Driver state estimation device

Abstract

To provide a driver state estimation device capable of correctly estimating the state of a driver regardless of a travel environment.SOLUTION: A driver state estimation device (100) comprises: an in-vehicle camera (32) that detects a line of sight of a driver; and a controller (10) configured to estimate a state of the driver on the basis of the line of sight of the driver. The controller sets a predetermined visual range including a line-of-sight direction of when the driver directs the line of sight thereof toward an advancing direction of the vehicle, acquires a distribution of gazing points of the driver within a predetermined time on the basis of the line of sight of the driver, and estimates that the driver is in an abnormal state when a ratio of gazing points included in the predetermined visual range among all the gazing points in the acquired distribution of the gazing points is equal to or greater than a predetermined ratio.SELECTED DRAWING: Figure 6

Description

[Technical Field]

[0001] The present invention relates to a driver state estimation device that estimates the state of a driver who drives a vehicle. [Background technology]

[0002] Conventionally, driver condition detection devices that detect abnormalities in a vehicle driver have been proposed (see, for example, Patent Document 1). The device described in Patent Document 1 detects the amplitude and frequency of the vehicle driver's saccades (saccadic eye movements in which the driver intentionally moves their gaze), and also detects the level of attention that increases as the number of points in the external environment of the vehicle that the driver needs to check while driving increases, and detects abnormalities in the driver based on the level of attention and the amplitude and frequency of the driver's saccades. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Patent Publication No. 2021-077136 Summary of the Invention [Problem to be solved by the invention]

[0004] In a driving environment that requires quick visual search over a wide range, for example, when turning right at an intersection and needing to quickly move the gaze over a wide range to simultaneously check multiple objects of attention, such as vehicles in the oncoming lane and pedestrians crossing the street, the amplitude of saccades increases when the driver's condition is normal, whereas the amplitude of saccades does not increase and tends to remain low when the driver's condition is abnormal due to the onset of a brain disease, etc. Therefore, it is possible to estimate whether the driver's condition is normal or not based on the amplitude of saccades.

[0005] However, in a driving environment where quick visual search over a wide area is not required, such as when driving on a highway with few other vehicles around and few attention objects to check, the amplitude of saccades does not increase even when the driver's condition is normal, so there is no clear difference in the amplitude of saccades between when the driver's condition is normal and when it is abnormal. In this case, it is difficult to accurately estimate the driver's condition using the conventional techniques described above. In other words, depending on the driving environment, it may be difficult to accurately estimate the driver's condition.

[0006] The present invention has been made to solve such problems, and aims to provide a driver state estimation device that can correctly estimate the driver's state regardless of the driving environment. [Means for solving the problem]

[0007] In order to solve the above-mentioned problems, the present invention provides a driver state estimation device that estimates the state of a driver driving a vehicle, and includes a gaze detection device that detects the driver's gaze, and a controller configured to estimate the driver's state based on the driver's gaze.The controller is configured to set a predetermined visual range that includes the gaze direction when the driver is looking in the direction of travel of the vehicle, obtain a distribution of the driver's gaze points within a predetermined time based on the driver's gaze, and estimate that the driver is in an abnormal state if the proportion of gaze points included in the obtained distribution of gaze points that are included in the predetermined visual range is equal to or greater than a predetermined proportion.

[0008] According to the present invention configured in this manner, the controller estimates that the driver is in an abnormal state if, among all gaze points included in the distribution of the driver's gaze points within a specified time period, the proportion of gaze points included in a specified visual range that includes the driver's gaze direction when the driver is looking in the direction of travel of the vehicle is equal to or greater than a specified proportion.Therefore, based on the proportion of gaze points included in the specified visual range, it is possible to identify that the driver's gaze is becoming more likely to focus near the direction of travel due to some kind of illness, and it is possible to correctly estimate that the driver is in an abnormal state regardless of the driving environment.

[0009] In the present invention, preferably, the driver state estimating device further includes a driving environment information acquisition device that acquires driving environment information of the vehicle, and the controller is configured to set the size of the predetermined visual range based on the driving environment information.

