JP2019016278A - Vehicle driving support apparatus - Google Patents

Abstract

To be capable of estimating a type of whether a traveling path of a vehicle is an ordinary road or an expressway with high accuracy without depending on a car navigation device.SOLUTION: A vehicle driving support apparatus comprises: acquiring an object for estimating a road type, such as a pedestrian, a traffic light, a lane width, on the basis of image information of a running environment imaged by an on-vehicle camera unit 21 mounted on an own vehicle Mv, and obtaining the number of counts per unit time or a ratio per unit distance of the acquired objects so as to calculate a feature element indicating a feature of a road type (S11); setting an evaluation point for evaluating whether it is an ordinary road or an expressway by comparing with a threshold value for each calculated feature element (S12); calculating total evaluation points respectively by totalizing the set evaluation points of the ordinary road and the expressway (S14); and estimating whether a road on which the own vehicle Mv is traveling is the ordinary road or the expressway by comparing the total evaluation point of the ordinary road with the total evaluation point of the expressway.SELECTED DRAWING: Figure 4

Description

  The present invention relates to a vehicle travel support apparatus that estimates a road type of a traveling path of a host vehicle based on image information of a traveling environment ahead of the host vehicle captured by an imaging unit in automatic driving.

  Conventionally, in order to reduce the driver's driving load while driving, ACC (Adaptive Cruise Control), automatic brake control, Lane Departure Prevention (LDP) control, Lane Keep Assist (Lane Keep Assist) Control, lane change control, automatic start control, etc., using information obtained from the camera mounted on the vehicle, etc., part or all of the driving operation (start, acceleration, steering, braking, stop) of the vehicle An automatic driving system that is automatically performed by an electronic control system has been developed.

  And the automatic driving by this automatic driving system is a mode (highway mode) that is assumed to be used on an automobile-only road (in many cases, it is a highway and is hereinafter referred to as “highway”), There is a mode (general road mode) that is assumed to be used not only on expressways but also on general roads. As the automatic driving selected in the highway mode, there are a fully automatic driving in which the driver is not involved in the driving operation at all, or a conditional automatic driving in which all the driving is performed automatically but the driver operates in an emergency. Further, the general road mode includes partial automatic driving in which the driver's operation is partially automated under limited conditions, and basically driving assistance control in which the driver drives but supports the partial operation.

  For example, lane departure prevention control, lane keeping control, lane change control, and automatic start control are included in the highway mode, and preceding vehicle tracking control (ACC) and automatic brake control are included in the general road mode.

  Therefore, when the traveling path on which the vehicle travels is switched from the highway to the general road, it is necessary to switch the automatic driving from the highway mode to the general road mode. Similarly, when the traveling route is switched from a general road to a highway, it is necessary to switch the automatic driving from the general road mode to the highway mode.

  However, it is complicated for the driver to switch the automatic driving mode each time the traveling path is switched, and the switching operation may be forgotten. In particular, when the traveling route is switched from the highway to the general road, if the automatic driving mode is forgotten to be switched, the highway mode is executed on the general road where many pedestrians are coming and going.

  As a technique for determining whether the traveling path of a vehicle is a general road from an expressway, for example, as disclosed in Patent Document 1 (Japanese Patent Laid-Open No. 2010-49382), the determination is based on information from a car navigation device. There are many cases.

JP 2010-49382 A

  However, the technology for determining whether the traveling path of the host vehicle is a general road or a highway based on information from the car navigation device cannot be applied to a vehicle not equipped with a car navigation device, and is versatile. There is a missing problem. Further, in order to correctly switch the automatic driving mode based on the information from the car navigation device, it is necessary to always update to the latest road map, and there is an inconvenience that maintenance costs increase.

  Furthermore, in a system that automatically switches the automatic driving mode based on information from the car navigation device, it is necessary to construct a system that connects the map information and the automatic driving system via an in-vehicle communication line.

  Therefore, it is difficult to construct using a later-described navigation device, and there is a problem of lack of versatility because a genuine navigation device installed from the beginning is essential.

  In view of the above circumstances, the present invention can estimate the type of road on which the host vehicle travels with high accuracy without relying on a car navigation device in automatic driving, and can obtain high versatility. An object of the present invention is to provide a travel support device.

