Driver state estimation apparatus

Abstract

To provide a driver state estimation apparatus capable of accurately estimating that a driver is in an inattentive state regardless of a travel environment.SOLUTION: A driver state estimation device (100) comprises a controller (10) configured to estimate a state of a driver on the basis of travel environment information a sight line of the driver. The controller calculates a predicted value of gaze frequency at which the driver gazes at a cautionary object, within a predetermined observation time, on the basis of relative risk, observable time, and vehicle speed, calculates a predicted value of gaze duration during which the driver continuously gazes at the cautionary object, within the predetermined observation time, on the basis of the observable time, acquires actual measured values of gaze frequency and gaze duration at / during which the driver gazes at the cautionary object within the predetermined observation time, calculates an abnormality degree of the driver on the basis of a product of a difference between the actual value and predicted value of gaze frequency, and a difference between the actual value and predicted value of gaze duration, and estimates that the driver is in a careless state when the abnormality degree is equal to or greater than a predetermined threshold.SELECTED DRAWING: Figure 3

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] One of the main causes of traffic accidents is a state in which a driver lacks concentration on driving, known as a distracted state. Conventionally, proposed technologies for detecting a distracted state include a technology that estimates a driver's concentration on driving based on the proportion of states in which the driver gazes at a forward gaze point, a driving gaze point, and a non-driving gaze point, and the duration of gaze (see, for example, Patent Document 1), and a technology that estimates that the current driver is in a state of decreased attention when the time constant of a driver model that expresses the time delay of gaze point movement is larger than the time constant of the driver's previous driver model or the time constant of a normative driver model (see, for example, Patent Document 2). [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Patent No. 7164275 specification [Patent Document 2] Patent No. 6958886 specification Summary of the Invention [Problem to be solved by the invention]

[0004] However, the conventional technology described above does not take into account differences in the driving environment, such as the vehicle speed and the surrounding congestion, and estimates the driver's state uniformly regardless of the driving environment. Therefore, when the driving environment changes significantly, for example, when entering a highway from an ordinary road, there is a possibility that the technology may erroneously determine that the driver is in a distracted state.

[0005] The present invention has been made to solve such problems, and aims to provide a driver state estimation device that can accurately estimate whether a driver is in an absentminded state regardless of the driving environment. [Means for solving the problem]

[0006] 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, the device comprising: a driving environment information acquisition device that acquires driving environment information of the vehicle; a gaze detection device that detects the driver's gaze; and a controller configured to estimate the state of the driver based on the driving environment information and the driver's gaze, the controller calculates a relative risk that represents the risk of the vehicle colliding with a cautionary object around the vehicle based on the driving environment information, calculates an observable time that represents the time during which the cautionary object was present in a position that the driver could gaze at, and calculates a relative risk, an observable time, and the vehicle state. Based on the vehicle speed and the vehicle speed, a predicted value of the gaze frequency, which indicates the number of times the driver will gaze at the object of attention during a specified observation time, is calculated; based on the observable time, a predicted value of the gaze time that the driver will continuously gaze at the object of attention during the specified observation time is calculated; based on the driving environment information and the driver's line of sight, actual measured values ​​of the gaze frequency and gaze time that the driver gazes at the object of attention during the specified observation time are obtained; based on the difference between the actual and predicted gaze frequency values ​​and the difference between the actual and predicted gaze time values, the driver's abnormality level is calculated based on the product of the difference between the actual and predicted gaze time values; and if the abnormality level is equal to or greater than a specified threshold, the driver is estimated to be in a distracted state.

[0007] According to the present invention configured in this manner, the controller calculates a predicted value of the gaze frequency based on the relative risk, the observable time, and the vehicle speed, calculates a predicted value of the gaze time based on the observable time, and estimates that the driver is in an absentminded state if the driver's abnormality level calculated based on the product of the difference between the actual and predicted values ​​of the gaze frequency and the difference between the actual and predicted values ​​of the gaze time is equal to or greater than a predetermined threshold. Therefore, it is possible to predict the gaze frequency and gaze time of a driver in a normal state with high accuracy by reflecting the influence of the driving environment on the gaze frequency and gaze time, and to accurately estimate the driver's state based on the difference from the actual values ​​of the gaze frequency and gaze time. This makes it possible to accurately estimate that the driver is in an absentminded state regardless of the driving environment.

