JP2011013751A - Consciousness deterioration determining device and program - Google Patents

Abstract

PROBLEM TO BE SOLVED: To accurately determine the consciousness deteriorating state of a driver.SOLUTION: A consciousness deterioration determining device computes Time to Lane Crossing TLC based on a distance L to the end of a lane, vehicle speed v, and a yaw angle θ (102), determines that a vehicle approaches a lane and is in a risk situation when the TLC is greater than a predetermined threshold value thrc (104), obtains a sensor value detected by a tread force sensor 30 and a torque sensor 32 (106), stores, in an arousal buffer, the sensor value obtained within a predetermined period of time after travel start (108, 112), stores, in a current buffer, the value obtained after the predetermined period of time elapsed from the travel start (108, 110), computes Mahalanobis distance d between distribution of the sensor values stored in the arousal buffer and distribution of the sensor values stored in the current buffer (114), and determines that a driver is in the consciousness deteriorating state when the distance d is greater than a predetermined threshold value thrd (116, 118).

Description

  The present invention relates to an awareness reduction determination apparatus and program, and more particularly to an awareness reduction determination apparatus and program for determining a driver's awareness reduction state based on a vehicle running state and a driver's driving operation state.

  Conventionally, data based on the driving operation state of the driver is detected, based on the detected data, it is determined whether the driver is in a state of reduced consciousness, an alarm is issued to the driver, etc. Has been done to help.

  For example, while applying torque to the steering of the vehicle, the amount of steering rotation (steering angle change amount) is detected, and the steering angle change amount is equal to or greater than a predetermined threshold based on the magnitude of the applied torque. In this case, a steering holding state determination device that determines that the gripping force of the steering wheel is reduced has been proposed (see Patent Document 1). In the steering holding state determination device of Patent Document 1, when the steering angle change amount decreases with time, or when the number of times the steering angle change amount becomes equal to or greater than the threshold value exceeds a predetermined number, the driver Is determined to be in a low arousal state.

JP 2008-221967 A

  However, since the technique described in Patent Document 1 calculates the steering holding state even in a situation where a low arousal state is not assumed, the low arousal state can be achieved even when the steering holding force is reduced regardless of the low arousal state. There is a problem that the so-called S / N ratio is lowered, leading to erroneous detection and an increase in undetected.

  The present invention has been made to solve the above-described problems, and an object of the present invention is to provide a device for determining consciousness reduction and a program capable of accurately determining a driver's consciousness lowered state.

  In order to achieve the above object, the consciousness decrease determination device according to the present invention is based on a running state detection value that detects a running state of the host vehicle or a blink detection value that detects a blink of a driver. A risk determination means for determining whether or not the driver is in a dangerous situation and a muscle relaxation for determining a muscle relaxation state of the driver based on a driving operation state detection value obtained by detecting a driving operation state using the driver's muscle strength Determining means, and determining means for determining that the driver's consciousness is reduced when the risk determining means determines that the situation is dangerous and the muscle relaxation determining means determines that the muscle is relaxed; , Including.

  Further, the computer program for determining consciousness reduction of the present invention causes the computer to be dangerous around the vehicle based on the detected value of the driving state detected by the driving state of the host vehicle or the detected blink value of the driver. A risk determination unit that determines whether or not the vehicle is in a situation; a muscle relaxation determination unit that determines a muscle relaxation state of the driver based on a driving operation state detection value obtained by detecting a driving operation state using the muscle strength of the driver; In order to function as a determination unit that determines that the driver's consciousness is lowered when the risk determination unit determines that the situation is dangerous and the muscle relaxation determination unit determines that the muscle is relaxed. It is a program.

  According to the awareness reduction determination apparatus and program of the present invention, the risk determination means is based on the driving state detection value in which the driving state of the host vehicle is detected or the blink detection value in which the driver's blink is detected. Determine whether or not is in a dangerous situation. The muscle relaxation determining means determines the driver's muscle relaxation state based on the driving operation state detection value obtained by detecting the driving operation state using the driver's muscle strength. In the awake state, when the vicinity of the host vehicle is in a dangerous situation, some driving operation should be performed. Therefore, the determination means is determined to be a dangerous situation by the danger determination means, and the muscle relaxation determination means. When it is determined that the muscle is relaxed, it is determined that the driver's consciousness is reduced.

