JP2008120288A - Driving support device - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide a driving support device achieving a proper running according to a present situation by predicting future vehicle operation performed by a driver from a vehicle situation stored in association with past vehicle operation of the driver. <P>SOLUTION: When a forward vehicle running in front of one's own vehicle is detected, this driving support device starts a learning system, detects a state of the own vehicle and surroundings of the own vehicle by a forward radar device 3, various kinds of sensors or the like (S5, S6), stores them in association with the vehicle operation of the driver, in a learning information DB 8 accumulatively (S8). The driving support device predicts whether the driver changes a lane later from a learning result thereof and the present vehicle state (S14), and suppresses the lane change from being disturbed such as lane keep assist control, cruise control or the like when it is predicted that the lane change is performed (S16). <P>COPYRIGHT: (C)2008,JPO&INPIT

Description

  The present invention relates to a driving support device that supports driving by predicting a vehicle operation to be performed by a driver in the future, and in particular, a future driver based on a vehicle situation stored in association with a past driver's vehicle operation. The present invention relates to a driving support device that predicts a vehicle operation performed by the vehicle.

In recent years, from the viewpoint of preventing accidents when driving a vehicle, the driver detects the obstacles such as people and bicycles located around the vehicle by radar or images of captured cameras and prevents the collision with the obstacles. There are an increasing number of vehicles equipped with driving support devices that perform warning and vehicle control.
As one of such driving assistance devices, there is one having a lane keeping assist function for adding a steering force so that the vehicle travels in the vicinity of the center of the lane in order to assist the driver's steering operation. Some vehicles have a lane departure warning function that prompts the driver to perform a steering operation to avoid departure by outputting a buzzer sound or displaying a warning when there is a possibility that the vehicle will depart from the lane. In addition, a cruise control function that adds braking force or driving force to maintain the vehicle speed set by the driver or to follow the vehicle ahead in order to assist the driver's brake operation or accelerator operation. Some have.
According to such a technique, it is possible to perform advanced and safe inter-vehicle distance control in consideration of the preceding vehicle, and appropriately follow the sudden acceleration and sudden braking of the preceding vehicle by smooth acceleration and deceleration control.

Further, some conventional driving assistance devices perform more appropriate vehicle control by learning the past driver's vehicle operation characteristics and correcting the control amount based on the learning result. For example, Japanese Patent Laid-Open No. 2000-315300 discloses a cruise control in which a millimeter-wave radar is used to detect the distance between vehicles ahead and to follow the vehicle ahead while keeping a certain distance from the vehicle ahead. A driving support device that learns and stores the driver's vehicle operating characteristics during operation and performs more appropriate vehicle control based on the current driving state of the driver determined based on changes in the driver's vehicle operating characteristics Are listed.
JP 2000-315300 A (Pages 3 to 5, FIGS. 2 to 3)

  Here, in the case where there is a forward vehicle that travels forward while the vehicle is traveling, the driver does not necessarily travel following the forward vehicle. That is, in a specific situation such as when there is no other vehicle in the surroundings and the preceding vehicle is traveling at a low speed, it may be considered that the vehicle travels ahead of the preceding vehicle by changing the lane. However, in the driving support device described in Patent Document 1 described above, regardless of the situation of the vehicle, the vehicle is decelerated against the driver's intention by the cruise control control acting during overtaking. There is a risk of control. Further, when a steering operation is performed to change the lane, a steering force is applied so that the vehicle travels near the center of the lane by the lane keep assist control. Therefore, there has been a problem of giving discomfort and stress to the driving driver.

  The present invention has been made to solve the above-described conventional problems, and it becomes possible to predict the future vehicle operation of the driver by learning the past vehicle operation of the driver under various circumstances. An object of the present invention is to provide a driving support device that enables a driver to perform a driving operation without causing discomfort and stress by unnecessary vehicle control that does not conform to the driver's intention.

  In order to achieve the above object, the driving support device (1) according to claim 1 of the present application detects the vehicle state of the driver and the state detection means (3, 4, 5A to 5D, 12) for detecting the vehicle state. Operation detection means (13-17), storage means (8) for storing the detection results of the situation detection means in association with the driver's vehicle operation detected by the operation detection means, and detection by the situation detection means And prediction means (6) for predicting a future driver's vehicle operation from the current vehicle situation and the past vehicle situation stored in the storage means.

  A driving support device (1) according to claim 2 is the driving support device according to claim 1, further comprising a forward vehicle detection means (3) for detecting a forward vehicle traveling in front of the vehicle, wherein the situation detection is performed. The means (3, 4, 5A to 5D, 12) detects the own vehicle speed, the relative speed with respect to the preceding vehicle, and the inter-vehicle distance to the preceding vehicle when the preceding vehicle is detected by the preceding vehicle detecting means, and the predicting means (6) is characterized by predicting whether or not the driver will perform a vehicle operation for changing lanes in the future.

