JP2964286B2 - Drowsy driving detection device - Google Patents

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

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

[0002]

2. Description of the Related Art Automobiles have various operation means that can be operated by a driver, such as a steering wheel, an accelerator pedal, a brake pedal, a shift lever, a turn signal lever, a wiper switch, a lighting switch, and a steering wheel.
When the operation of these operation means is reduced, the driving becomes monotonous and the driver may start falling asleep.

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

Further, as shown in Japanese Patent Application Laid-Open No. 58-175094, when a certain time has elapsed without the number of operations being less than a predetermined value, numerical data "1" is added, and the added value is present. Some alarms are issued to prevent falling asleep when the value is reached.

[0005]

However, in the above method, since the monotonousness of the driving is determined in a sampling manner at regular time intervals, it is difficult to catch a continuous state change of the driver. The present invention has been made in consideration of the above circumstances, and the dozing driving detection device according to claim 1 can accurately detect a driver's dozing while considering a continuous state change of the driver from the start of driving to the present. Aim.

The dozing driving detecting device according to the second and third aspects can accurately detect the dozing of the driver while considering the continuous state change of the driver from the start of driving to the present, and at the same time, detect the dozing. The purpose is to prevent.

[0007]

According to a first aspect of the present invention, there is provided a drowsiness driving detecting apparatus, wherein predetermined predetermined numerical values are sequentially added as time elapses during driving of the vehicle, and various operations that can be operated by the driver. and monotonousness counter preset weighted value corresponding to the operation to Rugoto operation means is performed is subtracted, and a drowsy driving discriminating means for discriminating a drowsy driving, based on an output of the monotonousness counter Prepare.

[0008] wherein dozing operation detecting apparatus of claim 2, and a single Furnishing counter certain figures that are sequentially added with the elapsed time determined in advance during the operation of the vehicle, various driver can operate
Calculates the average value of the elapsed time between operations of the operating means, and calculates the average
A method for determining the amount of increase in the value of the monotonicity counter in time
And each time the operation of the various operation means is performed,
Weight value set in advance corresponding to
Means for subtracting the product with the quantity from said monotonicity counter;
A drowsiness driving determining means for determining drowsiness driving based on the output of the monotonicity counter .

A dozing driving detecting apparatus according to claim 3 is provided.
The drowsy driving detection device according to claim 1 or 2.
Te, provided with a increased ratio calculating means for calculating the rate of increase of the output of the monotonousness counter, the drowsy driving determination
The means is arranged so that the output of the monotonicity counter is higher than a first set value.
The output of the increase ratio calculating means is a second set value
Is intended to determine the drowsy driving is larger than, and a wake means to the actuating prompting wakefulness of the driver when the drowsy driving by the <br/> drowsy driving discrimination means is discriminated.

[0010]

According to the first aspect of the present invention, while the vehicle is driving, a predetermined constant value is sequentially added to the monotonicity counter as time elapses, and various operation means that can be operated by the driver are provided. operation is subtracted from the performed preset weighted value monotonousness counter corresponding to the operation to Rugoto, drowsy driving is determined based on the output of the monotonousness counter.

According to the second aspect of the present invention, while the vehicle is driving, a predetermined constant value is sequentially added to the monotonicity counter as time elapses, and various operating means which can be operated by the driver are provided. Find the average value of the time elapsed between operations
Increase in the value of the monotonicity counter within the average time.
Addition is required. Then, the operation of various operation means is performed.
Weighting value set in advance for each operation
Is multiplied by the above calculated increment and decrements from the monotonicity counter.
The drowsy driving is determined based on the output of the monotonicity counter .

[0012] In dozing operation detecting apparatus according to claim 3, wherein
In claim 1 or claim 2, the rate of increase in the output of the monotonicity counter is calculated, and the output of the monotonicity counter is set to the first setting.
If the calculated increase rate is larger than the predetermined value and
If it is larger than the predetermined value, it is determined that the vehicle is dozing.
The awakening means is activated to determine this drowsy driving
I do.

[0013]

An embodiment of the present invention will be described below with reference to the drawings. In FIG. 1, reference numeral 1 denotes a control unit which comprises 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 turn signal operation detection unit 6, and a wiper operation detection for detecting operations of various operation units. The means 7, the lighting operation detecting means 8, and the steering angle sensor 9 are connected.