  In this way, when it is determined that the situation is dangerous and it is determined that the muscle is relaxed, it is determined that the state of consciousness is lowered. The state can be accurately determined.

  In the apparatus for determining declining consciousness of the present invention and the program, the muscle relaxation determining means may be configured such that the difference between the distribution of the driving operation state detection value detected when the driving operation state is awakened and the distribution of the current driving operation state detection value. Can be determined to be in a muscle relaxed state when is greater than a predetermined determination threshold. Further, the difference can be the Mahalanobis distance or the KL information amount between the distribution of the driving operation state detection value detected when the driving operation state is awakened and the current distribution of the driving operation state detection value. In this way, a stable determination result can be obtained by determining using the distribution of the driving operation state detection values.

  Moreover, in the consciousness fall determination apparatus and program of this invention, the driving operation state detection value detected at the time of awakening can be used as the driving operation state detection value detected within a predetermined time from the start of traveling. In this way, the vehicle operation state detection value that is detected at the time of awakening, which is a criterion for determination, is regarded as being in the awake state within a predetermined time from the start of traveling, and thus the vehicle And the individual characteristics of the driver are reflected, and the determination accuracy can be improved.

  In the apparatus for determining declining consciousness and the program according to the present invention, the muscle relaxation determining means is based on a driving operation state detection value detected when the danger determining means determines a dangerous situation. The relaxation state can be determined. Thereby, it is sufficient to determine the muscle relaxed state only when it is determined that the situation is dangerous, and useless calculation can be omitted. In addition, when determining using the distribution of the driving operation state detection value, by using the driving operation state detection value detected when it is determined to be a dangerous situation, when it is not determined to be a dangerous situation Compared with the case where determination is made including the detected driving operation state detection value, variation in the distribution of the driving operation state detection value can be suppressed and determination can be made with high accuracy.

  Further, in the consciousness deterioration determination device and program according to the present invention, the risk determination means may be a proximity threshold in which a distance between the lane position detected as the running state detection value and the distance between the own vehicle or a distance between the preceding vehicle and the own vehicle is predetermined If it is smaller, it can be determined that the vicinity of the host vehicle is in a dangerous situation.

  Further, in the consciousness deterioration determining device and program according to the present invention, the danger determining means may determine that the surroundings of the host vehicle are in a case where the eye-closing time of the driver determined based on the blink detection value is equal to or longer than a predetermined time. It can be determined that the situation is dangerous.

  In the apparatus for determining declining consciousness and the program of the present invention, the detected value of the driving operation state may be at least one of steering torque when steering the steering, pedaling force when depressing the accelerator pedal, and pedaling force when depressing the brake pedal. Can be used as a detected value.

  As described above, according to the device for determining consciousness reduction and the program of the present invention, since it is determined that the situation is in a dangerous state and the muscle is relaxed, it is determined that the state of consciousness is reduced. It is possible to obtain an effect that it is possible to accurately determine the driver's consciousness reduction state by eliminating information on the state of no muscle relaxation.

It is the schematic which shows the structure of the consciousness fall determination apparatus which concerns on 1st Embodiment. It is an image figure which shows distribution of a driving | running operation state detection value. It is a flowchart which shows the content of the consciousness fall determination processing routine of 1st Embodiment. It is the schematic which shows the structure of the consciousness fall determination apparatus which concerns on 2nd Embodiment. It is a flowchart which shows the content of the consciousness fall determination processing routine of 2nd Embodiment. It is the schematic which shows the structure of the consciousness fall determination apparatus which concerns on 3rd Embodiment. It is a flowchart which shows the content of the consciousness fall determination processing routine of 3rd Embodiment.