  Further, the driving support device (1) according to claim 3 is the driving support device according to claim 1 or 2, wherein the storage means (8) performs a vehicle operation in which the driver starts a lane change. The vehicle status when the vehicle is not operated and the vehicle status when the vehicle operation is not changed are respectively stored, and the prediction means (6) is a vehicle in which the driver starts the lane change in the past based on the current vehicle status. Comparing means (6) is provided for comparing the vehicle condition when the operation is performed and the vehicle condition when the lane change is not performed, and the driver can change the lane based on the comparison result of the comparing means. It is characterized by predicting whether or not to perform vehicle operation.

  Further, the driving support device (1) according to claim 4 is the driving support device according to claim 2 or 3, wherein the prediction means (6) predicts that the vehicle operation for changing the lane is performed. And vehicle control means (6) for controlling the vehicle so as not to prevent lane change.

  Further, the driving support device (1) according to claim 5 is the driving support device according to claim 4, wherein the vehicle control means (6) maintains a constant inter-vehicle distance from the vehicle ahead of the lane in which the vehicle is currently traveling. The control is to suppress the deceleration control.

  Further, the driving support device (1) according to claim 6 is the driving support device according to claim 4, wherein the vehicle control means (6) suppresses steering control so that the vehicle does not deviate from the lane in which the vehicle currently travels. It is control.

  Furthermore, the driving assistance apparatus (1) according to claim 7 is the driving assistance apparatus 1 according to claims 4 to 6, wherein the detection result of the situation detection means (3, 4, 5A to 5D, 12) is obtained. Based on the above, the vehicle is provided with risk judging means (6) for judging whether or not the vehicle is in a dangerous situation when the vehicle does not change the lane, and predicts that the vehicle operation for changing the lane is performed by the prediction means (6). Even if it is determined that the vehicle is in a dangerous state by the danger determination means, the vehicle control means (6) does not control the vehicle.

  In the driving support apparatus according to claim 1 having the above-described configuration, the vehicle situation is stored in association with the driver's vehicle operation, and a future driver's vehicle operation is predicted from the current vehicle situation and the stored past vehicle situation. Therefore, it is possible to accurately predict the future vehicle operation of the driver under various situations based on the learning result. Accordingly, it is possible to cause the driver to perform a driving operation without causing discomfort and stress by unnecessary vehicle control.

  In the driving support device according to claim 2, when there is a forward vehicle traveling in front of the vehicle, the vehicle speed, the relative speed with respect to the forward vehicle, and the inter-vehicle distance to the forward vehicle are detected. Since it is predicted whether or not to change the vehicle, it is appropriate to determine whether the driver changes the lane and performs the overtaking action or follows the driving, especially in the situation where there is a forward vehicle. It becomes possible to predict accurately.

  In the driving support device according to claim 3, the vehicle situation when the driver performs the vehicle operation to start the lane change and the vehicle situation under the situation where the vehicle operation of the lane change is not performed are respectively stored. By comparing the current vehicle status against the vehicle status when the driver has operated the vehicle to start lane change in the past and the vehicle status under the situation where the vehicle operation of lane change has not been performed, the driver Predicts whether or not to perform vehicle operation for changing lanes, so that it is possible to accurately predict whether the driver will change lanes and perform an overtaking operation or follow the vehicle based on the learning result. It becomes possible.

  Further, in the driving support device according to the fourth aspect, the vehicle is controlled so as not to disturb the lane change when it is predicted that the vehicle operation for changing the lane is performed. Even when the control for preventing the vehicle is executed, the lane can be changed smoothly in accordance with the driver's intention.

  Further, in the driving support device according to claim 5, when it is predicted that the vehicle operation for changing the lane is performed, the vehicle is controlled so as to suppress the deceleration control for keeping the distance between the vehicle and the vehicle ahead of the lane that is currently traveling constant. Therefore, even if it is difficult to accelerate the vehicle by cruise control, it is possible to smoothly change lanes according to the driver's intention by temporarily suppressing cruise control. It becomes.

  In the driving support device according to the sixth aspect of the present invention, the vehicle is controlled so as to suppress the steering control so that the vehicle does not deviate from the lane in which the vehicle currently travels when it is predicted that the vehicle operation for changing the lane is performed. Even if it is difficult for the vehicle to move to another lane due to the keep assist control, the lane keep assist control can be temporarily suppressed to smoothly change the lane according to the driver's intention. Is possible.

