JP2007122155A - Branch route entry estimation device - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To nearly certainly estimate that a vehicle enters a branch route before the vehicle enters the branch route. <P>SOLUTION: This branch route entry estimation device has a gaze detection means detecting a gaze of a driver to a branch route direction before the branch route when the vehicle travels on a road wherein the branch route is present ahead, and has an estimation means 2 estimating that the vehicle enters the branch route on the basis of a gaze frequency, or a cumulative time or the like of the gazing that is a detection result detected by the gaze detection means 6. <P>COPYRIGHT: (C)2007,JPO&INPIT

Description

  The present invention relates to a branch path approach estimation apparatus suitable for incorporation in a cruise control system that automatically controls the speed of a vehicle.

In a cruise control system that automatically controls the speed of a vehicle, the approach of the vehicle to the branch road is estimated by detecting the driving lane and the branch point reflector using the information output from the car navigation system. Thus, a configuration for automatically controlling the vehicle speed (deceleration control) has been considered (see, for example, Patent Document 1).
Japanese Patent Application No. 2004-319441

  In the case of the configuration described in Patent Document 1, since the current location information of the vehicle output from the car navigation device includes an error, the vehicle is not branched after entering the branch road. Could not be estimated to have entered. For this reason, there has been a problem that the vehicle cannot be decelerated in time when the branch road is sharply curved immediately after branching.

  Therefore, an object of the present invention is to provide a branch path approach estimation device that can estimate that a vehicle enters a branch path before the vehicle enters the branch path.

  The branch path approach estimation device according to the present invention includes gaze detection means for detecting a driver's gaze in the direction of the branch path before the branch path when the vehicle is traveling on a road having a branch path ahead. In addition to the above, the present invention is characterized in that it includes estimation means for estimating that the vehicle enters a branch path based on the number of gazes, the cumulative gaze time, and the like, which are detection results detected by the gaze detection means.

  According to the above configuration, the vehicle enters the branch road because it is estimated to enter the branch road based on the number of gazes, the cumulative stop time, and the like, which are detection results detected by the gaze detection means. It is possible to estimate that the vehicle will enter the branch road before doing so.

  Further, in the case of the above configuration, the gaze detection unit is configured to detect the driver's gaze when the driver's line of sight, face orientation, or the like is within the gaze range of the branch road calculated in advance within a specified distance in front. It is preferable that it is comprised so that it may detect.

  Further, the gaze detection means is configured to detect gaze in the direction of the driver's branch path and gaze in the direction opposite to the driver's branch path direction, and the estimation means is configured to gaze in both directions. It is even more preferable that the configuration is such that it is estimated that the vehicle enters the branch path based on the detection result.

  Furthermore, the gaze range of the branch road is a view angle obtained by subtracting the maximum view angle from the vehicle travel direction to the main line prescribed far point from the maximum view angle from the vehicle travel direction to the branch route prescribed far point. Is a good configuration.

  Hereinafter, an embodiment in which the present invention is applied to a cruise control system will be described with reference to the drawings. First, FIG. 1 is a block diagram showing an electrical configuration of the cruise control system of the present embodiment. The cruise control system 1 includes an inter-vehicle control ECU (electronic control device for inter-vehicle control) 2, an engine ECU (electronic control device for engine control) 3, a brake ECU (electronic control device for brake control) 4, and a navigation ECU (navigation). A control device 5 and a gaze point detection ECU (gaze point detection electronic control device) 6 are mainly configured. Each ECU2-6 is comprised so that communication is possible via in-vehicle LAN7.

  The inter-vehicle control ECU 2 is an electronic circuit mainly composed of a microcomputer, and includes a vehicle speed signal, a steering angle signal, a yaw rate signal, a target inter-vehicle time signal, wiper switch information, a control state signal for idle control and brake control, not shown. Information indicating the state of the winker is received from the engine ECU 3. Further, the inter-vehicle control ECU 2 receives distance measurement data from a laser sensor 8 to be described later, and further receives road information from a navigation ECU 5 to be described later. Then, the inter-vehicle control ECU 2 performs inter-vehicle control calculation, calculation of speed for driving the vehicle stably at each node, vehicle speed control, and the like based on the received data.