The vehicle speed sensor 2 detects a vehicle speed V of the vehicle. The brake operation detecting means 3 detects an operation of a brake pedal. The exhaust detection unit 4 detects an operation of an exhaust brake switch. Shift operation detecting means 5
Detects the operation of the shift lever of the transmission. The turn signal operation detecting means 6 detects an operation of the turn signal lever. The wiper operation detecting means 7 detects an operation of a wiper switch. The lighting operation detecting means 8 detects an operation of a lighting switch. The steering angle sensor 9 detects a steering angle Q of the steering. Further, the control unit 1
The monotonicity timer 10, the counter 11, the counter 12, the alarm 13, and the memory 14 are connected. Timer 10
Is used to count the operation time t and the control cycle time (= 1/10 second). The monotonicity counter 11 is used for counting and holding the monotonicity T.
The counter 12 is used for counting and holding the total number of operations N. The alarm 13 emits an alarm sound for urging the driver to wake up, and a buzzer is used, for example.

The memory 14 is a storage means for storing a weight value n _i (i = 1, 2,...) For the operation of each operation means, and the weight value n _i is previously associated with each operation means. It is memorized. The memory 14 also stores various set value data.

The weighting value _ni is determined in consideration of the fact that the monotonous feeling eliminated by the execution of the 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 is larger "2.5" as the weighting value n _i since large eliminated amount of monotonousness is set. That is, one operation of the turn signal lever is detected as it is as the number of operations "1", and one operation of the brake is detected as "2.5" as the number of operations. Similarly, for other operations, weighting values n in consideration of the amount of elimination of monotonicity are respectively set. on the other hand,
The control unit 1 has the following functional means. (1) During operation, a predetermined time (control cycle time 1/10
Every second), a constant value To is added by the monotonicity counter 11, and
Adding means for obtaining the monotony of T. (2) when at least one of various operating means is operated by the driver, reading means from the memory 13 the weighting value n _i corresponding to the operation means.

(3) Means for adding the read weight values n _i (n = Σn _i ) and integrating the added value n as the total number of operations N during operation by the counter 12. Here, the weight value n
_{Adding i} is a countermeasure for the case where a plurality of operating means are operated at the same time, although the actual rate seems to be low. (4) A means for counting the operation time t by the timer 10. (5) Means for calculating an average value [= t / N] of elapsed time (= no operation time) between each operation during operation by dividing the operation time t by the total number of operations N. (6) By multiplying the average value over time by the above-mentioned constant value To, the monotonicity increment [= (t /
N) · To].

(7) The weighting value n is added to the monotonicity increase amount.
(= Addition value of n _i ) to obtain a monotonic degree cancellation amount [= (t / N) · To · n] based on the current operation. (8) Subtraction means for correcting the monotonicity T by subtracting the integrated value of the monotonicity counter 11 by the monotonicity cancellation amount. (9) Monotonicity increase rate calculating means for calculating an increase rate of the monotonicity T. (10) A drowsy driving determining means for determining a drowsy driving in accordance with the monotonic degree T and the increasing rate of the monotonic degree T. (11) Awakening means for activating the alarm 13 when a drowsy driving is determined by the driving determining means. Next, the operation of the above configuration will be described.

[0020] First, as shown in the flowchart of FIG. 2, when the ignition switch is turned on, has been the engine is started, the control unit 1 is the system startup, monotonousness counter <br/> monotonousness T and counter data 11 The total number of operations N of 12 is cleared (step 101).

[0021] detecting the vehicle speed V of the vehicle speed sensor 2 exceeds a predetermined value V ₁ (YES in step 102), the count of the timer 10 operating time t (in seconds) is started (step 103).
At the same time, a constant value To is integrated by the monotonicity counter 11 (step 104). This integrated value is held as monotonicity T. Examples of the above-mentioned constant value V _1, the driver is assumed an easy-to-remember highway the monotony, for example, to not 60Km 70
Determined in km.

After the vehicle speed V once exceeds the constant value V ₁ , the counting of the operation time t and the integration of the constant value To are repeatedly executed every 1/10 of the control cycle time. During driving, various operations are performed by the driver, and the following types are available.

Operation of the accelerator pedal. Operation of the brake pedal. Operation of the exhaust brake switch. Operation of the shift lever. Operation of the turn signal lever. Operation of the wiper switch. Light switch operation. Steering operation etc.