  Further, in the driving support device according to claim 7, even if it is predicted that the vehicle operation of the lane change is performed when it is determined that the vehicle is in a dangerous situation unless the vehicle changes the lane. The vehicle is not controlled so as not to disturb the lane change, so the driver is not forced to change the lane when the distance to the vehicle ahead is too close or the relative speed is very high. Such vehicle control becomes possible. Thereby, it is possible to reliably avoid contact with the vehicle ahead by changing the lane.

DETAILED DESCRIPTION Hereinafter, a driving assistance apparatus according to the present invention will be described in detail with reference to the drawings based on an embodiment that is embodied.
First, a schematic configuration of the driving support device 1 according to the present embodiment will be described with reference to FIGS. 1 and 2. FIG. 1 is a schematic configuration diagram of a driving support apparatus 1 according to the present embodiment. FIG. 2 is a block diagram schematically showing a control system of the driving support apparatus 1 according to the present embodiment.

  As shown in FIGS. 1 and 2, the driving support device 1 according to the present embodiment includes a front radar device (situation detection unit, front vehicle detection unit) 3 installed on a vehicle 2 and an in-vehicle camera (situation detection). Means) 4, blinker lamps (situation detection means) 5A to 5D, driving support ECU (prediction means, comparison means, vehicle control means, risk determination means) 6, vehicle DB 7, and learning information DB (storage means) 8 And various sensors such as a vehicle speed sensor 12 connected to the vehicle ECU 9 and the driving support ECU 6.

  Here, the front radar apparatus 3 is attached in the vicinity of the upper center of a license plate mounted in front of the vehicle 2 and basically includes a radio wave transmission unit and a radio wave reception unit. Then, a radio wave beam is emitted from the radio wave transmission unit to the front of the vehicle 2 and a reflected radio wave reflected by a front object (specifically, another vehicle) is received by the radio wave reception unit. As a result, the distance and relative speed to the vehicle traveling in front of the vehicle 2 can be detected based on the received reflected radio wave intensity and wavelength.

  The in-vehicle camera 4 uses a solid-state image sensor such as a CCD, for example, is attached to the upper surface of the instrument panel, and is installed with the line-of-sight direction facing the driver's seat. Then, the face of the driver sitting in the driver's seat is imaged, and the direction of the driver's face is detected. Further, the driving support ECU 6 predicts a lane change and an overtaking operation as will be described later based on the detected face direction of the driver.

  Further, the blinker lamps 5A to 5D are composed of blinker lamps 5A and 5B arranged in front of the vehicle 2, and blinker lamps 5C and 5D arranged in the rear of the vehicle 2, and based on the operation of the driver. The blinker lamps 5A to 5D positioned in the left turn direction when making a right / left turn are turned on. Further, the driving support ECU 6 detects lighting states of the blinker lamps 5A to 5D, and predicts a lane change and an overtaking operation as will be described later.

  Further, the driving support ECU (Electronic Control Unit) 6 detects the vehicle ahead by the processing in which the vehicle operation of the driver and the vehicle situation are associated with each other and stored in the learning information DB 8 at a predetermined timing, or by the front radar device 3. When the current vehicle situation is compared with the past vehicle situation stored in the learning information DB 8, it is predicted whether the vehicle will perform lane change and overtaking operation, and the cruise control function based on the prediction result And an electronic control unit that performs control processing for suppressing vehicle control by the lane keep assist function.

  Here, the driving assistance ECU 6 is configured with the CPU 31 as a core, and a ROM 32 and a RAM 33 which are storage means are connected to the CPU 31. The ROM 32 stores a driving support processing program (see FIG. 4), which will be described later, and various other programs necessary for controlling the liquid crystal display 6 and the like. The RAM 33 is a memory for temporarily storing various data calculated by the CPU 31. The driving assistance ECU 6 may also be used as an ECU used for controlling the navigation device.

  The vehicle DB 7 is a storage unit that stores various parameter information about the vehicle such as the drive system design value and the shape design value of the vehicle 2. Then, the driving assistance ECU 6 performs lane keep assist control and cruise control control using various parameter information stored in the vehicle DB 7. It is also used for vehicle status detection and vehicle operation prediction.

  The learning information DB 8 is a DB that stores vehicle conditions such as a vehicle speed and an inter-vehicle distance with a preceding vehicle in association with a driver's vehicle operation at predetermined time intervals when the vehicle 2 is traveling. Here, in the driving support device 1 according to the present embodiment, as the vehicle operation associated with the vehicle situation, the vehicle operation for changing the lane to overtake the preceding vehicle and the vehicle in front without changing the lane are performed. There is a vehicle operation to follow the vehicle.