  Further, the inter-vehicle control ECU 2 receives detection signals from the cruise control switch 9, the target inter-vehicle setting switch 10, and the accelerator switch. Among these, the cruise control switch 9 includes a control start switch, a control end switch, an accelerator switch, a coast switch, and the like. The control start switch is a switch for making cruise control ready to start, and the cruise control can be started by turning on the control start switch while the target inter-vehicle setting switch 10 is ON. In this cruise control, the inter-vehicle control and the constant speed traveling control are selectively executed under predetermined conditions. The accelerator switch is a switch for gradually increasing the stored set vehicle speed by pressing the accelerator switch, and the coast switch gradually decreases the stored set vehicle speed by pressing the accelerator switch. It is a switch for. Further, the inter-vehicle distance between the host vehicle and the preceding vehicle can be set via the target inter-vehicle setting switch 10. The inter-vehicle distance can be set in stages according to the driver's preference. The inter-vehicle control ECU 2 has a function of estimating a traveling lane and a function of estimating means for estimating entry into a branch road.

  The laser sensor 8 is an electronic circuit mainly composed of a scanning distance measuring device using a laser beam and a microcomputer. The scanning distance measuring device uses the scanning distance measuring device to measure the distance and angle between the vehicle ahead and a stop (for example, a roadside object). Detect relative speed and so on. Then, based on the vehicle speed signal received from the inter-vehicle distance control ECU 2, the curve curvature radius (estimated R), etc., the own lane probability of the front vehicle is calculated, and the front vehicle information such as the relative speed with respect to the front vehicle is calculated. Send to. Further, stop object information such as the position of the stop object and the distance from the estimated traveling path of the own vehicle (the course of the own vehicle) is transmitted to the inter-vehicle distance control ECU 2. Further, a diagnosis signal (diagnosis information) of the laser sensor 3 itself is also transmitted to the inter-vehicle control ECU 2. For example, the scanning cycle of the laser sensor 3 is set to 100 msec, and ranging data is output every 100 msec.

  The engine ECU 3 is an electronic circuit mainly composed of a microcomputer, and includes a throttle opening sensor, a vehicle speed sensor 11 as speed detecting means for detecting vehicle speed, a brake switch for detecting whether or not the brake is depressed, and other It receives wiper switch information and tail switch information received via a detection signal from sensors and switches, or a known communication line such as in-vehicle LAN 7. Further, a steering angle signal and a yaw rate signal from the brake ECU 4, or a target acceleration signal, a fuel cut request signal, an OD cut request signal, a third speed shift down request signal, an alarm request signal, a diagnosis signal, and display data from the inter-vehicle control ECU 2 A signal is received.

  Further, the engine ECU 3 transmits necessary display information to a display device such as an LCD provided in the meter cluster via the in-vehicle LAN 7 for display, or displays the vehicle speed signal, steering angle signal, yaw rate signal, target An inter-vehicle time signal, a wiper switch information signal, an idle control and a control state signal for brake control are transmitted to the inter-vehicle control ECU 2. And engine ECU3 has the function to control acceleration / deceleration so that it may become a set vehicle speed with brake ECU4.

  The brake ECU 4 is an electronic circuit mainly composed of a microcomputer. The brake ECU 4 obtains the steering angle and the yaw rate from the steering sensor 12 that detects the steering angle of the vehicle and the yaw rate sensor 13 that detects the yaw rate. It transmits to the inter-vehicle control ECU 2 via the engine ECU 3 and controls a brake actuator for duty-controlling opening / closing of the pressure increase control valve / pressure reduction control valve provided in the brake hydraulic circuit in order to control the braking force. . Further, the brake ECU 4 sounds an alarm buzzer in response to an alarm request signal from the inter-vehicle control ECU 2 via the engine ECU 3.