[0010] According to the present invention configured in this manner, the controller sets the size of the predetermined visual range based on the driving environment information. Therefore, by setting an appropriate size of the predetermined visual range in accordance with the driving environment information, it is possible to more accurately estimate whether the driver's condition is abnormal or not in accordance with the driving environment.

[0011] In the present invention, the controller is preferably configured to obtain the number of objects of attention around the vehicle based on driving environment information, and when the number of objects of attention is equal to or greater than a predetermined threshold, set the predetermined visual range larger than when the number of objects of attention is less than the predetermined threshold.

[0012] According to the present invention configured in this manner, when the number of objects to pay attention to is equal to or greater than a predetermined threshold, the controller sets the predetermined visual range to be larger than when the number of objects to pay attention to is less than the predetermined threshold.Therefore, taking into account the characteristic that the gaze of a driver in an abnormal state tends to be more concentrated near the direction of travel of the vehicle the fewer the number of objects to pay attention to, the controller can set the size of the predetermined visual range that is more likely to show differences from a driver in a normal state, and can more accurately estimate whether the driver's state is abnormal depending on the driving environment.

[0013] In the present invention, the controller is preferably configured to set, based on the driver's line of sight, a circular range having a center on an average direction of a distribution of line of sight directions within a predetermined time period as the predetermined visual range.

[0014] According to the present invention configured in this manner, the controller sets a circular range centered on the average direction of the distribution of gaze directions within a specified time period as the predetermined visual range. Therefore, the predetermined visual range that serves as a basis for estimating the driver's state can be set based on the actual gaze direction of the driver, making it possible to more accurately estimate whether the driver's state is abnormal. [Effects of the Invention]

[0015] According to the driver state estimating device of the present invention, the driver state can be correctly estimated regardless of the driving environment. [Brief explanation of the drawings]

[0016] [Figure 1] 1 is an explanatory diagram of a vehicle equipped with a driver state estimating device according to an embodiment of the present invention. [Figure 2] 1 is a block diagram of a driver state estimating device according to an embodiment of the present invention. [Figure 3] FIG. 1 is a diagram illustrating an example of the distribution of gaze points of a driver who is viewing the traveling direction of a vehicle. [Figure 4] 10 is a graph showing the relationship between the size of the central range and the central confirmation proportion p. [Figure 5] 1 is a graph showing the difference Δp between the median confirmation rate pu for subjects with brain disease and the median confirmation rate pn for subjects without disease. [Figure 6] 4 is a flowchart of a driver state estimation process according to an embodiment of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0017] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS A driver state estimating device according to an embodiment of the present invention will now be described with reference to the accompanying drawings.

[0018] [System Configuration] First, the configuration of a driver state estimating device according to this embodiment will be described with reference to Figures 1 and 2. Figure 1 is an explanatory diagram of a vehicle equipped with a driver state estimating device, and Figure 2 is a block diagram of the driver state estimating device.

[0019] The vehicle 1 according to this embodiment includes a driving force source 2 such as an engine or an electric motor that outputs driving force, a transmission 3 that transmits the driving force output from the driving force source 2 to the driving wheels, a brake 4 that applies a braking force to the vehicle 1, and a steering device 5 for steering the vehicle 1.

[0020] The driver state estimation device 100 is configured to estimate the state of the driver of the vehicle 1 and, as necessary, control the vehicle 1 or perform driving assistance control. As shown in Fig. 2, the driver state estimation device 100 includes a controller 10, a plurality of sensors, a plurality of control systems, and a plurality of information output devices.

[0021] Specifically, the multiple sensors include an exterior camera 21 and radar 22 that acquire driving environment information about the vehicle 1, a navigation system 23 for detecting the position of the vehicle 1, and a positioning system 24. The multiple sensors also include a vehicle speed sensor 25, an acceleration sensor 26, a yaw rate sensor 27, a steering angle sensor 28, a steering torque sensor 29, an accelerator sensor 30, and a brake sensor 31 that detect the behavior of the vehicle 1 and driving operations by the driver. The multiple sensors also include an in-vehicle camera 32 that detects the driver's line of sight. The multiple control systems include a powertrain control module (PCM) 33 that controls the driving force source 2 and the transmission 3, a dynamic stability control system (DSC) 34 that controls the driving force source 2 and the brakes 4, and an electric power steering system (EPS) 35 that controls the steering device 5. The multiple information output devices include a display 36 that outputs image information and a speaker 37 that outputs audio information.