Each vehicle operation will be specifically described below with reference to FIG. 3. When there is a vehicle 2 and a forward vehicle 43 traveling in front of the vehicle 2 on a road where the lane 41 and the lane 42 are arranged side by side, The vehicle 2 can perform a vehicle operation of changing the lane to the adjacent lane 42 and overtaking. In addition, it is possible to perform a vehicle operation in which the vehicle continuously travels on the lane 41 and travels following the vehicle 43 while keeping a certain distance between the vehicles ahead.
And, in the situation where the vehicle is following without changing the lane, the vehicle speed V of the vehicle 2, the inter-vehicle distance L to the front vehicle 43, and the relative speed S (S = V−v) with respect to the front vehicle 43 every 100 ms. Is detected by the front radar device 3 and the vehicle speed sensor 12, and is accumulated and stored in the learning information DB 8 in association with the vehicle operation during normal traveling. Further, when there is a forward vehicle 43 traveling in front of the vehicle 2, particularly when the driver performs a vehicle operation for changing lanes, the vehicle speed V of the vehicle 2 at that time and The inter-vehicle distance L and the relative speed S with respect to the preceding vehicle 43 are similarly detected by the front radar device 3 and the vehicle speed sensor 12, and are accumulated and stored in the learning information DB 8 in association with the vehicle operation for changing the lane (S8 in FIG. 4). .
In the first embodiment, a hard disk is used as a storage medium for the vehicle DB 7 and the learning information DB 8, but a magnetic disk, memory card, magnetic tape, magnetic drum, CD, MD, DVD, optical disk, MO, IC card. An optical card or the like can also be used as an external storage device.

  The vehicle ECU 9 is an electronic control unit of the vehicle 2 that controls the operation of the engine, transmission, brake, steering, and the like, and is connected to a throttle actuator 18, a brake actuator 19, a steering 20, and a control switch 21. ing. Here, the control switch 21 includes a lane keep switch for switching ON / OFF of the lane keep assist control and a cruise control switch for switching ON / OFF of the cruise control control.

The lane keep assist control and cruise control control will be briefly described below.
Lane Keep Assist Control is a lane maintenance assist that adds steering force so that the vehicle travels near the center of the lane when the vehicle may deviate from the current lane to assist the driver in driving. Provide control.
The processing in the vehicle ECU 9 when the lane keep assist control is executed will be described. In the lane keep assist control, the steering force is applied by controlling the steering 20 so that the vehicle travels near the center of the lane. This steering force is a relatively small steering force that assists the steering force by the driver, and is set according to the curve radius of the lane, the angle difference between the vehicle and the center line of the lane, and the offset amount.

In addition, the cruise control control includes a constant speed traveling control that automatically adjusts the vehicle speed so as to travel at a vehicle speed (target vehicle speed) set by the driver, and the presence or absence of a forward vehicle and the forward vehicle by the front radar device 3. And a follow-up travel control that automatically adjusts the vehicle speed or acceleration so that the vehicle travels while keeping the distance between the vehicle constant when a vehicle is present ahead.
The processing in the vehicle ECU 9 when executing the cruise control control will be described. When the constant speed traveling control is executed, a control output is performed to the throttle actuator 18 so that the vehicle speed stored at the start of the automatic driving is maintained, and the vehicle speed is Feedback control is performed so that the vehicle speed detected by the sensor 12 matches the stored vehicle speed. In the follow-up running control, when a forward vehicle is detected by the forward radar device 3, a target inter-vehicle distance is calculated and output according to the own vehicle speed, and the target speed is calculated based on the target inter-vehicle distance and the current vehicle speed. The vehicle travels following the preceding vehicle by calculating and controlling the throttle actuator 18 and the brake actuator 19 so that the current vehicle speed matches the target vehicle speed. When the front radar device 3 does not detect a front vehicle and there is no front vehicle, constant speed traveling control is performed.

  The driving support ECU 6 includes a vehicle speed sensor (status detection means) 12, an accelerator sensor (operation detection means) 13, a brake sensor (operation detection means) 14, a steering sensor (operation detection means) 15, and a gyro sensor (operation detection means). 16, various sensors of a shift lever switch (operation detection means) 17 are connected. Here, the vehicle speed sensor 12 is a sensor that generates a vehicle speed pulse in accordance with the rotation of the vehicle wheel and detects the travel distance and the vehicle speed of the vehicle. The accelerator sensor 13 is a sensor that detects the amount of operation of the accelerator pedal by the driver. The brake sensor 14 is a sensor that detects the amount of operation of the brake pedal by the driver. The steering sensor 15 is attached to the inside of the steering device, and is a sensor that detects a steering angle when the steering wheel is steered. The gyro sensor 16 is a sensor that detects the turning angle of the vehicle 2. The shift lever switch 17 is built in a shift lever (not shown), and the shift position is “P (parking)”, “N (neutral)”, “R (reverse)”, “D (drive)”, It is detected whether the position is “2 (second speed)” or “L (low)”.