  The present invention has road type identification means for identifying a road type on which the host vehicle travels, and a plurality of automatic driving modes corresponding to the road type, and corresponds to the road type estimated by the road type identification means. In a vehicle driving support apparatus having driving support control means for setting an automatic driving mode, the vehicle driving support apparatus has imaging means for imaging a traveling environment ahead of the host vehicle, and the road type identification means is the imaging means picked up by the imaging means A road type estimation target acquisition unit that acquires a road type estimation target based on image information of a driving environment, and a unit time or unit distance of each road type estimation target acquired by the road type estimation target acquisition unit Per physical quantity is set as a feature element representing the feature of each road type, and each feature element is compared with a threshold value set for each feature element. Road type evaluation means for evaluating the road type, road type total evaluation means for totaling evaluation of the road type for each feature element evaluated by the road type evaluation means to obtain a total evaluation of the road type, Road type estimation means for comparing the total evaluation of the road types aggregated for each road type by the road type total evaluation means and estimating the road type, and the driving support control means includes the road type estimation means The automatic driving mode corresponding to the road type estimated in step S3 is executed.

  According to the present invention, since the road type is estimated based on the image information of the driving environment imaged by the imaging means, the type of the road on which the host vehicle runs without depending on the car navigation device in automatic driving. Can be estimated with high accuracy, and high versatility can be obtained.

Schematic configuration diagram of the driving support device Schematic bird's-eye view showing the driving state of the vehicle by automatic driving Flow chart showing road type estimation routine Flow chart showing total evaluation point calculation processing subroutine Flow chart showing automatic operation mode setting routine Explanatory drawing of the image of the general road imaged by the in-vehicle camera unit Explanatory diagram of highway image taken with in-vehicle camera unit Explanatory drawing of the evaluation table showing evaluation points for general roads and expressways for each feature element (Part 1) Explanatory drawing of the evaluation table showing evaluation points for general roads and expressways for each feature element (Part 2)

  Hereinafter, an embodiment of the present invention will be described with reference to the drawings. The driving support device 1 shown in FIG. 1 is mounted on the host vehicle Mv shown in FIG. The driving support apparatus 1 includes a driving support control unit 11 as driving support control means, an engine control unit (hereinafter referred to as “E / G_ECU”) 12, a power steering control unit (hereinafter referred to as “PS_ECU”) 13, a brake. Each control unit such as a control unit (hereinafter referred to as “BK_ECU”) 14 and a road type identification unit 16 as road type identification means are provided. Further, the control units 11 to 14 are connected so as to be capable of bidirectional communication through an in-vehicle communication line 15 such as a CAN (Controller Area Network). Each of the units 11 to 14 includes a microcomputer having a CPU, a ROM, a RAM, and the like, and a control program for realizing an operation set for each system is stored in the ROM.

  In addition to the road type identification unit 16 described above, an in-vehicle camera unit 21, an automatic driving switch 22, a driving state detection sensor 23, and the like as an imaging unit are connected to the input side of the driving support control unit 11, and the output side Is connected to a notification means 26 for notifying the driver of switching and cancellation of automatic driving.

  The in-vehicle camera unit 21 includes a main camera 21a, a sub camera 21b, and an image processing unit (IPU) 21c. Both cameras 21a and 21b are stereo cameras that are mounted in the cabin front part of the host vehicle Mv and image the forward traveling environment. The IPU 21c performs predetermined image processing on the driving environment images captured by both the cameras 21a and 22b, and transmits them as driving environment information to the driving support control unit 11 and the road type identification unit 16.

  The road type identification unit 16 acquires a road type estimation object (hereinafter abbreviated as “object”) for each frame based on the travel environment information acquired by the in-vehicle camera unit 21, and stores it in the storage means (HDD) 17. Store sequentially. Based on the object data stored in the storage unit 17, the road type of whether the traveling path on which the host vehicle Mv travels is a general road or an expressway is estimated.

  The automatic operation switch 22 is a composite switch for arbitrarily selecting normal operation (switch OFF) and automatic operation (switch ON) and setting the set vehicle speed during ACC operation. The automatic operation switch 22 is an instrument panel or steering handle. It is provided at a position where the driver can operate.

  The traveling state detection sensor 23 is a general term for sensors that detect the traveling state of the host vehicle Mv, and representatively includes a vehicle speed sensor that detects the host vehicle speed, a steering angle sensor that detects the steering angle, and the host vehicle. There are a yaw rate sensor that detects a yaw rate acting on Mv and a three-axis acceleration sensor that detects three-dimensional acceleration.

  The notification means 26 informs the driver of the start / interruption of automatic driving, switching of the automatic driving mode, etc. by flashing display, character display, voice, etc., using a display lamp, indicator, speaker, buzzer, etc. It is configured.

