Driving assistance device

Abstract

The present invention provides a driving assistance device that can perform warning or intervention actions for driving control without hindering smooth driving even when there are multiple objects. The driving assistance device includes: a danger prediction unit that predicts a dangerous state of the vehicle based on information on the driving state of the vehicle and information on the surrounding environment of the vehicle; a driving assistance control unit that performs driving assistance control based on the predicted dangerous state; a mistake detection unit that acquires biometric information of the occupant and detects that the occupant feels danger based on the biometric information; and a mistake data storage unit that stores a mistake learning model, which is accumulated from information on the driving state of the vehicle and information on the surrounding environment of the vehicle when the occupant feels danger, and the driving assistance control unit performs driving assistance control based on the predicted dangerous state, and information on the driving state of the vehicle and information on the surrounding environment of the vehicle when the occupant feels danger.

Description

Technical Field

[0001] The present invention relates to a driving assistance device. Background Art

[0002] Conventionally, as a cause of traffic accidents, it has been clarified that the time to detect a dangerous state is late, and at the same time, the element of driver's judgment error is large. Although whether a driver can make an appropriate judgment depends on the driver's skill, in recent years, in order to make a vehicle travel properly regardless of the driver's skill, a driving assistance device has been put into practical use. For example, in Patent Document 1, there is disclosed such a driving assistance device that evaluates the positional relationship between an object such as a person or another vehicle detected by using a camera or radar and the movement of the own vehicle, and predicts a collision or intersection to give a warning and / or intervene in the driving control. This driving assistance device determines the collision risk between the own vehicle and the object based on the position of the object and the predicted forward road, and performs driving assistance to avoid a collision when the collision risk is high.

[0003] Prior Art Documents

[0004] Patent Documents

[0005] Patent Document 1: Japanese Unexamined Patent Application Publication No. 2014-191597 Summary of the Invention

[0006] Technical Problem

[0007] However, when there are multiple objects in a certain traffic situation, since a warning or an intervention in the driving control is executed after the accuracy of the predicted collision or intersection based on each positional relationship is determined, it may hinder smooth driving.

[0008] The present invention has been made in view of the above problems, and an object of the present invention is to provide a driving assistance device that can execute a warning or an intervention in the driving control operation without hindering smooth driving even when there are multiple objects.

[0009] Technical Solution

[0010] In order to solve the above problems, according to a certain aspect of the present invention, there is provided a driving assistance device, which includes: a danger prediction unit that predicts a dangerous state of the vehicle based on information on the driving state of the vehicle and information on the surrounding environment of the vehicle; a driving assistance control unit that performs driving assistance control based on the predicted dangerous state; an error detection unit that obtains biometric information of the occupant and detects that the occupant feels danger based on the biometric information; and an error data storage unit that stores an error learning model obtained by accumulating information on the driving state of the vehicle and information on the surrounding environment of the vehicle when the occupant feels danger, and the driving assistance control unit performs driving assistance control based on the predicted dangerous state, and information on the driving state of the vehicle and information on the surrounding environment of the vehicle when the occupant feels danger.

[0011] In addition, it may further include a driving tendency data storage unit that accumulates data on the driving operation tendency of the driver of the vehicle when performing driving assistance control, and the driving assistance control unit also performs driving assistance control based on the data on the driving operation tendency of the driver.

[0012] In addition, the driving tendency data storage unit may accumulate at least one of the frequency at which the occupant feels danger, the driving operation when feeling danger, the degree of danger when feeling danger, or the driving skill of the driver as the driving operation tendency of the driver, and the driving assistance control unit may set the content of the driving assistance control based on this data.

[0013] In addition, the driving assistance control unit may also set the execution timing of the driving assistance control based on the data on the driving operation tendency of the driver.

[0014] In addition, the driving assistance control unit may also set the content of the driving assistance control based on the elapsed time since the dangerous state was predicted.

[0015] In addition, the driving assistance control unit may also set the content of the driving assistance control based on the driver's concentration or wakefulness.

[0016] Technical Effects

[0017] As described above, according to the present invention, even in the presence of multiple objects, it is possible to perform warning or intervention actions for driving control without hindering smooth driving. Brief Description of the Drawings

[0018] Figure 1 It is a block diagram showing a configuration example of a driving assistance device according to an embodiment of the present invention.

[0019] Figure 2 It is a block diagram showing a specific functional configuration of a traffic condition prediction unit.

[0020] Figure 3 It is a block diagram showing the specific functional configuration of the driving assistance control unit.

[0021] Figure 4 It is an explanatory diagram showing a collision example of the vehicle.

[0022] Figure 5 It is an explanatory diagram showing a setting example of warnings and vehicle control.

[0023] Figure 6 It is an explanatory diagram showing another setting example of warnings and vehicle control.

[0024] Figure 7 It is an explanatory diagram showing yet another setting example of warnings and vehicle control.

[0025] Figure 8 It is an explanatory diagram showing another collision example of the vehicle.

[0026] Figure 9 It is an explanatory diagram showing a contact example of the vehicle.

[0027] Figure 10 It is a flowchart showing an operation example of the driving assistance device of this embodiment.

[0028] Figure 11 It is a flowchart showing traffic condition prediction processing.

[0029] Figure 12 It is a flowchart showing driving assistance control processing.

[0030] Symbol Explanation

[0031] 10… Driving assistance device

[0032] 50… Electronic control unit

[0033] 51… Error detection unit

[0034] 53… Error learning model

[0035] 55… Danger prediction unit

[0036] 57… Collision stagger determination unit

[0037] 59… Driving tendency estimation unit

[0038] 61… Warning control unit

[0039] 63… Vehicle control unit

[0040] 65… Driving evaluation unit

[0041] 69… Driving tendency database

[0042] 70…Traffic condition prediction unit

[0043] 71…Traffic environment recognition unit

[0044] 73…Traffic participant extraction unit

[0045] 75…Traffic participant behavior estimation unit

[0046] 77…Own vehicle behavior prediction unit

[0047] 79…Behavior learning model

[0048] 81…Traffic condition understanding and prediction unit

[0049] 90…Driving assistance control unit

[0050] 91…Risk evaluation unit

[0051] 93…Risk evaluation verbalization processing unit

[0052] 95…Warning and control execution determination unit Detailed implementation manners

[0053] Hereinafter, with reference to the drawings, preferred implementation manners of the present invention will be described in detail. It should be noted that in this specification and the drawings, for components having substantially the same functional configuration, duplicate descriptions thereof are omitted by assigning the same reference numerals.