[0008] In the present invention, the controller is preferably configured to identify the type of object to be careful of based on driving environment information, calculate the degree of abnormality for each type of object to be careful of, calculate an integrated degree of abnormality by combining the degrees of abnormality calculated for each type of object to be careful of, and estimate that the driver is in a distracted state if the integrated degree of abnormality is equal to or greater than a predetermined threshold value.

[0009] According to the present invention configured in this manner, the controller calculates an integrated abnormality degree by combining the abnormality degrees calculated for each type of object of attention, and if the integrated abnormality degree is equal to or greater than a predetermined threshold, it estimates that the driver is in a distracted state.Therefore, even if different systematic errors are included in the predicted values ​​of gaze frequency and gaze time depending on the type of object of attention, the driver's state can be estimated using the abnormality degrees calculated for each type of object of attention so that these multiple systematic errors are not superimposed, and it can be more accurately estimated that the driver is in a distracted state.

[0010] In the present invention, the types of attention objects preferably include a preceding vehicle, a lateral vehicle, and an unconfirmed object.

[0011] According to the present invention configured in this manner, even if different systematic errors are contained in the predicted values ​​of gaze frequency and gaze duration for each of the preceding vehicle, the vehicle to the side, and the unidentified object, the controller can estimate the driver's state using the degree of abnormality calculated individually for each of the preceding vehicle, the vehicle to the side, and the unidentified object so that these multiple systematic errors do not overlap, and can more accurately estimate whether the driver is in a distracted state. [Effects of the Invention]

[0012] According to the driver state estimating device of the present invention, it is possible to accurately estimate whether the driver is in an absentminded state regardless of the driving environment. [Brief explanation of the drawings]

[0013] [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] 4 is a flowchart of a driver state estimation process according to an embodiment of the present invention. [Figure 4] 1 is a conceptual diagram illustrating types of attention objects to which a driver's gaze is directed in an embodiment of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0014] 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.

[0015] [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.

[0016] 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.

[0017] 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.

[0018] 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.

[0019] 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 approach of surrounding structures at the four corners of vehicle 1, and various sensors that detect the driver's condition (e.g., a heart rate sensor, an electrocardiogram sensor, a steering wheel grip force sensor, etc.).

[0020] 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.

[0021] 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, the road, dividing lines (lane boundaries, white lines, yellow lines), traffic signals, traffic signs, stop lines, intersections, obstacles, etc.). Based on the image data received from the exterior camera 21, the controller 10 can also identify the curvature of the road on which the vehicle 1 is traveling and the illuminance outside the vehicle 1. The exterior camera 21 corresponds to an example of a "traveling environment information acquisition device" in the present invention.

[0022] 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.

[0023] 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 controller 10 can also identify the curvature and gradient of the road on which the vehicle 1 is traveling 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).

[0024] 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). Furthermore, the controller 10 can identify the gradient of the road on which the vehicle 1 is traveling based on the speed and acceleration of the vehicle 1. 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). Note that the vehicle speed sensor 25 and the acceleration sensor 26 also correspond to examples of the "traveling environment information acquisition device" in the present invention.

[0025] 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.

[0026] 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.

[0027] 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.

[0028] 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.

[0029] 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.

[0030] 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.

[0031] [Driver state estimation processing] Next, the driver state estimation process performed by the driver state estimation device 100 of this embodiment will be described with reference to Figures 3 and 4. Figure 3 is a flowchart of the driver state estimation process for estimating whether the driver is absentminded or normal. Figure 4 is a conceptual diagram for explaining the types of attention objects that the driver will direct their gaze towards.

[0032] The driver state estimation process 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).

[0033] When the driver state estimation process is started, first, the controller 10 acquires driving environment information based on signals received from sensors including the outside camera 21, radar 22, vehicle speed sensor 25, and acceleration sensor 26 (step S1).

[0034] Next, the controller 10 detects the driver's line of sight based on the signal received from the in-vehicle camera 32 (step S2).

[0035] Next, the controller 10 acquires an object (attention object) around the vehicle 1 to which the driver should turn his / her gaze, based on the driving environment information acquired in step S1 (step S3). In the driver state estimation process of this embodiment, another vehicle is used as the attention object.