  The navigation ECU 5 is mainly composed of a microcomputer and an HDD that records a map database, and is connected to a GPS antenna 14 to calculate the current position (current location) of the host vehicle and to drive the host vehicle. It has a function of outputting information related to the travel path to the inter-vehicle distance control ECU 2 at regular intervals (in this embodiment, approximately every 1 second).

  The map database stores information on roads (road information) such as link information, node information, segment information, and link connection information. The link information includes a link ID, which is a unique number for identifying the link, a link class for identifying an expressway, a toll road, a general road, or an attachment road (branch road), and the number of road lanes. There is information about the link itself, such as the lane width (lane width), the start and end coordinates of the link, and the link length indicating the length of the link. The node information includes information such as a node ID that is a unique number of nodes connecting the links, node latitude, node longitude, right / left turn prohibition at intersections, presence / absence of traffic lights, and whether or not a branch point exists. Further, the segment information includes information such as segment ID, start point (node) latitude (degrees), start point (node) longitude (degrees), segment direction (dir), and segment length (internode distance). Note that the values of the starting point latitude and starting point longitude include decimal places and are converted from “minutes” and “seconds” to “degrees”. In addition, in the inter-link connection information, for example, data indicating whether or not traffic is permitted for reasons such as one-way traffic is set. Even in the case of the same link, for example, in the case of one-way traffic, it is possible to pass from one link but not from another link. Therefore, whether or not traffic is allowed is determined depending on the connection mode between the links.

  The navigation ECU 5 has a function as means for detecting the number of lanes and a function of detecting (specifying) the current position of the vehicle. The navigation ECU 5 has substantially the same configuration as a car navigation device having a known configuration, and includes a signal from the GPS antenna 14, a detection signal from the vehicle speed sensor 11, a detection signal from the steering sensor 12, and In response to the detection signal from the yaw rate sensor 13, various car navigation controls (map display, vehicle current position detection and map matching, optimum route search to the destination, route guidance for the set route, etc.) Control function).

  The gazing point detection ECU 6 includes an image signal from the camera 15 that captures the direction of the driver's face, the movement of the eyeball, and the like, navigation information from the navigation ECU 5 (current position information of the vehicle, road information of the road on which the vehicle is traveling, etc.) In response to this, it has a function of detecting the driver's gaze in the direction of the branch road before the branch road. Then, the gazing point detection ECU 6 transmits information such as the number of gazing times and the accumulated stop time, which are the detected detection results, to the inter-vehicle distance control ECU 2. In the case of this configuration, the gazing point detection ECU 6 has a function as gazing detection means. The gazing point detection ECU 6 and the inter-vehicle distance control ECU 2 constitute a branch path approach estimation device. The camera 15 is disposed in an appropriate part of the instrument panel of the vehicle (part where the driver's face and eyes are easily photographed).

  Next, the contents of the operation of the above-described configuration, in particular, the control for estimating the approach to the branch road and the vehicle speed control for the branch road in the control of the cruise control system 1 will be described with reference to FIGS. This will be described with reference to FIGS. 4, 5, 6, and 7. FIG. The flowchart of FIG. 4 shows the control contents of the main routine of each control described above. The flowchart of FIG. 5 shows the control contents of the control (subroutine) for estimating the approach to the branch path. 4 and FIG. 5 is configured to be executed by appropriately sharing the vehicle distance control ECU 2 and the gazing point detection ECU 6 (including other ECUs) as appropriate.

  First, in step S10 of FIG. 4, it is determined whether or not the cruise control switch 9 is turned on. If it is not turned on, the process proceeds to “NO” and nothing is done. On the other hand, if it is turned on, the process proceeds to “YES” and proceeds to step S20, where there is a branch road ahead of the vehicle based on the current position information of the vehicle and road information around the road on which the vehicle is traveling. Determine whether or not. If there is no branch path, the process proceeds to “NO”, returns to step S10, and does nothing.

  On the other hand, if there is a branch path, the process proceeds to “YES”, the process proceeds to step S30, and a process (subroutine) for estimating entry into the branch path is executed. This process will be described with reference to the flowchart of FIG.

  First, in step S100 of FIG. 5, estimation processing for estimating entry into a branch path according to the conventional technique (configuration described in Patent Document 1) is executed. In this estimation process, when the approach to the branch road is estimated, in step S110, the process proceeds to “YES”, the process proceeds to step S120, and it is estimated that the branch road is entered. Turn on the flag for.

  On the other hand, when the approach to the branch road is not estimated in the estimation process in step S100, the process proceeds to “NO” in step S110 and proceeds to step S130. In this step S130, the vehicle is traveling on the branch side end lane, that is, the end lane in the direction of the branch road (the left lane if the branch road direction is, for example, left, and the right lane if the branch road direction is, for example, right). For example, it is determined whether or not the winker in the branch direction has been turned on during the period from the specified distance before the branch road (for example, 100 m) to the branch point. In this determination, detection of whether or not the vehicle is traveling in the branch side end lane may be performed using the lane detection method (means) described in Patent Document 1.

  In step S130, if the turn-direction blinker is turned on, the process proceeds to “YES”, and the process proceeds to step S120, where it is estimated that the vehicle enters the branch path. On the other hand, if the turn signal in the branch direction is not turned on, the process proceeds to “NO”, the process proceeds to step S140, and it is determined whether or not the vehicle is located in the branch path entry determination area based on the degree of gaze. Here, the branch path entry determination area is an area from the specified distance before the branch path (for example, 200 m) to passing through the branch point.

  In step S140, if the vehicle is not in the area, the process proceeds to “NO”, and the process proceeds to step S180, where it is estimated that the vehicle has not entered the branch road. That is, for example, the flag for estimating the branch road is turned off. .

  On the other hand, if the vehicle is in the above-mentioned area in step S140, the process proceeds to “YES”, the process proceeds to step S150, and the gaze detection process for the branch road direction gaze range is executed. In this case, specifically, the number of times and the time when the driver gazes at the branch road direction from the specified distance before the branch road (for example, 200 m) to passing through the branch point, and the opposite direction of the branch road (branch road) The number of times and the time when the driver gazes in the direction opposite to the direction) are measured.

  Here, the number of times of branch road direction gaze is the number of times of gaze continuously for a specified time (for example, 0.2 seconds). Further, the branch direction gazing time is a total time (cumulative time) of the gazing time when the gazing is continuously performed for a specified time (for example, 0.2 seconds) or longer.

  As shown in FIG. 3, the bifurcation direction gaze is a gaze (the direction of the line of sight or face is directed) in an area C surrounded by the horizontal direction gaze range A and the vertical course gaze range B. To do).

  Here, as shown in FIG. 2, the horizontal branching direction gazing range A is a branching road viewing angle (ie, from the own vehicle traveling direction P1 to the branching center P2) at a prescribed forward distance (for example, 50 m) D1 from the own vehicle. The maximum viewing angle K2 from the angle K1 to the branch path specified far point (for example, 500 m from the own vehicle) P3. In other words, the viewing angle obtained by subtracting the forward specified distance branch path viewing angle K1 from the branch path specified far point maximum viewing angle K2 is the horizontal branch path direction gaze range A.

  However, when there is no branch point at a prescribed forward distance from the host vehicle, the branch road viewing angle K1 is set to a prescribed minimum angle (for example, 5 degrees). The specified minimum angle is also used when the branch path viewing angle is equal to or less than the specified minimum angle. Furthermore, when the main line of the road curves to the branch road side, the maximum viewing angle up to the main line specified far point is not within the branch road direction gazing range.

  Further, as shown in FIG. 3, the vertical course watching range B is obtained by shifting the main line far point P4 from the front / rear inclination of the vehicle, the current position (current position) of the car navigation information, and the gradient ahead of the traveling path, It is a range within a specified angle (for example, ± 10 degrees) K3, K4. However, the range that overlaps the room mirror and bonnet is excluded.

  On the other hand, gazing in the opposite direction of the branch path is gazing within a range surrounded by a horizontal direction and a vertical direction described below. Here, the horizontal direction is a range opposite to the branch path from the vehicle traveling direction P1 to a specified minimum angle (for example, 10 degrees) or more to a specified angle (for example, 90 degrees). The vertical direction is set to the same range as the vertical direction gaze range B of the branch direction gazing described above.

  Then, the process proceeds to step S160 in FIG. 5, and whether or not the difference in the number of gazes is, for example, 3 times or more, that is, the number of gazes in the branch path direction is more than the number of gazes in the direction opposite to the branch path. It is determined whether or not the specified number of times is, for example, three or more. Here, if the number of gazes in the direction of the branch path is three or more times, it can be estimated that the vehicle enters the branch path. Therefore, the process proceeds to “YES” in step S160, proceeds to step S120, and enters the branch path. Estimate the approach.

  On the other hand, if the number of gazes in the direction of the branch path is not more than 3 times, the process proceeds to “NO” in step S160 and proceeds to step S170 to determine whether or not the gaze time difference is, for example, 1 second or more. It is determined whether or not the gaze time in the road direction is longer than the gaze time in the opposite direction of the branch road by a specified time, for example, 1 second or more. Here, if the gaze time in the direction of the branch path is longer than 1 second, it can be estimated that the vehicle enters the branch path. Therefore, the process proceeds to “YES” in step S170, proceeds to step S120, and enters the branch path. Estimated to enter.

  On the other hand, if the gaze time in the direction of the branch path is not longer than 1 second, the process proceeds to “NO” in step S170 and proceeds to step S180 to estimate that there is no entry to the branch path (estimation of approach to the branch path). Turn off the flag for). The numerical values such as the various specified distances, the specified number of times, and the specified time described above are examples, and may be set as appropriate based on experiments and the like. The numerical values may be configured to be set by a user (driver or the like), or may be configured to be changeable by a learning function.

  Thereafter, the process proceeds to step S40 in FIG. 4 to determine whether or not the approach to the branch path has been estimated, that is, whether or not the branch path approach estimation flag is on. Here, when branch road approach is not estimated, it progresses to "NO" in step S40, returns to step S10, and does nothing.

  On the other hand, when the branch road approach is estimated (the branch road approach estimation flag is on), the process proceeds to “YES” in step S40 and proceeds to step S50, and the vehicle speed control for the branch road is performed. Make an announcement to that effect. In this case, for example, a message “Starting vehicle speed control to go out to the ramp way (or service area)” is output (announced) from the speaker.

  And it progresses to step S60 and it is judged (detected) whether there was a rejection response from a driver | operator. In this case, examples of the rejection response include turning on (or increasing) the accelerator, a voice response “does not need to be done”, and turning on the cancel switch. Here, if there is a rejection response from the driver, the process proceeds to “YES” in step S60, returns to step S10, and does nothing.

  On the other hand, if there is no rejection response from the driver in step S60, the process proceeds to “NO”, and the process proceeds to step S70 to execute the vehicle speed control for the branch road. In this case, the vehicle speed is controlled according to the road shape (curve degree, etc.) of the branch road (rampway, service area, etc.). In the present embodiment, it is preferable that the vehicle speed control device described in Japanese Patent Application No. 2004-175148 or Patent Document 1 is used for control.

  According to the present embodiment having such a configuration, since it is configured to estimate that the vehicle enters the branch road based on the number of times of gaze in the branch road direction, the accumulated time of the gaze, etc., the vehicle enters the branch road. It is possible to almost certainly estimate that the vehicle will enter the branch road before As a result, even when the branch road is sharply curved immediately after branching, the vehicle can be sufficiently decelerated (deceleration is sufficient in time) by the vehicle speed control of the cruise control system.

  Here, in the branch path approach estimation control with the configuration described in Patent Document 1, a case where the estimation cannot be accurately performed will be described with reference to FIG. As shown in FIG. 6, the case where the leftmost lane of the three lanes of the road becomes a branch road as it is is a case where estimation cannot be accurately performed depending on the above-mentioned Patent Document 1. In this case, if you continue to drive in the left lane, you will enter the branch road, but you have to make a margin for the maximum measurement error of the current location accuracy (GPS accuracy) of the car navigation device. Therefore, it is not possible to estimate the approach to the branch road unless it is about 10 to several tens of meters after the branch.

  However, if the reflector at the branching point can be detected and the vehicle travels to the left of the reflector, it is possible to estimate the approach to the branch at that time, but as shown in FIG. When there is a vehicle on the right side in two lanes and the reflector at the branch point is blocked (including when the reflector is dirty or damaged), the reflector cannot be detected, so it enters the branch road. Cannot be estimated.

  In each of the above cases, according to the present embodiment, since it is configured to estimate entering the branch road based on the number of times of gaze in the direction of the driver's branch road, the cumulative time of gaze, etc., the branch road The approach to can be estimated almost certainly.

  In addition, as shown in FIG. 7, when the main line is curved in the same direction as the branch road, even if the driver is gazing at the main line, there is a risk of erroneously estimating that the main road is approaching. . On the other hand, according to the present embodiment, since the range of the maximum viewing angle K1 up to the main line prescribed far point P2 is removed from the branch direction gazing range A, only the direction in which the branch is located is watched. Since the approach to the branch road can be estimated based on the degree of the road, it is possible to increase the estimation accuracy of the approach to the branch road.

  On the other hand, as a method of estimating the main line far point, in the case of a configuration in which the front monitoring camera is mounted on the vehicle, the image of the front monitoring camera is analyzed to detect the vanishing point of the main line, and the main line far point is detected. There is also a method. Examples of image analysis methods include edge detection, thinning, line connection processing, line segment matching, Hough transform, and the like, and these methods may be used as appropriate.

The block diagram of the cruise control system which shows one Example of this invention The figure explaining the horizontal branch road direction gaze range Diagram explaining branch direction gazing range Flow chart (Part 1) Flow chart (Part 2) Figure 2 equivalent when the shape of the branching path is different Fig. 2 equivalent diagram when main line shape is different

Explanation of symbols

  In the drawings, 1 is a cruise control system, 2 is an inter-vehicle control ECU (estimating means), 3 is an engine ECU, 4 is a brake ECU, 5 is a navigation ECU, 6 is a gaze point detection ECU (gaze detection means), and 9 is a cruise control system. The switch 10 is a target inter-vehicle setting switch, 11 is a vehicle speed sensor, 14 is a GPS antenna, and 15 is a camera.

Claims (4)

Gaze detection means for detecting the driver's gaze in the direction of the branch road before the branch road when the vehicle is traveling on a road having a branch road ahead;
A branch path approach estimation device comprising: an estimation means for estimating that the vehicle enters a branch path based on the number of times of gaze, the accumulated time of gaze, and the like as detection results detected by the gaze detection means.   The gaze detection means is configured to detect a driver's gaze when a driver's line of sight, face orientation, or the like is within a gaze range of a branch road calculated in advance within a specified distance in front. The branch path approach estimation apparatus according to claim 1, wherein The gaze detection means is configured to detect gaze in the driver's branch path direction and gaze in the direction opposite to the driver's branch path direction,
3. The branch path approach estimation apparatus according to claim 1, wherein the estimation unit is configured to estimate that the vehicle enters a branch path based on detection results of gaze in both directions. The gazing range of the branch road is a viewing angle obtained by subtracting the maximum viewing angle from the traveling direction of the vehicle to the main line specified far point from the maximum viewing angle from the moving direction of the vehicle to the branch path specified far point. The branch path approach estimation apparatus according to claim 2.

Images