[0054] <1. Configuration example of driving assistance device>

[0055] First, a configuration example of the driving assistance device according to the implementation manner of the present invention will be described. Figure 1 It is a block diagram showing a configuration example of the driving assistance device 10 of the present implementation manner.

[0056] The driving assistance device 10 is mounted on a vehicle and is configured to detect information on the vehicle occupants, the driving state and operation state of the vehicle, and the surrounding environment of the vehicle, and to execute control for assisting the driving of the vehicle using the various detected information. The driving assistance device 10 includes: an occupant information detection unit 41, a surrounding information detection unit 43, a vehicle information detection unit 45, an operation information detection unit 47, an electronic control device 50, a warning device 31, and a vehicle control device 33.

[0057] (1-1. Occupant information detection unit)

[0058] The occupant information detection unit 41 detects information on vehicle occupants such as the driver and / or passengers of the vehicle. The occupant information detection unit 41 includes one or more detection devices for detecting information for estimating the mood and / or feelings of the occupants. The electronic control device 50 is configured to be able to obtain the information detected by the occupant information detection unit 41.

[0059] The passenger information detection unit 41 may include at least one of the following: for example, a camera for detecting the heartbeat and / or body temperature of a passenger based on a captured image, a radio wave Doppler sensor for detecting the heartbeat of a passenger, a non-wearable pulse sensor for detecting the pulse of a passenger, electrodes embedded in the steering wheel for measuring the heartbeat or electrocardiogram of the driver, a pressure measuring device embedded in the driver's seat for measuring the seat pressure distribution during the period when the passenger is seated on the seat, a device for detecting a change in the position of the seat belt for measuring the heartbeat or respiration of a passenger, a TOF (Time of Flight) sensor for detecting information on the position (biological position) of a passenger, or a thermal imager for measuring the surface temperature of the passenger's skin. In addition, the passenger information detection unit 41 may also be a wearable detector such as a wearable device worn by the passenger to detect the passenger's biological information.

[0060] (1-2. Surrounding information detection unit)

[0061] The surrounding information detection unit 43 detects information on the surrounding environment of the vehicle. The surrounding information detection unit 43 detects information on people, other vehicles, bicycles, other obstacles, etc. present around the vehicle as the surrounding environment of the vehicle. The electronic control device 50 is configured to be able to acquire the information detected by the surrounding information detection unit 43. The surrounding information detection unit 43 includes at least one of detectors such as a camera for photographing the surroundings of the vehicle, a radar for detecting an object around the vehicle, and a RiDAR for detecting the distance and / or azimuth to an object around the vehicle. In addition, the surrounding information detection unit 43 may also include a communication device for obtaining information from an external device of the vehicle such as vehicle-to-vehicle communication or vehicle-to-roadside communication. Furthermore, the surrounding information detection unit 43 may also include a detector for detecting information related to road surface friction.

[0062] (1-3. Vehicle information detection unit)

[0063] The vehicle information detection unit 45 detects information on the driving state of the vehicle. The vehicle information detection unit 45 detects information on the driving state of the vehicle such as vehicle speed, acceleration, and yaw rate. The electronic control device 50 is configured to be able to acquire the information detected by the vehicle information detection unit 45. The vehicle information detection unit 45 may also include at least one of, for example, a vehicle speed sensor, an acceleration sensor, and an angular velocity sensor.

[0064] (1-4. Operation information detection unit)

[0065] The operation information detection unit 47 detects information on the driving operation state of the vehicle. The operation information detection unit 47 detects information on the driving operation state of the vehicle, such as the acceleration operation amount, the braking operation amount, and the steering wheel steering angle. The electronic control device 50 is configured to be able to acquire the information detected by the operation information detection unit 47. The operation information detection unit 47 may include at least one of, for example, an accelerator position sensor, a brake stroke sensor, and a steering angle sensor.

[0066] (1-5. Warning device)

[0067] The warning device 31 is controlled by the electronic control device 50 to perform a warning action as one of the driving assistance controls. For example, the warning device 31 may be a display device that displays a warning display, may be a speaker that emits a warning sound or a warning voice, or may be a warning light that warns by emitting light. The display device may be, for example, a display panel provided on the control panel or a HUD (Head Up Display) projected on the front window. In addition, it may be an instrument display device inside the instrument panel, may be a display device of the navigation system, or may be a multifunctional display that presents various information.

[0068] (1-6. Vehicle control device)

[0069] The vehicle control device 33 is controlled by the electronic control device 50 to perform an autonomous driving control as one of the driving assistance controls. The vehicle control device 33 includes one or more control devices that perform the driving control of the vehicle. For example, the vehicle control device 33 includes a control device that controls the driving of a power transmission mechanism, a steering system, a braking system, etc. The power transmission mechanism includes an engine, one or more drive motors, and a transmission. Basically, the vehicle control device 33 performs the driving control of the vehicle based on the driver's driving operation. In addition, the vehicle control device 33 receives an instruction from the electronic control device 50 and performs a driving assistance control.

[0070] (1-7. Electronic control device)

[0071] The electronic control device 50 is configured to include an arithmetic processing device such as a CPU (Central Processing Unit) or an MPU (Micro Processing Unit), and storage elements such as a RAM (Random Access Memory) or a ROM (Read Only Memory). The arithmetic processing device executes various arithmetic processes by executing programs stored in the storage elements. It may also include, together with or in place of the storage elements, storage media such as an HDD (Hard Disk Drive), a CD (Compact Disc), a DVD (Digital Versatile Disc), an SSD (Solid State Disc), a USB (Universal Serial Bus) flash memory, and a storage device. It should be noted that part or all of the electronic control device 50 may be constituted by an updatable device such as firmware, or may be a program module or the like that is executed according to an instruction from a CPU or the like.

[0072] The electronic control device 50 is directly connected, or connected via a communication line such as a CAN (Controller Area Network) or a LIN (Local Inter-Net), to the occupant information detection unit 41, the surrounding information detection unit 43, the vehicle information detection unit 45, the operation information detection unit 47, the warning device 31, and the vehicle control device 33.

[0073] In the present embodiment, the electronic control device 50 includes: a traffic condition prediction unit 70, an error detection unit 51, a danger prediction unit 55, a collision stagger determination unit 57, a driving tendency estimation unit 59, a driving assistance control unit 90, a warning control unit 61, a vehicle control unit 63, and a driving evaluation unit 65. These units are functions realized by the arithmetic processing device executing programs.