[0022] Other sensors may also include a peripheral sonar that measures the distance and position of surrounding structures relative to vehicle 1, a corner radar that measures the proximity of surrounding structures at the four corners of vehicle 1, and various sensors that estimate the driver's condition (e.g., a heart rate sensor, an electrocardiogram sensor, a steering wheel grip force sensor, etc.).

[0023] The controller 10 performs various calculations based on signals received from a plurality of sensors, and sends control signals to the PCM 33, DSC 34, and EPS 35 to appropriately operate the driving force source 2, transmission 3, brake 4, and steering device 5, and also sends control signals to the display 36 and speaker 37 to output desired information. The controller 10 is composed of a computer equipped with one or more processors 10a (typically a CPU), memory 10b (ROM, RAM, etc.) for storing various programs and data, input / output devices, etc.

[0024] The exterior camera 21 captures images of the surroundings of the vehicle 1 and outputs image data. Based on the image data received from the exterior camera 21, the controller 10 recognizes objects (for example, preceding vehicles, parked vehicles, pedestrians, roads, dividing lines (lane boundaries, white lines, yellow lines), traffic signals, traffic signs, stop lines, intersections, obstacles, etc.). The exterior camera 21 corresponds to an example of the "driving environment information acquisition device" in the present invention.

[0025] The radar 22 measures the position and speed of an object (particularly, a preceding vehicle, a parked vehicle, a pedestrian, an object fallen on the road, etc.). For example, a millimeter wave radar can be used as the radar 22. The radar 22 transmits radio waves in the traveling direction of the vehicle 1 and receives reflected waves generated when the transmitted waves are reflected by the object. Then, the radar 22 measures the distance between the vehicle 1 and the object (e.g., the inter-vehicle distance) and the relative speed of the object with respect to the vehicle 1 based on the transmitted waves and the received waves. Note that in this embodiment, instead of the radar 22, a laser radar, an ultrasonic sensor, etc. may be used to measure the distance to the object and the relative speed. Also, a position and speed measuring device may be configured using a plurality of sensors. Note that the radar 22 corresponds to an example of a "driving environment information acquisition device" in the present invention.

[0026] The navigation system 23 stores map information internally and can provide the map information to the controller 10. The controller 10 identifies roads, intersections, traffic signals, buildings, etc. that exist around the vehicle 1 (particularly in the direction of travel) based on the map information and current vehicle position information. The map information may be stored in the controller 10. The positioning system 24 is a GPS system and / or a gyro system, and detects the position of the vehicle 1 (current vehicle position information). The navigation system 23 and the positioning system 24 also correspond to examples of the "driving environment information acquisition device" in the present invention.

[0027] The vehicle speed sensor 25 detects the speed of the vehicle 1 based on, for example, the rotational speed of the wheels or the drive shaft. The acceleration sensor 26 detects the acceleration of the vehicle 1. This acceleration includes the acceleration in the longitudinal direction of the vehicle 1 and the acceleration in the lateral direction (i.e., lateral acceleration). Note that in this specification, acceleration includes not only the rate of change of speed in the direction in which the speed increases, but also the rate of change of speed in the direction in which the speed decreases (i.e., deceleration).

[0028] The yaw rate sensor 27 detects the yaw rate of the vehicle 1. The steering angle sensor 28 detects the rotation angle (steering angle) of the steering wheel of the steering device 5. The steering torque sensor 29 detects the torque (steering torque) applied to the steering shaft via the steering wheel. The accelerator sensor 30 detects the amount of depression of the accelerator pedal. The brake sensor 31 detects the amount of depression of the brake pedal.

[0029] In-vehicle camera 32 captures an image of the driver and outputs image data. Controller 10 detects the driver's line of sight based on the image data received from in-vehicle camera 32. In-vehicle camera 32 corresponds to an example of the "line of sight detection device" of the present invention.

