Driver state determination device and driver state determination program

Abstract

To determine a plurality of states only by the potential of the head.SOLUTION: The control device 3 is configured to continuously acquire a brain wave signal indicating the potential of brain waves in the head of the driver who drives the vehicle. The control device 3 is configured to separate and extract a brain wave waveform, which is a waveform of a brain wave, and a non-brain wave waveform, which is a waveform other than the brain wave, from a brain wave signal waveform indicating a temporal change in the potential of the brain wave, based on the acquired brain wave signal. The control device 3 is configured to determine the state of the driver based on the extracted electroencephalogram waveform and non-electroencephalogram waveform.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present disclosure relates to a driver state determination device and a driver state determination program that determine the state of a driver who drives a vehicle. [Background technology]

[0002] Patent document 1 describes a technology for determining the state of a driver of a vehicle (e.g., drowsiness level, stress level, excitement level, etc.) using a facial muscle detection unit, an optical heart rate detection unit, a breathing detection unit, an electrical conductivity detection unit, and a gaze detection unit. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Patent No. 6699308 Summary of the Invention [Problem to be solved by the invention]

[0004] Conventionally, there is a method for determining a driver's state (e.g., drowsiness) using electroencephalograms from the potential of the head, but this alone does not allow for distinguishing between multiple driver states (e.g., drowsiness, relaxation, positive, negative).

[0005] In order to determine multiple states of a driver, multiple pieces of biometric information must be acquired, and detection units must be attached to multiple drivers, which makes the configuration of the device for determining the driver's state complicated.

[0006] The present disclosure aims to determine multiple conditions using only the electrical potential of the head. [Means for solving the problem]

[0007] One aspect of the present disclosure is a driver state determination device (3) including a signal acquisition unit (S10), extraction units (S20 to S50, S70 to S90, S110 to S140), and state determination units (S60, S100, S150, S160).

[0008] The signal acquisition unit is configured to continuously acquire electroencephalogram signals indicating electroencephalogram potentials in the head of a driver who drives a vehicle. The extraction unit is configured to separate and extract electroencephalogram waveforms, which are waveforms of electroencephalograms, and non-electroencephalogram waveforms, which are waveforms other than electroencephalograms, from the electroencephalogram signal waveforms that indicate changes in the electroencephalogram potential over time, based on the electroencephalogram signal acquired by the signal acquisition unit.

[0009] The state determination unit is configured to determine the state of the driver based on the electroencephalogram waveform and the non-electroencephalogram waveform extracted by the extraction unit. The driver's state determination device of the present disclosure configured in this manner can determine a plurality of states of the driver by acquiring only the electroencephalogram signal from the driver's head.

[0010] Another aspect of the present disclosure is a driver state determination program for causing a computer to function as a signal acquisition unit (S10), an extraction unit (S20 to S50, S70 to S90, S110 to S140), and a state determination unit (S60, S100, S150, S160).

[0011] A computer controlled by the driver state determination program of the present disclosure can constitute part of the driver state determination device of the present disclosure, and can achieve the same effects as the driver state determination device of the present disclosure. [Brief explanation of the drawings]

[0012] [Figure 1] FIG. 1 is a block diagram showing a configuration of a driver state determination system. [Figure 2] FIG. 1 is a diagram illustrating a configuration of an electroencephalogram detection device. [Figure 3] 10 is a graph showing electroencephalogram signal waveforms showing potential changes due to blinking, facial muscles, and the neck or shoulders. [Figure 4] FIG. 2 is a diagram illustrating a configuration of a state pattern database. [Figure 5] 10 is a flowchart showing a state determination process. [Figure 6] FIG. 10 is a diagram illustrating a method for calculating the α wave temporal content rate. [Figure 7] 1 is a graph showing electroencephalogram signal waveforms of a driver while driving on a straight road and a curved section. [Figure 8] 10 is a line graph showing changes over time in blink intervals. DETAILED DESCRIPTION OF THE INVENTION

[0013] Hereinafter, embodiments of the present disclosure will be described with reference to the drawings. A driver's state determination system 1 of this embodiment is mounted on a vehicle, and as shown in Fig. 1, includes an electroencephalogram detection device 2, a control device 3, a navigation device 4, a HUD 5, and a data storage device 6. HUD stands for Head-Up Display. Hereinafter, the vehicle equipped with the driver's state determination system 1 will be referred to as the host vehicle.