  DESCRIPTION OF EMBODIMENTS Hereinafter, an embodiment of a consciousness deterioration determination device of the present invention will be described in detail with reference to the drawings. In the present embodiment, a case where the present invention is applied to a consciousness deterioration determination device mounted on a vehicle will be described as an example.

  As shown in FIG. 1, the consciousness degradation determination device 10 according to the first embodiment detects a lane position sensor 20 that detects a lane position indicating a distance from the lane end to the host vehicle position, and detects the vehicle speed of the host vehicle. A vehicle speed sensor 22, a yaw angle sensor 24 for detecting a yaw angle which is an angle in the front-rear direction of the host vehicle with respect to the lane direction, a pedal force sensor 30 for detecting a brake pedal force, a torque sensor 32 for detecting a steering torque, and a driver Is provided with a warning device 40 that outputs a warning to the computer, and a computer 50 that controls the warning output by the warning device 40 based on the output from each sensor.

  For example, the lane position sensor 20 may detect a lane edge from a running image captured by an in-vehicle camera (not shown) and output the distance from the lane edge to the vehicle position, but is not limited thereto. It is not a thing.

  For example, the yaw angle sensor 24 may detect a lane from a running image captured by an in-vehicle camera (not shown), and may output the angle in the front-rear direction of the host vehicle with respect to the lane direction as a yaw angle. It is not limited to.

  As the pedal force sensor 30, for example, a pressure sensor that measures the hydraulic pressure provided in the hydraulic circuit of the brake can be used.

  The torque sensor 32 detects torque generated in the steering shaft connected to the steering handle.

  The alarm device 40 outputs an alarm message as a voice to the driver according to the control of the computer 50. The alarm device 40 may output an alarm sound to the driver.

  The computer 50 is connected to a CPU that controls the entire consciousness determination apparatus 10, a ROM as a storage medium that stores a program for a consciousness determination process routine, which will be described later, a RAM that temporarily stores data as a work area, and the like. It is configured to include a bus.

  If the computer 50 is described by functional blocks divided for each function realizing means determined based on hardware and software, detection of the lane position sensor 20, the vehicle speed sensor 22, and the yaw angle sensor 24 as shown in FIG. Based on the value, a dangerous situation determination unit 52 that determines whether or not the vehicle periphery is in a dangerous situation, and when the dangerous situation judgment unit 52 determines a dangerous situation, the pedal force sensor 30 and the torque sensor 32 Based on the sensor value, a muscle relaxation calculation unit 54 that calculates a value indicating the driver's muscle relaxation state, and based on the value calculated by the muscle relaxation calculation unit 54, it is determined whether or not the driver is in a state of reduced consciousness. And it can represent with the structure containing the determination part 56 which controls the alarm device 40 so that an alarm is output based on a determination result.

  The dangerous situation determination unit 52 acquires the distance L to the lane end detected by the lane position sensor 20 as the running state, the vehicle speed v detected by the vehicle speed sensor 22, and the yaw angle θ detected by the yaw angle sensor 24. Based on these, a lane departure prediction time TLC (Time to Lane Crossing) is calculated by the following equation (1).

TLC = L / (v · sin θ) (1)
Then, when the calculated TLC is larger than the predetermined threshold value thrc, it is determined that the vehicle periphery is in a dangerous situation.

  Since the muscle relaxation calculating unit 54 is supposed to perform some driving operation if the surroundings of the vehicle are in a dangerous situation, the brake which is the driving operation state when the dangerous situation judging unit 52 determines that the dangerous situation is present. A value indicating the muscle relaxed state of the driver is calculated using the pedaling force and the steering torque.