[0030] The PCM 33 controls the driving force source 2 of the vehicle 1 to adjust the driving force of the vehicle 1. For example, the PCM 33 controls the engine's spark plugs, fuel injection valves, throttle valves, variable valve mechanisms, the transmission 3, and an inverter that supplies power to the electric motor. When it is necessary to accelerate or decelerate the vehicle 1, the controller 10 sends a control signal to the PCM 33 to adjust the driving force.

[0031] The DSC 34 controls the driving force source 2 and brakes 4 of the vehicle 1 to perform deceleration control and attitude control of the vehicle 1. For example, the DSC 34 controls the hydraulic pump and valve unit of the brakes 4, and controls the driving force source 2 via the PCM 33. When it is necessary to perform deceleration control or attitude control of the vehicle 1, the controller 10 sends a control signal to the DSC 34 to adjust the driving force or generate a braking force.

[0032] The EPS 35 controls the steering device 5 of the vehicle 1. For example, the EPS 35 controls an electric motor that applies torque to a steering shaft of the steering device 5. When it is necessary to change the traveling direction of the vehicle 1, the controller 10 transmits a control signal to the EPS 35 to change the steering direction.

[0033] The display 36 is provided in front of the driver in the vehicle cabin and displays image information to the driver. For example, a liquid crystal display or a head-up display is used as the display 36. The speaker 37 is provided in the vehicle cabin and outputs various types of audio information.

[0034] [Driver state estimation overview] Next, an overview of driver state estimation by the driver state estimation device 100 of this embodiment will be described with reference to Fig. 3 to Fig. 5. Fig. 3 is a diagram illustrating an example of the distribution of gaze points of a driver who visually checks the traveling direction of the vehicle. Fig. 4 is a graph showing the relationship between the size of the central range and the central confirmation ratio p, which represents the ratio of gaze points included in the central range among all gaze points. Fig. 5 is a graph showing the central confirmation ratio p when an abnormality occurs. u and the normal median confirmation rate p n 10 is a graph showing the difference Δp between

[0035] In order to investigate how a driver's behavior of visually checking the surroundings of a vehicle (particularly the direction of travel of the vehicle) (hereinafter referred to as "exploratory behavior") differs between when the driver's condition is normal and when it is abnormal, the inventors conducted driving experiments using a driving simulator with multiple subjects with brain diseases and multiple healthy subjects without diseases. Specifically, the subjects were made to drive in various driving environments (general roads without intersections, general roads with intersections, expressways, etc.) with different numbers of objects to which the driver should pay attention (attention objects), and the subjects' eye movements while driving were measured.

[0036] As a result, it was found that healthy subjects without diseases (equivalent to drivers in a normal state) basically check the area around the vehicle by repeating the following exploratory behavior: looking in the vicinity of the vehicle's direction of travel, temporarily shifting their gaze toward an object of interest that is away from the direction of travel (e.g., another vehicle, rearview mirror, side mirror, etc.), and then returning their gaze to the vicinity of the direction of travel.

[0037] On the other hand, subjects with brain diseases (equivalent to drivers in an abnormal state) were more likely to direct their gaze in the vicinity of the vehicle's direction of travel, and were less likely to move their gaze away from the direction of travel than subjects without the disease.

[0038] Therefore, in order to quantitatively evaluate the proportion of gazes directed toward the vicinity of the vehicle's traveling direction, the inventors extracted gaze points where the gaze remained for a predetermined time (e.g., 0.3 seconds) for each subject with and without a brain disease, and obtained the distribution of gaze points. Then, as illustrated in Figure 3, the number of gaze points (shown by black circles in Figure 3) included in a predetermined visual range (hereinafter referred to as the "central range"; the range of circle A shown by imaginary lines in Figure 3) that includes the gaze direction when the driver directs his or her gaze toward the vehicle's traveling direction was identified, as well as the number of gaze points (shown by white circles in Figure 3) outside the central range, and the proportion of gaze points included in the central range among all gaze points (hereinafter referred to as the "central confirmation proportion").