  On the other hand, a throttle actuator 31 is connected to the output side of the E / G_ECU 12. The throttle actuator 31 opens and closes a throttle valve of an electronically controlled throttle provided in the throttle body of the engine, and adjusts the intake air flow rate by opening and closing the throttle valve by a drive signal from the E / G_ECU 12. The desired engine output is generated. In the automatic operation ACC control, when a preceding vehicle is detected, the target vehicle speed that follows the preceding vehicle is set. When the preceding vehicle is not detected, the set vehicle speed is set as the target vehicle speed, and the vehicle speed control is performed. Do. In this embodiment, the engine is exemplified as the drive source. However, the drive source may be an electric motor or a hybrid (HEV) using both the engine and the electric motor.

  An electric power steering motor 32 is connected to the output side of the PS_ECU 13. The electric power steering motor 32 applies a steering torque to the steering mechanism by the rotational force of the motor. In automatic operation, the electric power steering motor 32 is controlled by a drive signal from the PS_ECU 13 so that the current driving lane travels. Lane maintenance control for maintaining the vehicle lane, lane departure prevention control for preventing lane departure, lane change control for moving the host vehicle Mv to the adjacent traveling lane, and the like are executed.

  A brake actuator 33 is connected to the output side of the BK_ECU 14. The brake actuator 33 adjusts the brake hydraulic pressure supplied to the brake wheel cylinder provided on each wheel. When the brake actuator 33 is driven by a drive signal from the BK_ECU 14, each brake wheel 33 is driven by the brake wheel cylinder. Braking force is generated and the vehicle is forcibly decelerated. The BK_ECU 14 performs automatic brake control such as automatic stop and emergency stop in ACC control of automatic driving.

  Based on the traveling environment image information in front of the host vehicle imaged by both cameras 21a and 21b and imaged by the IPU 21c and the traveling state of the host vehicle Mv detected by the traveling state detection sensor 23, the traveling support control unit 11 Automatic driving control for autonomously driving the vehicle Mv is performed.

  At that time, the automatic operation mode (general road mode or highway mode) is switched according to the road type (general road or highway) estimated by the road type identification unit 16. In other words, in the expressway mode, all functions set for automatic operation such as lane departure prevention control, lane keeping control, lane change control, automatic start control, preceding vehicle following control (ACC), automatic brake control, etc. are executed. To do. On the other hand, in the general road mode, only limited automatic driving functions such as ACC control and automatic brake control are executed.

  Specifically, the estimation of the road type in the road type identification unit 16 is executed according to the road type estimation routine shown in FIG.

  This routine is started in synchronization with the driving environment image for each frame transmitted from the IPU 21c. First, the travel environment image information is read in step S1, and the object is acquired from the travel environment image in step S2. Note that the processing in step S2 corresponds to the road type estimation target acquisition means of the present invention.

  That is, the general road image shown in FIG. 6 and the highway image shown in FIG. In the general road shown in FIG. 6, a pedestrian crossing (i), an oncoming vehicle (ii), a road sign (iii), a pedestrian group (iv) in which a plurality of pedestrians are continuous or in a lump, an intersection (v ), A single pedestrian (vi), a vehicle traffic light (vii), and the like are complex. On the other hand, there are no pedestrian crossings (i), pedestrian groups (iv), pedestrians (vi), and intersections (v) intersecting at almost right angles on highways. The vehicle traffic signal (vii) is recognized at the entrance of the tunnel, and the oncoming vehicle (ii) is recognized only in the face-to-face traffic in the provisional two lanes.

  On the other hand, as in the image of the expressway shown in FIG. 7, on the expressway, the lane width (viii), which is the distance between the left and right lane markings (white line), is continuous in the traveling direction with an interval of 3 [m] or more. However, the radius of curvature (ix) of the curved road is set more gently than that of a general road. In addition, both sides of the road are demarcated by guardrails (x, xi), and many guide signs (xii) have a special letter “P” and a notice distance (“2 km”, “500 m”, etc.). . Therefore, an object (a pedestrian, a bicycle, a traffic light, a pedestrian crossing, a character, or the like) that includes a feature element that represents a feature of a road type is acquired from the travel environment image information using a pattern matching process or the like.

  Further, the distance between the object and the host vehicle Mv is calculated using the well-known triangulation principle based on the parallax between the cameras 21a and 21b. These are stored in the storage means 17 in association with each frame. In addition, when the same object is recognized continuously in successive frames, the count number of these objects is 1.

  FIG. 8 and FIG. 9 illustrate object data. In addition, although (a)-(m) is hung up as a target object in the same figure, it is not limited to this, You may further add different target object data.

