JP2007219836A - Vehicle travel support device - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To perform more proper danger warning by performing danger prediction according to travel environment. <P>SOLUTION: A control unit 1 compares an image photographed by a camera 8 and a criterion template image that is a decision criterion, and predicts danger by similarity thereof. When predicting that the danger starts in the face, alarm output is performed by an alarm 9 according thereto. The criterion template image is updated according to subsequent vehicle operation. <P>COPYRIGHT: (C)2007,JPO&INPIT

Description

  The present invention relates to a vehicular travel support apparatus that supports vehicle collision avoidance.

  In order to support safe driving, danger warning technology is positioned as one of the key technologies in ITS (Intelligent Transport Systems). More specifically, the danger warning means that the driver is provided with information on traffic conditions and driving environment abnormalities, behavior of surrounding vehicles, the presence of pedestrians and bicycles, and the like.

  Techniques for performing such danger warnings have been proposed from various viewpoints. For example, Patent Document 1 discloses a technique for recognizing an object in the environment around the vehicle, calculating a risk level according to the type of the recognized target object, and outputting the calculated risk level.

JP 2003-81039 A

  However, the degree of risk can vary depending on the actual driving environment such as the driving situation and the driving skill of the driver. In this regard, in the technique disclosed in Patent Document 1 described above, such a traveling environment is not taken into account in the calculation of the degree of danger, and thus a danger warning may not be appropriately performed.

  Accordingly, an object of the present invention is to perform a more appropriate danger warning by performing a danger prediction according to a traveling environment.

  According to an aspect of the present invention, there is provided a vehicular driving support apparatus that detects a situation around a vehicle and compares the detection result of the surrounding situation detection unit with a predetermined criterion. A risk prediction means for predicting, a warning means for warning a driver when a danger is predicted by the danger prediction means, and an update means for updating the determination criteria according to operation of the vehicle .

  According to this configuration, the determination criterion used for the prediction of danger is updated according to the operation of the vehicle, so that information on the actual traveling environment can be reflected in the prediction of danger.

  According to a preferred embodiment of the present invention, the skill determination means for determining the driving skill of the driver, and the setting means for performing the initial setting of the determination criterion according to the driving skill determined by the skill determination means are further provided. It is preferable to have.

  According to this configuration, the degree of risk can be appropriately determined according to the driving skill of the driver.

  According to a preferred embodiment of the present invention, it is preferable that the skill determination means determines the driving skill based on driver registration information. According to this configuration, the driving skill can be easily determined.

  Alternatively, the skill determination means may determine the driving skill based on travel data during vehicle travel. According to this configuration, the driving skill can be determined more accurately.

  According to a preferred embodiment of the present invention, it is preferable that the danger predicting means predicts a danger by comparing a detection result of the ambient condition detecting means with a determination criterion for each predetermined driving situation.

  According to this configuration, it is possible to perform the risk determination and update the determination standard in accordance with the reality that the degree of danger varies depending on the driving situation.

  According to a preferred embodiment of the present invention, it is preferable that the alarm output means outputs an alarm in a manner corresponding to the driving situation.

  According to this configuration, the driver can easily identify the risk level.

  According to a preferred embodiment of the present invention, the update means sets the determination criterion in a direction in which a danger is likely to be predicted when a sudden brake or a sudden handle is detected within a predetermined time after an alarm by the alarm means. It is preferable to update.

  According to this configuration, it is possible to detect that a sudden driving operation has been performed even though a warning is given to the driver, and thereafter, a warning is issued to the driver earlier. Can do.

  According to a preferred embodiment of the present invention, after the warning by the warning means, if the sudden brake or the sudden handle is not detected within a predetermined time, the determination criterion is updated in a direction in which the danger is less likely to be predicted. It is preferable.

  According to this configuration, output of useless warnings can be suppressed.

  According to the present invention, risk prediction according to the driving environment is performed, and thus more appropriate danger warning can be performed.

  DESCRIPTION OF EMBODIMENTS Hereinafter, preferred embodiments of the present invention will be described in detail with reference to the drawings. In addition, this invention is not limited to the following embodiment, It shows only the specific example advantageous for implementation of this invention. In addition, not all combinations of features described in the following embodiments are indispensable as means for solving the problems of the present invention.