[0039] Figure 4 shows the relationship between the size of the central area and the median confirmation rate p when a driving experiment was conducted on a general road without intersections using a driving simulator. In Figure 4, the horizontal axis shows the size of the central area (the radius of the central area expressed as a visual angle based on the driver's head position), and the vertical axis shows the median confirmation rate p. The dashed line in Figure 4 indicates the median confirmation rate p of subjects with brain diseases. u The solid line indicates the median ascertained proportion of disease-free subjects, p n This shows:

[0040] As shown in Figure 4, regardless of the size of the median range, the median confirmed proportion of subjects with brain disease, p uis the median confirmed proportion of disease-free subjects, p n This indicates that subjects with brain diseases have a higher rate of directing their gaze to areas near the direction of travel of the vehicle compared to subjects without the disease. Furthermore, when the size of the central range was in the range of 2° to 15°, the median confirmation rate p u and median ascertained proportion of disease-free subjects p n The difference is particularly large.

[0041] where the median confirmed proportion of subjects with brain disease, p u and median ascertained proportion of disease-free subjects p n The difference Δp between the two is shown in Figure 5. In Figure 5, the horizontal axis indicates the size of the central range, and the vertical axis indicates Δp = p u -p n In addition, the solid line in Figure 5 indicates Δp when a driving experiment was conducted on a general road without intersections (i.e., a driving environment with an average number of objects to be careful of), the dashed line indicates Δp when a driving experiment was conducted on a general road with intersections (i.e., a driving environment with a relatively large number of objects to be careful of), and the dashed line indicates Δp when a driving experiment was conducted on a highway (i.e., a driving environment with a relatively small number of objects to be careful of).

[0042] As shown in Figure 5, regardless of the driving environment, Δp has a peak value when the size of the central range is in the range of 2° to 15°. That is, the median confirmation rate p u is the median confirmed proportion of disease-free subjects, p nThere is a general tendency for the central range to be larger than the central range. Furthermore, the size of the central range where Δp peaks is largest (6°) in driving environments with a relatively large number of attention objects (dash-dotted line in Figure 5), smallest (3°) in driving environments with a relatively small number of attention objects (dashed line in Figure 5), and intermediate (4°) in driving environments with an average number of attention objects (solid line in Figure 5). This indicates that the smaller the number of attention objects, the stronger the tendency for subjects with brain diseases to focus their gazes near the vehicle's direction of travel compared to subjects without the disease. Therefore, a smaller central range makes it easier to see differences in the central confirmation ratio p, that is, differences in the distribution of gaze points. Therefore, by calculating the central confirmation ratio p from the distribution of the driver's gaze points, it is possible to accurately estimate whether the driver's condition is abnormal regardless of the driving environment. By setting a central range of an appropriate size depending on the number of attention objects, it is possible to more accurately estimate whether the driver's condition is abnormal depending on the driving environment.

[0043] [Driver state estimation processing] Next, the flow of the driver state estimation process performed by the driver state estimation device 100 of this embodiment will be described with reference to Fig. 6. Fig. 6 is a flowchart of the driver state estimation process for estimating the driver's state.

[0044] The driver state estimation process in FIG. 6 is started when the power supply of the vehicle 1 is turned on, and is repeatedly executed by the controller 10 at a predetermined cycle (for example, every 0.05 to 0.2 seconds).

[0045] When the driver state estimation process is started, the controller 10 acquires driving environment information based on signals received from sensors including the outside camera 21, radar 22, navigation system 23, positioning system 24, vehicle speed sensor 25, acceleration sensor 26, yaw rate sensor 27, steering angle sensor 28, steering torque sensor 29, accelerator sensor 30, and brake sensor 31 (step S1).

[0046] Next, the controller 10 detects the driver's line of sight based on the signal received from the in-vehicle camera 32 (step S2).

[0047] Next, the controller 10 acquires objects (attention objects) that the driver should pay attention to ahead of the vehicle 1 in the traveling direction based on the driving environment information acquired in step S1 (step S3). Examples of attention objects include other vehicles, obstacles, pedestrians, traffic lights, road signs, etc.