[0074] (1-7-1. Traffic Condition Prediction Unit)

[0075] The traffic condition prediction unit 70 predicts the traffic condition in which the vehicle is located based on the information transmitted from the surrounding information detection unit 43, the vehicle information detection unit 45, and the operation information detection unit 47. That is, the traffic condition prediction unit 70 predicts the traffic condition in which the vehicle is located at least based on the driving state and operation state of the own vehicle, the traffic environment around the own vehicle, and the state of traffic participants.

[0076] Figure 2FIG. is a block diagram showing a specific functional configuration of the traffic condition prediction unit 70. The traffic condition prediction unit 70 includes: a traffic environment recognition unit 71, a traffic participant extraction unit 73, a traffic participant behavior estimation unit 75, a host vehicle behavior prediction unit 77, and a traffic condition understanding and prediction unit 81. In addition, the traffic condition prediction unit 70 is configured to be able to refer to the behavior learning model 79.

[0077] Based on the information transmitted from the surrounding information detection unit 43, the traffic environment recognition unit 71 obtains information on the traffic environment around the vehicle. Specifically, the traffic environment recognition unit 71 performs image processing on the captured image obtained by the camera and performs arithmetic processing on the detection data using a radar and / or LiDAR, etc., to identify traffic signal machines, traffic signs, white lines on the road, buildings, guardrails, and curbstones and other obstacles around the host vehicle. In addition, the traffic environment recognition unit 71 may also obtain information such as the size of the identified object and / or the distance to the object, and the relative speed with respect to the object. Furthermore, the traffic environment recognition unit 71 may also obtain information on the color of the traffic signal machine.

[0078] Based on the information transmitted from the surrounding information detection unit 43, the traffic participant extraction unit 73 extracts traffic participants around the vehicle. Specifically, the traffic participant extraction unit 73 extracts a plurality of traffic participants such as other vehicles, bicycles, and pedestrians around the host vehicle. In addition, the traffic participant extraction unit 73 may also obtain information such as the distance to the extracted traffic participant and / or the relative speed with respect to the traffic participant.

[0079] The traffic participant behavior estimation unit 75 estimates the behavior of the traffic participants extracted by the traffic participant extraction unit 73. Specifically, the traffic participant behavior estimation unit 75 inputs the information of the traffic participants extracted by the traffic participant extraction unit 73 into the behavior learning model 79, and estimates the subsequent behavior of each traffic participant based on the output from the behavior learning model 79. Thereby, it is estimated what actions the traffic participants will take. The behavior learning model 79 is a learning model that learns the behaviors of traffic participants such as other vehicles, bicycles, and pedestrians in various traffic conditions, and is pre-stored in a storage element or a storage medium. In this case, the storage element or the storage medium has the function of a behavior data storage unit. The behavior learning model 79 may also be updated sequentially using the information obtained by the traffic condition prediction unit 70.

[0080] Based on the information transmitted from the vehicle information detection unit 45 and the operation information detection unit 47, the host vehicle behavior prediction unit 77 predicts the behavior of the host vehicle. Specifically, the host vehicle behavior prediction unit 77 predicts the behavior of the host vehicle based on the current driving state of the vehicle detected by the vehicle information detection unit 45 and the driving operation state of the vehicle detected by the operation information detection unit 47.

[0081] The traffic condition understanding and prediction unit 81 understands the current traffic condition in which the host vehicle is located based on the information respectively obtained by the traffic environment recognition unit 71, the traffic participant behavior estimation unit 75, and the host vehicle behavior prediction unit 77, and predicts the traffic condition in which the host vehicle will be located thereafter. Specifically, the traffic condition understanding and prediction unit 81 takes into account the behavior of traffic participants and the behavior of the host vehicle for the traffic environment around the host vehicle to understand and predict the traffic condition of the host vehicle. In this way, the traffic condition prediction unit 70 predicts the traffic condition in which the host vehicle is located.

[0082] (1-7-2. Collision and Intersection Judgment Unit)

[0083] The collision and intersection judgment unit 57 determines whether a collision or intersection between the host vehicle and other traffic participants will occur based on the information of the current traffic condition of the host vehicle predicted by the traffic condition prediction unit 70. The collision and intersection judgment unit 57 determines whether the trajectory of the behavior plan of the traffic participants and the trajectory of the behavior plan of the host vehicle will intersect based on the current traffic environment, the predicted behavior of the traffic participants, and the predicted behavior of the host vehicle, and makes a judgment on collisions, etc. based on a so-called physical model. The judgment on collisions, etc. between the host vehicle and other traffic participants performed by the collision and intersection judgment unit 57 is mainly based on the judgment result that does not consider the technical factors of the individual driver.

[0084] (1-7-3. Error Detection Unit)

[0085] The error detection unit 51 detects an error, which is a state in which the occupant feels danger, based on the information sent from the occupant information detection unit 41. Specifically, the error detection unit 51 detects an error based on changes in the facial expression, facial orientation, line of sight, pulse or heartbeat, blood pressure, electrocardiogram, etc. of the occupant detected by the occupant information detection unit 41.

[0086] For example, in a state where it is detected based on the information of the facial orientation and the line of sight that the occupant is looking outside the vehicle, and in a case where there are sudden changes in the pulse or heartbeat, blood pressure, electrocardiogram, etc., the error detection unit 51 detects an error. Thereby, the accuracy of the state in which the occupant feels danger about the traffic condition outside the vehicle can be improved. Furthermore, it is also possible to detect an error when, after detecting that the occupant is looking askance based on the information of the facial orientation and the line of sight, and then detecting the situation where the line of sight returns to a proper state after the askew state, and in a case where there are sudden changes in the pulse or heartbeat, blood pressure, electrocardiogram, etc., the error detection unit 51 detects an error. The threshold value of the change speed of the pulse or heartbeat, blood pressure, electrocardiogram, etc. determined to indicate that the occupant feels danger can be preset to an appropriate value. It is also possible to classify the level of the error according to the change speed of the pulse or heartbeat, blood pressure, electrocardiogram, etc. However, the method of detecting an error is not limited to the above examples.

[0087] The error detection unit 51 obtains information on the current traffic condition of the host vehicle predicted by the traffic condition prediction unit 70, accumulates information on the traffic condition of the host vehicle when an error is detected, and causes the error learning model 53 to learn sequentially. The error learning model 53 is a learning model obtained by learning data on the traffic condition when an error is detected, that is, data on the traffic condition that the passengers feel dangerous. As a mathematical model for constructing the error learning model 53, a known model such as a classifier, a support vector machine, a proximity method, a neural network such as deep learning, or a Bayesian network that classifies input data based on labels or teacher data can be used. The error learning model 53 is stored in a storage element or a storage medium. In this case, the storage element or the storage medium has a function as an error data storage unit.