[0036] Next, the controller 10 calculates an actual measurement value f of the gaze frequency to each attention object i during the most recent observation time (for example, 10 seconds) based on the driver's line of sight detected in step S2 and the attention object acquired in step S3. (i) and the actual measurement value of gaze time g (i) Specifically, based on the direction of the driver's line of sight identified based on the image acquired from the in-vehicle camera 32 and the position of the attention object acquired by the outside camera 21 and radar 22, if the direction of the driver's line of sight and the direction of the attention object overlap for a predetermined time (for example, 0.1 seconds) or more with the driver's head position as the reference, the controller 10 determines that the driver has gazed at the attention object. (i) is the number of times that the driver changed from not gazing at the attention object i to gazing at it during the most recent observation time (for example, 10 seconds). Also, the actual measurement value of the gaze time g (i)is the maximum or average value of the time that the driver continuously gazes at the attention object i during the most recent observation time (for example, 10 seconds). The controller 10 calculates the actual measurement value f of the gaze frequency obtained. (i) and the actual measurement value of gaze time g (i) is stored in the memory 10b.

[0037] Next, the controller 10 calculates the observable time T obs (i) (Step S5) The observable time T obs (i) is the time during which the attention object i was present in a position that the driver could gaze upon during the most recent observation time (for example, 10 seconds). For example, the controller 10 may calculate the time during which the attention object i was present within a predetermined angle range (for example, within 80 degrees left and right, and within 50 degrees up and down) from the traveling direction of the vehicle 1 based on the driver's head position as the observable time T obs (i) It is calculated as follows.

[0038] Next, the controller 10 calculates the relative risk R of each attention object i based on the driving environment information acquired in step S1. (i) The relative risk R is calculated (step S6). (i) is a numerical value between 0 and 1 that expresses the level of risk of the vehicle 1 colliding with the attention object i. For example, the controller 10 calculates the time to collision (TTC) of the attention object i based on the position and relative speed of the attention object i acquired by the outside camera 21 and the radar 22. Then, with the TTC as a variable, the smaller the TTC, the lower the relative risk R (i) The relative risk R (i) Calculate.

[0039] Next, the controller 10 calculates the speed v of the vehicle 1 acquired in step S1, the observable time T obs (i) , and the relative risk R calculated in step S6 (i)Based on this, the gaze frequency prediction value f p (i) (Step S7) calculates the gaze frequency prediction value f p (i) is calculated by the following equation, which models the gaze frequency of a driver in a normal state with respect to an object. p (i) is stored in the memory 10b. TIFF2025125309000002.tif14110

[0040] Here, v is the vehicle speed of vehicle 1, and h1 and h2 are each a nonlinear function. Based on data on vehicle speed, attention objects, and line of sight obtained through driving experiments using a driving simulator, the gaze frequency of a driver in a normal state under various driving conditions is measured, and the measured data is used to perform regression analysis, thereby determining the coefficients and constant terms of h1 and h2. The coefficients and constant terms of h1 and h2 that have been determined in advance are stored in memory 10b.

[0041] Generally, the higher the vehicle speed v, the lower the driver's dynamic visual acuity, so that in high-speed areas, the driver tends to be slow to notice an object of attention and the frequency of gaze tends to decrease. (i) Objects with high risk are likely to be detected late and the frequency of gaze decreases because they remain in the driver's field of vision for a short time. (i) affect the frequency of gazes. Furthermore, the observable time T obs (i) The longer the time, the more frequently the driver will look at the object of attention. Therefore, the vehicle speed v and relative risk R (i) and the observable time T obs (i) By hierarchically modeling the relationship between these, it is possible to predict the frequency of gaze on an attention object i with high accuracy.

[0042] Next, the controller 10 calculates the observable time T obs (i)Based on this, the gaze time prediction value g for each attention object i is calculated. p (i) (Step S8) calculates the gaze time prediction value g p (i) is calculated by the following equation, which models the gaze time of a driver in a normal state to an object. p (i) is stored in the memory 10b. TIFF2025125309000003.tif14110

[0043] Here, k is a nonlinear function. Based on data on attention objects and gaze obtained through driving experiments using a driving simulator, the driver's gaze time in a normal state under various driving conditions is measured, and regression analysis is performed using the measured data to determine the coefficient and constant term of k. The coefficient and constant term of k that have been determined in advance are stored in memory 10b.