  FIG. 1 is a diagram illustrating an arrangement configuration of a driving support device in a vehicle according to the present embodiment, and FIG. 2 is a block diagram illustrating a hardware configuration of the driving support device according to the present embodiment.

  A steering sensor 2 is provided in the vicinity of the steering device and detects a steering angle. 3 is a steering actuator for operating the steering of the steering device, and 4 is a brake actuator for operating a brake. Reference numeral 5 denotes a vehicle speed sensor. Reference numeral 6 denotes a throttle actuator 6 for operating the throttle. Reference numeral 7 denotes an antenna for performing communication with a server device (not shown). Reference numeral 8 denotes a camera that acquires an image for detecting the surrounding situation of the vehicle, such as a CCD camera, a CMOS camera, or an infrared camera. An alarm device 9 has a sound output function. Reference numeral 10 denotes an IC card reader, which reads various information of the driver from the IC card inserted therein. Reference numeral 1 denotes a control unit that controls the driving support apparatus. As shown in FIG. 2, each unit described above is connected to this control unit.

  As shown in FIG. 2, the control unit 1 is a computer having a CPU 11, a RAM 12, and a ROM 13 as basic configurations. As shown in the figure, the ROM 13 stores a control program 13a for realizing the driving support processing of the present invention, and a plurality of risk prediction determination image (hereinafter referred to as “template images”) data 13b serving as risk prediction determination criteria. Has been. Instead of storing the template image data 13b in the driving support device, the template image data 13b may be stored in a server device provided in the service center and periodically updated.

  Hereinafter, the function of the driving assistance apparatus in this embodiment is demonstrated.

  The travel support apparatus according to the present embodiment performs risk prediction before reaching the stage of collision prediction or collision avoidance, which is highly likely to lead to a danger but normally cannot recognize a dangerous state yet. At the stage of predicting danger, the driver is alerted to prevent accidents from occurring.

  The driving support device according to the present embodiment predicts the danger depending on where the host vehicle is currently located under what kind of driving situation, and transmits a warning corresponding to the situation to the driver. In the present embodiment, the driving support apparatus holds a plurality of typical driving situation template images 13b as risk determination criteria. The image of the vehicle surroundings acquired by the camera 8 is compared with each of these template images, and the template image with the highest similarity is specified. As a result, the driving situation at the current position is specified. If the maximum similarity exceeds a predetermined value, it is determined that the risk is high, and a warning is issued as described above.

  FIG. 3A to FIG. 3H show examples of driving situations with a high degree of risk that should be issued and warning contents corresponding to the driving support apparatus.

(Operational situation 1: Fig. 3A)
The driving situation 1 is a situation where the vehicle 100 will pass straight through the intersection. Under this situation, for example, a warning “a vehicle may come out from the left side” is appropriate.

(Driving situation 2: Fig. 3B)
The driving situation 2 is a situation where the vehicle 100 turns left at the intersection. Under this circumstance, for example, a warning “Your motorcycle on the left may be involved” is appropriate.

(Driving situation 3: Fig. 3C)
The driving situation 3 is a situation where the vehicle 100 turns left at the intersection and a pedestrian crossing is provided on the left turn side. Under this circumstance, for example, a warning “There may be people on the pedestrian crossing turning left” is appropriate.

(Driving situation 4: Fig. 3D)
Driving situation 4 is a situation where the vehicle 100 turns right at the intersection and a pedestrian crossing is provided on the right turn side. Under this circumstance, for example, a warning “There may be people on the pedestrian crossing turning right” is appropriate.

(Operation status 5: FIG. 3E)
The driving situation 5 is a situation where the vehicle 100 travels on the right curve. Under this circumstance, for example, a warning “An oncoming vehicle may cross the center line” is appropriate.

(Operation situation 6: Fig. 3F)
The driving situation 6 is a situation in which the host vehicle 100 passes the right side of the vehicle parked in parallel. Under this circumstance, for example, a warning “People may come out from between parked vehicles” is appropriate.

(Operation situation 7: FIG. 3G)
The driving situation 7 is a situation where the host vehicle 100 crosses the oncoming lane. Under this circumstance, for example, a warning “a person may come out from the shadow of an oncoming vehicle” is appropriate.

(Operation situation 8: Fig. 3H)
The driving situation 8 is a situation where the host vehicle 100 changes lanes to the left lane. Under this circumstance, for example, a warning “There may be a vehicle on the left rear” is appropriate.