  Specifically, the dangerous situation determination unit 52 determines that there is a dangerous situation, and the pedaling force detected by the pedaling force sensor 30 and the steering torque detected by the torque sensor 32 within a predetermined time from the start of traveling are detected at the time of awakening. The sensor value is stored in the awakening buffer. Further, it is determined that the dangerous situation determination unit 52 is in a dangerous situation, and the pedaling force detected by the pedaling force sensor 30 and the steering torque detected by the torque sensor 32 after the elapse of a predetermined time from the start of traveling are used as current sensor values. Store in buffer. Then, as shown in FIG. 2, the sensor values stored in the awakening buffer and the sensor values stored in the current buffer are represented as distributions plotted in a coordinate system with the steering torque and the brake pedal force as axes. The distance d between the distribution of sensor values stored in the wakefulness buffer (hereinafter referred to as “distribution during wakefulness”) and the distribution of sensor values stored in the current buffer (hereinafter referred to as “current distribution”) Calculated as a value representing the relaxed state. The distance d between the distribution at the time of awakening and the current distribution is calculated by, for example, the Mahalanobis distance expressed by Equation (2).

Here, μ _c is an average value of sensor values currently stored in the buffer, μ _a is an average value of sensor values stored in the awakening buffer, and Σ is a covariance matrix. A larger value of d indicates that the distribution at awakening is different from the current distribution.

  The determination unit 56 determines that the driver is in a state of reduced consciousness when the distance d between the awakening distribution and the current distribution is greater than a predetermined threshold value thrd, and an alarm is output based on the determination result. The alarm device 40 is controlled.

  Next, with reference to FIG. 3, the consciousness decline determination processing routine of the first embodiment will be described. This routine starts when the CPU executes a consciousness deterioration determination program stored in the ROM when the engine is started.

  In step 100, the distance L to the lane edge detected by the lane position sensor 20, the vehicle speed v detected by the vehicle speed sensor 22, and the yaw angle θ detected by the yaw angle sensor 24 are acquired.

  Next, in step 102, the lane departure prediction time TLC is calculated by substituting the distance L to the lane edge, the vehicle speed v, and the yaw angle θ acquired in step 100 into the above equation (1), and the TLC value is calculated. Assign to variable c.

  Next, in step 104, it is determined whether or not the variable c is larger than a predetermined threshold value thrc. If c> thrc, it is determined that the vehicle is close to the lane and is in a dangerous situation, and the process proceeds to step 106. If c ≦ thrc, the vicinity of the vehicle is not in a dangerous situation. Determine and return to step 100.

  In step 106, sensor values detected by the pedal force sensor 30 and the torque sensor 32 are acquired.

  Next, in step 108, it is determined whether or not a predetermined time has elapsed since the start of traveling. This determination is made for the purpose of using the sensor value acquired during the awakening as the sensor value during the awakening, assuming that the state is an awakening state in which the consciousness has not decreased within a predetermined time from the start of running. If it is within the predetermined time from the start of traveling, the process proceeds to step 110, the sensor value acquired in step 106 is stored in the awakening buffer, and the process returns to step 100.

  On the other hand, if it is determined in step 108 that a predetermined time has elapsed from the start of traveling, the process proceeds to step 112, and the sensor value acquired in step 106 is stored in the current buffer.

  Next, in step 114, the distance d between the distribution at the time of awakening and the current distribution is calculated by the above equation (2).

  Next, in step 116, it is determined whether or not the distance d between the awakening distribution and the current distribution is greater than a predetermined threshold value thrd. If d> thrd, it is determined that the driver is in a state of reduced consciousness, the process proceeds to step 118, and an alarm is output to the driver.

  On the other hand, if it is determined in step 116 that d ≦ thrd, the process proceeds to step 120 and is acquired so that determination can be performed using the latest sensor value as a value indicating the current driving operation state. After that, a sensor value that has passed a predetermined time t seconds or more is deleted from the current buffer, and the process returns to step 100.

  As described above, according to the consciousness decrease determination apparatus of the first embodiment, when it is determined that the situation is dangerous and it is determined that the muscle is relaxed, it is determined that the consciousness decrease state. It can suppress that the information of the muscle relaxation state which does not depend on a reduction | decrease is contained as noise, and the determination precision of a consciousness fall improves. In addition, since the sensor value at the time of awakening, which is a criterion for judgment, is determined as a dangerous situation and the sensor value acquired during a predetermined time period from the start of running is used, the distribution at the time of awakening also includes noise. Therefore, a value indicating a muscle relaxed state calculated on the basis of the distribution at the time of awakening can be calculated with high accuracy.

