JP2018097485A - Driving support apparatus, driving support method, driving support program, and driving support system - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a technology of driving support in accordance with a state and characteristics of a driver.SOLUTION: A driving support apparatus includes: data acquisition means of acquiring activity data of a driver measured by a sensor for sensing a state or activity of a part of a body; reference data management means of setting reference data for each state of the driver, on the basis of the activity data of the driver measured in past; estimation means of estimating a state of the driver by comparing the acquired activity data of the driver with the reference data; determination means of determining a type to which the driver belongs, on the basis of driving operation characteristics; and presentation means of presenting driving support information in accordance with the estimated state of the driver and the type of the driver.SELECTED DRAWING: Figure 6

Description

  The present invention relates to a driving support device, a driving support method, a driving support program, and a driving support system.

  In the recent automobile society, various driving support functions are mounted on vehicles in order to prevent traffic accidents. One of the main causes of traffic accidents is random driving in which the driver's attention is reduced due to fatigue or thinking. On the other hand, when a driver's state is estimated and it is presumed that it is an indiscreet state where attention is reduced, a technique for issuing a warning for alerting has been proposed (for example, see Patent Document 1). ).

JP2015-33457A

  For example, a method has been proposed in which whether or not the driver is in a state of ambiguity is estimated based on biological information obtained by measuring the driver's heart rate, sweating amount, or the like. However, biological information such as heart rate and sweating amount in a normal state varies depending on the driver. Further, it is conceivable that a driver practicing safe driving and a driver who tends to neglect safe driving have different timings for recognizing danger and characteristics related to driving operations such as acceleration and deceleration. When the characteristics of the driver are different, the biological information measured in the random state may be different. Therefore, even if it is estimated whether or not the driver is in a state of ambiguity without considering the driver's characteristics, driving support information such as warnings according to the driver's condition and characteristics is presented at an appropriate timing. It seems difficult to do.

  Then, an object of this invention is to provide the technique which performs the driving assistance according to a driver | operator's state and characteristic.

  In order to solve the above-described problems, the present invention responds to “a type to which a driver determined based on characteristics of driving operation belongs” and “a driver state estimated by comparing life activity data with reference data”. I decided to provide driving assistance. The life activity data is data measured by a sensor that detects a state or activity of a part of the body.

  Specifically, the present invention is a driving support device, which is a data acquisition means for acquiring a driver's life activity data measured by a sensor for detecting a state or activity of a part of the body, and for each state of the driver. The reference data management means for setting the reference data of the driver, the estimation means for estimating the driver's state by comparing the acquired driver's life activity data with the reference data, and the driver based on the characteristics of the driving operation Determination means for determining a type to which the vehicle belongs, and presentation means for presenting driving support information corresponding to the estimated driver state and the type to which the driver belongs.

According to the above driving assistance device, it is possible to present appropriate driving assistance information according to the state of the driver and the type to which the driver belongs. The state of the driver is roughly divided into a normal state and an abnormal state. The non-normal state is, for example, a state where attention is reduced due to fatigue or thoughts, a state where there is no calmness while driving aside, and a state where the destination is rushed. The type to which the driver belongs (hereinafter also referred to as the driver type) is a type for classifying the driver based on the characteristics of the driving operation such as the accelerator, the brake, and the steering wheel. The type to which the driver belongs may be a predefined type, or may be a type extracted from accumulated driving operation characteristic data by statistical processing such as clustering. The life activity data is data measured by a sensor that detects a state or activity of a part of the body, and includes, for example, a gaze activity amount obtained from a gaze movement, a heart rate, and the like. The driving support information includes information that raises the driver's awareness of safe driving and leads to coaching.

  According to the driving support apparatus including the above-described reference data management means, the reference data for determining the state for each driver is set. For this reason, when the movement of the driver's line of sight or the driving operation is different from the reference data in the normal state of the driver, the state of the driver is estimated to be an abnormal state. Since the reference data corresponding to the driver is set, it is possible to accurately estimate the driver's state.

  Further, the reference data management means may update the set reference data at a predetermined timing. With such reference data management means, the reference data is updated based on the accumulated past life activity data, so that it is possible to estimate the driver's state with higher accuracy. For example, in a patient with visual field stenosis, the visual field gradually becomes narrower or part of the visual field becomes narrower, so that the biological activity data measured in the normal state may change gradually. By updating the reference data at a predetermined timing, the driving support apparatus can accurately estimate the state of the driver even for a patient with visual field stenosis or the like. The predetermined timing is, for example, the timing when the driver finishes traveling.

  The sensor may measure the driver's gaze activity amount, and the estimation means may estimate the driver's state based on a change in the driver's gaze activity amount. With such a driving support device, it is possible to estimate the driver's state by a simple process such as imaging of the line of sight.

  The present invention can also be understood from a method aspect. For example, the present invention provides a data acquisition step in which a computer acquires a driver's life activity data measured by a sensor that detects a state or activity of a body part, and a driver's life activity data measured in the past. A reference data management step for setting reference data for each state of the driver, and an estimation step for estimating the driver's state by comparing the acquired driver's life activity data with the reference data; A determination unit that determines a type to which the driver belongs based on characteristics of the driving operation, and a presentation step that presents driving support information according to the estimated state of the driver and the type to which the driver belongs. It may be a support method.

  The present invention can also be understood from the aspect of a computer program. For example, the present invention provides a computer with a data acquisition step of acquiring a driver's life activity data measured by a sensor that detects a state or activity of a part of the body, and a driver's life activity data measured in the past. A reference data management step for setting reference data for each state of the driver, and an estimation step for estimating the driver's state by comparing the acquired driver's life activity data with the reference data; Driving means for executing determination means for determining a type to which the driver belongs based on characteristics of the driving operation and a presentation step for presenting driving support information according to the estimated driver state and the type to which the driver belongs It may be a support program.

The present invention can also be understood from the aspect of the system. For example, the present invention is a driving support system including a server and a driving support device, and the server includes classification means for classifying a driver into a plurality of types based on characteristics of driving operation. Data acquisition means for acquiring the driver's life activity data measured by a sensor that detects a part of the state or activity of the driver, and reference data for each driver state based on the acquired driver's life activity data The reference data management means for setting the driver, the estimation means for estimating the driver's state by comparing the acquired driver's life activity data with the reference data, and the type to which the driver belongs based on the characteristics of the driving operation And a presenting means for presenting driving support information corresponding to the estimated driver state and the type to which the driver belongs.

  ADVANTAGE OF THE INVENTION According to this invention, the driving assistance according to a driver | operator's state and characteristic can be performed.

FIG. 1 is a diagram illustrating a hardware configuration of a driving support system. FIG. 2 is a diagram illustrating a functional configuration of the driving support device. FIG. 3 is a diagram illustrating a functional configuration of the server. FIG. 4 is a diagram illustrating an example of a questionnaire for determining the type of driver. FIG. 5 is a diagram illustrating an example of a graph showing the movement of the line of sight for each state. FIG. 6 is a diagram illustrating an example in which the driver's state is estimated from the gaze activity amount. FIG. 7 is a diagram illustrating the content of driving support on a downhill. FIG. 8 is a diagram illustrating the timing of driving support on a downhill. FIG. 9 is a diagram illustrating a display example of driving support information. FIG. 10 is a diagram illustrating the content of driving assistance during a left turn or a right turn. FIG. 11 is a diagram illustrating a display example of the recognition signal device. FIG. 12 is a diagram illustrating the timing for displaying the recognition signal. FIG. 13 is a diagram illustrating the timing for displaying the recognition signal. FIG. 14 is a diagram illustrating an example of displaying a visual recognition state of the driver around the vehicle body. FIG. 15 is a diagram illustrating an example of displaying a visual recognition state of the driver around the vehicle body in a casual state. FIG. 16 is a flowchart illustrating the flow of processing for presenting driving support information.

  Hereinafter, embodiments will be described. The embodiment described below is merely an example, and the technical scope of the present disclosure is not limited to the following aspect.

  In the present embodiment, the driving support device acquires the driver's life activity data measured by a sensor that detects a state or activity of a part of the body, and drives based on the acquired driver's life activity data. The person's condition is estimated. Further, the driving support device determines a type to which the driver belongs based on characteristics of the driving operation, and presents driving support information according to the estimated driver state and the type to which the driver belongs. Accordingly, the driving support device can present appropriate driving support information according to the characteristics of the driver and the driving state.

<Hardware configuration>
FIG. 1 is a diagram illustrating a hardware configuration of a driving support system. The driving support system 100 includes a driving support device 1 and a server 2. The driving support device 1 and the server 2 are connected to each other by a network N1. The driving support device 1 is connected to various devices mounted on the vehicle 3 through a network N2.

  The driving support device 1 includes a processor 11, a main storage device 12, an auxiliary storage device 13, and a network interface 14. These are electrically connected to each other by a bus 15.

  The processor 11 executes various processes by loading the OS and various computer programs held in the auxiliary storage device 13 into the main storage device 12 and executing them. However, a part of the processing by the computer program may be executed by a hardware circuit. The processor 11 is, for example, a CPU (Central Processing Unit) or a DSP (Digital Signal Processor).

The main storage device 12 provides the processor 11 with a storage area for loading a program stored in the auxiliary storage device 13 and a work area for executing the program. The main storage device 12 is used as a buffer for holding data. The main storage device 12 is, for example, a ROM (Read Only Memory), a RAM (Random).
This is a semiconductor memory such as Access Memory.

The auxiliary storage device 13 stores various programs and data used by the processor 11 when executing each program. The auxiliary storage device 13 is, for example, an EPROM (Erasable Programmable ROM) or a hard disk drive (Hard).
A non-volatile memory such as a disk drive (HDD). The auxiliary storage device 13 holds, for example, an operating system (Operating System, OS), a driving support program, and other various application programs. The driving support program is a program for presenting driving support information according to the state of the driver and the type to which the driver belongs.

  The network interface 14 is an interface for inputting / outputting information to / from the network. The network interface 14 includes an interface connected to a wired network and an interface connected to a wireless network. The network interface 14 is, for example, a wireless circuit for connecting to a mobile phone network such as a NIC (Network Interface Card), a wireless LAN (Local Area Network) card, a 3G (3rd Generation), or an LTE (Long Term Evolution). . Data received by the network interface 14 is output to the processor 11.

  Note that the hardware configuration of the driving assistance device 1 shown in FIG. 1 is an example, and is not limited to the above, and components can be omitted, replaced, or added as appropriate according to the embodiment. For example, the driving support device 1 may include an interface with various devices such as a wearable sensor and acquire data from the various devices.

  The server 2 includes a processor 21, a main storage device 22, an auxiliary storage device 23, and a network interface 24. These are electrically connected to each other by a bus 25.

  The processor 21 executes various processes by loading the OS and various computer programs held in the auxiliary storage device 23 into the main storage device 22 and executing them. However, a part of the processing by the computer program may be executed by a hardware circuit. The processor 21 is, for example, a CPU or a DSP.

  The main storage device 22 provides the processor 21 with a storage area for loading a program stored in the auxiliary storage device 23 and a work area for executing the program. The main storage device 22 is used as a buffer for holding data. The main storage device 22 is a semiconductor memory such as a ROM and a RAM, for example.

The auxiliary storage device 23 is a processor 2 for executing various programs and each program.
1 stores data to be used. The auxiliary storage device 23 is, for example, a nonvolatile memory such as an EPROM or a hard disk drive. The auxiliary storage device 23 holds, for example, an OS, a program for analyzing various data, and various other application programs.

  The network interface 24 is an interface for inputting / outputting information to / from the network. The network interface 24 includes an interface for connecting to wired and wireless networks. The network interface 24 is, for example, a NIC or a wireless LAN card. Data received by the network interface 24 is output to the processor 11.

  Note that the hardware configuration of the server 2 shown in FIG. 1 is an example, and is not limited to the above, and components can be omitted, replaced, or added as appropriate according to the embodiment.

  The vehicle 3 is a vehicle on which a driver who is a target for driving assistance rides, and includes a sensor 31 and an output device 32. Note that the number of sensors 31 is not limited to one, and a plurality of sensors 31 may be provided.