[0014] The brain wave detecting device 2 detects the brain waves of the driver of the vehicle. The control device 3 is an electronic control device mainly composed of a microcomputer including a CPU 11, a ROM 12, a RAM 13, etc. Various functions of the microcomputer are realized by the CPU 11 executing a program stored in a non-transitory tangible recording medium. In this example, the ROM 12 corresponds to the non-transitory tangible recording medium storing the program. Furthermore, the execution of this program executes a method corresponding to the program. Note that some or all of the functions executed by the CPU 11 may be configured as hardware using one or more ICs, etc. Furthermore, the number of microcomputers constituting the control device 3 may be one or more.

[0015] The navigation device 4 is configured to acquire road map data from a map recording medium that stores road map data and various other information, and to detect the current position of the vehicle based on GPS positioning signals received by a GPS receiver. GPS stands for Global Positioning System. The navigation device 4 also performs route guidance control to provide guidance on a route from the current location to a destination.

[0016] The HUD 5 emits display light to display an image from below the windshield of the vehicle toward the windshield, thereby projecting a virtual image onto the windshield, allowing the driver to visually recognize the virtual image superimposed on the actual scenery ahead of the vehicle.

[0017] The data storage device 6 is a device for storing various data, and stores a waveform pattern database 61 (to be described later) and a state pattern database 62 (to be described later).

[0018] 2, the brain wave detection device 2 includes an EEG electrode 21 and a reference electrode 22. The brain wave detection device 2 outputs an EEG signal indicating the potential difference between the EEG electrode 21 and the reference electrode 22.

[0019] The EEG electrode 21 is attached, for example, to a hat worn by the driver. The EEG electrode 21 is attached to the hat at a position where it comes into contact with the right forehead of the driver when the driver puts on the hat. The right forehead corresponds to Fp2 in the International 10-20 System. The EEG electrode 21 may also be attached at a position where it comes into contact with the left forehead of the driver. The left forehead corresponds to Fp1 in the International 10-20 System. The reference electrode 22 is attached, for example, to the earlobe of the driver's right ear.

[0020] The control device 3 sequentially acquires the electroencephalogram signals from the electroencephalogram detection device 2, and generates an electroencephalogram signal waveform that indicates the change over time in the potential difference indicated by the electroencephalogram signals. The waveform pattern database 61 includes a waveform pattern of an EEG signal including an eyeblink potential (hereinafter referred to as a first pattern), a waveform pattern of an EEG signal including a myoelectric potential of facial muscles (hereinafter referred to as a second pattern), and a waveform pattern of an EEG signal including a myoelectric potential of the neck or shoulders (hereinafter referred to as a third pattern). The first, second, and third patterns are generated by learning in advance using a large amount of data. Note that since the first, second, and third patterns differ from person to person, the waveform pattern database 61 may be set for each individual.

[0021] The first pattern is, for example, a waveform included in the dashed elliptical regions R11 and R12 in the electroencephalogram signal waveform graph G1 in FIG. 3, and is a waveform pattern that is a single convex waveform with a large amplitude.

[0022] The second pattern is, for example, a waveform included in the dashed rectangular region R21 in the electroencephalogram signal waveform graph G2 in Fig. 3, and is a waveform pattern that is not a single event and has a medium amplitude (or RMS value). RMS is an abbreviation for Root Mean Square.

[0023] The third pattern is, for example, a waveform included in a dashed rectangular area R31 in the electroencephalogram waveform graph G3 in FIG. 3, and is a waveform pattern that is not a single event and has a large amplitude (or RMS value). Brain waves are small amplitude waves of around 0.5 to 30 Hz.

[0024] As shown in Fig. 4, the state pattern database 62 sets state determination conditions for determining the corresponding state pattern for each of a plurality of state patterns of the driver. The state determination conditions are generated by learning in advance using a large amount of data. Since state determination conditions vary from person to person, the state pattern database 62 may be set for each individual.