[0088] It should be noted that "error" refers to a state of recognizing a situation that, although no major disaster or accident has occurred, is only one step away from directly causing a major disaster or accident. The object passengers for detecting errors are not limited to the driver and may also include passengers in the vehicle.

[0089] (1-7-4. Danger prediction unit)

[0090] The danger prediction unit 55 uses the error learning model 53 obtained by accumulating and learning data, and predicts the dangerous state of the host vehicle based on the traffic condition predicted by the traffic condition prediction unit 70. That is, the danger prediction unit 55 has the following function: using the error learning model 53 that has learned examples of past traffic conditions that the passengers of the vehicle feel dangerous, to predict whether danger is approaching in the current traffic condition.

[0091] Specifically, the danger prediction unit 55 inputs data on the driving state of the vehicle and information on the surrounding environment to the error learning model 53, and predicts the dangerous state of the host vehicle based on the output error state. When the output from the error learning model 53 indicates that an error was detected in the past, the danger prediction unit 55 predicts that the predicted traffic condition is a dangerous state for the host vehicle. It is also possible to predict the danger level for the host vehicle based on the error level when the error learning model 53 is learning the error level data.

[0092] As information on the driving state of the vehicle set as input data, it preferably includes data on the acceleration in the front-rear, left-right, and up-down directions of the vehicle, the yaw angle, the pitch angle, and the angular velocity of the roll angle, the vehicle speed, and the steering angle. Furthermore, information such as the engine speed and the output of the direction indicator can also be included as information on the driving state of the vehicle. In addition, as information on the surrounding environment set as input data, it preferably includes data on the driving lane of the own vehicle, the relative distance, relative speed, and forward direction related to traffic participants such as other vehicles and / or pedestrians, and the number of lanes and signal information of the road during driving. Furthermore, information such as the weather and road surface conditions can also be included as information on the surrounding environment.

[0093] Regarding the above-mentioned collision stagger determination unit 57 that determines the occurrence of a collision or the like based on a physical model, the danger prediction unit 55 objectively predicts the dangerous state of the vehicle according to the current traffic conditions based on past cases where the vehicle occupants actually felt danger. Thus, it is possible to identify the following situation: after a time when the accuracy of determining that a collision or the like will occur in the collision stagger determination unit 57 is low, if the vehicle continues to travel as it is, the possibility of a collision or the like occurring is high.

[0094] (1-7-5. Driving Tendency Estimation Unit)

[0095] The driving tendency estimation unit 59 estimates the driving tendency of the driver in the current traffic conditions of the own vehicle based on the information on the current traffic conditions of the own vehicle predicted by the traffic conditions prediction unit 70. Specifically, the driving tendency estimation unit 59 refers to the accumulated driving tendency database (DB) 69 and estimates the frequency at which the driver felt danger in the past in the current traffic conditions, the degree of dependence of the driver on the driving assistance control, etc. The driving tendency database 69 is a database obtained by accumulating information on the traffic conditions in which the state where the driver felt danger in the past was detected, the degree of danger at that time, and the actual driving operations of the driver when the driving assistance control was executed as the personal information of the driver, and is stored in a storage element or a storage medium. In this case, the storage element or the storage medium has the function of a driving tendency data storage unit. The driving tendency database 69 can also include information on the driving skills of the driver. By using the result of estimating the driving tendency of the driver for the driving assistance control, the intervention degree of the driving assistance control can be changed according to the driving tendency of the driver.

[0096] (1-7-6. Driving Assistance Control Unit)

[0097] The driving assistance control unit 90 performs predetermined driving assistance control based on the information transmitted from the occupant information detection unit 41 and the information obtained by the danger prediction unit 55, the collision stagger determination unit 57, and the driving tendency estimation unit 59. In the present embodiment, the driving assistance control unit 90 calculates the information for the operation instructions of the warning control unit 61 and the vehicle control unit 63.

[0098] Figure 3 FIG. is a block diagram showing the specific functional configuration of the driving assistance control unit 90. The driving assistance control unit 90 includes: a danger level evaluation unit 91, a danger level evaluation verbalization processing unit 93, and a warning / control execution determination unit 95.

[0099] Based on the prediction result of the dangerous state obtained by the collision stagger determination unit 57 based on the physical model and the prediction result of the dangerous state obtained by the danger prediction unit 55 based on the error learning model, the danger level evaluation unit 91 comprehensively evaluates the danger level of the own vehicle. For example, the danger level evaluation unit 91 may quantify the prediction results of the dangerous states obtained by the collision stagger determination unit 57 and the danger prediction unit 55 into the accuracy of the dangerous state, and set the larger value as the danger level. Alternatively, the danger level evaluation unit 91 may also quantify the prediction results of the dangerous states obtained by the collision stagger determination unit 57 and the danger prediction unit 55 into the accuracy of the dangerous state, and set the sum value thereof as the danger level.

[0100] When evaluating the danger level, the danger level evaluation unit 91 may respectively weight the prediction results of the dangerous states obtained by the collision stagger determination unit 57 and the danger prediction unit 55. In addition, the danger level evaluation unit 91 may weight the danger level corresponding to the predicted dangerous state. For example, the danger level may be weighted according to whether the vehicles collide with each other, whether the vehicle collides with a pedestrian or a bicycle, a frontal collision or a minor contact, or the relative speed between the own vehicle and the collision opponent.

[0101] The danger level evaluation verbalization processing unit 93 performs verbalization processing for warning the occupants including the driver. For example, the danger level evaluation verbalization processing unit 93 verbalizes information such as what kind of dangerous state it is in, what the object to be noted is, and which direction to pay attention to according to the evaluation result of the danger level. The verbalized information is sent to the warning control unit 61 for warning actions based on voice and / or warning actions based on display.

[0102] The warning and control execution determination unit 95 determines whether to execute the control of the warning control unit 61 and the vehicle control unit 63 based on the evaluation result of the risk level. In the present embodiment, the warning and control execution determination unit 95 sets different contents of the intervention actions of the warning or vehicle control based on the elapsed time since the prediction of a dangerous state such as a collision of the vehicle 1. Specifically, it determines whether to execute the control in the following manner: in the initial stage of predicting a collision or the like of the vehicle 1, it is set to execute only the warning, and as the progress of the lag of the driver's judgment becomes larger, the degree of intervention in the vehicle control becomes larger. In addition, in the present embodiment, the warning and control execution determination unit 95 sets different contents of the intervention actions of the warning or vehicle control according to the driving tendency of the driver. Specifically, it determines whether to execute the control in the following manner: the lower the driving skill of the driver, or the higher the degree of dependence on the driving assistance control, the greater the degree of intervention in the vehicle control. Or, it determines whether to execute the control in the following manner: the lower the driving skill of the driver, or the higher the degree of dependence on the driving assistance control, the earlier the execution time of the driving assistance control.