  Next, a second embodiment will be described. The second embodiment is different from the first embodiment in that the driver's closed eye state is determined as a dangerous situation. In addition, about the structure and process similar to 1st Embodiment, the same code | symbol is attached | subjected and description is abbreviate | omitted.

  As shown in FIG. 4, the consciousness decrease determination device 210 according to the second embodiment includes a blink sensor 26 that detects a blink of a driver, a treading force sensor 30, a torque sensor 32, an alarm device 40, And a computer 250.

  The blink sensor 26 may detect the opening degree of the driver's eyes by performing image recognition processing on the driver's face image captured by a camera (not shown) that captures the driver's face. It is not limited to.

  If the computer 250 is described in terms of functional blocks divided for each function realizing means determined based on hardware and software, the closed eye state of the driver is determined based on the detection result of the blink sensor 26 as shown in FIG. When the closed eye state determination unit 53 and the closed eye state determination unit 53 determine that the closed eye time has continued for a predetermined time or more, the muscle relaxed state of the driver based on the sensor values of the pedal force sensor 30 and the torque sensor 32 It can be expressed by a configuration including a muscle relaxation calculation unit 54 that calculates a value indicating the value and a determination unit 56.

  The closed eye state determination unit 53 sets a state where the eye opening of the driver detected by the blink sensor 26 is equal to or less than a predetermined opening threshold value as a closed eye state, and when the closed eye state continues for a predetermined time or more, Judged to be in a dangerous situation.

  Next, with reference to FIG. 5, a consciousness decrease determination processing routine in the consciousness decrease determination apparatus 210 of the second embodiment will be described. This routine starts when the CPU executes a consciousness deterioration determination program stored in the ROM when the engine is started.

  In step 220, the eye opening of the driver detected by the blink sensor 26 is acquired.

  Next, in Step 222, it is determined whether or not the driver is in an eye-closed state by determining whether or not the eye opening acquired in Step 220 is equal to or less than a predetermined opening threshold. If it is closed, the process proceeds to step 224. If it is not closed, the process returns to step 220.

  In step 224, it is determined whether or not the duration of the closed eye state has exceeded a predetermined threshold value thre. If not, the process returns to step 220. If it has exceeded, the process proceeds to step 106. The same processing as that of the embodiment is executed.

  As described above, according to the consciousness decrease determination device of the second embodiment, it is determined that the driver is in a dangerous situation with the closed eye for a predetermined time or more as a precursor state of consciousness decrease. Thus, the same effect as that of the first embodiment can be obtained.

  Next, a third embodiment will be described. The third embodiment is different from the first embodiment in that the determination of the dangerous situation and the determination of the muscle relaxed state are processed in parallel, and the inter-vehicle distance is used as the running state. In addition, about the structure and process similar to 1st Embodiment, the same code | symbol is attached | subjected and description is abbreviate | omitted.

  As shown in FIG. 6, the consciousness decrease determination device 310 according to the third embodiment includes an inter-vehicle distance sensor 28 that detects an inter-vehicle distance and a relative speed between the host vehicle and a preceding vehicle, a torque sensor 32, and an alarm device. 40 and a computer 350 for controlling alarm output by the alarm device 40 based on the output from each sensor.

  The inter-vehicle distance sensor 28 detects a relative distance from the preceding vehicle as the inter-vehicle distance, and detects a differential value of the relative distance as a relative speed with respect to the preceding vehicle and outputs it to the computer 350. As the inter-vehicle distance sensor 28, for example, a laser radar can be used.