  As a result, the driving assistance ECU 6 detects the current vehicle speed of the vehicle 2 based on the output signal of the vehicle speed sensor 12 and determines the driver's accelerator operation amount and brake operation amount based on the output signals of the accelerator sensor 13 and the brake sensor 14. The steering angle of the vehicle 2 is detected based on the output signal of the steering sensor 15. Further, the vehicle direction is detected by integrating the turning angle detected by the gyro sensor 16. Further, the current shift position of the vehicle 2 is detected by the shift lever switch 17. Then, the driving assistance ECU 6 performs lane keep assist control and cruise control control based on the detected parameters. It is also determined whether or not the vehicle operation for changing the lane has been performed and whether or not the vehicle is in a dangerous situation when the lane change is not performed.

  Next, a driving support processing program executed by the driving support ECU 6 in the driving support device 1 having the above configuration will be described with reference to FIG. FIG. 4 is a flowchart of the driving support processing program according to the present embodiment. Here, the driving support processing program is executed at predetermined intervals (for example, every 100 ms) after the ignition of the vehicle is turned on, and learns the driver's vehicle operation together with the situation of the vehicle 2 and the surrounding situation of the vehicle 2, This is a program that predicts a future driver's vehicle operation using the learning result and performs vehicle control according to the prediction result. The program shown in the flowchart in FIG. 4 below is stored in the ROM 32 and RAM 33 provided in the driving support ECU 6 and is executed by the CPU 31.

  First, in step (hereinafter abbreviated as S) 1 in the driving support processing program, the CPU 31 uses the front radar device 3 to detect a forward vehicle traveling ahead within a predetermined distance from the host vehicle. Then, in S2, it is determined whether or not a forward vehicle has been detected. If it is determined that a forward vehicle has been detected (S2: YES), the process proceeds to S3. On the other hand, when it is determined that the preceding vehicle has not been detected (S2: NO), the driving support processing program is terminated.

  In S3, the CPU 31 determines whether or not lane keep assist control or cruise control control is being executed. As described above, the driver can freely switch whether or not the lane keep assist control and the cruise control control are executed by the control switch 21.

  If it is determined as a result of the determination in S3 that either the lane keep assist control or the cruise control control is being executed (S3: YES), the process proceeds to S9. On the other hand, when it is determined that neither the lane keep assist control nor the cruise control control is being executed (S3: NO), the process proceeds to S4.

  In S4, the CPU 31 activates the learning system. Here, when the learning system is activated, vehicle conditions such as the vehicle speed and the inter-vehicle distance from the preceding vehicle are detected in subsequent S5 to S8, and the detection results are cumulatively stored in association with the driver's vehicle operation. The Then, based on the stored learning contents, the driver's vehicle operation is predicted as described later (S14).

  When the learning system is activated, first, the situation of the vehicle is detected in S5. Specifically, the vehicle speed V is detected by the vehicle speed sensor 12.

  Next, in S6, the surrounding situation of the vehicle is detected. Specifically, the inter-vehicle distance L and the relative speed S to the preceding vehicle detected in S1 are detected based on the intensity and wavelength of the reflected radio wave received by the front radar device 3.

  Subsequently, the driver's vehicle operation is detected in S7. Specifically, it is determined that the host vehicle straddles the lane from the detection result of the steering sensor 15 and the gyro sensor 16 and the recognition result of an image captured by a camera (not shown) provided in front of the vehicle body. In the case where the vehicle is operated, it is detected that the vehicle operation for changing the lane is performed in order to pass the vehicle ahead. On the other hand, when it is determined that the host vehicle does not straddle the lane, it is detected that the vehicle operation for following the preceding vehicle is performed without changing the lane.

  Then, in S8, the CPU 31 determines the vehicle state (the inter-vehicle distance L and the relative speed S to the preceding vehicle, the relative speed S, and the own vehicle speed V) detected in S5 and S6 by the driver's vehicle operation (in the preceding vehicle). In contrast, the learning information DB 8 is cumulatively stored in the learning information DB 8 in association with the vehicle operation for changing the lane in order to pass the vehicle or the vehicle operation for following the vehicle ahead without changing the lane.

As a result of the learning process by the learning system of S4 to S8, the inter-vehicle distance L and the relative speed S to the preceding vehicle are continuously stored in the learning information DB 8 every 100 ms as shown in FIG. Then, as shown in FIG. 6, a table in which the vehicle speed V is further added and whether or not the driver has performed a vehicle operation for changing the lane in each vehicle situation is created.
For example, the learning information DB 8 shown in FIG. 6 learns that the vehicle operation for changing the lane has been performed in the past while the host vehicle is traveling in the state of the inter-vehicle distance L1, the relative speed S1, and the host vehicle speed V1. In addition, it is learned that the vehicle operation for changing the lane is not performed while the host vehicle is traveling under the conditions of the inter-vehicle distance L2, the relative speed S2, and the host vehicle speed V2.

