the respective steering speeds is obtained, and a predetermined deviation (= upper quadrant) of each steering speed is obtained. The difference e between the position and the lower quadrant is obtained (step 111).

Then, the total number of operations of the counter 11, No,
The number of times of steering M, the average value d of each steering speed, and the predetermined deviation e of each steering speed are stored in the memory 14 as reference values (step 112). In this way, the individual-level driving operation data for each driver is captured during the initial driving over the constant time t _s1 . After the lapse of the initial operation, the timer 10 starts counting the operation time t ₂ and the awakening degree determination time t ₃ .

When the vehicle speed V exceeds a constant value V ₁ (step
(YES at 114), steering angle data based on the detection result of the steering angle sensor 9 is accumulated in the memory 14 (step 115).
Further, the counter 11 integrates the constant value To to obtain the monotonicity T (step 116). T = T + To The accumulation of the constant value To is repeatedly executed every 1/10 second which is the control cycle time.

When at least one operation other than the steering operation is executed during driving (YES in step 117),
Weighting value n _i are predetermined for the operating means is read from the memory 14, the weighting value n
_i is added (step 118). Then, the added value n is integrated by the counter 11 as the total number of operations N during operation (step 119). n = Σn _i N = N + n The operating time t ₂ is divided by the total number of operations N, and the average value [= t ₂ / N] of the elapsed time (= non-operation time) between the operations after the initial operation is calculated. Be done.

The average value of the elapsed time is multiplied by the monotonicity increase amount per second (= 10 · To), and the monotonicity increase amount between each operation during operation [= (t ₂ / N) · 10. To] is required.

This monotonicity increase amount is multiplied by the weighted value n (= added value of n _i ) read out, and the monotonicity elimination amount [= (t ₂ / N) · 10 · To · n]
Is required. The integrated value of the counter 11 is reduced by the monotonicity elimination amount (step 120), and the monotonicity T is corrected. T = T − [(t ₂ / N) · 10 · To · n] Therefore, as can be seen from the experimental data of FIG. 5, the monotonicity T continues to increase if there is no operation, and the monotonicity T increases with each operation. It is solved only by the amount according to the operation. Each time an operation is performed, the count value of the no-operation time t ₄ is stored in the memory 14, and the count value is cleared (step
121). When the monotonicity T becomes a negative value (step 122
YES), the monotonicity T is corrected to zero (step 123).
). In this way, the counting of the monotonicity T and the accumulation of the steering angle data are repeated until the awakening level determination time t ₃ reaches 30 seconds (step 124).

By the way, when the vehicle speed V is lower than the constant value V ₁ (NO in step 114), the steering angle data stored in the memory 14 is cleared (step 125).
). At the same time, the awakening degree determination time t ₃ is cleared and returned to zero (step 126). When the vehicle speed V drops to zero (YES in step 127), that is, when the vehicle stops, the awakening degree display described later is turned off (step 12).
8). However, in this case, the value of the no-operation time t ₄ and the monotonicity T are retained.

When the awakening degree determination time t ₃ exceeds 30 seconds (YES in step 124), the average value of the non-operation times t ₄ stored in the 30 seconds is obtained (step 129).
). Similarly, based on the steering angle data stored for 30 seconds, the average value of the steering speeds of the respective steering during the latest 30 seconds is obtained (step 130). Similarly, based on the steering angle data stored for 30 seconds, the number of times of steering in the latest 30 seconds is obtained (step 131). On the other hand, four membership functions for monotonicity, no-operation time, steering speed, and number of times of steering are stored in the memory 14.

As shown in FIG. 6, these membership functions have three classes, a triangular type, and the antecedent part is A,
Each reference value obtained in the initial operation (total operation number No, each steering number M, average value d of each steering speed, predetermined deviation e of each steering speed) is divided into three parts B and C. The shape is determined according to the total number of operations N obtained after the lapse of the initial operation.

(1) The shape of the membership function for monotonicity is divided into three classes of "high", "middle" and "low", and the delimiter values A, B, C are determined as follows. It

By dividing the initial operation time t _s1 by the total number of operations No, the average value b of the non-operation time is obtained. The average value b of this non-operation time is multiplied by the monotonicity increase amount per second (= 10 · To) to obtain the monotonicity increase amount a between each operation. b = t ₁ / No a = (t ₁ / No) · 10 · To

A value (= 4 · a) obtained by multiplying the monotonicity increase amount a by a constant 4 is determined as the delimiter value A. A value (= 8 · a) obtained by multiplying the monotonicity increase amount a by a constant 8 is determined as the delimiter value B. A value obtained by multiplying the monotonicity increase amount a by a constant 12 (=
12.a) is determined as the delimiter value C. An example is shown in FIG.

(2) The shape of the membership function for the no-operation time is divided into three classes of "long", "middle" and "short", and the delimiter values A, B, C are determined as follows. To be done. The average value b is directly determined as the delimiter value A. The value calculated based on the average value b is the delimiter value B,
It is decided as C respectively. An example is shown in FIG.

(3) The shape of the membership function for the steering speed is divided into three classes of "fast", "middle" and "slow", and the delimiter values A, B and C are determined as follows. It

The deviation e is multiplied by a constant 0.75, and a value (= d-0.75e) obtained by subtracting the multiplied value from the average value d is determined as the delimiter value A. The deviation e is multiplied by a constant 0.25, and a value (= d−0.25e) obtained by subtracting the multiplied value from the average value d is determined as the delimiter value B. The deviation e is multiplied by a constant 0.25, and a value (= d + 0.25e) obtained by adding the multiplication value to the average value d is determined as the delimiter value C. An example is shown in FIG.

(4) The shape of the membership function with respect to the number of times of steering is divided into three classes of "large", "middle" and "small", and the division values A, B and C are determined as follows. It The minimum value f, the average value g, the maximum value h, and the standard deviation i of each steering count M are obtained.

F or (g-2.i) or (2.g-
Among h), the largest one is determined as the delimiter value A. g
Is determined as the delimiter value B. The minimum value of (g + 2 · i) or h is determined as the delimiter value C. An example is shown in FIG.

Then, fuzzy reasoning is executed by using these membership functions, and the awakening degree of the driver is obtained (step 132). The fuzzy inference will be described below. The monotonicity fuzzy variable grade is calculated from the present monotonicity T (value of the counter 11) and the membership function of FIG. 7.

For example, when the monotonicity T is "19.00",
The monotonicity T is two classes “high” as shown in FIG.
Corresponding to "intermediate", two fuzzy variable grades "0.4
7 "" 0.53 "is the membership function of the mean and Figure 8 of the calculation. Step 129 in the non-operation time of 30 seconds obtained t _4, fuzzy variable grade of non-operation time is calculated.

For example, when the average value of each no-operation time t ₄ is “496.9 seconds”, the average value is 2 as shown in FIG.
Two fuzzy variable grades “0.92” and “0.08” are calculated corresponding to one class “middle” and “short”. Step
The fuzzy variable grade of the steering speed is calculated from the average value of the steering speed for 30 seconds obtained in 130 and the membership function of FIG.

For example, the average value of the steering speed is "5.54deg /
In the case of “second”, the average value corresponds to one class “slow” as shown in FIG. 9, and one fuzzy variable grade “1.
0 "is calculated. The fuzzy variable grade of the number of times of steering is calculated from the number of times of steering for 30 seconds obtained in step 131 and the membership function of FIG.

For example, when the number of times of steering is "9.0 times / second", the number of times of steering corresponds to one class "small" and one fuzzy variable grade "1.
0 "is calculated.

The memory 14 further stores the format of the control rules shown in FIG. 11, and by applying the fuzzy variable grades calculated above to the control rules, the awakening of the required amount is performed. A degree class is required.

In this case, six fuzzy variable grades have been calculated, the applicable places of fitting are shown by enclosing them with lines in FIG. 11, and the numerical data to be fitted are shown in FIG.

Regarding the four items of monotonicity, no-operation time, steering speed, and number of times of steering, the classes whose fuzzy variable grades are not all zero are "4.5", "4.0", "3.5", and "3.0".
It is four.

The minimum value of the fuzzy variable grades of each item corresponding to the class "4.5" is "0.47". Among the fuzzy variable grades of each item corresponding to class “4.0”, the minimum value is “0.08”. Class “3.5
Of the fuzzy variable grades for each item corresponding to
The minimum value is "0.53". Of the fuzzy variable grades of each item corresponding to class "3.0", the minimum value is "0.08"
Is.

Regarding the arousal level in the consequent part, membership functions of 9 classes, triangular type, and required width "1 to 5" shown in FIG. 13 are prepared.
It is stored in 4.

For this membership function of arousal level,
The extracted fuzzy variable grade for each class is applied as shown by the shaded area in FIG. 13, and the center of gravity of the shaded area is calculated, so that the necessary amount of arousal level X (=
“3.9”) is required. This is the end of fuzzy reasoning.

Thus, when the required amount X of the arousal level is obtained,
It is displayed on the display 15 (step 133). By looking at this display, the driver can grasp his / her driving condition. In addition, the passenger can talk to the driver, give attention, and take appropriate measures so that the driver does not fall asleep.

After that, the awakening degree determination time t ₃ is forcibly set to 15 seconds (step 135), and the fuzzy inference for obtaining the necessary amount X of the awakening degree is performed based on the latest detection data for 30 seconds. Is executed every 15 seconds. When the ignition switch is turned off and the engine stops operating (step 134), the system is stopped.

On the other hand, as shown in the flow chart of FIG. 14, the required amount X of awakening degree obtained by fuzzy inference
And the set values "4", "3", "2" and "1" stored in advance in the memory 14 are sequentially compared (steps 201 to 204).

Here, the set value "4" is a level which almost corresponds to a dozing state. The setting "3" is a level where you can sometimes see dozing and meandering driving. The setting "2" is a level where you are very sleepy, such as frequent yawning. The setting "1" is a level that is slightly drowsy.

If the required amount X of arousal level is larger than the set value "4" (YES in step 201), the awakening device 13d operates for a predetermined time (step 205), and light, wind, sound and vibration are emitted together. Subject to electrical shock to the driver's body.

If the required amount X of the arousal level is larger than the set value "3" (YES in step 202), the awakening device 13c operates for a predetermined time (step 206), a sound is emitted, or a vibration is generated by the driver. Added to the body of.

If the required amount X of the arousal level is larger than the set value "2" (YES in step 203), the awakening device 13d operates for a predetermined time (step 207) to emit light or a strong wind of the driver. It is sprayed on the body.

If the required amount X of the arousal level is larger than the set value "1" (YES in step 204), the awakening device 13a operates for a predetermined time (step 208), and a odor is emitted.
A weak wind is blown on the driver's body. Required Awakening Level X
Is smaller than the set value “1” (NO in step 204),
The wake up device does not work. In this way, by giving the driver a wakeful action of a level according to the required amount of wakefulness X,
The driver's drowsiness can be prevented and safety is improved.

In particular, the continuous change in the driver's state is captured as a monotonicity, and the characteristics of the steering operation leading to drowsiness driving are also captured, and these are used as the input for fuzzy reasoning, and the initial driving without worrying about the drowsiness driving. At times, individual driver's driving data for each driver is fetched and included as a reference value for fuzzy inference, so that the driver's drowsiness can be accurately detected and reliability is improved.

The wake-up device is not limited to the wake-up device of the above-mentioned embodiment, and various kinds can be used. Besides, the present invention is not limited to the above-described embodiments, and various modifications can be made without departing from the scope of the invention.

[0064]

As described above, according to the present invention, there is an integrating means for calculating a monotonicity by accumulating a constant value at every predetermined time during driving of a vehicle, and operation of various operating means except steering. When a steering operation is performed, a driving operation detecting portion having subtraction means for correcting a monotonicity by subtracting a weighting value set in advance corresponding to the operation from the integrated value of the integrating portion, and each of the steering operation within a predetermined time. A steering operation detecting unit that has at least one of a steering speed detecting unit that obtains an average value of steering speeds of steering, and a steering number detecting unit that obtains the number of times of steering in a certain period of time; Since the fuzzy inference unit that estimates the awakening degree of the driver based on the membership function corresponding to each of the steering operation detection units is provided, It can accurately detect the dozing of the driver taking into account the continuous state change of the driver up.

[Brief description of drawings]

FIG. 1 is a block diagram showing the configuration of a control circuit according to an embodiment of the present invention.

FIG. 2 is a flowchart for explaining the operation of the embodiment.

FIG. 3 is a flow chart for explaining the operation of the embodiment.

FIG. 4 is a flowchart for explaining the operation of the embodiment.

FIG. 5 is a diagram showing an example of experimental data of the same example.

FIG. 6 is a diagram showing a prototype of a membership function used for fuzzy inference according to the embodiment.

FIG. 7 is a diagram showing the shape of a membership function for monotonicity used for fuzzy inference according to the same embodiment.

FIG. 8 is a diagram showing a shape of a membership function with respect to no-operation time used for fuzzy inference according to the same embodiment.

FIG. 9 is a diagram showing the shape of a membership function for steering speed used in fuzzy inference according to the embodiment.

FIG. 10 is a diagram showing a shape of a membership function with respect to the number of times of steering used for fuzzy inference according to the same embodiment.

FIG. 11 is a diagram showing a format of a control rule used for fuzzy inference according to the embodiment.

FIG. 12 is a diagram showing a format in which each fuzzy variable grade is applied to the control rule of FIG. 11.

FIG. 13 is a diagram showing the shape of a membership function with respect to arousal level used for fuzzy reasoning in the example.

FIG. 14 is a flowchart for explaining the operation of each awakening device of the same embodiment.

[Explanation of symbols]

1 ... Control unit, 11, 12 ... Counter, 13 ... Awakening means,
14 ... Memory.

Claims (1)

[Claims] 1. An integrating means for accumulating a constant value every predetermined time to obtain a monotonic degree while the vehicle is operating, and corresponding to the operation when various operating means other than steering are operated. A driving operation detecting unit having a subtracting unit for correcting a monotonicity by subtracting a preset weighting value from the integrated value of the integrating unit, and a steering speed for obtaining an average value of steering speeds of respective steerings within a constant time of the steering. A steering operation detecting unit having at least one of a detecting unit and a steering number detecting unit for obtaining the number of times of steering of the steering within a fixed time, and members corresponding to the driving operation detecting unit and the steering operation detecting unit, respectively. A fuzzy reasoning unit that estimates the driver's arousal level based on the ship function, and uses the arousal level as an index for drowsy driving. Detection device.