[0103] In the case where the risk level is relatively low, or in the case where it is estimated that the loss caused by the collision is small, the warning and control execution determination unit 95 may determine not to execute the intervention in the vehicle control and only execute the warning control. On the other hand, in the case where the risk level is high, or in the case where it is determined that the loss caused by the collision is large, the warning and control execution determination unit 95 may determine to execute both the warning control and the intervention in the vehicle control.

[0104] (1-7-7. Warning control unit)

[0105] The warning control unit 61 generates a control signal for the warning device 31 based on the determination result obtained by the warning and control execution determination unit 95. When making the warning device 31 execute a warning action, the warning control unit 61 generates a control signal for causing the warning device 31 to perform a predetermined warning action, and outputs this control signal to the warning device 31. Thereby, it is possible to prompt the driver to perform a driving operation to avoid the dangerous state of the vehicle 1, thereby being able to avoid a dangerous state such as a collision of the vehicle 1, and in addition, being able to reduce the loss. In the case of performing a warning action by voice or text display, the warning control unit 61 outputs the verbalized information generated by the risk level evaluation verbalization processing unit 93 to the warning device 31. Thereby, the warning device 31 can perform a warning action based on voice or text display.

[0106] (1-7-8. Vehicle control unit)

[0107] The vehicle control unit 63 generates a control signal for the vehicle control device 33 based on the determination result obtained by the warning and control execution determination unit 95. When a dangerous state such as a collision of the vehicle is predicted, the vehicle control unit 63 automates part or all of the vehicle to avoid the dangerous state or reduce the loss. For example, the vehicle control unit 63 generates control signals for decelerating the vehicle, performing emergency braking, and making a turn, and outputs the control signals to the vehicle control device 33. Thereby, the vehicle 1 performs an action to avoid a collision, and can avoid dangerous states such as a collision of the vehicle 1 and can also reduce the loss.

[0108] (1-7-9. Driving Evaluation Unit)

[0109] The driving evaluation unit 65 evaluates the driving tendency of the driver individual when the driving assistance control is executed. For example, the driving evaluation unit 65 accumulates information on the predicted dangerous state and degree of danger of the vehicle 1, traffic conditions information, and information on the actually performed driving operations in the driving tendency database 69. The more information on the predicted dangerous state and degree of danger of the vehicle 1, the more it is presumed that the driving skill of the driver is lower. The driving tendency database 69 may also include information on the driving skill of the driver individual. In addition, the earlier the driver performs a deceleration or stop action and avoids the dangerous state with respect to the information on the dangerous state and degree of danger of the vehicle 1, the more it is presumed that the driver has a higher degree of dependence on the driving assistance control. In addition, the driving evaluation unit 65 may accumulate various information capable of evaluating the driving tendency of the driver in the driving tendency database 69 along with the execution of the driving assistance control.

[0110] <2. Action Examples of Driving Assistance Device>

[0111] So far, the configuration example of the driving assistance device of the present embodiment has been described. Next, an example of a collision between a vehicle and a bicycle or another vehicle will be used to describe the action example of the driving assistance device of the present embodiment.

[0112] Figure 4 An example in which the vehicle 1 turning right at an intersection collides with the bicycle 3 passing through the crosswalk on the right-turn target road that appears from the shadow of the oncoming vehicle X is shown. Figure 5 An example of the warning and vehicle control settings executed by the driving assistance device 10 based on the progress degree of the judgment lag and the driving tendency of the driver is shown.

[0113] The vehicles A1, A2, and A3 respectively represent the positions of the vehicle 1 at a certain moment before the collision, and the bicycles B1, B2, and B3 respectively represent the positions of the bicycle 3 at the moments corresponding to the positions shown by the vehicles A1, A2, and A3.

[0114] First, when the driving assistance device of the present embodiment is not mounted on the vehicle 1, since a driver with a high level of driving skills is at the position shown by the vehicle A1 and can predict that the vehicle 1 will collide with the bicycle 3 on the crosswalk when noticing the bicycle 3 emerging from the shadow of the oncoming vehicle X, the vehicle 1 will be stopped. On the other hand, a driver with a low level of driving skills at the position shown by the vehicle A1 cannot predict the collision between the vehicle 1 and the bicycle and continues to drive the vehicle 1 as it is. Furthermore, the judgment to stop the vehicle 1 is also delayed at the position shown by the vehicle A2, and as a result, a collision with the bicycle 3 occurs at the position shown by the vehicle A3.

[0115] On the other hand, when the driving assistance device 10 of the present embodiment is mounted on the vehicle 1, the traffic condition prediction unit 70 of the driving assistance device 10, at the position shown by the vehicle A1, recognizes the position including the crosswalk and the driving lane, the lighting state of the traffic signal, and the traffic environment of the oncoming vehicle X and the bicycle 3, and predicts that if the vehicle 1 continues to drive as it is, the vehicle 1 will collide with the bicycle 3 at the position of the vehicle A3. At this time, the driving assistance control unit 90 of the driving assistance device 10 is set to perform different contents of driving assistance corresponding to the encounter frequency of mistakes as the driving tendency of the driver. In Figure 5 the example shown, when the driving skills of the driver are relatively high and the encounter frequency of mistakes is low or medium, no driving assistance action is particularly performed. On the other hand, when the driving skills of the driver are relatively low and the encounter frequency of mistakes is high, it is set to perform a warning (recommendation) implemented by voice.

[0116] In addition, during the period when the vehicle 1 does not stop and advances from the position shown by the vehicle A1 to the position shown by the vehicle A2 (A1→A2), when the driving skills of the driver are relatively high and the encounter frequency of mistakes is low or medium, it is set to perform a warning (recommendation) implemented by voice. On the other hand, when the driving skills of the driver are relatively low and the encounter frequency of mistakes is high, it is set to intervene in the vehicle control to reduce the driving torque of the vehicle 1.

[0117] Furthermore, when the vehicle 1 still has not stopped afterwards, during the period from the position shown by vehicle A2 to the position shown by vehicle A3 (A2→A3), when the driver's driving skill is relatively high and the encounter frequency of mistakes is low, it is set to perform a warning implemented by means of a warning sound, lighting of a warning lamp, etc. In addition, when the driver's driving skill is relatively high and the encounter frequency of mistakes is medium, it is set to intervene in the vehicle control in order to reduce the driving torque of the vehicle 1. Furthermore, when the driver's driving skill is relatively low and the encounter frequency of mistakes is high, it is set to intervene in the vehicle control in order to force the vehicle 1 to stop by generating a braking force for the vehicle 1.