[0024] (YES in step 105) when at least one of these operations is performed, weighting values n _i are predetermined for the operating means memory 14
(Step 106). The read weight values _ni are added (step 107), and the added value n is integrated by the counter 12 as the total number of operations N during operation (step 108). n = Σn _i N = N + n The operation time t is divided by the total number of operations N, and the average value of the elapsed time between operations during operation (= no operation time) [= t /
N]. The average value of the lapse of time is multiplied by the monotonicity increase amount per second (= 10 · To) to obtain the monotonicity increase amount between each operation [= (t / N) · 10 · To].

[0025] The (sum of = n _i) monotonically probability additional weighting value is the read out amount n is multiplied, monotonousness eliminate the amount based on the operation of the current [= (t / N) · 10 · To · n ] Is required. Monotonic degree only this monotonous degree eliminate the amount of counter 11
Is subtracted (step 109), and the monotonicity T is corrected. T = T − [(t / N) · 10 · To · n] Accordingly, as can be seen from the experimental data of FIG. 3, the monotonicity T continues to increase without any operation, and the operation is performed each time the operation is performed. It is canceled by the amount corresponding to. By monitoring the monotonicity T, it is possible to reliably capture a continuous state change of the driver from the start of driving to the present. If the monotonicity T becomes a negative value (YES in step 110), the monotonicity T is corrected to zero (step 110).
111). When the ignition switch is turned off and the operation of the engine is stopped (step 112), the calculation of the monotonic degree T ends.

On the other hand, as shown in the flowchart of FIG. 4, the monotonicity T stored in the monotonicity counter 11 is sequentially compared with a set value Ts stored in the memory 14 in advance (step 201).

If the monotonicity T is larger than the set value Ts (YES in step 201), the amount of increase ΔT ₁ per unit time of the monotonicity T (= increase rate of the monotonicity T) is stored in the memory 14 in advance. Is compared with the set value ΔT _s1 (step 202). The increase amount ΔT ₁ is the increase amount of the monotone T from one minute before to the present.

If the increment ΔT ₁ is larger than the set value ΔT _s1 (YES in step 202), then the increment ΔT ₂ per unit time of the monotonic degree T (increase rate of the monotonic degree T) is stored in the memory 14 in advance. Is compared with the set value ΔT _s2 (step 203). The increase amount ΔT ₂ is an increase amount of the monotonicity T from 30 minutes before to the present.

If the increase amount ΔT ₂ is larger than the set value ΔT _s2 (YES in step 203), the elapsed time t ₁ from the previous alarm sound generation timing to the present time and the memory 14
Is compared with the set time t _s stored in the step (step 204). The time t ₁ is for preventing a trouble that the alarm sound is continuously and frequently emitted, and is counted by the timer 10.

[0030] longer than the elapsed time t ₁ set time t _s (YES in step 204), the alarm device 13 alarm sound operates for a predetermined time is generated. This warning sound acts to encourage the driver to wake up.

[0031] That is, monotonousness T is the set value Ts or higher, monotonousness increment [Delta] T ₁ of the latest per minute T set value [Delta] T _s1 or more, further increase of the latest per 30 minutes monotonousness T [Delta] T ₂
When the three conditions that are equal to or _larger than the set value ΔT _s2 are satisfied, it is determined that the driver is dozing and a warning sound is issued.

Therefore, it is possible to accurately detect the driver's dozing while taking into account the continuous state change of the driver from the start of driving to the present. As a result, dozing can be prevented beforehand, and safety is improved.

By the way, there is a specific pattern leading to the drowsy driving, and by taking this into account as an essential condition for the drowsiness detection, the reliability of the drowsiness detection can be improved.

That is, there are various types of specific patterns that lead to drowsy driving, such as a long time between turning the steering wheel to the next steering wheel, a slow speed of moving the steering wheel, and a small number of times of turning the steering wheel. Therefore, the specific pattern is determined based on the steering angle Q detected by the steering angle sensor 9.

First, when the steering angle Q exceeds a predetermined threshold, it is regarded as one steering. When the time interval from one steering to the next steering is 10 seconds or more, the steering is turned from one steering to the next steering. Is determined to be a specific pattern having a long time.

The steering speed is obtained for each steering operation. When the average value of the steering speeds for a certain period of time, for example, 30 seconds, is equal to or smaller than a predetermined value, it is determined that the specific pattern has a low speed at which the steering wheel is moved. When the number of times of steering for a certain period of time, for example, 30 seconds, is equal to or less than a predetermined value, it is determined that the specific pattern has a small number of times of turning the steering wheel.