  The sensor 31 includes a plurality of sensors such as a sensor that measures information about a person on board, an external sensor that measures the state of the outside, and an in-vehicle sensor that measures the speed of the vehicle 3 and detects a driving operation. The sensor 31 detects the driver's line of sight or measures biological information in order to estimate the driver's state. The sensor 31 also detects obstacles around the vehicle 3 and recognizes road information such as road signs and road markings. Furthermore, the sensor 31 measures the speed and acceleration of the vehicle, and detects driving operations on the steering wheel, accelerator, brake, and the like.

  Specifically, the sensor 31 is a camera for detecting the driver's line of sight, a heart rate sensor or an electroencephalogram sensor for measuring biological information, a radar for recognizing the surrounding situation of the vehicle 3, a stereo camera, or the like. It is a sensor. Note that in V2X communication including road-to-vehicle communication in which information is exchanged between the vehicle and the roadside machine and vehicle-to-vehicle communication in which the vehicle directly exchanges information, a device used for communication with the roadside machine or another vehicle is also a kind of sensor 31. It is.

  The output device 32 displays the driving support information presented by the driving support device 1. The output device 32 is, for example, a head-up display (Head-Up Display, HUD) that displays information superimposed on the human visual field, or an in-vehicle liquid crystal display (Liquid Crystal Display, LCD). The HUD is a transmissive inorganic electroluminescence (EL) display, which can be installed on a dashboard or can be projected on the entire windshield.

  The network N1 is a worldwide public packet communication network such as the Internet, and connects the driving support apparatus 1 and the server 2. Instead of the Internet, a WAN (Wide Area Network) or other communication network may be employed.

  The network N2 is a communication network constructed by a dedicated communication line, and connects the driving support device 1 and the vehicle 3. As the network N2, Wi-Fi, Bluetooth (registered trademark), Ethernet (registered trademark), a body area network (Body Area Network, BAN) constructed by wireless communication with a small terminal placed on the surface of the body, etc. In-vehicle communication networks such as a controller area network (CAN) and a FlexRay may also be adopted.

<Functional configuration>
<< Driving support device >>
FIG. 2 is a diagram illustrating a functional configuration of the driving support device 1. The driving support device 1 includes a type determination unit F11, a data acquisition unit F12, a state estimation unit F13, a reference data management unit F14, a presentation unit F15, and a driving support information database D11 as functional configurations. The driving support device 1 reads out the program stored in the auxiliary storage device 13 to the main storage device 12 and executes it by the processor 11, whereby the type determination unit F11, the data acquisition unit F12, and the state estimation unit F13. , Functioning as a computer including a reference data management unit F14, a presentation unit F15, and a driving support information database D11.

  In the present embodiment, each function provided in the driving support device 1 is executed by the processor 11 that is a general-purpose processor. However, some or all of these functions are performed by one or more dedicated processors and hardware operations. It may be executed by a circuit or the like. Here, the hardware arithmetic circuit refers to, for example, an adder circuit, a multiplier circuit, a flip-flop, etc. combined with logic gates. Some or all of these functions may be executed by a separate computer.

  The type determination unit F11 determines the type of the driver. The type determination unit F11 determines the type of the driver according to the driving operation characteristics such as the accelerator, the brake, and the steering wheel. Specifically, the characteristics of the driving operation are data such as the accelerator depression time, the brake depression timing, and the steering wheel turning speed when the driver actually drives the vehicle 3. The type determination unit F11 compares with data related to a plurality of types of driving operation characteristics set in advance (hereinafter also referred to as teacher data), and determines which type the driver belongs to based on the degree of matching To be able to. The teacher data for each type may be set in advance based on characteristic driver actual measurement data and held in the auxiliary storage device 13 of the driving support device 1. When the driver does not change, the determined driver type can be held in the auxiliary storage device 13 of the driving support device 1.

  Further, when there is no teacher data, the server 2 accumulates data related to the characteristics of driving operations of a plurality of drivers, and each driver is classified into a plurality of types recursively by a technique such as clustering. Good. The type determination unit F11 determines to which driver type the driver to be determined belongs in the server 2 belongs to.

  The characteristic of the driving operation may be based on the answer result of the questionnaire including the question related to the characteristic of the driving operation, not the actual driving operation of the accelerator, the brake, the steering wheel, and the like. That is, the type determination unit F11 determines the type of the driver based on the answer to the driver's questionnaire.

  FIG. 4 is a diagram illustrating an example of a questionnaire for determining the type of driver. The questionnaire shown in FIG. 4 illustrates nine questions regarding driving operations. Each question is answered in four stages: (1) not applicable, (2) a little true, (3) some good, (4) true. The type determination unit F11 compares the questionnaire response of the determination target driver with the questionnaire response for each type serving as the teacher data, based on the degree of match, as in the case of determining the type by actual driving operation. Thus, it can be determined which type the driver belongs to.

Further, as in the case where the type is determined by actual driving operation, when there is no teacher data, the server 2 accumulates answers of questionnaires of a plurality of drivers, and each driving is recursively performed by a method such as clustering. A person may be classified into a plurality of types. The type determination unit F11 determines to which driver type the driver to be determined belongs in the server 2 belongs to. The type determination unit F11 is an example of a “determination unit”. The type of driver is an example of “a type to which the driver belongs”.

  The data acquisition unit F12 acquires data measured by the sensor 31 mounted on the vehicle 3. The data measured by the sensor 31 is, for example, data for estimating the driver's state, and is a gaze activity amount calculated from the driver's gaze detected by the camera. The data measured by the sensor 31 may be biological information such as a driver's heart rate and brain waves. The data acquisition unit F12 may acquire data measured by a wearable sensor worn by the driver in addition to the sensor 31 mounted on the vehicle 3. Furthermore, the data acquisition unit F12 acquires information such as road signs or obstacles recognized by the sensor 31. Information such as road signs or obstacles can be used to determine the timing for presenting driving support information. The data acquisition unit F12 is an example of a “data acquisition unit”.

  Based on the data acquired by the data acquisition unit F12, the state estimation unit F13 estimates the state of the driver, such as whether the driver is in a normal state or is in a casual state with reduced attention. The state of the driver is not limited to the normal state and the random state, and may be a state of calmness, a frustrated state, or the like, and driving support information corresponding to the state may be defined in advance. Further, different driving support information may be presented according to the degree of the state of disorder. Here, an example in which the state of the driver is estimated based on the gaze activity amount will be described with reference to FIGS. 5 and 6.

  FIG. 5 is a diagram illustrating an example of a graph showing the movement of the line of sight for each state. Graph G1, graph G2, and graph G3 show line-of-sight movements during normal driving, random driving, and side-view driving, respectively. The horizontal axis of each graph represents time, and the vertical axis represents the amount of gaze activity. In FIG. 5, the amount of gaze activity means the amount of gaze movement. The movement destination area of the line of sight counted as a positive activity amount is, for example, the front right sidewalk, the rear right side mirror, the rear left side mirror, the rear rearview mirror, the front right opposite lane, the front left sidewalk, and the forward traveling direction. . The movement destination area of the line of sight counted as a negative amount of activity is, for example, a lateral direction by looking aside or looking away, or a downward direction by carrying or the like.

  A graph G1 showing the movement of the line of sight during normal driving shows a state in which the amount of positive activity increases for a certain time T. During normal driving, the driver turns his face and line of sight at predetermined intervals toward the front, left and right of the road, and the rear, indicating that the driver is checking the situation for safe driving. A graph G <b> 2 showing the movement of the line of sight during the rough driving shows a state in which the amount of positive activity decreases in a certain time T. When driving abruptly, the driver feels drowsy or thinks, so the amount of gaze activity decreases compared to when driving with safety in mind, and the surrounding situation is properly checked It is shown that they are not. A graph G3 showing the movement of the line of sight during the side-view driving shows a state in which the amount of negative activity increases in a certain time T. When driving aside, the driver's line-of-sight activity in a different direction from normal driving increases, such as the frequency of looking down to see a mobile phone placed on his lap. It shows that he is driving aside without checking properly.

  FIG. 6 is a diagram illustrating an example in which the driver's state is estimated from the gaze activity amount. First, the camera as the sensor 31 of the vehicle 3 detects the driver's line of sight (P1). An image captured by the camera is analyzed by an existing image processing technique. The direction of the line of sight can be acquired by a three-dimensional vector.

  Based on the line-of-sight information detected in P1, the line-of-sight activity ET is calculated (P2). The line-of-sight activity ET is calculated based on the amount of activity related to the direction of movement of the line of sight and the amount of activity related to the frequency of movement of the line of sight.

First, the moving direction of the line of sight is evaluated (P21). With the eye position as the origin O, the movement direction of the line of sight in a certain time interval T is plotted from the three-dimensional vector acquired in the process of P1. Area A1, area A2, and area B are areas set in advance. The area A1 is an area where it is necessary to distribute the line of sight. The area A2 is an area for which it is recommended to distribute the line of sight. Area B is an area where it is not recommended to distribute the line of sight. The amount of activity related to the movement direction of the line of sight is calculated by weighting the frequency of the line of sight distributed to each area corresponding to the area. Specifically, the line of sight to the area A1 and the area A2 is weighted as a positive activity amount. In addition, since the area A1 is an area where it is necessary to distribute the line of sight, the degree of weighting is greater than the area A2. On the other hand, the line of sight to area B is weighted as a negative amount of activity.

  Next, the movement frequency of the line of sight is evaluated (P22). In order to estimate the movement frequency of the line of sight, a change in the amount of movement of the line of sight in a certain time interval T is measured, and the power spectrum of the absolute value of the line of sight movement is obtained. The histogram shown in P22 is a graph showing the frequency for each frequency band based on the obtained power spectrum. The vertical axis represents the frequency and the horizontal axis represents the frequency band. The frequency band in the range of H2 indicates the frequency (frequency) at which a line of sight moving with an appropriate frequency is detected. On the other hand, the frequency band in the range of H1 indicates the frequency (frequency) at which the line of sight moving at a frequency lower than the appropriate frequency is detected. The frequency band in the range of H3 indicates the frequency (frequency) at which the line of sight moving at a frequency higher than the appropriate frequency is detected. The amount of activity related to the movement frequency can be calculated by giving a weight according to the movement frequency of the line of sight. For example, negative weighting may be performed when the frequency is lower than the appropriate frequency, and positive weighting may be performed when the frequency is higher than the appropriate frequency.

  In addition, although the activity amount regarding a movement frequency can be measured irrespective of a moving direction, it is not restricted to this. A change in the amount of movement of the line of sight for each area described in P21 may be measured, and a histogram as shown in P22 may be generated for each area. In this case, the gaze activity amount may be calculated by weighting each area. The line-of-sight activity amount ET is obtained, for example, by adding the amount of activity related to the line-of-sight movement direction and the amount of activity related to the line-of-sight movement frequency.

  The gaze activity amount ET is calculated, and the road status ST in the time interval T in which the gaze is detected is evaluated (P3). The situation ST is, for example, a situation such as a curve with a poor view, a gentle curve, a straight line on an expressway, or an intersection. The situation ST can be estimated from GPS (Global Positioning System) and map information associated with road information. Further, the situation ST may be estimated by utilizing information on the road situation obtained by V2X communication or information such as speed obtained from the vehicle 3.

  The road status ST and the line-of-sight activity ET are processed based on a predetermined determination device (P4). The determiner defines conditions for determining the state of the driver for each road condition ST. For example, in a certain situation ST0, the determiner determines that the specified gaze activity amount ET0 is equal to or greater than a predetermined threshold value, and determines that the normal state is present. A predetermined threshold value can be set so as to determine. In addition, in a situation ST1, the determiner determines that the normal state is in the range of the line-of-sight activity amount ET1 within a predetermined value range, and is in a loose state if the line-of-sight activity amount ET1 is outside the range of the predetermined value. You may make it determine with there (P5). Note that the method for estimating the driver state shown in FIG. 6 is an example, and the driver state can be estimated by analyzing the movement of the line of sight by various methods. The state estimation unit F13 is an example of an “estimator”.

The reference data management unit F14 manages data serving as a reference (hereinafter also referred to as reference data) when estimating the state of the driver. The reference data is set for each state such as a normal state and a sloppy state of the driver. The reference data can be, for example, threshold values for the number of times that the line of sight is moved in a direction to be seen within a predetermined time and the number of times the line of sight is moved in another direction within a predetermined time. There are various ways of moving the line of sight and the frequency of movement depending on the driver, and when the number of times the rearview mirror is confirmed within a predetermined time in a given situation is less than the number of checks in the driver's normal state, the driver is in a loose state This makes it possible to recognize the change in the driver's own state with higher accuracy. The state estimation unit F13 can estimate the state of the driver by comparing the measured value for the driving driver with a threshold set as reference data.

  Further, the reference data may be updated based on the accumulated data of the driver's own gaze activity amount. The reference data management unit F14 accumulates the gaze activity amount of the driver in a similar situation around the vehicle 3 for each state of the driver, calculates an average value of the data accumulated at a predetermined timing, and calculates The reference data can be updated with the determined value. The driver's gaze activity data is stored in the auxiliary storage device 13 of the driving support device 1 or the auxiliary storage device 23 of the server 2. When the driver's line-of-sight activity data is accumulated in the auxiliary storage device 13, the reference data management unit F <b> 14 can periodically update the reference data based on the data accumulated in the auxiliary storage device 13. When the driver's gaze activity data is accumulated in the auxiliary storage device 23 of the server 2, the reference data management unit F <b> 14 acquires the reference data calculated from the data accumulated in the auxiliary storage device 23 by the server 2. The reference data may be updated with the acquired value. The reference data management unit F14 is an example of “reference data management means”.

  In this embodiment, although the state estimation part F13 and the reference data management part F14 demonstrated the example which estimates a driver | operator's state or manages reference | standard data based on a driver | operator's gaze activity amount, It is not limited to cases based on gaze activity. The state estimation unit F13 and the reference data management unit F14 may estimate the driver's state or manage reference data based on changes in biological information such as heart rate or driving operation characteristics.

  The presentation unit F15 presents driving support information according to the driver state estimated by the state estimation unit F13 and the driver type determined by the type determination unit F11. The driving support information corresponding to the driver's state and the driver's type is stored in advance in the driving support information database D11. The presented driving assistance information is transmitted to the vehicle 3 via the network N2 and displayed on the output device 32. Hereinafter, examples of the presentation contents of the driving support information will be described with reference to FIGS. The output device 32 is described as being a HUD, but is not limited thereto, and may be an in-vehicle liquid crystal display or the like. Moreover, the output device 32 should just be installed in the position which a driver | operator can visually recognize during a driving | operation, and it is desirable to install in the range of the viewing angle at the time of a driver | operator confirming the condition of the external field. In addition, for a driver with a limited visual field, such as a patient with a narrowed visual field, it is desirable that the driver is installed within the limited visual field range. The presentation unit F15 is an example of a “presentation unit”.

[Example 1-1 of driving support information]
FIG. 7 is a diagram illustrating the content of driving support on a downhill. On long downhills, the speed may accelerate even if engine braking is used. When there is a sharp curve at the end of the downhill, a warning for driving operation corresponding to the type of the driver is displayed on the HUD in order to decelerate the curve to a speed at which the curve can be safely turned. In the example of FIG. 7, type A and type B are exemplified as the driver type. A type A driver is assumed to be a type of driver who can properly perform a brake operation. The type B driver is assumed to be a driver who takes time to judge the situation in the outside world and does not perform brake operation properly. As a driver | operator's state, a normal state and a casual state are illustrated.

When the driver's state is the normal state, the driving support device 1 determines that a warning is not necessary for the type A driver. On the other hand, the driving assistance device 1 prompts the type B driver to decelerate by voice, and displays a mark instructing deceleration on the HUD. The mark for instructing deceleration schematically shows, for example, how the road flows in the direction opposite to the traveling direction.

  When the driver's state is an ambiguous state, the driving support device 1 sounds a notification sound or prompts the driver to check the speedometer by voice. The driving support device 1 displays a mark for calling attention to the HUD, for example, an exclamation mark. On the other hand, the driving assistance device 1 prompts the type B driver to step on the brake by voice. Moreover, the driving assistance apparatus 1 displays the mark which instruct | indicates deceleration to HUD similarly to a normal state, and also displays an engine brake, a normal brake, and a warning mark in steps according to the deceleration condition.

  FIG. 8 is a diagram illustrating the timing of driving support on a downhill. In the example of FIG. 8, the timing at which the content of the driving assistance described in FIG. 7 is displayed on the HUD is shown for each type of driver. Specifically, the driving support device 1 determines the speed of the vehicle 3, the total weight of the vehicle 3 including the passenger and the load, and the slope of the downhill so that the speed of the vehicle is reduced to 30 km / h at the tip of the downhill. The driving support information is displayed at an appropriate timing in consideration of the rate and the level of the driver's obscure state.

  When the type A driver is in a normal state, the driving support device 1 does not alert. On the other hand, when the type A driver is in a sloppy state, the driving support device 1 is a position where the vehicle 3 is to apply the engine brake or step on the brake to decelerate to the target speed of 30 km / h at the tip of the downhill A notification sound is sounded at the timing of reaching. In the example of FIG. 8, when the speed of the vehicle 3 reaches 60 km / h, a notification sound “phone” is sounded. If it is determined from the deceleration status of the vehicle 3 that it is difficult to decelerate to the target speed at the tip of the downhill, the driving support device 1 alerts the HUD with a voice saying “Please check the speed”. Display the mark for. In the example of FIG. 8, the driving support device 1 alerts when the speed of the vehicle 3 is reduced to 50 km / h.

  For the type B driver in the normal state, the driving support device 1 sounds a notification sound in the same manner as in the case where the type A driver is in a loose state. Furthermore, the driving assistance apparatus 1 displays a deceleration instruction on the HUD when entering a downhill.