[0025] The multiple state patterns include "a state of extreme sleepiness," "a state of resisting sleepiness," "a relaxed state," "a state requiring concentration and being highly stressful but perceived positively (e.g., fun)," "a state requiring concentration and being highly stressful but perceived negatively," "a state of feeling mental stress such as discomfort, difficulty, or tension," and "a normal state."

[0026] The condition for determining a "highly sleepy state" (hereinafter referred to as the first determination condition) is that alpha waves are abundant and blinking is infrequent. The condition for determining whether a person is "resisting sleepiness" (hereinafter referred to as the second condition) is that there are a lot of alpha waves and a lot of blinking.

[0027] The criteria for determining a "relaxed state" (hereinafter referred to as the third criteria) are that there are many alpha waves and blinking is normal. The conditions for determining whether a person is in a "positive state despite being in a situation that requires concentration and is stressful" (hereinafter referred to as the fourth condition) are that there are a lot of alpha waves and the blink intervals are variable.

[0028] The criteria for determining whether a situation requires concentration and is highly stressful, and is perceived negatively (hereinafter referred to as the fifth criteria) are that alpha waves are low or absent, and the intervals between blinks are variable. The criteria for determining whether a person is in a "state of mental stress such as discomfort, difficulty, or tension" (hereinafter referred to as the sixth criteria) are that alpha waves are low or absent, and that facial muscles are exerted.

[0029] The condition for determining the "normal state" (hereinafter referred to as the seventh condition) is that the alpha waves are normal and the blinking is normal. For example, if the alpha wave time content rate, which will be described later, within the determination period is greater than a first alpha wave determination value set in advance, it is determined that there are many alpha waves.

[0030] For example, if the alpha wave time content rate within the determination period is less than a second electroencephalogram determination value that is set to be smaller than the first electroencephalogram determination value, it is determined that there are few or no alpha waves. For example, if the number of blinks within the determination period is less than a preset first blink number determination value, it is determined that the number of blinks is small.

[0031] For example, if the number of blinks within the determination period is equal to or greater than a first blink number determination value and less than a second blink number determination value that is set to be greater than the first blink number determination value, the blinks are determined to be normal.

[0032] For example, if the number of blinks within the determination period is equal to or greater than a second blink number determination value, it is determined that the number of blinks is large. For example, if the standard deviation of blink intervals within a determination period is equal to or greater than a preset blink variation determination value, it is determined that blink intervals vary.

[0033] Next, we will explain the procedure of the state determination process executed by the control device 3. The state determination process is a process that is executed every time a preset execution period elapses while the control device 3 is in operation. In this embodiment, the execution period is, for example, 10 seconds.

[0034] 5, when the state determination process is executed, the CPU 11 of the control device 3 acquires, in S10, electroencephalogram signal waveforms that have not been acquired until the most recent execution cycle has elapsed (i.e., electroencephalogram signal waveforms for the most recent execution cycle) from among the electroencephalogram signal waveforms generated by the control device 3. Hereinafter, the electroencephalogram signal waveforms acquired in S10 will be referred to as the most recent electroencephalogram signal waveforms.

[0035] In S20, the CPU 11 compares the most recent electroencephalogram signal waveform with the first, second, and third patterns stored in the waveform pattern database 61. In S30, the CPU 11 determines whether the most recent electroencephalogram signal waveform includes the first pattern. If the most recent electroencephalogram signal waveform includes the first pattern, the CPU 11 determines in S40 that the driver has blinked.

[0036] In S50, the CPU 11 extracts a section including the first pattern from the most recent electroencephalogram signal waveform. In S60, the CPU 11 calculates a blink index value (hereinafter referred to as the blink index value) based on the waveform of the section extracted in S50, and proceeds to S160. In the present embodiment, the blink index value is the number of blinks (hereinafter referred to as the blink number) and the interval between blinks (hereinafter referred to as the blink interval).

[0037] If the most recent electroencephalogram signal waveform does not include the first pattern in S30, the CPU 11 determines whether or not the most recent electroencephalogram signal waveform includes the second pattern in S70. If the most recent electroencephalogram signal waveform includes the second pattern, the CPU 11 determines in S80 that the driver has moved a facial muscle.