[0118] When the encounter frequency of the driver's mistakes is low or medium, if the vehicle 1 still does not stop afterwards and advances to the position shown by vehicle A3, it is set to intervene in the vehicle control in order to force the vehicle 1 to stop by generating a braking force for the vehicle 1.

[0119] In this way, if it is recognized that the vehicle 1 equipped with the driving assistance device 10 may collide with the bicycle 3 at the position shown by vehicle A3, an action to avoid the movement after the vehicle 1 reaches the position shown by vehicle A2 is executed. Therefore, it is possible to foresee the collision of the vehicle 1 before the driver recognizes it, thereby reducing the risk of collision of the vehicle 1. In particular, in Figure 5 the set example shown, in combination with the progress degree of the judgment lag, the action content of the warning and the intervention in the vehicle control is set according to the encounter frequency of the driver's mistakes. Thus, it is possible to suppress the execution of excessive warnings or intervention actions in the vehicle control, and it is possible to execute warnings or intervention actions in the driving control without disturbing smooth driving.

[0120] In order to set the content of the warning or the intervention action in the vehicle control, the information on the driving tendency of the driver used in combination with the progress degree of the judgment lag is not limited to the encounter frequency of the driver's mistakes. For example, Figure 6Indicates the progress degree of the hysteresis of the combination judgment. An example of setting a warning or an intervention action for vehicle control using the information of relative evaluation, where the relative evaluation is between the evaluation of the vehicle's risk level obtained by the risk evaluation unit 91 and the recognition of the risk level when the driver himself feels at risk based on the information sent from the occupant information detection unit 41. In this setting example, depending on whether the driver recognizes a risk level equivalent to the evaluation content of the risk evaluation unit 91, whether the driver is more sensitive to the risk level compared to the evaluation content of the risk evaluation unit 91, or whether the driver is less sensitive to the risk level compared to the evaluation content of the risk evaluation unit 91, the setting content of the warning or the intervention action for vehicle control is made different. The recognition of the driver's risk level in this case is not limited to the recognition based on the driver's driving skills, but is manifested as an index depending on the driver's concentration or wakefulness during driving at this time.

[0121] In addition, Figure 7 Indicates the progress degree of the hysteresis of the combination judgment. An example of setting a warning or an intervention action for vehicle control using the information of the driver's dependence degree on the warning or the intervention action for vehicle control deduced based on the information accumulated in the driving tendency database 69. In this setting example, the levels of the driver's dependence degree on the warning or the intervention action for vehicle control are classified into low, medium, and high, and the setting content of the warning or the intervention action for vehicle control is made different according to each level.

[0122] Thus, it is possible to suppress the execution of excessive warnings or intervention actions for vehicle control, and it is possible to execute warnings or intervention actions for driving control without hindering smooth driving. In Figures 5 to 7 any of the shown setting examples, the timing of starting to execute the warning or the intervention action for vehicle control is different according to the driving operation tendency of the driver. Specifically, the higher the frequency of encountering the driver's mistakes, the later the driver recognizes the risk level compared to the vehicle's risk evaluation, or the higher the driver's dependence degree on the driving assistance control, the earlier the timing of starting to execute the warning or the intervention action for vehicle control. It should be noted that Figures 5 to 7 the setting content of the warning or the intervention action for vehicle control in Figures 5 to 7 is just an example and can be set appropriately. In addition, it is also possible to combine multiple setting examples illustrated in

[0123] Figure 8 is an example where the vehicle 1 driving on a narrow road intends to avoid a collision with the approaching oncoming vehicle X when overtaking the bicycle 3 but collides with the bicycle 3. Compared with Figure 4Similarly, vehicle A1, A2, and A3 respectively represent the positions of vehicle 1 at a certain moment before the collision, and bicycle B1, B2, and B3 respectively represent the positions of bicycle 3 at the moments corresponding to the positions shown by vehicle A1, A2, and A3.

[0124] First, in the case where the driving assistance device of the present embodiment is not mounted on vehicle 1, since a driver with a high driving skill level is at the position shown by vehicle A1 and can predict that vehicle 1 will collide with oncoming vehicle X when overtaking bicycle 3 when noticing that oncoming vehicle X is approaching, vehicle 1 will be decelerated. On the other hand, a driver with a low driving skill level cannot predict the collision between vehicle 1 and oncoming vehicle X at the position shown by vehicle A1 and continues to drive vehicle 1 as it is. Furthermore, the judgment to decelerate vehicle 1 is also delayed at the position shown by vehicle A2, and as a result, vehicle 1 collides with bicycle 3 at the position shown by vehicle A3.

[0125] On the other hand, in the case where vehicle 1 is equipped with the driving assistance device 10 of the present embodiment, the traffic condition prediction unit 70 of the driving assistance device 10 identifies the traffic environment including the driving position of vehicle 1, oncoming vehicle X, and bicycle 3 at the position shown by vehicle A1 and predicts that vehicle 1 will collide with the oncoming vehicle if it continues to drive as it is and overtakes bicycle 3. At this time, the driving assistance control unit 90 of the driving assistance device 10 is set to perform different driving assistance corresponding to the driving tendency of the driver in order to avoid the collision or contact between vehicle 1 and oncoming vehicle X and bicycle 3. In Figure 8 the example shown, the setting example shown in Figures 5 to 7 can also be applied.

[0126] Figure 9 This is an example where vehicle 1 traveling in the middle lane of a three-lane road changes lanes to the right lane in an attempt to avoid another vehicle X that has suddenly changed lanes from the left lane and comes into contact with a two-wheeler 5 that intends to overtake vehicle 1 from behind. Vehicle A1, A2, and A3 respectively represent the positions of vehicle 1 at a certain moment before the contact, and two-wheeler C1, C2, and C3 respectively represent the positions of two-wheeler 5 at the moments corresponding to the positions shown by vehicle A1, A2, and A3.

[0127] First, when the driving assistance device of the present embodiment is not mounted on the vehicle 1, since a driver with a high level of driving skills is at the position shown by the vehicle A1 and can predict that the other vehicle X will change lanes to the central lane when noticing that the large vehicle Y is approaching in front of the other vehicle X traveling in the left lane, the vehicle 1 will be decelerated. On the other hand, a driver with a low level of driving skills cannot predict the lane change of the other vehicle X and continues to drive the vehicle 1 as it is. Furthermore, at the position shown by the vehicle A2, the driver also notices belatedly that the two-wheeler 5 is overtaking from the rear, and as a result, the vehicle 1 comes into contact with the two-wheeler 5 at the position shown by the vehicle A3.