  For the type B driver in a busy state, a notification sound is emitted as in the case where the type B driver is in the normal state. Moreover, the driving assistance apparatus 1 displays a deceleration instruction on the HUD at the time of entering the downhill. Furthermore, when the type B driver is in a sloppy state, the driving assistance device 1 notifies the driver of the timing of the deceleration operation by voice and display on the HUD. Specifically, the driving support device 1 notifies the driver of the timing of applying the engine brake, the timing of stepping on the brake, and the timing when the deceleration is delayed according to the deceleration state of the vehicle 3. In the example of FIG. 8, the driving support device 1 displays on the HUD a mark that prompts the engine brake to be applied together with a notification sound.

  In addition, when the type B driver is in an ambiguous state, the driving support device 1 presents driving support information when the hourly speed of the vehicle 3 exceeds a predetermined threshold on a downhill. In the example of FIG. 8, the driving assistance device 1 displays a mark on the HUD that prompts the user to step on the brake when the speed of the vehicle 3 reaches 70 km / h. Further, the driving support device 1 prompts the user to step on the brake by voice when the deceleration is delayed and the speed of the vehicle 3 reaches 80 km / h, and a warning mark is displayed on the HUD. Note that when the deceleration is delayed, the driving support apparatus 1 may appropriately change the mode of notification, such as increasing the volume of a warning by voice, or increasing the display on the HUD to blink.

FIG. 9 is a diagram illustrating a display example of driving support information. FIG. 9 illustrates a state when the outside world is viewed from the driver's seat of the vehicle 3. A region M surrounded by a dotted line on the windshield is a HUD display region. In the area M, a warning mark is displayed when the driver of type A in FIG. The driving assistance apparatus 1 changes the display content of the area | region M according to a driver | operator's state and a driver | operator's type.

[Example 1-2 of driving support information]
FIG. 10 is a diagram illustrating the content of driving assistance during a left turn or a right turn. When making a left or right turn at an intersection, it is necessary to check various situations such as a vehicle from behind, an oncoming vehicle, a pedestrian crossing a pedestrian crossing, and a bicycle entering the intersection. In order to prompt the driver to check the surrounding situation, a warning corresponding to the type of the driver is displayed on the HUD. In the example of FIG. 10, type A and type B are exemplified as the driver type. A type A driver is assumed to be a type of driver who starts out carefully. A type B driver is assumed to be a type of driver who quickly turns by stepping on the accelerator. As a driver | operator's state, a normal state and a casual state are illustrated.

  When the driver's state is the normal state, the driving support device 1 determines that a warning is not necessary for the type A driver. On the other hand, the driving support device 1 prompts the type B driver to confirm the situation by voice, and displays a mark prompting the HUD to confirm the situation in each direction when turning left or right. The confirmation of the situation of the driver is promoted by displaying a mark prompting the confirmation of the situation on the HUD that enters the field of view while driving.

  When the driver's state is indiscreet, the driving assistance device 1 displays a mark for prompting the type A driver to confirm the situation in each direction when turning left or right on the HUD. Increase the blink rate. On the other hand, the driving assistance device 1 presents driving assistance information similar to that of the type A driver to the type B driver, and switches to warning display when the surrounding situation is not confirmed. The warning display may be made larger than the mark for prompting the situation confirmation, or the blinking speed may be made faster.

[Example 2 of driving support information]
FIG. 11 is a diagram illustrating a display example of the recognition signal device. FIG. 11 illustrates a situation when the outside world is viewed from the driver's seat of the vehicle 3. A region M surrounded by a dotted line on the windshield is a HUD display region. In the area M, three circles such as traffic lights (hereinafter referred to as recognition traffic lights) are displayed, and the rightmost circle shows a state of being painted red. As a display example of the recognition signal device, four examples are shown in FIG. Display example CT1 indicating a state in which all three circles are extinguished indicates that a stop sign has been recognized. Display example CT2 indicating a state in which the rightmost circle is lit red is displayed when the driver is prompted to decelerate. Display example CT3 showing a state in which the center circle is lit yellow is displayed when a safety confirmation action is taken in accordance with a stop instruction. The state CT4 in which the display of the recognition signal itself disappears prompts the start by the display of the recognition signal disappearing.

  12 and 13 are diagrams illustrating the timing for displaying the recognition signal. In the above-described example, whether the driver is in a normal state or a random state is estimated based on the amount of gaze activity, but in the example of the cognitive traffic signal according to Example 2, the driver is based on the timing of deceleration. It is estimated whether it is a normal state or a random state. 12 and 13, the horizontal axis direction represents distance, and the vertical axis direction represents speed per hour. The state of deceleration in the loose state is indicated by a one-dot chain line. The state of deceleration in the normal state is indicated by a solid line.

FIG. 12 exemplifies timing for displaying a cognitive traffic signal to a type A driver who is assumed to be correctly stopping once. It is assumed that the type A driver starts deceleration at a position T1 that is a predetermined distance away from the stop line in the normal state. The predetermined distance is a distance set as reference data for a type A driver. The driving support device 1 is located at the position T1.
11 displays the display example CT1 of the recognition signal device in FIG. 11 on the HUD as the driving support information, and notifies the driver that there is a stop sign.

  If the vehicle is not decelerated at a position T2 that has traveled a predetermined distance from the position T1, for example, a distance of 5 m from the position T1, the type A driver is estimated to be in a loose state. At this time, the driving assistance apparatus 1 displays the red signal display example CT2 on the HUD. When the vehicle 3 is stopped at the position T3 that has reached the stop line, and it is detected from the movement of the line of sight that the driver has performed a safety confirmation act, the driving support device 1 displays a yellow signal display example CT3 on the HUD. . On the other hand, if the vehicle is decelerated at the position T2, the type A driver is estimated to be in the normal state. In this case, the driving assistance apparatus 1 does not display the display example CT2 of the red signal, and turns off the display of the recognition signal device at the position T3 of the stop line (state CT4).