[0048] Next, the controller 10 acquires the distribution of the driver's gaze points for a recent predetermined time (e.g., 30 seconds) based on the driver's gaze detected in step S2 (step S4). For example, when the controller 10 detects that the driver's gaze has stopped for a predetermined time (e.g., 0.3 seconds) based on the driver's gaze detected in step S2, the controller 10 identifies the position of the gaze point by expressing the gaze direction, i.e., the direction from the driver's head position toward the gaze point, as a combination of azimuth and elevation angles based on the vehicle's traveling direction. Then, the controller 10 stores the identified positions of the gaze points in memory 10b. The storage of the gaze point positions is repeated during the execution of the driver state estimation process. Then, in step S4, the controller 10 reads out the gaze point positions for the most recent predetermined time stored in memory 10b and acquires the gaze point distribution.

[0049] Next, the controller 10 determines whether the number of attention objects acquired in step S3 is equal to or greater than a predetermined threshold N1 (step S5). N1 is set in advance and stored in the memory 10b. When the number of attention objects is less than N1, the driving environment corresponds to a driving environment with a relatively small number of attention objects, such as a highway.

[0050] As a result, if the number of attention objects is not equal to or greater than N1 (i.e., less than N1) (step S5: NO), the controller 10 sets a central range A1 of a size corresponding to a driving environment in which the number of attention objects is relatively small, and calculates the proportion of fixation points included in the central range A1 (central confirmation proportion p) (step S6). The central range A1 is set as a circular range centered on the average direction of the distribution of gaze directions over the most recent predetermined time period (e.g., 30 seconds). The size of the central range A1 (the radius of the central range expressed in visual angles based on the driver's head position) is set to 3 degrees, for example, based on the results of the driving experiment described above.

[0051] On the other hand, if the number of objects to be warned about is N1 or more (step S5: YES), the controller 10 determines whether the number of objects to be warned about acquired in step S3 is equal to or greater than a predetermined threshold value N2 (step S7). N2 is a value greater than N1, and is preset and stored in the memory 10b. A driving environment in which the number of objects to be warned about is equal to or greater than N1 but less than N2 corresponds to a driving environment in which the number of objects to be warned about is average, such as an ordinary road without an intersection. Furthermore, a driving environment in which the number of objects to be warned about is N2 or more corresponds to a driving environment in which the number of objects to be warned about is relatively large, such as an ordinary road with an intersection.

[0052] As a result, if the number of attention objects is not equal to or greater than the predetermined threshold N2 (i.e., equal to or greater than N1 but less than N2) (step S7: NO), the controller 10 sets a central range A2 of a size corresponding to the number of attention objects in an average driving environment, and calculates the proportion of gaze points included in the central range A2 (central confirmation proportion p) (step S8). The central range A2 is set as a circular range centered on the average direction of the distribution of gaze directions over the most recent predetermined time period (e.g., 30 seconds). The size of the central range A2 is set to 4 degrees, for example, based on the results of the driving experiment described above.

[0053] If the number of attention objects is N2 or more (step S7: YES), the controller 10 sets a central range A3 of a size corresponding to a driving environment in which the number of attention objects is relatively large, and calculates the proportion of fixation points included in the central range A3 (central confirmation proportion p) (step S9). The central range A3 is set as a circular range centered on the average direction of the distribution of gaze directions over the most recent predetermined time period (e.g., 30 seconds). The size of the central range A3 is set to 6 degrees, for example, based on the results of the driving experiment described above.

[0054] After the processing of step S6, S8 or S9, the controller 10 determines whether the calculated median confirmation rate p is equal to or less than the threshold value p th It is determined whether the threshold value p is equal to or greater than the threshold value p (step S10). th is preset and stored in the memory 10b. th is set to 0.5 based on the results of the above-mentioned driving experiment, for example.

[0055] As a result, the median confirmation rate p is set to the threshold p th If this is the case (step S10: YES), it is considered that the driver's gaze is concentrated within the central range and the driver rarely moves his / her gaze outside the central range. Therefore, the controller 10 estimates that the driver is in an abnormal state (step 11).

[0056] Next, the controller 10 transmits control signals to the display 36 and the speaker 37, causing the display 36 and the speaker 37 to output an alarm to notify the driver that the driver is in an abnormal state (step S12). At this time, image information and audio information (gaze guidance information) for guiding the driver's gaze to an object of attention that the driver did not visually recognize may be output from the display 36 and the speaker 37.