[0038] In S90, the CPU 11 extracts a section including the second pattern from the most recent electroencephalogram signal waveform. In S100, the CPU 11 calculates an index value of the mimetic muscles (hereinafter referred to as the mimetic muscle index value) based on the waveform of the section extracted in S90, and proceeds to S160. In this embodiment, the mimetic muscle index value is the RMS value of the waveform of the section extracted in S90.

[0039] If the most recent electroencephalogram signal waveform does not include the second pattern at S70, the CPU 11 determines whether or not the most recent electroencephalogram signal waveform includes the third pattern at S110. If the most recent electroencephalogram signal waveform includes the third pattern, the CPU 11 determines in S120 that the driver has moved their body.

[0040] In S130, the CPU 11 extracts a section including the third pattern from the most recent electroencephalogram signal waveform, and then proceeds to S160. If the most recent electroencephalogram signal waveform does not include the third pattern in S110, the CPU 11 determines in S140 that the most recent electroencephalogram signal waveform is all brain waves.

[0041] In S150, the CPU 11 calculates an index value of an electroencephalogram (hereinafter referred to as an electroencephalogram index value) based on the most recent electroencephalogram signal waveform, and proceeds to S160. In this embodiment, the electroencephalogram index value is the proportion of time during which alpha waves occur per unit time (hereinafter referred to as an alpha wave temporal content rate).

[0042] The alpha wave temporal content rate can be obtained by extracting only the alpha wave band by performing a wavelet transform on the EEG signal waveform and calculating the ratio of the number of peaks exceeding the threshold to the number of peaks per unit time, as shown in Figure 6. In Figure 6, black circles represent peaks exceeding the threshold, and white circles represent peaks below the threshold.

[0043] 5, when the process proceeds to S160, the CPU 11 determines the driver's state based on the electroencephalogram signal waveform from the current time point until a preset determination period (60 seconds in this embodiment) ago, and then proceeds to S170. Specifically, the CPU 11 determines the driver's state by determining whether any one of the first to seventh determination conditions set in the state pattern database 62 is established, using the index values ​​calculated in S60, S100, and S150 within the most recent determination period. For example, if the execution cycle is 10 seconds and the determination period is 60 seconds, the driver's state is determined using a maximum of six index values.

[0044] Here, the concept of state determination will be explained. In experiments conducted by the inventors of the present invention, it was found that the blink intervals tend to be longer on curved roads compared to straight roads. When comparing vehicle speeds, the blink intervals tend to be longer when the vehicle is traveling at a high speed.

[0045] Graph G11 in Fig. 7 is the waveform of the electroencephalogram signal of the driver when the vehicle is traveling on a straight road. Graph G12 in Fig. 7 is the waveform of the electroencephalogram signal of the driver when the vehicle is traveling on a curved section. Comparing graph G11 and graph G12, the blink intervals in graph G12 are sometimes longer than those in graph G11.

[0046] From these findings, it is thought that when the driver's load increases due to road conditions or the like, the number of blinks decreases. FIG. 8 is a line graph showing changes in blink intervals over time.

[0047] Sections T1, T2, T3, T4, and T5 in FIG. 8 are sections in which the vehicle is traveling at a speed of 40 km / h. Sections T11, T12, T13, T14, and T15 are sections where the vehicle is traveling at 70 km / h. Sections T21, T22, T23, T24, and T25 are sections where the vehicle is traveling at 100 km / h. Sections T2, T5, T12, T15, T22, and T25 are sections where the vehicle is traveling on curved sections. Sections T4 and T14 are sections where the vehicle is traveling on bumpy roads.

[0048] As shown in Figure 8, the blink intervals vary in sections T22 and T25 (i.e., sections where the vehicle is traveling at high speed around a curved section). There are no blinks in sections where the load is particularly heavy, but multiple blinks occur in sections where there is a little more leeway.

[0049] From blink intervals alone, it is not possible to determine whether a person is feeling positive (e.g., enjoying the stress) or negative about a stressful situation, but by combining this with brain waves (e.g., alpha waves), it is possible to distinguish between positive and negative feelings, enabling a more precise assessment of the state.