  FIG. 13 exemplifies the timing for displaying the cognitive traffic signal for a type B driver who is assumed to tend to exceed the stop line of the temporary stop. The type B driver starts deceleration at a position T11 that is a predetermined distance away from the stop line in the normal state. The predetermined distance is a distance set as reference data for a type B driver. The driving support device 1 displays the display example CT1 of the recognition signal device of FIG. 11 on the HUD as driving support information at the position T11, and notifies the driver that there is a stop sign. In order to encourage the driver of type B to promptly decelerate, the driving support device 1 recognizes at a position T10 before the position T11, for example, a position where the vehicle 3 has temporarily recognized a stop sign. The display example CT1 of the traffic light may be displayed on the HUD.

  If the vehicle is not decelerated at the time of the position T12 that has traveled a predetermined distance from the position T11, for example, the distance from the position T11 is 5 m, it is estimated that the type B driver is in a casual state. At this time, the driving assistance apparatus 1 displays the red signal display example CT2 on the HUD. When the vehicle 3 is stopped at the position T13 that has reached the stop line, and it is detected from the movement of the line of sight that the driver has performed a safety confirmation act, the driving support device 1 displays a yellow signal display example CT3 on the HUD. . On the other hand, if the vehicle is decelerated at the position T12, the type B driver is estimated to be in the normal state. In this case, the driving assistance apparatus 1 does not display the red signal display example CT2. In addition, at the stop line position T13, the driving support device 1 displays the yellow signal display example CT3 on the HUD. By displaying the yellow signal display example CT3 on the HUD, the type B driver can recognize that he / she has taken a safety confirmation action, and can raise awareness of safe driving.

[Example 3 of driving support information]
FIG. 14 is a diagram illustrating an example of displaying a visual recognition state of the driver around the vehicle body. The sensor 31 of the vehicle 3 detects a line of sight directed from the driver's interior to the external 6 directions D1 to D6. The driving assistance device 1 displays the confirmation frequency in each direction stepwise by the size of the ellipse and displays it on the HUD. The confirmation frequency in each direction is not limited to an ellipse and may be represented by an arrow or the like. The driver can recognize the confirmation status around the vehicle 3 from the size of the graphic displayed in each direction. The example of FIG. 14 shows that the confirmation frequency for each direction from D1 to D6 is in the standard state.

  FIG. 15 is a diagram illustrating an example of displaying a visual recognition state of the driver around the vehicle body in a casual state. In the example of FIG. 15, the confirmation frequency in the directions D3 and D4 is less than that in the standard state, and the size of the ellipse in the directions D3 and D4 is smaller than that in the standard state shown in FIG. Further, the confirmation frequency in the azimuth D5 is considerably lower than that in the standard state, and the size of the ellipse in the azimuth D5 is smaller than that in the standard state shown in FIG. The driving support device 1 can make the driver recognize that the confirmation frequency for the directions D3, D4, and D5 is less than the standard state, and can call attention to confirm each direction.

  Furthermore, when the driver is in a state of disambiguation, the driving support device 1 may detect an obstacle that is close to each direction and display it in the detected direction. In the example of FIG. 15, an image of a motorcycle detected in the direction D5 is displayed. The external environment such as an obstacle is detected by the sensor 31 provided in the vehicle 3, and the driving support device 1 can recognize the external environment by acquiring data regarding the condition detected by the vehicle 3. In addition, when the driver is in an ambiguous state, the driving support device 1 may change the display mode such as the display size, color, and blinking speed to alert or warn.

  In addition to the driving support information exemplified above, the presentation unit F15 can switch the content of the driving support information based on the map information associated with the terrain information. For example, while driving in an area with many slopes, the driving support device 1 may display a display prompting the use of the engine brake at an appropriate frequency and timing according to the driver's condition and the driver's type. Good. The map information can be stored and used in the auxiliary storage device 13 of the driving support device 1.

  In the functional configuration of FIG. 2, the driving support information database D <b> 11 is a database for storing driving support information corresponding to the state of the driver and the type of the driver. The driving support information database D <b> 11 is constructed by managing data stored in the auxiliary storage device 13 by a database management system (DBMS) program executed by the processor 11. The driving support information database D11 is, for example, a relational database. The driving support information database D11 stores the contents of the driving support information for each of the driver state and the driver type shown in FIGS.

<< Server >>
FIG. 3 is a diagram illustrating a functional configuration of the server. The server 2 includes a type management unit F21 and a data management database D21 as functional configurations. The server 2 functions as a computer including the type management unit F21 and the data management database D21 by the program stored in the auxiliary storage device 23 being read out to the main storage device 22 and executed by the processor 21. .

  In the present embodiment, each function of the server 2 is executed by the processor 21 which is a general-purpose processor. However, part or all of these functions are one or more dedicated processors, hardware arithmetic circuits, and the like. May be executed by Here, the hardware arithmetic circuit refers to, for example, an adder circuit, a multiplier circuit, a flip-flop, etc. combined with logic gates. Some or all of these functions may be executed by a separate computer.

  The type management unit F21 statistically analyzes data related to driving operation characteristics accumulated in the data management database D21, and classifies the driver into a plurality of types using a technique such as clustering. Data relating to the characteristics of the driving operation for each type is duplicated in the auxiliary storage device 13 of the driving assistance device 1, and the type determination unit F11 of the driving assistance device 1 determines the type of the driver based on the duplicated data. Also good.

The data management database D21 is a database for storing information for estimating the driver's state such as a gaze activity amount and information regarding characteristics of the driving operation for estimating the driver's state. The driving support information database D11 is constructed by a database management system (DBMS) program executed by the processor 21 managing data stored in the auxiliary storage device 23. The data management database D21 is, for example, a relational database. The data stored in the data management database D21 is
Various data measured by the sensor 31 provided in the vehicle 3 are received and accumulated via the driving support device 1.

<Process flow>
FIG. 16 is a flowchart illustrating the flow of processing for presenting driving support information. The flow of this process starts, for example, when the driver starts driving the vehicle 3. In addition, the process illustrated in FIG. 16 is repeatedly executed when a change in the state of the driver or a change in the external environment is recognized until the driving of the vehicle 3 is completed.