Further, in the learning system, a vehicle operation determination graph shown in FIG. 7 is created based on the table shown in FIG. The graph shown in FIG. 7 extracts the own vehicle speed V when the vehicle operation for changing the lane is performed among the own vehicle speeds V stored in the learning information DB 8 corresponding to the specific inter-vehicle distance L and relative speed S. Is a statistical graph. Then, of all the extracted vehicle speed V data, an area including ± 40% of the average value Vt is defined as a lane change control area, and an area including other data is defined as a normal control area.
As will be described later, in the prediction of the vehicle operation of the driver, it is determined that the vehicle operation of the lane change is performed when the current vehicle state is in the lane change control region, and the vehicle ahead is determined to be in the normal control region. It is determined that the following vehicle operation for normal traveling is performed.

  On the other hand, as a result of the determination in S3, when it is determined that either lane keep assist control or cruise control control is being executed (S3: YES), the situation of the host vehicle is detected in S9. Specifically, the vehicle speed V is detected by the vehicle speed sensor 12.

  Next, the surrounding situation of the vehicle is detected in S10. Specifically, the inter-vehicle distance L and the relative speed S to the preceding vehicle detected in S1 are detected based on the intensity and wavelength of the reflected radio wave received by the front radar device 3.

Subsequently, in S11, the CPU 31 does not perform the vehicle operation for changing the lane and the vehicle situation when the driver has performed the vehicle operation to start the lane change in the past learned by the learning system. The future vehicle operation of the driver is predicted by comparing with the vehicle conditions below. Specifically, the control determination value used for predicting the vehicle operation of the driver (the vehicle status of the current vehicle detected in S9 and S10 (the inter-vehicle distance L to the vehicle ahead, the relative speed S, the vehicle speed V )) Is in the lane change control region for comparison.
Here, the lane change control area is an area defined for each specific inter-vehicle distance L and relative speed S as shown in FIG. 7, and when the detected own vehicle speed V is in the corresponding lane change control area ( (Vmin ≦ V ≦ Vmax) is predicted that the vehicle operation for changing the lane is performed, and when the vehicle is in the normal control region (V <Vmin, Vmax <V), it is predicted that the vehicle operation for the normal traveling following the preceding vehicle is performed. Is done. Note that S11 corresponds to the processing of the comparison means.

  Then, as a result of the determination in S11, when it is determined that the control determination value is in the lane change control region (S11: YES), that is, when it is predicted that the driver will perform a lane change vehicle operation in the future. Shifts to S12. On the other hand, if it is determined that the control determination value is in the normal control region (S11: NO), that is, the vehicle operation of the normal traveling following the preceding vehicle is performed without the vehicle operation of changing the lane in the future by the driver. If it is predicted, the driving support processing program is terminated without performing vehicle control optimization (S16) described later.

In S12, the CPU 31 captures an image of the occupant captured by the in-vehicle camera 4 and performs an analysis process to detect the direction of the occupant's face.
Specifically, first, an image captured by the in-vehicle camera 4 is input using analog communication means such as NTSC or digital communication means such as i-link, and converted into a digital image format such as jpeg or mpeg. . Next, luminance correction is performed on the background, the occupant's face, and the eyeball in the captured image based on the luminance difference. After that, binarization processing for separating the target occupant's face and eyeball from the image, geometric processing for correcting distortion, smoothing processing for removing image noise, and the like, the boundary line between the background and the face (ie , A face outline) and a boundary line between the face and the eyeball (that is, eye position). Then, the direction in which the driver is facing is detected from the detected face outline and eye position.

  Next, in S <b> 13, the CPU 31 uses the front radar device 3 to detect other vehicles that travel in adjacent left and right lanes within a predetermined distance from the host vehicle. Moreover, it detects also about the lighting state of the blinker lamps 5A-5D of the own vehicle.

  In S14, in addition to the determination result of whether or not the control determination value in S11 is in the lane change control region, the direction of the driver's face detected in S12 and the left and right lanes detected in S13 Based on the presence / absence of the vehicle and the lighting state of the blinker lamps 5A to 5D, a prediction process is performed again to determine whether or not the driver will perform a vehicle operation for changing the lane in the future. Specifically, even if it is determined in S11 that the control determination value is in the lane change control region, if the driver is facing the front, if there is a vehicle in the left and right lanes, or the blinker lamp 5A When ˜5D is not lit, it is exceptionally predicted that the driver will not perform vehicle operations for changing lanes in the future. On the other hand, when the driver is not facing the front, there is no vehicle in the left and right lanes, and the blinker lamps 5A to 5D are lit, it is predicted that the driver will perform a vehicle operation for changing the lane in the future. .