[0050] As shown in FIG. 5, when the process proceeds to S170, the CPU 11 controls the in-vehicle devices based on the state determination result of S160 and ends the state determination process. Specifically, the CPU 11, for example, causes the HUD 5 to display the state determination result of S160. That is, if the first determination condition is met, the HUD 5 displays that the driver is in a state of strong drowsiness. If the third determination condition is met, the HUD 5 displays that the driver is in a state of relaxation. If the fourth determination condition is met, the HUD 5 displays that the driver is in a state where concentration is required but is taking a positive view. If the fifth determination condition is met, the HUD 5 displays that the driver is in a state where concentration is required and the driver is in a state of heavy stress. If the sixth determination condition is met, the HUD 5 displays that the driver is in a state of feeling mental stress.

[0051] Furthermore, when the CPU 11 determines that the driver is "very sleepy," the CPU 11 causes the navigation device 4 to guide the driver to a route that is not congested. Furthermore, when the CPU 11 determines that the driver is "in a state where concentration is required and the driver is under a heavy load," the CPU 11 causes the navigation device 4 to guide the driver to a route with little traffic or pedestrians, a flat route, or the like. The control device 3 configured in this manner is configured to continuously acquire electroencephalogram signals that indicate the electroencephalogram potential in the head of a driver who drives a vehicle.

[0052] The control device 3 is configured to separate and extract electroencephalogram waveforms, which are waveforms of electroencephalograms, and non-electroencephalogram waveforms, which are waveforms other than electroencephalograms, from the electroencephalogram signal waveforms that indicate time changes in the electroencephalogram potential based on the acquired electroencephalogram signals. The non-electroencephalogram waveforms in this embodiment are waveforms generated by the driver's blinking, the movement of the driver's facial muscles, or the movement of the driver's neck or shoulders.

[0053] The control device 3 is configured to determine the state of the driver based on the extracted electroencephalogram waveform and non-electroencephalogram waveform. Such a control device 3 can determine a plurality of states of the driver by acquiring only the electroencephalogram signal from the driver's head.

[0054] Furthermore, the control device 3 compares the waveform of the acquired electroencephalogram signal with the first, second, and third patterns to extract non-electroencephalogram waveforms corresponding to blinking, movement of facial muscles, and movement of the neck or shoulders from the electroencephalogram signal waveform. Such a control device 3 determines the occurrence of an electrooculogram or electromyogram and uses sections other than those in which an electrooculogram or electromyogram occurs as an electroencephalogram waveform, thereby preventing electroencephalogram waveforms with small potentials from being buried in noise (i.e., the electrooculogram or electromyogram).

[0055] The control device 3 is also configured to separate and extract electroencephalogram waveforms and non-electroencephalogram waveforms each time a preset execution cycle elapses. The control device 3 is configured to determine the driver's state based on multiple waveforms extracted as multiple consecutive execution cycles elapse. Such a control device 3 can determine the driver's state using not only electroencephalogram waveforms but also non-electroencephalogram waveforms.

[0056] The control device 3 is also configured to support the driver by providing notification or route guidance to the driver based on the result of the determination of the driver's state. Such a control device 3 can provide support according to the driver's state.

[0057] The electroencephalogram signal indicates the potential of the electroencephalogram at the forehead of the driver. Such a control device 3 can suppress fluctuations in the detected electroencephalogram potential caused by the driver's hair.

[0058] In the embodiment described above, the control device 3 corresponds to a driver state determination device, S10 corresponds to processing as a signal acquisition unit, S20 to S50, S70 to S90, and S110 to S140 correspond to processing as an extraction unit, and S60, S100, S150, and S160 correspond to processing as a state determination unit.

[0059] The first to seventh judgment conditions correspond to the state judgment conditions, the alpha wave temporal content rate corresponds to a value related to the content, and S170 corresponds to processing performed by the support unit. Although one embodiment of the present disclosure has been described above, the present disclosure is not limited to the above embodiment and can be implemented in various modifications.

[0060] [Variation 1] In the above embodiment, the blink index value is the number of blinks and the blink interval, but the time during which the eyes are closed (that is, the eye closure time) may also be used as the blink index value.