  In addition, the template image for each driving situation is not a single image, but a plurality of template images with different vehicle positions are held under the driving situation, and a reference template image is selected from among them depending on the driving skill of the driver. May be determined. As an example, a template image of driving situation 1 shown in FIG. 4 will be described. As shown in the figure, for example, n template images of A1 to An are prepared as template images of the driving situation 1. Here, as the vehicle goes from A1 to An, the image shows that the position of the vehicle approaches the intersection. Then, a reference template image is set from among these according to the driving skill of the driver. FIG. 4A shows an example of an initial setting state, and A2 is set as a reference template image. As will be described later, the reference template can be updated as shown in (b) in accordance with a predetermined driving operation. Similarly, updatable reference template images are set for other driving situations.

  In this case, the image of the vehicle surroundings acquired by the camera 8 is compared with a reference template image that is a risk determination criterion for each driving situation, and the reference template image with the highest similarity is specified. In this way, the driving situation at the current position is specified, and if the maximum similarity exceeds a predetermined value, it is determined that the risk is high, and a warning is issued as described above.

  In this way, the driving support device assumes various driving situations in advance and stores the template image 13b of each driving situation as a risk criterion. However, the driving situation as described above is only a typical example of a very wide variety of actual driving situations. However, it is also difficult to presume and store template images of all driving situations. Therefore, in the present embodiment, for example, as shown in FIG. 4A, the template images 13b related to the above driving situations 1 to 6 are held in advance, and other driving situations ( For example, when the driving situation 7 or 8) is encountered, it is possible to additionally register an image obtained from the camera 8 at that time as a template image of a new driving situation (see FIG. 4C).

  FIG. 5 is a flowchart showing a processing procedure of the driving support device that realizes the functions as described above. A program corresponding to this flowchart is included in the control program 13a and executed by the CPU 11.

  First, in step S1, the driver's driving skill is determined. This can be determined, for example, by reading the driving skill data of the driver stored in the IC card via the IC card reader 10. FIG. 6 shows an example of the driving skill data of the driver stored in the IC card. As shown in the figure, the driving skill level of each driving situation 1 to 6 is described in the IC card as the driving skill data including the identification information of the driver. The driving skill level values (A2, B3,..., Fn) in the figure correspond to the template image numbers in FIG.

  Alternatively, instead of reading the driving skill data of the driver stored in the IC card as described above, the driving skill level of the driver may be determined based on the frequency of past sudden braking and sudden steering. Specifically, history data relating to the driving operation of the driver is held, and the frequency of sudden braking and sudden steering for each driving situation described above is read from this history data. Then, referring to the driving skill determination table related to sudden braking as shown in FIG. 7A and the driving skill determination table related to sudden steering as shown in FIG. Identify the driving skill level for each sudden braking and sudden steering frequency.

  Next, the process proceeds to step S2. Here, for each driving situation, initial setting of a reference template image is performed according to the driving skill of the driver determined in step S1. For example, as shown in FIG. 6, when the driving skill level in the driving situation 1 is determined to be A2, the template image A2 shown in FIG. 4A corresponding to this is set as the reference template image. Is set. The other driving conditions are set in the same manner.

  Next, in step S3, the environment around the vehicle is detected. Specifically, a vehicle surrounding image photographed by the camera 8 is acquired. It is assumed that the latest images for a predetermined time taken by the camera 8 are always stored in the RAM 12 or the like.

  Next, in step S4, the vehicle surrounding image obtained in step S3 is compared with the reference template image of each driving situation, and the reference template image having the highest similarity is specified, and the maximum similarity is a predetermined value. Determine if it has exceeded. When the maximum similarity exceeds a predetermined value, it is determined that danger is imminent in the driving situation related to the reference template image (danger prediction). In this case, the process proceeds to step S5 to cause the alarm device 9 to output an alarm. At this time, as shown in FIGS. 3A to H, it is preferable to perform alarm output of contents or modes according to the driving situation. This is because the driver can immediately determine what kind of danger is imminent.

  In subsequent step S6, it is determined whether or not a predetermined time has elapsed since the danger was predicted in step S4. When the predetermined time has elapsed, the process proceeds to step S7 (the alarm output in step S5 is maintained).