  First, in step S101, the type determination unit F11 determines the type of the driver. The type determination unit F11 can determine the type of the driver to which the driver who is the determination target belongs among the predefined driver types according to the characteristics of the driving operation. The type determination unit F11 may determine the type of the driver based on an answer to the driver's questionnaire. Further, the type determination unit F11 may acquire information on the type of the driver determined in the server 2. Note that the process of step S101 only needs to be executed before step S105, and may be executed after any of the processes of step S102 to step S104.

  In step S <b> 102, the data acquisition unit F <b> 12 acquires data for estimating the driver's state measured by the sensor 31 from the vehicle 3. The data acquisition unit F12 may acquire data for estimating the driver's state from a wearable sensor worn by the driver.

  In step S103, the state estimation unit F13 estimates the driver's state based on the data acquired by the data acquisition unit F12. The state of the driver is, for example, a casual state in which attention is reduced in addition to a normal state where appropriate driving is possible as usual. In addition, if the corresponding driving support information is defined in the driving support information database D11, the state estimation unit F13 may estimate the driver's state as a state of calmness, a state of being impatient, or the like.

  In step S104, the state estimation unit F13 determines whether or not the driver is in a normal state. If the driver is in a normal state (S104; Yes), the process proceeds to step S105. If the driver is not in a normal state (S104; No), the process proceeds to step S106.

  In step S <b> 105, the presentation unit F <b> 15 determines whether or not the driver type is a driving assistance target in a normal state. For example, drivers who are apt to neglect safe driving and beginner drivers are subject to driving assistance in order to raise their awareness of safe driving and give advice on driving operations even in normal conditions. It is determined that there is. When it is determined that the driver is a target for driving assistance (S105; Yes), the process proceeds to step S106. When it is determined that the driver is not a driving assistance target (S105; No), the process ends.

  In step S106, the presentation unit F15 determines whether it is time to display the driving support information. The presentation unit F15 is based on the information on the terrain associated with the map information, the speed recognized by the sensor 31 of the vehicle 3, road signs, obstacles, etc., in addition to the driver state and the driver type. It can be determined whether or not it is time to display the driving support information. If it is determined that it is time to display the driving support information (S106; Yes), the process proceeds to step S107. If it is determined that it is not time to display the driving support information (S106; No), the process of step S106 is repeated at a predetermined interval until it is time to display the driving support information.

In step S107, the presentation unit F15 acquires and presents driving support information corresponding to the driver's state and the driver's type from the driving support information database D11. The content of the driving assistance information presented is illustrated in FIGS. 7 and 10. The driving support information is displayed on the output device 31 of the vehicle 3. For example, the driving support information can be displayed within the range of the viewing angle of the driver of the vehicle 3 as in a region M shown in FIGS. 9 and 11. In addition, the driving support information may be displayed on the output device 31 of the vehicle 3 at the timing described with reference to FIGS. When the driving support information is displayed on the output device 31 of the vehicle 3, the process shown in FIG. The process shown in FIG. 16 is repeatedly executed at a predetermined timing until the driver finishes driving the vehicle 3.

  In the embodiment described above, the driving support device 1 can present driving support information according to the estimated driver state and the driver type. In addition, the driving support device 1 can set the reference data for estimating the driver's state, and update the reference data based on the accumulated data, thereby accurately estimating the driver's state. it can. Moreover, the driving assistance apparatus 1 can present driving assistance information in a timely manner by changing the timing of presenting driving assistance information according to the state of the driver and the type of the driver. Furthermore, the driving assistance device 1 can effectively alert the driver by displaying the driving assistance information in an easily recognizable manner within the range of the viewing angle of the driver.

DESCRIPTION OF SYMBOLS 100 Driving support system 1 Driving support apparatus 2 Server 3 Vehicle 11, 21 Processor 12, 22 Main storage device 13, 23 Auxiliary storage device 14, 24 Network interface 15, 25 Bus N1, N2 Network

Claims (6)

Data acquisition means for acquiring a driver's life activity data measured by a sensor for detecting a state or activity of a part of the body;
Reference data management means for setting reference data for each state of the driver based on the driver's life activity data measured in the past;
Estimating means for estimating the state of the driver by comparing the acquired life activity data of the driver with the reference data;
Determining means for determining a type to which the driver belongs based on characteristics of the driving operation;
Presenting means for presenting driving support information corresponding to the estimated state of the driver and the type to which the driver belongs,
Driving assistance device. The reference data management means updates the set reference data at a predetermined timing.
The driving support device according to claim 1. The sensor measures a gaze activity amount of the driver,
The estimation means estimates the driver's state based on a change in the driver's gaze activity amount.
The driving support device according to claim 1 or 2. Computer
A data acquisition step for acquiring a driver's life activity data measured by a sensor for detecting a state or activity of a part of the body;
A reference data management step for setting reference data for each state of the driver based on the driver's life activity data measured in the past;
An estimation step of estimating the state of the driver by comparing the acquired life activity data of the driver with the reference data;
When the driver is classified according to the characteristics of the driving operation, the presenting step of presenting the driving support information according to the estimated state of the driver and the type to which the driver belongs is executed.
Driving support method. On the computer,
A data acquisition step for acquiring a driver's life activity data measured by a sensor for detecting a state or activity of a part of the body;
A reference data management step for setting reference data for each state of the driver based on the driver's life activity data measured in the past;
An estimation step of estimating the state of the driver by comparing the acquired life activity data of the driver with the reference data;
Determining means for determining a type to which the driver belongs based on characteristics of the driving operation;
The presenting step of presenting driving support information corresponding to the estimated state of the driver and the type to which the driver belongs is executed.
Driving assistance program. A driving support system including a server and a driving support device,
The server
A classification means for classifying the driver into a plurality of types based on the characteristics of the driving operation;
The driving support device includes:
Data acquisition means for acquiring a driver's life activity data measured by a sensor for detecting a state or activity of a part of the body;
Reference data management means for setting reference data for each state of the driver based on the driver's life activity data measured in the past;
Estimating means for estimating the state of the driver by comparing the acquired life activity data of the driver with the reference data;
Determining means for determining a type to which the driver belongs based on characteristics of the driving operation;
Presenting means for presenting driving support information corresponding to the estimated state of the driver and the type to which the driver belongs,
Driving support system.

Images