  If the computer 350 is described in terms of functional blocks divided for each function realizing means determined based on hardware and software, as shown in FIG. 6, the situation in which the periphery of the vehicle is dangerous based on the detection value of the inter-vehicle distance sensor 28. A risk determination unit 352 that determines whether the driver is in a relaxed state, a muscle relaxation determination unit 354 that determines whether or not the driver is in a muscle relaxation state based on the sensor value of the torque sensor 32, and a danger situation determination unit 352 A determination unit 356 that determines that the driver is in a state of reduced consciousness and controls the alarm device 40 so that an alarm is output when the muscle relaxation determination unit 354 determines that the state is a muscle relaxation state. Can be expressed in a configuration including

  Based on the inter-vehicle distance l between the host vehicle and the preceding vehicle detected by the inter-vehicle distance sensor 28 and the relative speed v ′ with respect to the preceding vehicle, the dangerous situation determination unit 352 performs the vehicle collision time TTC according to the following equation (3). (Time To Collation) is calculated.

TTC = l / v ′ (3)
Then, when the calculated TTC is greater than a predetermined threshold value thrf, it is determined that the vehicle periphery is in a dangerous situation.

  The muscle relaxation determination unit 354 acquires the steering torque detected by the torque sensor 32 as the driving operation state, stores it in the current buffer as the current sensor value, and calculates the average value g of the stored sensor values. Further, an average value of sensor values at awakening obtained by experiment is stored in a predetermined area in advance as a threshold value thrg, and the current average value g and the threshold value thrg are compared to determine whether or not the muscle is relaxed. judge. In the case of the muscle relaxed state, the steering torque is smaller than that at the time of awakening. Therefore, when g <thrg, it is determined that the muscle is relaxed.

  Next, with reference to FIG. 7, a consciousness decrease determination processing routine in the consciousness decrease determination apparatus according to the third embodiment will be described. This routine starts when the CPU executes a consciousness deterioration determination program stored in the ROM when the engine is started.

  In step 320, the inter-vehicle distance l detected by the inter-vehicle distance sensor 28 and the relative speed v 'are acquired.

  Next, in step 322, the vehicle collision time TTC is calculated by substituting the inter-vehicle distance l and the relative speed v 'acquired in step 320 into the above equation (3), and the value of TTC is substituted into the variable f.

  In step 324, the sensor value detected by the torque sensor 32 is acquired and stored in the current buffer.

  Next, in step 326, the average value g of the sensor values currently stored in the buffer is calculated.

  Next, in Step 328, it is determined whether or not the variable f is larger than a predetermined threshold value thrf and the current average value g is smaller than a threshold value thrg that is an average value at the time of awakening. If the determination is affirmative, it is determined that the driver is in a state of danger and is in a muscle relaxed state, so the driver is determined to be in a state of reduced consciousness, and the process proceeds to step 118 to output an alarm to the driver.

  On the other hand, if a negative determination is made in step 328, the process proceeds to step 120, the sensor value that has passed a predetermined time t seconds or more after being acquired is deleted from the current buffer, and the process returns to step 320.

  As described above, according to the consciousness decrease determination device of the third embodiment, when it is determined that the situation is dangerous and it is determined that the muscle is relaxed, it is determined that the consciousness is decreased. It can suppress that the information of the muscle relaxation state which does not depend on a reduction | decrease is contained as noise, and the determination precision of a consciousness fall improves.

  In the first and second embodiments, the muscle relaxation state is determined using the sensor value distribution, and in the third embodiment, the determination is made using the average value of the sensor values. In the first and second embodiments, the determination may be made using the average value of the sensor values, and in the third embodiment, the determination may be made using the distribution of sensor values. .

  Further, in the first and second embodiments, the sensor value at the time of awakening is the sensor value detected within a predetermined time from the start of running, and in the third embodiment, the sensor value at the time of awakening obtained by an experiment is calculated. Although the case where the average value is used as the determination criterion has been described, the average value of the sensor values at awakening obtained by experiments in the first and second embodiments may be used. Also in this embodiment, a sensor value detected within a predetermined time from the start of traveling may be used.

  In the first and second embodiments, the case where the distance between the awakening distribution and the current distribution is calculated by the Mahalanobis distance as the value indicating the muscle relaxation state has been described. A KL (kullback-leaver) information amount indicating the degree of difference between the probability distribution and the probability distribution of the current sensor value may be used. The KL information amount is an information amount indicating a larger value as the degree of difference between the distribution at awakening and the current distribution is larger.