The determination processing of this specific pattern is performed in step 20.
As shown in the flow chart of FIG. 5, the process enters the step before the step 205 for generating an alarm sound as shown in FIG. 5, so that an alarm sound is emitted only when any one specific pattern exists. Thus, it is considered that useless or unnecessary generation of an alarm sound is eliminated.

In the above-described embodiment, the alarm 13 that emits an alarm sound is used as an awakening means. However, if it is a device that urges the driver to wake up, for example, a device that generates vibration, a device that generates electrical stimulation, Equipment that sends wind, equipment that emits light, etc.
Various uses are possible. In addition, the present invention is not limited to the above embodiment, and various modifications can be made without departing from the scope of the invention.

[0039]

As described above, according to the present invention,

The drowsy driving detection device according to the first aspect of the present invention adds a predetermined constant value to a monotonicity counter sequentially as time elapses while the vehicle is driving, and operates various operation means that can be operated by the driver. corresponding to the operation is subtracted from monotonousness counter preset weighted value been conducted Rugoto, since a configuration to determine the drowsy driving based on the output of the monotonousness counter, until now the start of the operation The driver's falling asleep can be accurately detected in consideration of the continuous state change of the driver.

[0041] The doze operation detecting apparatus according to claim 2, as well as added to sequentially monotonousness counter with a certain numerical value predetermined during operation of the vehicle over time, the operation of the various operating means which the driver can operate The average value of the elapsed time between
The amount of increase in the value of the monotonicity counter within the average time of
Corresponding to each operation of various operation means
Between the weight value set in advance and the increase amount obtained above.
The product is subtracted from the monotonic counter and the monotonic counter is subtracted.
Because it was configured to determine dozing driving based on the output ,
Kill in accurately detecting the dozing of the driver taking into account the ongoing change of state of the driver up to the present from the start of operation.

[0042] The dozing driving detecting device according to claim 3 is characterized in that :
3. The method according to claim 2, wherein the output of the monotonicity counter is increased.
Addition ratio is calculated, and the output of the monotonicity counter is set to the first set value.
A larger value and the calculated increase rate is the second set value.
If it is larger, it is determined that the driver is dozing, and this
The awakening means is activated when the driving is determined, so that it is possible to accurately detect the driver's dozing while considering the continuous state change of the driver from the start of driving to the present, and at the same time, to prevent the driver from falling asleep. .

[Brief description of the drawings]

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

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

FIG. 3 is a view showing an example of experimental data of the embodiment.

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

FIG. 5 is a flowchart for explaining the operation of a variation of snooze detection of the embodiment.

[Explanation of symbols]

DESCRIPTION OF SYMBOLS 1 ... Control part, 11 ... Monotone degree counter, 12 ... Counter,
13 ... alarm, 14 ... memory.

Claims (3)

(57) [Claims] With 1. A certain numbers predetermined during operation of the vehicle is sequentially added with the elapsed time, corresponds to the operation in Rugoto performed the operation of the various operating means which the driver can operate A drowsiness driving detection device, comprising: a dangling degree counter for subtracting a weight value set in advance from the dangling degree counter; and drowsiness driving determining means for determining a drowsiness driving based on an output of the monotonicity counter. 2. The method according to claim 1, wherein the predetermined numerical value is determined while driving the vehicle.
Are added sequentially over time.SimplyAn upholstery counter;The time elapsed between the operations of various operating means that can be operated by the driver
Finds an average value, and said monotone degree counter within the average time
Means for determining the increase in the value of Corresponds to each operation of the various operation means
Between the predetermined weighting value and the obtained increase amount.
Means for subtracting the product from the monotonicity counter; Monotonous
Based on the output of the degree counter Drowsiness to determine drowsy driving
A drowsy driving detection device, comprising: (3)A doze according to claim 1 or claim 2.
In the operation detection device,  An increase rate for calculating an increase rate of the output of the monotone degree counter
Combination calculation meansWith The drowsy driving determining means includes an output of the monotonicity counter.
Is larger than the first set value and the increase rate calculating means
If the output is greater than the second set value, it is determined that the driver is dozing.
To do same When dozing driving is determined by the dozing driving determining means
Awakening means for activating the awakening of drivingWith  A drowsy driving detection device, characterized in that: