JP6575451B2 - Driving support device and driving support program - Google Patents

Description

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

  An automatic driving vehicle equipped with an automatic driving system has a function of automatically detecting and avoiding danger while performing surrounding monitoring, and realizes automatic driving control without involving the driver. On the other hand, the driver does not fully trust the detection of the danger by monitoring the periphery of the automatic driving system, and doubts that the automatic driving system can detect the danger reliably. For this reason, even if the driver is in a state that can be avoided by automatic driving control, the driver releases the automatic driving control by braking at the timing (sense) at which the driver perceives the danger. I feel stress.

JP 2011-198247 A JP 2002-120676 A

  For such a situation, Patent Literature 1 proposes a danger warning mainly on the vehicle side. For example, by detecting the driver's gaze (gaze) direction and warning the driver that a danger other than the gaze direction has occurred, the vehicle is subject to object monitoring (moving objects such as pedestrians and bicycles, We have proposed a method that always displays the state of detecting obstacles (such as obstacles) visually, such as marking the detected object using the video obtained from the camera on the display in the vehicle ( Patent Document 2).

  However, the driver needs to look at the display to feel stress because the object being detected is always displayed and to recognize the object being detected by the vehicle. There is a problem that is not appropriate for a person to detect dangers intuitively. In addition, risk detection is mainly performed by the device side, and the risk detection accuracy, distance range, blind spot, and malfunctions of the device side are always present, and the driver always feels uneasy during automatic driving. Yes.

  The present invention has been made in view of the above circumstances, and an object of the present invention is to provide an automatic driving support device and an automatic driving support capable of notifying whether or not the automatic driving system detects a moving body that the user feels dangerous. To provide a program.

  According to the first aspect of the present invention, when the user speaks the moving body confirmation instruction, the voice recognition unit (8a) recognizes the moving body confirmation instruction as a voice, so that the attention area setting unit (24a) performs the automatic driving system (2). An attention area to which a user pays attention is set within the sensing range. And when a mobile body detection part (24b) detects the mobile body located in an attention area, a mobile body notification part (8c) notifies a user of presence of the said mobile body. Thereby, since the user can confirm that the automatic driving system has detected a dangerous moving body, the automatic driving by the automatic driving system (2) can be continued with peace of mind.

The functional block diagram which shows the whole system in one Embodiment Figure showing the field of view from the driver The figure which shows the process until the automatic driving system detects the car (the 1) Diagram showing the process until the automatic driving system detects a car (Part 2) Diagram showing the process until the automatic driving system detects a car (Part 3) The figure which shows the process in which the automatic driving system could not detect the car (part 1) Diagram showing the process by which the automatic driving system could not detect the car (Part 2) Diagram showing the process by which the automated driving system could not detect the car (Part 3) The figure which shows the process in which the automatic driving system was not able to detect a car (the 4) Diagram showing the process until the automatic driving system detects two cars (Part 1) Diagram showing the process until the automatic driving system detects two cars (part 2) Diagram showing the process until the automatic driving system detects two cars (Part 3) Diagram showing the process until the automatic driving system detects a motorcycle (part 1) Diagram showing the process until the automatic driving system detects a motorcycle (part 2) Diagram showing the process until the automatic driving system detects a motorcycle (part 3) Diagram showing the process by which the automatic driving system could not detect a motorcycle (part 1) Diagram showing the process by which the automatic driving system could not detect a motorcycle (part 2) Diagram showing the process by which the automatic driving system could not detect a motorcycle (Part 3) Flow chart showing speech recognition processing Flow chart showing line-of-sight direction detection processing Flow chart showing mobile body notification processing Flow chart showing attention area setting processing Flow chart showing moving object detection processing

Hereinafter, an embodiment will be described with reference to the drawings.
As shown in FIG. 1, the entire system is configured by combining a navigation device 1 and an automatic driving system 2. The automatic driving system 2 includes a locator device 3 (corresponding to a driving support device), a traveling track management device 4, and a vehicle motion control device 5.

  The navigation device 1 receives GPS radio waves radiated from GPS satellites and captured by the GPS in-dash antenna 6 and calculates various parameters extracted from the GPS signals to specify the current position of the own vehicle as the own vehicle position. Have The navigation device 1 also outputs various types of navigation information such as the host vehicle position, the destination, the route from the host vehicle position to the destination, and the estimated arrival time to the locator device 3. In addition, the navigation device 1 outputs a display command signal and a voice output command signal to the HMI device 7.

  The HMI device 7 is a display or a speaker. When the display command signal is input from the navigation device 1, the HMI device 7 displays display information such as warnings and route guidance on the display according to the display command signal. When the voice output command signal is input from the navigation device 1, the HMI device 7 outputs voice information such as warning and route guidance from the speaker according to the voice output command signal.

  The locator device 3 includes a control unit 8, a GPS receiver 9, a gyro sensor 10, a G sensor 11, a road network data storage unit 12, and a detailed map data storage unit 13. The GPS receiver 9 receives a GPS radio wave radiated from a GPS satellite and captured by the GPS roof antenna 14, calculates various parameters extracted from the GPS signal, and specifies the current position of the own vehicle as the own vehicle position. Then, a position signal indicating the specified vehicle position is output to the control unit 8.

  The gyro sensor 10 detects an angular velocity acting on the host vehicle, and outputs an angular velocity signal indicating the detected angular velocity to the control unit 8. The G sensor 11 detects acceleration acting on the host vehicle, and outputs an acceleration signal indicating the detected acceleration to the control unit 8.

  The road network data storage unit 12 stores road network data and outputs the road network data to the control unit 8. The road network data is map information indicating the shape of the road, the position of the road, the connection between a plurality of roads, information on the lanes constituting the road, and the like.

  The detailed map data storage unit 13 stores detailed map data and outputs the detailed map data to the control unit 8. Detailed map data is a map that includes the number of lanes that make up the road, the width of the lane, the position and type of dot lines that divide the lane, the increase or decrease in lanes, the connection between lanes, whether vehicles can move between lanes Information.

  The control unit 8 corrects the own vehicle position indicated by the position signal input from the GPS receiver 9 with the angular velocity indicated by the angular velocity signal input from the gyro sensor 10 or the acceleration indicated by the acceleration signal input from the G sensor 11. . The locator device 3 can specify the position of the host vehicle with higher accuracy than the navigation device 1.

  The steering angle sensor 15 detects the steering angle of the steering wheel and outputs a steering angle signal indicating the detected steering angle of the steering wheel to the traveling track management device 4. The accelerator sensor 16 detects an accelerator operation amount, and outputs an accelerator signal indicating the detected accelerator operation amount to the traveling track management device 4. The brake sensor 17 detects a brake operation amount and outputs a brake signal indicating the detected brake operation amount to the traveling track management device 4.

  The vehicle front camera 18 captures the front of the host vehicle and outputs a video signal including the captured image to the traveling track management device 4. The vehicle front camera 18 is, for example, a CCD image sensor, a CMOS image sensor, or the like, and may be singular or plural. The millimeter wave radar 19 transmits a millimeter wave to the front of the host vehicle, detects the presence of an object (for example, a preceding vehicle) in front of the host vehicle based on the reception state of the reflected wave, and outputs a detection signal indicating the detection result to the traveling track. Output to the management apparatus 4. The laser radar 20 transmits laser light in front of the host vehicle, detects the presence of an object in front of the host vehicle based on the reception state of the reflected wave, and outputs a detection signal indicating the detection result to the traveling track management device 4. . The millimeter wave radar 19 and the laser radar 20 may be singular or plural.

  The driver photographing camera 21 photographs the driver's face while the driver is sitting in the driver's seat and faces the front of the vehicle, and outputs a video signal including the photographed image to the locator device 3. The driver photographing camera 21 is a CCD (Charge Coupled Device) image sensor, a CMOS (Complementary Metal Oxide Semiconductor) image sensor, or the like, and may be singular or plural.

Microphone 22 outputs a sound collection signal indicating the collected sound to locator device 3.
The speaker 23 generates a sound signal from the locator device 3 as sound.
The traveling track management device 4 includes a steering angle signal input from the steering angle sensor 15, an accelerator signal input from the accelerator sensor 16, a brake signal input from the brake sensor 17, a video signal input from the vehicle front camera 18, and a millimeter wave radar 19. The traveling track on which the host vehicle travels is specified using the detection signal input from the vehicle and the detection signal input from the laser radar 20.

  When the vehicle trajectory control device 5 inputs the travel trajectory information from the travel trajectory management device 4, the vehicle motion control device 5 controls the motion of the host vehicle so that the host vehicle travels according to the travel trajectory indicated by the travel trajectory information.

  The control unit 8 of the locator device 3 is configured by a microcomputer having a CPU (Central Processing Unit), a ROM (Read Only Memory), a RAM (Random Access Memory), and an I / O (Input / Output). The control unit 8 executes a computer program stored in the non-transitional tangible recording medium, thereby executing processing corresponding to the computer program and controlling the overall operation of the locator device 3.