  In the first and second embodiments, the case where the brake pedal force is detected by the pedal force sensor as one of the driving operation states has been described. However, the pedal force sensor is provided on the accelerator pedal to detect the accelerator pedal force. Also good. Further, the driving operation state is not limited to the steering torque and the pedaling force, but may be any value that can detect the driving operation state using the muscle strength of the driver.

  In the above-described embodiment, the case where a warning is output when it is determined that the driver is in a state of reduced consciousness has been described. However, the driving of the driver is supported by other methods such as control to apply a brake. You may do it.

10, 210, 310 Decrease in consciousness determination device 20 Lane position sensor 22 Vehicle speed sensor 24 Yaw angle sensor 26 Blink sensor 28 Inter-vehicle distance sensor 30 Treading force sensor 32 Torque sensor 40 Alarm device 50, 250, 350 Computer 52, 352 Risk condition determination unit 53 Eye-Closed State Determination Unit 54 Muscle Relaxation Calculation Unit 354 Muscle Relaxation Determination Unit 56, 356 Determination Unit

Claims (10)

A risk determination means for determining whether or not the surrounding area of the host vehicle is in a dangerous situation based on a driving state detection value for detecting the driving state of the host vehicle or a blink detection value for detecting a blink of a driver;
Muscle relaxation determination means for determining a muscle relaxation state of the driver based on a driving operation state detection value obtained by detecting a driving operation state using the muscle strength of the driver;
A determination means for determining that the driver's consciousness is reduced when the risk determination means determines that the situation is dangerous and the muscle relaxation determination means determines that the muscle is relaxed;
Consciousness reduction determination device including   The muscle relaxation determining unit is configured to reduce muscle relaxation when a difference between a distribution of driving operation state detection values detected at awakening of different driving operation states and a distribution of current driving operation state detection values is larger than a predetermined determination threshold. The consciousness reduction determination apparatus according to claim 1, wherein the apparatus is determined to be in a state.   The consciousness deterioration determination device according to claim 2, wherein the difference is a Mahalanobis distance or a KL information amount between a distribution of driving operation state detection values detected at awakening of different driving operation states and a distribution of current driving operation state detection values. .   The consciousness deterioration determination apparatus according to claim 2 or 3, wherein the driving operation state detection value detected at the time of awakening is a driving operation state detection value detected within a predetermined time from the start of traveling.   The muscle relaxation determining means determines the muscle relaxed state of the driver based on a driving operation state detection value detected when the danger determining means determines that the situation is dangerous. The consciousness fall determination apparatus of any one of Claims.   When the distance between the lane position detected as the running state detection value and the distance between the own vehicle or the distance between the preceding vehicle and the own vehicle is smaller than a predetermined proximity threshold, the danger determination means The consciousness fall determination apparatus of any one of Claims 1-5 which determines that it exists in.   The said danger determination means determines that the said vehicle periphery is in a dangerous situation, when the eye-closing time of the said driver calculated | required based on the said blink detection value becomes more than predetermined time. Item 6. The consciousness reduction determination device according to any one of items 5 to 6.   The driving operation state detection value is a detection value obtained by detecting at least one of a steering torque when steering a steering wheel, a depression force when depressing an accelerator pedal, and a depression force when depressing a brake pedal. The consciousness deterioration determination apparatus according to any one of 7. Computer
A risk determination means for determining whether or not the surrounding area of the host vehicle is in a dangerous situation based on a driving state detection value for detecting the driving state of the host vehicle or a blink detection value for detecting a blink of a driver;
Muscle relaxation determination means for determining a muscle relaxation state of the driver based on a driving operation state detection value obtained by detecting a driving operation state using the muscle strength of the driver;
A determination means for determining that the driver's consciousness is reduced when the risk determination means determines that the situation is dangerous and the muscle relaxation determination means determines that the muscle is relaxed;
Decrease awareness program for functioning.   A consciousness decrease determination program for causing a computer to function as each means constituting the consciousness decrease determination device according to any one of claims 1 to 8.

Images