  In step S7, it is determined whether sudden braking or sudden steering has occurred, for example, based on the outputs of the snake angle sensor 2 and the vehicle speed sensor 5 within the predetermined time after the danger is predicted in step S4. Here, it can be said that the case where the sudden braking or the sudden steering is generated is highly likely to be a case where a sudden driving operation for avoiding danger is performed in spite of the alarm output in step S5. Therefore, in such a case, the process proceeds to step S8, and a template image that is one level lower is set as a reference template image. For example, as shown in FIG. 4A, when the template image A2 of the driving situation 1 is set as the reference template image, in step S8, the template image A1 is updated to the reference template image. In other words, in this case, the determination criterion is updated in a direction in which danger is likely to be predicted.

  On the other hand, if a sudden brake or a sudden handle is not detected in step S7, the process proceeds to step S9, and a template image that is one level higher than the reference template image is set as the reference template image. That is, in this case, the determination criterion is updated in a direction in which the danger is less likely to be predicted.

  And after execution of said step S8 or step S9, it progresses to step S10 and complete | finishes the alarm output currently maintained in step S5.

  In step S4, when the maximum similarity is not more than a predetermined value, the process proceeds to step S11. In step S11, it is determined whether sudden braking or sudden steering has occurred. Here, when a sudden brake or a sudden handle is detected, it can be considered that the danger avoidance operation has been performed under a situation that is not one of the driving situations 1 to 6. In this case, the process proceeds to step S12, where a plurality of images before a predetermined time before the occurrence of sudden braking and sudden steering are read out, and these images are added as template images for new driving conditions (see FIG. 4C). Alternatively, selection of a newly added template image and corresponding warning content can be set in the above server device.

  When the occurrence of sudden braking or sudden steering is detected in step S7 or step S11, an external storage device or server device (not shown) (not shown) is associated with the image taken by the camera 8 at that time. May be used for the determination of the driving skill in step S1.

It is a figure which shows the arrangement configuration to the vehicle of the driving assistance device in embodiment. It is a block diagram which shows the hardware constitutions of the driving assistance apparatus in embodiment. , , , , , , , It is a figure which shows the example of the high driving | running | working condition with which the driving assistance device in embodiment assumes the warning condition according to it. It is a figure which illustrates notionally handling of the image data for danger prediction determination in embodiment. It is a flowchart which shows the process sequence of the driving assistance device in embodiment. It is a figure which shows an example of the driving skill data of the driver in embodiment. It is a figure which shows an example of the table for driving skill determination in embodiment.

Explanation of symbols

1: Control unit 2: Snake angle sensor 5: Vehicle speed sensor 7: Communication antenna 8: Camera 9: Alarm device 10: IC card reader 11: CPU
12: RAM
13: ROM
13a: Control program 13b: Image for risk prediction determination (template image) data

Claims (8)

A vehicle travel support device for assisting vehicle collision avoidance,
An ambient condition detecting means for detecting an ambient condition of the vehicle;
A danger prediction means for predicting danger by comparing the detection result of the ambient condition detection means with a predetermined criterion;
Alarm means for warning the driver when danger is predicted by the danger prediction means;
Updating means for updating the determination criterion according to operation of the vehicle;
A vehicle travel support device comprising: Skill determination means for determining the driving skill of the driver;
Setting means for initial setting of the determination criteria according to the driving skill determined by the skill determination means;
The vehicle travel support apparatus according to claim 1, further comprising:   The vehicle driving support apparatus according to claim 2, wherein the skill determination means determines the driving skill based on driver registration information.   The vehicle travel support apparatus according to claim 2, wherein the skill determination unit determines the driving skill based on travel data during vehicle travel.   5. The risk prediction unit according to claim 1, wherein the risk prediction unit predicts a risk by comparing a detection result of the ambient state detection unit with a determination criterion for each predetermined driving situation. The vehicle travel support apparatus according to claim.   The vehicular travel support apparatus according to claim 5, wherein the alarm means issues an alarm in a manner corresponding to the driving situation.   The update means updates the determination criterion in a direction in which a danger is likely to be predicted when a sudden brake or a sudden handle is detected within a predetermined time after the warning by the warning means. 6. The vehicle travel support device according to any one of 6 to 6.   The update means updates the determination criterion in a direction in which a danger is less likely to be predicted when a sudden brake or a sudden handle is not detected within a predetermined time after the warning by the warning means. Item 8. The vehicle travel support device according to Item 7.

Images