[0128] On the other hand, when the vehicle 1 is mounted with the driving assistance device 10 of the present embodiment, the traffic condition prediction unit 70 of the driving assistance device 10 identifies the traffic environment including the driving position of the vehicle 1, the other vehicles X, Y, and the two-wheeler 5 at the position shown by the vehicle A1, and predicts that if the vehicle 1 continues to drive as it is, it will collide with the other vehicle X that changes lanes from the left lane. At this time, the driving assistance control unit 90 of the driving assistance device 10 is set to perform different contents of driving assistance corresponding to the driving tendency of the driver in order to avoid the collision or contact between the own vehicle 1 and the other vehicles X and the two-wheeler 5. In Figure 9 the example shown, the setting example shown in Figures 5 to 7 can also be applied.

[0129] <3. Control Processing of Driving Assistance Device>

[0130] Next, with reference to Figures 10 to 12 the flowchart shown, the control processing performed by the driving assistance device of the present embodiment will be described. Figure 10 It is a flowchart showing the overall flow of the control processing performed by the driving assistance control unit 90. Figure 11 It is a flowchart showing the flow of the traffic condition prediction processing performed by the traffic condition prediction unit 70, and Figure 12 it is a flowchart showing the flow of the driving assistance control processing performed by the driving assistance control unit 90. The control processing shown in these flowcharts can be executed continuously during the startup period of the system of the vehicle 1, or can be executed after an input for starting the operation of the driving assistance control is received.

[0131] First, the traffic condition prediction unit 70 predicts the traffic condition in which the vehicle 1 is located (step S11). For example, as Figure 11As shown, the traffic environment recognition unit 71 obtains information on the surrounding environment of the vehicle 1 based on the information transmitted from the surrounding information detection unit 43 (step S41). Next, the traffic participant extraction unit 73 extracts traffic participants such as other vehicles, pedestrians, and bicycles existing around the vehicle 1 based on the information transmitted from the surrounding information detection unit 43 (step S43). Next, the traffic participant behavior estimation unit 75 inputs the information of the extracted traffic participants into the behavior learning model 79, and estimates the behavior of each traffic participant based on the output from the behavior learning model 79 (step S45). Next, the own vehicle behavior prediction unit 77 predicts the behavior of the own vehicle 1 based on the information on the driving state of the vehicle 1 detected by the vehicle information detection unit 45 and the information on the operation state of the vehicle 1 detected by the operation information detection unit 47 (step S47). Next, the traffic condition understanding and prediction unit 81 understands and predicts the traffic condition of the own vehicle by taking into account the behavior of the traffic participants and the behavior of the own vehicle for the traffic environment around the own vehicle 1. In this way, the traffic condition prediction unit 70 predicts the traffic condition in which the vehicle 1 is located.

[0132] Next, the error detection unit 51 detects an error, which is a state in which the passenger of the vehicle 1 feels danger (step S13). Specifically, the error detection unit 51 obtains information for estimating the emotion and / or feeling of the passenger of the vehicle 1 based on the information transmitted from the passenger information detection unit 41, and detects an error based on this information. For example, in a state where it is detected based on the information on the face orientation and line of sight that the passenger is looking outside the vehicle, and in a case where there is a sudden change in pulse or heartbeat, blood pressure, electrocardiogram, etc., the error detection unit 51 detects an error. Further, it is also possible to detect an error when the error detection unit 51 detects a sudden change in pulse or heartbeat, blood pressure, electrocardiogram, etc. after detecting that the passenger is looking askance based on the information on the face orientation and line of sight and then detecting the state of returning from the askew line of sight state to the proper line of sight state.

[0133] Next, the error detection unit 51 inputs the data of the traffic condition in which the vehicle 1 is located when an error is detected into the error learning model 53, and causes the error learning model 53 to learn (update) sequentially (step S15). The target passenger for detecting an error is not limited to the driver, and may also include passengers.

[0134] Next, the collision / intersection determination unit 57 determines whether a collision or intersection of the vehicle 1 occurs based on the traffic condition predicted by the traffic condition prediction unit 70, using a physical model (step S17). Specifically, the collision / intersection determination unit 57 determines whether the trajectory of the behavior plan of the traffic participant and the trajectory of the behavior plan of the own vehicle intersect according to the physical model based on the current traffic environment, the predicted behavior of the traffic participant, and the predicted behavior of the own vehicle.

[0135] Next, the danger prediction unit 55 predicts the danger level of the vehicle 1 based on the traffic conditions predicted by the traffic condition prediction unit 70, using the error learning model 53 (step S19). Specifically, the danger prediction unit 55 inputs data on the information of the driving state of the vehicle and the information of the surrounding environment into the error learning model 53, and predicts the dangerous state of the vehicle based on the output error state. When the output from the error learning model 53 indicates that an error has been detected in the past, the danger prediction unit 55 predicts that the predicted traffic condition is a dangerous state for the vehicle. Based on past cases where the vehicle occupants actually felt danger, the dangerous state of the vehicle 1 is objectively predicted according to the current traffic conditions. Thus, it is possible to predict the occurrence of a collision or the like of the vehicle 1 starting from a time when the accuracy of determining the occurrence of a collision or the like using the physical model in the collision crossing determination unit 57 is low.

[0136] Next, the driving tendency estimation unit 59 refers to the driving tendency database 69 to estimate the driving tendency of the driver under the predicted traffic conditions (step S21). Specifically, the driving tendency estimation unit 59 refers to the driving tendency database 69 to estimate the frequency at which the driver himself felt danger in the past under the current traffic conditions, the degree of dependence of the driver himself on the driving assistance control, and the like. Thus, it is possible to estimate the driving skills of the driver, the effectiveness in the case where the driving assistance control is executed, and the like, and to change the degree of intervention actions of the warning or vehicle control.

[0137] Next, the driving assistance control unit 90 executes driving assistance control based on the predicted danger level (step S23). In the driving assistance device 10 of the present embodiment, the driving assistance control unit 90 executes at least one of warning control or vehicle control based on the information transmitted from the occupant information detection unit 41 and the information obtained by the danger prediction unit 55, the collision crossing determination unit 57, and the driving tendency estimation unit 59. For example, as Figure 12 shown, the danger level evaluation unit 91 comprehensively evaluates the danger level of the vehicle based on the prediction result of the dangerous state obtained by the collision crossing determination unit 57 based on the physical model and the prediction result of the dangerous state obtained by the danger prediction unit 55 based on the error learning model (step S51).