[0044] The inventors have determined that the observable time T obs (i) It was experimentally confirmed that the longer the observable time T obs (i) By modeling the gaze duration using

[0045] Next, the controller 10 calculates the actual measurement value f of the gaze frequency for each attention object i. (i) and the actual measurement value of gaze time g (i) and the gaze frequency prediction value f p (i) and gaze time prediction value g p (i) Based on this, the abnormality degree GF of the driver's state for each type of attention object is calculated. f , G.F. s and GF u (Step S9). GF f indicates that the object of attention is a preceding vehicle, and GF s indicates that the object of attention is a vehicle on the side, and GF uindicates that the attention object is an unidentified object.

[0046] Here, the types of attention objects in this embodiment will be described with reference to Fig. 4. In Fig. 4, A is the host vehicle, B is a preceding vehicle traveling in the same lane as the host vehicle A, and C and D are lateral vehicles traveling in an adjacent lane ahead of the host vehicle. It is also assumed that the driver gazes at the preceding vehicle B and the lateral vehicle C, but does not gaze at the lateral vehicle D (for example, the driver directs his / her gaze for less than 0.1 seconds). In this embodiment, the types of attention objects are classified into three types: (1) the preceding vehicle B, (2) the lateral vehicle C, and (3) the unconfirmed object D.

[0047] The position of the leading vehicle is identified by image data acquired from the exterior camera 21, while the position of the lateral vehicle is identified by the radar 22, so different systematic errors are included in the position determination and gaze determination. Therefore, if the gaze frequency and gaze duration are evaluated without distinguishing between the leading vehicle, the lateral vehicle, and the unidentified object, multiple systematic errors will be included, and the estimation accuracy of the driver state will decrease.

[0048] Therefore, we classify objects to be careful of into three types: (1) preceding vehicles, (2) vehicles to the side, and (3) unidentified objects. By evaluating the difference between the actual and predicted values ​​of gaze frequency and gaze time, we are able to appropriately estimate the driver's state.

[0049] Specifically, the controller 10 calculates the actual measurement value f of the gaze frequency stored in the memory 10b for each attention object i during the most recent predetermined time (for example, 10 seconds). (i) and the actual measurement value of gaze time g (i) and the gaze frequency prediction value f p (i) and gaze time prediction value g p (i) and the anomaly degree GF for each attention object i is obtained using the following formula: val (i)The subscript "val" of this abnormality level is expressed as "f" if the type of object to be warned about is a leading vehicle, "s" if it is a side vehicle, or "u" if it is an unconfirmed object. In addition, "MA" in the formula below indicates the moving average for the most recent specified period. TIFF2025125309000004.tif14127

[0050] When there are multiple attention objects of the same type, the abnormality degree GF val (i) By calculating the average value of f , G.F. s and GF u is calculated.

[0051] Next, the controller 10 calculates the abnormality degree GF f , G.F. s and GF u For example, the controller 10 calculates the integrated abnormality degree d based on the abnormality degree GF f , G.F. s and GF u Three-dimensional data is accumulated using each of the above as a variable, and the Mahalanobis distance between the latest data point of this three-dimensional data and the center of gravity (average) of the accumulated data set is calculated as the integrated abnormality degree d.

[0052] Next, the controller 10 determines whether the integrated abnormality degree d calculated in step S10 is equal to or exceeds a threshold value d th It is determined whether or not this is the case (step S11).

[0053] As a result, the integrated anomaly score d is equal to the threshold d th If it is not equal to or greater than this (step S11: NO), the controller 10 estimates that the driver's state is normal (step S12), and ends the driver state estimation process.

[0054] On the other hand, the integrated anomaly level d is the threshold d thIf this is the case (step S11: YES), the controller 10 estimates that the driver is in an absentminded state (step S13).

[0055] Next, the controller 10 transmits control signals to the display 36 and the speaker 37 to output an alarm from the display 36 and the speaker 37 to notify the driver that the driver is in a distracted state (step S14). 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. After step S14, the controller 10 ends the driver state estimation process.

[0056] [Variations] In the above-described embodiment, the integrated abnormality degree d and the threshold value d th The driver's condition is estimated by comparing the overall abnormality score d with the abnormality score GF f , G.F. s and GF u The driver's state may be estimated by comparing the respective values ​​of the vehicle speed and the vehicle speed with predetermined threshold values.