  In addition to the normal function, the control unit 8 includes a voice recognition unit 8a, a line-of-sight direction determination unit 8b, and a moving body notification unit 8c. Each of these units 8a to 8c is configured by a program executed by the control unit 8, and is realized by software.

  The voice recognition unit 8a recognizes voice generated by the driver using a voice signal input from the microphone 22. The line-of-sight direction determination unit 8b uses the video signal input from the driver photographing camera 21, analyzes the movement of the driver's head and eyeballs, determines the line-of-sight direction of the driver, and notifies the traveling track management device 4. As will be described later, the moving body notification unit 8c generates the presence of the moving body detected by the traveling track management device 4 from the speaker 23 by voice.

  The control unit 24 of the traveling track management device 4 includes an attention area setting unit 24a and a moving body detection unit 24b in addition to the normal functions. Each of these units is configured by a program executed by the control unit, and is realized by software.

  The attention area setting unit 24a receives the driver's line-of-sight direction determined by the line-of-sight direction determination unit 8b, and sets the area of interest to which the driver pays attention within the sensing range. The moving body detection unit 24b detects a moving body located in the attention area and notifies the locator device 3 of the moving body.

  Now, when the automatic driving system 2 performs automatic driving, the driver does not participate in driving. For example, when a vehicle that the driver feels dangerous (hereinafter referred to as dangerous vehicle) is found, automatic driving is performed. It becomes an uneasy psychological state whether the system 2 detects the dangerous vehicle. In this case, if all the moving bodies detected by the automatic driving system 2 are notified to the driver, notification of the moving bodies frequently occurs and is troublesome. The dangerous vehicle includes not only a case where the own vehicle is moving, but also a vehicle which moves toward the own vehicle when the own vehicle is stopped.

For this reason, in the present embodiment, the automatic driving system 2 sets only dangerous vehicles as detection targets, and notifies the driver of the presence of dangerous vehicles when the dangerous vehicles are detected.
As shown in FIG. 2, when the driver finds one dangerous vehicle that enters so as to cross an intersection located ahead, the driver detects the one vehicle while visually checking the dangerous vehicle. “?” Is issued (see FIG. 3A).

  When the input from the microphone 22 is detected in the voice recognition process shown in FIG. 8 (S101: YES), the locator device 3 recognizes the driver's utterance content (S102), and moves by analyzing the content. It is determined whether it is a body confirmation instruction (S103: NO) or a moving body confirmation cancellation instruction (S107: NO). In this case, since it is a moving body confirmation instruction (S103: YES), by setting Start = 1 (S104), after setting the start of the moving body confirmation operation, the moving body detected from the moving body confirmation instruction Is set as Driver = N (S105), that is, the number of recognized drivers is set. In the state of Start = 1 (S106: NO), a standby state is entered.

  “Vehicle”, “Automobile”, “Passenger car”, “Truck” etc. are also synonymous with “Car” (corresponding to the type), and “Detection”, “Recognition”, “Confirmation”, “Discovery” Is also determined as a synonym for “detection”, and “detection?”, “Detection?”, Etc. are determined as synonyms as “detected?”. Further, when there is one dangerous vehicle, “1” may be omitted, and when “1” is omitted, Driver = 1 is set.

  The locator device 3 determines whether Start = 1 in the gaze direction detection process shown in FIG. 9 (S201: NO). If Start = 1 (S201: YES), the locator device 3 is based on the peripheral sensor information. The driver's line-of-sight direction is detected (S202).

  In the attention area setting process shown in FIG. 11, the traveling track management device 4 determines whether the locator device 3 has detected the line-of-sight direction when Start = 1 (S401: YES) (S402: NO). When the locator device 3 detects the line-of-sight direction (S402: YES), an attention area is set based on the line-of-sight direction (S403). The attention area is an area that is set within the sensing range of the traveling track management device 4 based on the line-of-sight direction (within the range indicated by the broken line in FIG. 3A). As shown in FIG. In the case of an oblique left direction with respect to the forward direction, the range is set to a range of 90 degrees from the forward direction of the vehicle to the left direction (indicated by hatching in the drawing). Similarly, when the line-of-sight direction is diagonally right with respect to the front direction of the vehicle, the range is set to 90 degrees from the front direction of the vehicle to the right direction.

  In the moving body detection process shown in FIG. 12, the traveling track management device 4 determines whether an attention area is set when Start = 1 (S501: YES) (S502: NO). When the attention area is set as described above (S502: YES), the mobile body is detected from the peripheral sensor information (S503), and the number detected in the attention area is set as Sensor = M (S504). Such setting of the number of vehicles is performed on the condition that it is determined whether or not the detected moving body is a car based on the surrounding sensor information and is determined to be a car. In this case, since the number of detected vehicles is 0, Sensor = 0 is set.

  In the moving object notification process shown in FIG. 10, the locator device 3 determines whether the attention area has been set when Start = 1 (S301: YES) (S302: NO). When the attention area is set as described above (S302: YES), a voice notification for Sensor = M is executed (S303). In this case, since Sensor = 0, as shown in FIG. 3B, a voice is uttered from the speaker 23 as “no moving object is detected”.

  Next, the locator device 3 determines whether Driver = Sensor (S304). That is, it is determined whether the content of the driver's speech matches the content detected by the driver. In this case, Driver = Sensor is not satisfied (S304: NO), that is, the driver recognizes the car, but the car is not detected in the attention area, so the Sensor is updated in the attention area. (S305: NO).

  When the dangerous vehicle advances at the same time as the host vehicle advances, the dangerous vehicle comes to be located in the attention area as shown in FIG. 3C. Then, the traveling track management device 4 detects the moving body in the moving body detection process of FIG. 12 (S503), and sets the number M of detected mobile bodies as 1 (S504).

  Since the locator device 3 is updated to Sensor = 1 in the moving body notification process of FIG. 10 (S305: YES), the locator device 3 executes a voice notification for Sensor = 1 (S306). That is, as shown in FIG. 3C, the speaker 23 utters by voice like “one moving body has been detected”. Next, it is confirmed that Driver = Sensor (S304: YES), that is, after confirming that the driver's utterance content matches the detected content of the locator device 3, by setting Start = 0 (S307), The moving object confirmation operation is terminated.

With the above operation, the driver can grasp that the automatic driving system 2 is operating normally, can avoid the brake, and can continue the automatic driving with peace of mind.
On the other hand, the locator device 3 continues to notify the update contents when the update contents do not match (S304: NO) in the moving body notification process of FIG. 10 (S306), as shown in FIGS. 4A to 4D. Thus, for example, when a dangerous vehicle cannot be detected behind a building and there is no notification of detection of a moving object from the traveling track management device 43, the driver brakes to avoid danger spontaneously at the timing when the driver feels dangerous. It comes to multiply. In such a case, the driver ends the moving body checking operation by saying "Please end detection".

  In the voice recognition process of FIG. 8, the locator device 3 sets Start = 0 (S108) and ends the movement check operation when the voice recognition result is the cancellation of the moving body check (S107: YES). “Detection”, “recognition”, “confirmation”, “discovery”, etc. are also determined as synonyms for “detection”. Also, “Please stop”, “End”, “Stop”, etc. are also synonymous with “Please end”.

On the other hand, as shown in FIG. 5A, when the attention area is set and one vehicle already exists in the attention area, the driver says, “Do you detect two cars?”. In this case, since one vehicle located in the area of interest is detected, as shown in FIG. 5B, the speaker 23 utters by voice as “One moving body has been detected”. As a result, although the driver recognizes two cars, the automatic driving system 2 can detect only one car, and thus has not yet detected one car located far away. I can understand that.
Then, as shown in FIG. 5C, in a state where two cars are detected in the attention area, “two moving bodies have been detected” are uttered.

  Next, as shown in FIGS. 6A to 6C and FIGS. 7A to 7c, an example will be described in which, for example, a motorcycle that is a dangerous vehicle travels in the same direction. When the driver recognizes that there is a motorcycle behind the front vehicle traveling in front of the host vehicle as shown in FIG. 6A during automatic driving, while viewing the motorcycle, "Is it detected?" In this case, since the traveling track management device 4 does not detect the motorcycle, the locator device 3 utters from the speaker 23 as “No moving object detected” as shown in FIG. 6B. The locator device 3 grasps that the driver's remark content is different from the content detected by the driver, waits for the detection content to be updated in the area of interest, and immediately after the detection content is updated, immediately after FIG. As shown in the drawing, the update content is uttered from the speaker 23 such as “One mobile unit has been detected” by voice. It should be noted that “motorcycle”, “single vehicle”, “two-wheeled vehicle” and the like are also synonymous with “motorcycle”.

  On the other hand, as shown in FIG. 7C, when the traveling track management device 4 cannot detect the motorcycle, the traveling track management device 4 does not notify the detection of the moving body, so the driver avoids the risk spontaneously at the timing when the driver feels danger. Therefore, it is possible to cancel the automatic driving and switch to the driver's own driving.

According to such an embodiment, the following effects can be produced.
The locator device 3 voice-inputs a moving body confirmation instruction indicating the situation recognized by the driver, so that the moving body recognized by the traveling track management device 4 in the attention area within the sensing range is voiced to the driver. Since the notification is made, the driver can confirm the presence of the moving body detected by the automatic driving system 2 and can continue the automatic driving with peace of mind. In this case, even if the driver reaches an area where he / she feels danger to the dangerous vehicle, if the traveling track management device 4 has not detected the target dangerous vehicle, the driver will take the risk instantly. It is possible to avoid danger by releasing the automatic driving and to appropriately avoid voluntary danger avoidance.

Since the traveling track management device 4 sets the attention area based on the driver's line-of-sight direction, the attention area can be reliably set without requiring any special operation by the driver.
Since the type and number of dangerous vehicles are included in the moving body confirmation instruction indicating the situation recognized by the driver, it is surely confirmed whether the traveling track management device 4 has detected the dangerous vehicles including the type and number of vehicles. can do.

(Other embodiments)
The present invention is not limited to the above-described embodiment, but may be modified or expanded as follows, each modified example may be combined with the above-described embodiment, or each modified example may be combined.
Instead of setting the attention area in the driver's line-of-sight direction, the moving body confirmation instruction may include the attention direction. For example, if the dangerous vehicle is located on the left front side, say “Are you detecting one car on the left front?” And give the moving body confirmation instruction, and set the attention area in the direction corresponding to “Left front”. Notice.

  The attention area is set to a range of 90 degrees from the front to the left or right in the sensing range, but is not limited to the range of 90 degrees, and the range from the front to the line of sight in the sensing range Set it, predict the position of the moving body based on the map, set it to a range including that position, or set it to the direction of the vehicle approaching the own vehicle when joining on the automobile exclusive road Also good.

When the automatic driving system is configured as a system in which the driver is not completely involved, that is, when there is no driver, the attention area may be set in the line-of-sight direction of the user on board.
You may make it give the function of the attention area setting part 24a and the mobile body detection part 24b which the traveling track management apparatus 4 has to the locator apparatus 3.

  Although the present disclosure has been described with reference to the embodiments, it is understood that the present disclosure is not limited to the embodiments and structures. The present disclosure includes various modifications and modifications within the equivalent range. In addition, various combinations and forms, as well as other combinations and forms including only one element, more or less, are within the scope and spirit of the present disclosure.

In the drawings, 2 is an automatic driving system, 3 is a locator device (driving support device), 8a is a voice recognition unit, 8b is a gaze direction determination unit, 8c is a moving body notification unit, 24a is an attention area setting unit, and 24b is a moving body. It is a detection unit.

Claims (6)

A driving support device that notifies the user of the presence of a moving body recognized by the automatic driving system (2),
A voice recognition unit (8a) for voice recognition of a user's statement;
An attention area setting unit that sets an attention area to which a user pays attention within a sensing range of the automatic driving system when the voice recognition result by the voice recognition unit is a moving object confirmation instruction that instructs to confirm a moving object (24a)
A moving body detection unit (24b) for detecting a moving body located in the area of interest;
When the mobile object detection unit detects a mobile object, a mobile object notification unit (8c) that notifies the user of the presence of the mobile object;
A driving assistance device comprising: A line-of-sight direction determination unit (8b) for determining the line-of-sight direction of the user;
The driving assistance device according to claim 1, wherein the attention area setting unit sets the attention area based on a user's gaze direction determined by the gaze direction determination unit.   The driving assistance device according to claim 1, wherein the attention area setting unit sets the attention area based on an attention direction included in the moving body confirmation instruction.   The driving support apparatus according to any one of claims 1 to 3, wherein the moving body confirmation instruction includes a type of the moving body.   The driving support apparatus according to claim 4, wherein the moving body confirmation instruction includes the number of moving bodies. A driving support program for notifying the user of the presence of a moving body recognized by the automatic driving system,
A procedure for recognizing user speech,
When the voice recognition result is a moving body confirmation instruction that instructs to confirm the moving body, a procedure for setting an area of interest to which the user pays attention within the sensing range of the automatic driving system;
Detecting a moving body located in the area of interest;
If a mobile object is detected, a procedure for notifying the user of the presence of the mobile object,
A driving assistance program to execute.

Images