[0061] [Variation 2] In the above embodiment, the electroencephalogram index value is the alpha wave temporal content rate, but the alpha wave content rate may also be used as the electroencephalogram index value. The alpha wave content rate is the proportion of alpha waves among all electroencephalogram components (i.e., alpha waves, beta waves, theta waves, delta waves, gamma waves, etc.). Furthermore, electroencephalograms other than alpha waves (e.g., beta waves, theta waves, etc.) may also be used to determine the driver's state.

[0062] [Variation 3] In the above embodiment, the driver's state is determined using the first to seventh determination conditions. However, if the driver's facial direction can be detected, the driver's state may be determined using the eighth determination condition described below. The eighth determination condition is that the facial muscles are exerted, the neck or shoulder muscles are exerted, and the face is facing forward. If the eighth determination condition is met, the CPU 11 determines that the driver is feeling scared. This is due to the shrugging of the shoulders or neck.

[0063] [Variation 4] In the above embodiment, the driver's state is determined based on the result of the determination, and the driver is guided to a route that avoids traffic jams. However, the driver may be supported by performing at least one of the following based on the determination result: notification, warning, actuation, vehicle control, and route guidance. The notification may be a display recommending a break to wake up from drowsiness. The warning may be a display calling attention to driving due to excessive drowsiness. The actuation may be, for example, blowing air toward the driver to relieve drowsiness. The vehicle control may be a control to change the steering wheel play from a small state to a large state in order to reduce the driver's load during driving.

[0064] [Variation 5] In the above embodiment, both the waveform generated by the blinking of the driver and the waveform generated by the movement of the facial muscles of the driver are extracted. However, it is also possible to extract either the waveform generated by the blinking of the driver or the waveform generated by the movement of the facial muscles of the driver.

[0065] [Variation 6] In the above embodiment, the driver's state is determined using the first to eighth determination conditions. However, the driver's state may be determined using at least one of the first to eighth determination conditions.

[0066] The control device 3 and the method described herein may be implemented by a special-purpose computer configured with a processor and memory programmed to execute one or more functions embodied in a computer program. Alternatively, the control device 3 and the method described herein may be implemented by a special-purpose computer configured with a processor configured with one or more dedicated hardware logic circuits. Alternatively, the control device 3 and the method described herein may be implemented by one or more special-purpose computers configured with a processor and memory programmed to execute one or more functions in combination with a processor configured with one or more hardware logic circuits. Furthermore, the computer program may be stored as instructions executed by a computer on a computer-readable non-transitory tangible recording medium. The method for implementing the functions of each unit included in the control device 3 does not necessarily need to include software; all of the functions may be implemented using one or more hardware components.

[0067] In the above embodiments, multiple functions of one component may be realized by multiple components, or one function of one component may be realized by multiple components. Furthermore, multiple functions of multiple components may be realized by one component, or one function realized by multiple components may be realized by one component. Furthermore, part of the configuration of the above embodiments may be omitted. Furthermore, at least part of the configuration of the above embodiments may be added to or substituted for the configuration of another of the above embodiments.

[0068] In addition to the control device 3 described above, the present disclosure can also be realized in various forms, such as a system including the control device 3 as a component, a program for causing a computer to function as the control device 3, a non-transient physical recording medium such as a semiconductor memory on which this program is recorded, and a method for determining the driver's state. [Explanation of symbols]

[0069] 1...Driver state determination system, 2...Electroencephalogram detection device, 3...Control device, 4...Navigation device, 11...CPU, 12...ROM, 13...RAM, 21...Electroencephalogram electrode, 22...Reference electrode

Claims

1. a signal acquisition unit (S10) configured to continuously acquire electroencephalogram signals indicating electroencephalogram potentials in the head of a driver who drives a vehicle; an extraction unit (S20 to S50, S70 to S90, S110 to S140) configured to separate and extract electroencephalogram waveforms, which are waveforms of the electroencephalograms, and non-electroencephalogram waveforms, which are waveforms other than the electroencephalograms, from an electroencephalogram signal waveform showing a time change in the potential of the electroencephalogram based on the electroencephalogram signal acquired by the signal acquisition unit; a state determination unit (S60, S100, S150, S160) configured to determine the state of the driver based on the electroencephalogram waveform and the non-electroencephalogram waveform extracted by the extraction unit; A driver state determination device (3) comprising:

2. The driver state determination device according to claim 1, The driver state determination device, wherein the non-electroencephalogram waveform is a waveform generated by the blinking of the driver, the movement of the facial muscles of the driver, or the movement of the neck or shoulders of the driver.