[0057] In the above embodiment, the integrated abnormality degree d is calculated using the Mahalanobis distance, but the integrated abnormality degree d may be calculated by other calculation methods. For example, the abnormality degree GF f , G.F. s and GF u The combined value obtained by normalizing the above may be used as the integrated abnormality degree d.

[0058] Furthermore, in the above-described embodiment, other vehicles are used as attention targets, but pedestrians, obstacles, and the like may also be used in addition to other vehicles.

[0059] In addition, by performing individual learning for each driver, the gaze frequency prediction value f p (i) and gaze time prediction value g p (i) may be corrected.

[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 calculates the relative risk R (i) and the observable time T obs (i) and the speed v of vehicle 1, the predicted value f of the gaze frequency is calculated. p (i) Calculate the observable time T obs (i) Based on this, the predicted value of the gaze time g p (i) Calculate the actual value of gaze frequency f (i) and the predicted value f p (i) The difference between the two and the actual measurement value of the gaze time g (i) and the predicted value g p (i) The abnormality level d of the driver calculated based on the product of the difference between th In the above cases, it is estimated that the driver is in a distracted state, so that the gaze frequency and gaze duration of a driver in a normal state can be predicted with high accuracy by reflecting the influence of the driving environment on the gaze frequency and gaze duration, and the driver's state can be accurately estimated based on the difference from the actual measured values ​​of the gaze frequency and gaze duration. This makes it possible to accurately estimate that the driver is in a distracted state regardless of the driving environment.

[0062] The controller 10 also calculates the abnormality level GF val (i) The integrated abnormality degree d is calculated by combining the above, and the integrated abnormality degree d is calculated by combining the above and the above. th If the above condition is met, it is estimated that the driver is absentminded. Therefore, even if different systematic errors are included in the predicted values ​​of the gaze frequency and gaze time depending on the type of attention object, the abnormality degree GF is calculated for each type of attention object so that these multiple systematic errors are not superimposed. val (i) The driver's state can be estimated using the above equation, and it can be more accurately estimated that the driver is in an absentminded state.

[0063] Furthermore, even if different systematic errors are included in the predicted values ​​of the gaze frequency and gaze time for each of the preceding vehicle, the lateral vehicle, and the unconfirmed object, the controller 10 calculates the abnormality degree GF f , G.F. s and GF u The driver's state can be estimated using the above equation, and it can be more accurately estimated that the driver is in an absentminded state. [Explanation of symbols]

[0064] 1 vehicle 10 Controllers 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 driving environment information acquisition device for acquiring driving environment information of the vehicle; a gaze detection device for detecting the gaze of the driver; a controller configured to estimate a state of the driver based on the driving environment information and the driver's line of sight, The controller Calculating a relative risk representing a risk of the vehicle colliding with a caution object around the vehicle based on the driving environment information; calculating an observable time representing a time during which the attention object was present in a position that the driver could gaze upon based on the driving environment information; Calculating a predicted value of a gaze frequency representing the number of times the driver gazes at the attention object during a predetermined observation time based on the relative risk, the observable time, and the speed of the vehicle; calculating a predicted value of a gaze time during which the driver continuously gazes at the attention object during a predetermined observation time based on the observable time; Based on the driving environment information and the line of sight of the driver, actual measurement values ​​of a gaze frequency and a gaze time during which the driver gazes at the attention object during a predetermined observation time are acquired, calculating an abnormality degree of the driver based on a product of a difference between an actual measurement value and a predicted value of the gaze frequency and a difference between an actual measurement value and a predicted value of the gaze time; When the degree of abnormality is equal to or greater than a predetermined threshold, it is estimated that the driver is in an absentminded state. Driver state estimation device.

2. The controller Identifying the type of the attention object based on the driving environment information; Calculating the degree of abnormality for each type of the attention object; calculating an integrated abnormality degree by combining the abnormality degrees calculated for each type of the attention object; When the integrated abnormality degree is equal to or greater than a predetermined threshold, it is estimated that the driver is in an absentminded state. The driver state estimating device according to claim 1 .

3. The driver state estimation device according to claim 2 , wherein the types of the attention object include a preceding vehicle, a lateral vehicle, and an unconfirmed object.

Images