[0057] Also, the median confirmation rate p is the threshold p thIf the number is not equal to or greater than the above (step S10: YES), it is considered that the driver is frequently moving his / her gaze not only within the central range but also outside the central range, and therefore the controller 10 estimates that the driver's condition is normal (step S13).

[0058] After step S12 or S13, the controller 10 ends the driver state estimation process.

[0059] [Variations] In the above-described embodiment, the central range is set as a circular range centered on the average direction of the distribution of gaze directions over the most recent predetermined time period (e.g., 30 seconds). However, the central range may also be centered on the direction of travel of the vehicle, or may have a shape other than circular.

[0060] [Actions and Effects] Next, the effects of the driver state estimating device 100 of the present embodiment described above will be described.

[0061] The controller 10 determines whether the proportion of gaze points included in the central range including the gaze direction when the driver directs his / her gaze in the traveling direction of the vehicle 1 (central confirmation proportion p) among all gaze points included in the distribution of the driver's gaze points within a predetermined time is greater than or equal to a predetermined threshold p th If the above conditions are met, it is estimated that the driver is in an abnormal state. Therefore, based on the central confirmation rate p, it is possible to identify that the driver has a strong tendency to focus his or her gaze on areas near the direction of travel due to some kind of illness, and it is possible to correctly estimate that the driver is in an abnormal state regardless of the driving environment.

[0062] In addition, the controller 10 sets the size of the central range based on the driving environment information, and by setting an appropriate size of the central range according to the driving environment information, it is possible to more accurately estimate whether the driver's condition is abnormal or not according to the driving environment.

[0063] Furthermore, when the number of objects to pay attention to is equal to or greater than a predetermined threshold, the controller 10 sets the central range to be larger than when the number of objects to pay attention to is less than the predetermined threshold. Therefore, taking into account the characteristic that the gaze of a driver in an abnormal state tends to be more concentrated near the direction of travel of the vehicle 1 the fewer the number of objects to pay attention to, the controller 10 can set the size of the central range that is likely to show differences from a driver in a normal state, and can more accurately estimate whether the driver's state is abnormal or not depending on the driving environment.

[0064] Furthermore, the controller 10 sets a circular range centered on the average direction of the distribution of gaze directions within a specified time as the central range, so that the central range that serves as the basis for estimating the driver's state can be set based on the actual gaze direction of the driver, enabling more accurate estimation of whether the driver's state is abnormal or not. [Explanation of symbols]

[0065] 1 vehicle 10 Controller 100 Driver state estimation device 21 Exterior camera 22 Radar 23 Navigation System 24 Positioning System 25 Vehicle speed sensor 26 Acceleration sensor 27 Yaw rate sensor 28 Steering angle sensor 29 Steering torque sensor 30 Accelerator sensor 31 Brake sensor 32 In-car camera 36 Display 37 Speaker

Claims

1. A driver state estimation device that estimates a state of a driver who drives a vehicle, comprising: a gaze detection device for detecting the gaze of the driver; a controller configured to estimate a state of the driver based on the line of sight of the driver; The controller a predetermined visual range including a line of sight when the driver directs his / her gaze in the traveling direction of the vehicle; Acquire a distribution of the driver's gaze points within a predetermined time based on the driver's line of sight; The system is configured to estimate that the driver is in an abnormal state when a ratio of gaze points included in the predetermined visual range among all the gaze points included in the acquired distribution of gaze points is equal to or greater than a predetermined ratio. Driver state estimation device.

2. Further, a driving environment information acquisition device for acquiring driving environment information of the vehicle is provided, The controller is configured to set the size of the predetermined visual range based on the driving environment information. The driver state estimating device according to claim 1 .

3. The controller acquiring the number of attention objects around the vehicle based on the driving environment information; When the number of the attention objects is equal to or greater than a predetermined threshold, the predetermined visual range is set to be larger than when the number of the attention objects is less than the predetermined threshold. The driver state estimating device according to claim 2 .

4. The controller The predetermined visual range is set to a circular range having a center on an average direction of a distribution of gaze directions within a predetermined time based on the driver's gaze. The driver state estimating device according to claim 1 or 2.

Images