3. The driver state determination device according to claim 2, further comprising: a waveform pattern database (61) including a first pattern indicating a waveform of the potential of the blink, a second pattern indicating a waveform of the myoelectric potential of the facial muscles, and a third pattern indicating a waveform of the myoelectric potential of the neck or the shoulders; The extraction unit A driver state determination device that extracts the non-EEG waveforms corresponding to the blinking, the movement of the facial muscles, and the movement of the neck or the shoulders from the EEG signal waveform by comparing the waveform of the EEG signal acquired by the signal acquisition unit with the first pattern, the second pattern, and the third pattern.

4. The driver state determination device according to any one of claims 1 to 3, further comprising: a state pattern database (62) in which state determination conditions for determining a corresponding state pattern are set for each of a plurality of state patterns indicating a plurality of mutually different states of the driver, The driver state determination device is configured to determine the state of the driver by comparing the electroencephalogram waveforms and non-electroencephalogram waveforms extracted by the extraction unit with the state pattern database.

5. The driver state determination device according to claim 3, The waveform pattern database includes the first pattern generated in advance by learning using a plurality of pieces of data on the potential of the blinks, the second pattern generated in advance by learning using a plurality of pieces of data on the myoelectric potential of the facial muscles, and the third pattern generated in advance by learning using a plurality of pieces of data on the myoelectric potential of the neck or the shoulders.

6. The driver state determination device according to claim 4, A driver state determination device in which the multiple state determination conditions in the state pattern database are set to make a determination using at least one of the driver's brain waves, blink potential, facial muscle myoelectric potential, and neck or shoulder muscle myoelectric potential.

7. The driver state determination device according to any one of claims 1 to 3, The state determination unit calculating at least one of a blink count, a blink interval, and an eye-closure time as a blink index value that is an index value of the blinks of the driver based on the non-electroencephalogram waveform corresponding to the blinks of the driver; calculating an RMS value of the non-electroencephalogram waveform as a facial muscle index value that is an index value of the facial muscle movement of the driver based on the non-electroencephalogram waveform corresponding to the facial muscle movement of the driver; calculating a value related to the content of at least one of α waves, β waves, and θ waves as an electroencephalogram index value, which is an index value of the electroencephalogram waveform, based on the electroencephalogram waveform; A driver state determination device configured to determine the state of the driver using at least one of the blink index value, the facial muscle index value, and the electroencephalogram index value.

8. The driver state determination device according to any one of claims 1 to 3, the extraction unit is configured to separate and extract the electroencephalogram waveform and the non-electroencephalogram waveform every time a predetermined execution period elapses; The driver state determination device is configured to determine the state of the driver based on a plurality of waveforms extracted by the extraction unit as a plurality of consecutive execution periods pass.

9. The driver state determination device according to any one of claims 1 to 3, The driver state determination device, wherein the electroencephalogram signal indicates the potential of the electroencephalogram at the forehead of the driver's head.

10. The driver state determination device according to any one of claims 1 to 3, further comprising: A driver state determination device comprising an assistance unit (S170) configured to assist the driver by performing at least one of notification, warning, actuation, vehicle control, and route guidance to the driver based on the determination result of the state determination unit.

11. Computer, a signal acquisition unit (S10) configured to continuously acquire electroencephalogram signals indicating electroencephalogram potentials in the head of a driver who drives a vehicle; an extraction unit (S20 to S50, S70 to S90, S110 to S140) configured to separate and extract electroencephalogram waveforms, which are waveforms of the electroencephalograms, and non-electroencephalogram waveforms, which are waveforms other than the electroencephalograms, from an electroencephalogram signal waveform that indicates a time change in the potential of the electroencephalogram, based on the electroencephalogram signal acquired by the signal acquisition unit; and a state determination unit (S60, S100, S150, S160) configured to determine the state of the driver based on the electroencephalogram waveform and the non-electroencephalogram waveform extracted by the extraction unit; A driver state determination program to function as a

Images