Subsequently, in S15, it is determined whether or not the control optimization of the vehicle control of the own vehicle is necessary. Here, the case where the optimization of the vehicle control is necessary is a case where the driver is predicted to perform a vehicle operation for changing the lane in S14 and the vehicle does not change the lane. This is a case where it is determined that the vehicle is not in a dangerous situation. On the other hand, the case where optimization of vehicle control is not necessary means that the vehicle is dangerous when it is predicted in S14 that the driver will not operate the vehicle for changing the lane in the future, or when the vehicle does not change the lane. This is a case where it is determined that the situation will be unsatisfactory.
Then, whether or not the vehicle is in a dangerous situation when the lane change is not performed is determined based on the detection results of the forward radar device 3 and the vehicle speed sensor 12. Specifically, when the distance to the preceding vehicle is too close or the relative speed is very high, it is determined that the vehicle is in a dangerous situation when the lane change is not performed. Note that S15 corresponds to the processing of the danger determination means.

  As a result of the determination in S15, if it is determined that the control optimization of the vehicle control of the own vehicle is necessary (S15: YES), the vehicle control is optimized (S16). Here, the optimization of the vehicle control in the driving support device 1 according to the present embodiment means that the vehicle is controlled so as not to prevent the lane change and the overtaking operation predicted to be performed in the future. Specifically, a lane that adjusts the steering 20 so as not to depart from the lane in which the vehicle currently travels, and a control that suppresses cruise control control that decelerates in order to keep the inter-vehicle distance of the vehicle ahead of the lane that currently travels constant. This is control that suppresses keep assist control. Then, the cruise control control and the lane keep assist control are temporarily suppressed, so that the driver can smoothly change the lane and pass the vehicle. Note that S11, S14, and S15 correspond to the process of the prediction unit, and S16 corresponds to the process of the vehicle control unit.

  On the other hand, as a result of the determination in S15, if it is determined that the control optimization of the vehicle control of the own vehicle is not required (S15: NO), the driving support processing program is terminated without performing the vehicle control optimization. . Therefore, it is possible to control the vehicle so that the driver is not forced to change lanes or overtake the vehicle when the distance to the vehicle ahead is too close or the relative speed is very high. Thereby, it is possible to reliably avoid contact with the preceding vehicle due to lane change and overtaking operation.

As described above in detail, in the driving support device 1 according to the present embodiment, when a forward vehicle traveling in front of the host vehicle is detected, the learning system is activated to determine the host vehicle situation and the surrounding situation of the host vehicle. It is detected by the forward radar device 3 and various sensors (S5, S6), and is accumulated in the learning information DB 8 in association with the vehicle operation of the driver (S8). On the other hand, the learning result and the current vehicle Whether or not the driver will perform a lane change driving operation in the future is predicted from the situation (S14), and if it is predicted that the lane change driving operation will be performed, the lane such as lane keep assist control or cruise control control Since the control that prevents the change is suppressed (S16), it is possible to accurately predict the future vehicle operation of the driver under various situations based on the learning result. Accordingly, it is possible to cause the driver to perform a driving operation without causing discomfort and stress by unnecessary vehicle control. Further, based on the learning result, it is possible to accurately predict whether the driver changes the lane and performs the overtaking operation or follows the driving especially in a situation where there is a forward vehicle.
If it is predicted that a driving operation for changing the lane will be performed, it is difficult to accelerate the vehicle by the cruise control control by suppressing the control for preventing the lane change such as the lane keeping assist control and the cruise control control (S16). Even under circumstances, it is possible to smoothly change lanes according to the driver's intention by temporarily suppressing the cruise control. Even if it is difficult for the vehicle to move to another lane due to the lane keep assist control, the lane change can be made smoothly according to the driver's intention by temporarily suppressing the lane keep assist control. Can be performed.
Further, the learning system stores the vehicle situation when the driver performs the vehicle operation for starting the lane change and the vehicle situation under the situation where the driver does not perform the lane change operation in the learning information DB 8, respectively. By comparing the vehicle status against the vehicle status when the driver has operated the vehicle to start lane change in the past and the vehicle status under the situation where the vehicle operation of lane change has not been performed, the driver Since it is predicted whether or not to change the vehicle operation, it is possible to accurately predict whether the driver will change the lane based on the learning result and perform the overtaking operation or follow the vehicle. Become.
Furthermore, if it is determined that the vehicle is in a dangerous situation if the vehicle does not change the lane (S15: NO), the lane change is prevented even if it is predicted that the vehicle operation for changing the lane will be performed. Vehicle control that prevents the driver from making excessive lane changes when the distance to the vehicle ahead is too close or the relative speed is very high. Is possible. Thereby, it is possible to reliably avoid contact with the vehicle ahead by changing the lane.