[0138] Next, the warning and control execution determination unit 95 determines whether it is necessary to execute warning control or vehicle control based on the evaluation result of the danger level (step S53). As Figures 5 to 7As exemplified, in the driving assistance device 10 of the present embodiment, the warning and control execution determination unit 95 sets the content of the warning or the intervention action of the vehicle control based on the progress degree of the judgment lag and the information on the driving tendency of the driver. Specifically, the warning and control execution determination unit 95 sets the content of the warning or the intervention action of the vehicle control in such a manner that the greater the progress degree of the judgment lag, the lower the driving skill of the driver, and the greater the dependence of the driver on the driving assistance control, the greater the degree of intervention in the vehicle control.

[0139] In addition, when the warning device 31 emits voice and performs text display, the risk level evaluation verbalization processing unit 93 performs verbalization processing for warning the passengers (step S55). Thus, the warning control unit 61 or the vehicle control unit 63 generates a control signal for the warning device 31 or the vehicle control device 33 based on the set warning action and the intervention action of the vehicle control. Therefore, a driving operation for the driver to avoid the dangerous state of the vehicle 1 can be prompted, or the vehicle 1 can be automatically decelerated or stopped to avoid dangerous states such as collisions of the vehicle 1, and losses can be reduced.

[0140] Next, the driving evaluation unit 65 accumulates the information on the dangerous state and risk level of the vehicle 1 predicted through various calculations and the information on the actually performed driving operations in the driving tendency database 69, and updates the driving tendency database 69 (step S25). Thus, the information indicating the driving tendency of the driver can be accumulated, the estimation accuracy of the driving tendency by the driving tendency estimation unit 59 can be improved, and the driving assistance control can be executed without disturbing the smooth driving according to the driving skill of the driver.

[0141] As described above, according to the driving assistance device 10 of the present embodiment, based on the predicted behavior of the own vehicle 1 and the behavior of the traffic participants around the own vehicle 1, the risk level of the vehicle 1 is evaluated not only based on the dangerous states such as collisions of the vehicle 1 determined according to the physical model, but also based on the dangerous states of collisions of the vehicle 1 predicted by the error learning model 53 obtained by learning the traffic conditions in which the passengers of the past vehicles felt dangerous. Therefore, even in a situation where the accuracy of the physical model is low, the risk prediction based on the objective data of the traffic environment can be performed, and the warning or the intervention action of the vehicle control can be started at an earlier timing. Thus, an avoidance action can be prompted to the driver, and the vehicle 1 can autonomously perform an action to avoid the dangerous state.

[0142] In addition, the driving assistance device 10 according to the present embodiment increases the degree of warning or vehicle control intervention in accordance with the progress of the lag in judgment before the time when a collision of the vehicle 1 or the like is assumed to occur. Therefore, it is possible to suppress the execution of excessive warnings or intervention actions for vehicle control, and it is possible to execute warnings or intervention actions for driving control without disturbing smooth driving.

[0143] In addition, the driving assistance device 10 according to the present embodiment changes the degree of warning or vehicle control intervention not only in accordance with the progress of the lag in the driver's judgment, but also in accordance with the driver's driving tendency. Therefore, it is possible to make the degree of warning or vehicle control intervention different according to the driver's individual driving skills and dependence on driving assistance control, and it is possible to execute warnings or intervention actions for driving control without disturbing smooth driving.

[0144] As described above, the preferred embodiments of the present invention have been described in detail with reference to the drawings, but the present invention is not limited to this example. It is obvious that those having ordinary knowledge in the technical field to which the present invention pertains can conceive of various modification examples or correction examples within the scope of the technical idea described in the claims, and this of course also belongs to the technical scope of the present invention.

[0145] For example, in the above-described embodiment, an example in which all the components of the driving assistance device 10 are mounted on the vehicle has been described, but the present invention is not limited to this example. A part of the functions of the driving assistance device 10 may be provided in an external device of the vehicle and configured to be able to communicate with an in-vehicle electronic control device. For example, at least one of the behavior learning model, the error learning model, and the driving tendency database may be stored in an external device of the vehicle, and the electronic control device and the external device may be configured to communicate via a wireless communication network such as mobile communication.

Claims

1. A driving assistance device, characterized in that, it comprises: a collision / intersection determination unit that determines whether a collision or intersection between the vehicle and other traffic participants will occur based on information on the driving state of the vehicle and information on the surrounding environment of the vehicle; an error detection unit that acquires biometric information of the occupant and detects the situation where the occupant feels danger based on the biometric information; an error data storage unit that stores an error learning model, which is formed by accumulating information on the driving state of the vehicle and information on the surrounding environment of the vehicle when the occupant feels the danger; a danger prediction unit that uses the error learning model and predicts whether a collision or intersection between the vehicle and other traffic participants will occur based on information on the driving state of the vehicle and information on the surrounding environment of the vehicle; and a driving assistance control unit that executes driving assistance control, wherein, when the collision / intersection determination unit determines that no collision or intersection between the vehicle and other traffic participants will occur, and when the danger prediction unit predicts that a collision or intersection between the vehicle and other traffic participants will occur, the driving assistance control unit executes warning control and an intervention action for vehicle control together with the warning control as the driving assistance control.

2. The driving assistance device according to claim 1, characterized in that, it further comprises: a driving tendency data storage unit that accumulates data on the driving operation tendency of the driver of the vehicle when the driving assistance control is executed, and the driving assistance control unit further executes the driving assistance control based on the data on the driving operation tendency of the driver.

3. The driving assistance device according to claim 2, characterized in that, the driving tendency data storage unit accumulates at least one of the frequency at which the occupant feels the danger, the driving operation when the occupant feels the danger, the degree of danger when the occupant feels the danger, or the driving skill of the driver as the driving operation tendency of the driver, and the driving assistance control unit sets the content of the driving assistance control based on this data.

4. The driving assistance device according to claim 2, characterized in that, the driving assistance control unit sets the execution timing of the driving assistance control based on the data on the driving operation tendency of the driver.

5. The driving assistance device according to claim 3, characterized in that, the driving assistance control unit sets the execution timing of the driving assistance control based on the data on the driving operation tendency of the driver.

6. The driving assistance device according to any one of claims 1 to 5, characterized in that, the driving assistance control unit sets the content of the driving assistance control based on the elapsed time since the dangerous state was predicted.

7. The driving assistance device according to any one of claims 1 to 5, characterized in that, the driving assistance control unit sets the content of the driving assistance control based on the driver's concentration or level of wakefulness.

Images