Note that the present invention is not limited to the above-described embodiment, and various improvements and modifications can be made without departing from the scope of the present invention.
For example, in this embodiment, the learning system is activated only when the lane keep assist control or the cruise control control is not executed (S4), but even when the lane keep assist control or the cruise control control is executed. It is good also as starting a learning system.

  Further, in the present embodiment, the front radar apparatus 3 using a millimeter wave radar is used for detection of the front vehicle, but it may be detected based on an image captured by the front camera. Moreover, it is good also as detecting by a sound wave sensor etc. Furthermore, it is good also as detecting a parallel running vehicle by communicating between vehicles.

  If it is determined that the road on which the vehicle currently travels is congested based on traffic jam information transmitted from a VICS (registered trademark: Vehicle Information and Communication System) center or the like, the lane change is performed in S14. Even if it is predicted that the vehicle operation will be performed, the vehicle control optimization (S16) may not be performed.

It is a schematic structure figure of a driving support device concerning this embodiment. It is a block diagram which shows typically the control system of the driving assistance device concerning this embodiment. It is the schematic diagram which showed the specific example of vehicle operation in case there exists a front vehicle. It is a flowchart of the driving assistance processing program which concerns on this embodiment. It is the figure which showed the inter-vehicle distance and relative speed with the front vehicle detected in predetermined intervals in the learning system. It is the figure which each showed the vehicle condition memorize | stored in learning information DB in the learning system, and vehicle operation at the time. It is the graph which showed the lane change control area | region and the normal control area | region.

Explanation of symbols

DESCRIPTION OF SYMBOLS 1 Driving assistance apparatus 2 Vehicle 3 Front radar apparatus 4 In-vehicle camera 5A-5D Winker lamp 6 Driving assistance ECU
8 learning information DB
12 Vehicle speed sensor 13 Accelerator sensor 14 Brake sensor 15 Steering sensor 16 Gyro sensor 17 Shift lever switch 31 CPU
32 ROM
33 RAM

Claims (7)

Status detection means for detecting the vehicle status;
Operation detecting means for detecting the driver's vehicle operation;
Storage means for storing the detection result of the situation detection means in association with the driver's vehicle operation detected by the operation detection means;
A driving support apparatus comprising: a prediction unit that predicts a future vehicle operation of a driver based on a current vehicle situation detected by the situation detection unit and a past vehicle situation stored in the storage unit. Forward vehicle detection means for detecting a forward vehicle traveling in front of the vehicle,
The situation detecting means detects the own vehicle speed, the relative speed with respect to the preceding vehicle, and the inter-vehicle distance to the preceding vehicle when the preceding vehicle is detected by the preceding vehicle detecting means,
The driving support apparatus according to claim 1, wherein the predicting unit predicts whether or not the driver will perform a vehicle operation for changing lanes in the future. The storage means stores a vehicle situation when the driver performs a vehicle operation for starting a lane change and a vehicle situation under a situation where the driver does not perform a lane change vehicle operation, respectively.
The prediction means includes
Comparing means for comparing the current vehicle situation with the vehicle situation when the driver has operated the vehicle to start lane change in the past and the vehicle situation under the situation where the vehicle operation of lane change has not been performed,
The driving support apparatus according to claim 1 or 2, wherein the driver predicts whether or not the driver performs a vehicle operation for changing lanes based on a comparison result of the comparing means.   4. The driving according to claim 2, further comprising vehicle control means for controlling the vehicle so that the lane change is not prevented when the prediction means predicts that the vehicle operation for changing the lane is performed. Support device.   5. The driving support apparatus according to claim 4, wherein the vehicle control means is a control that suppresses deceleration control for maintaining a constant inter-vehicle distance with a preceding vehicle in a lane that is currently running.   The driving support apparatus according to claim 4, wherein the vehicle control unit is a control that suppresses steering control so that the vehicle does not deviate from a lane in which the vehicle is currently traveling. A risk determination means for determining whether or not the vehicle is in a dangerous situation when the vehicle does not change lanes based on the detection result of the situation detection means;
Even if it is predicted that the vehicle operation for changing the lane will be performed by the prediction means, the vehicle control means does not control the vehicle when the danger determination means determines that a dangerous situation occurs. The driving support apparatus according to any one of claims 4 to 6, wherein the driving support apparatus is characterized by the following.

Images