  Next, the process proceeds to step S3, and it is checked whether or not the time Tim after the start of the sample has passed a set time (1 hour (1H) in this embodiment). If Tim ≧ 1H, the process proceeds to step S4, the object data acquired from the oldest traveling environment image information stored in the storage unit 17 is cleared, and the process proceeds to step S5. If Tim <1H, the process proceeds to step S5 as it is. Therefore, the object data stored in the storage unit 17 is stored when the object data is sequentially stored in the storage unit 17 when the time Tim after the start of the sample is within one hour (Tim <1H) and one hour has elapsed. (Tim ≧ 1H), the oldest object data is cleared and the newest object data is sequentially stored, so that the number of samples is constant.

  Then, when the process proceeds from step S3 or step S4 to step S5, the object data stored in the storage means 17 is read, and the type of whether the road on which the vehicle Mv is traveling is a general road or a highway is estimated. The total evaluation points used at the time are calculated.

  The total evaluation point calculation process in step S5 is executed according to a total evaluation point calculation process subroutine shown in FIG. In addition, the threshold value shown below is an illustration and can be set arbitrarily.

  In this subroutine, first, in step S11, a feature element for estimating a road type is calculated based on each acquired object. 7 to 8 exemplify characteristic elements a to m representing physical quantities per unit time or per unit distance. Details of each of the characteristic elements a to m will be described together in step S12 described later.

  In step S12, the type of whether the road on which the vehicle Mv is traveling is a general road or a highway is examined and evaluated for each of the acquired feature elements a to m. Note that the processing in this step corresponds to the road type evaluation means of the present invention.

  When the road is estimated as a general road, the evaluation point of the general road (hereinafter referred to as “general road evaluation point”) is set to 1, and the evaluation point of the highway (hereinafter referred to as “highway evaluation point”) is set to 0. And When the road is estimated to be a highway, the general road evaluation point is set to 0 and the highway evaluation point is set to 1.

  FIG. 8 to FIG. 9 illustrate characteristic elements a to m and evaluation points of road types (general roads or highways) based on the characteristic elements am. The threshold values described below are merely examples, and can be arbitrarily set from statistics, experiments, simulations, and the like, and can be changed as appropriate. In the following description, the recognized pedestrian vi and the like are objects, and the count number is a characteristic element.

(A) Number of pedestrians a
It is the number (count number) of unspecified pedestrians vi as shown in FIG. 6 within a predetermined time. When the host vehicle Mv is traveling on a general road, an unspecified pedestrian vi is normally detected. However, a pedestrian vi detected while traveling on a highway is a road construction worker, a broken car occupant, or the like. ,limited.

  In the present embodiment, when the number of pedestrians a per unit time (1H) exceeds the threshold (0.001 person), the evaluation point for a general road is set to 1, and the evaluation point for an expressway is set to 0. When the number of pedestrians a per unit time (1H) is 0.001 or less, the evaluation point for ordinary roads is set to 0 and the evaluation point for expressways is set to 1. If the time Tim after the start of the sample is less than 1 hour, the threshold value is 0.001 person · Tim / 1H.

(B) Number of pedestrian groups b
It is the number (count number) in the predetermined time of the unspecified pedestrian group iv shown in FIG. When the positional relationship between two or more pedestrians is within a predetermined distance (for example, 30 [cm]), the pedestrian group iv is counted as a pedestrian group iv. When the host vehicle Mv is traveling on a general road, the unspecified pedestrian group iv can be detected relatively easily, but the pedestrian group iv detected while traveling on the highway is a road construction work. The number of employees is extremely limited. In the present embodiment, the threshold value for comparing the number of pedestrian groups b per unit time (1H) is 0.0001, which is easier to estimate as a general road than the number of pedestrians a.

  If the number of pedestrian groups b exceeds the threshold (0.0001 people), the general road evaluation point is set to 1, and the highway evaluation point is set to 0. When the number of pedestrians a per unit time (1H) is 0.0001 or less, the evaluation point for ordinary roads is set to 0 and the evaluation point for expressways is set to 1. If the time Tim after the start of the sample is less than 1 hour, the threshold value is 0.0001 person · Tim / 1H.

(C) Number of bicycles c
Bicycle traveling on a highway cannot be assumed, but a motorcycle may be mistaken for a bicycle. Therefore, in this embodiment, when the number c of bicycles per unit time (1H) exceeds a threshold value (0.001 person), the evaluation point of the general road is set to 1, and the evaluation point of the expressway is set to 0. . When the number of bicycles per unit time (1H) is 0.001 or less, the evaluation point for ordinary roads is set to 0 and the evaluation point for expressways is set to 1. The evaluation when the time Tim after the start of the sample is less than 1 hour is as described above.

(D) Number of pedestrians closest to own vehicle
When the host vehicle Mv is stopped on the first road due to traffic jams, waiting for traffic lights, etc., it can be easily assumed that the pedestrian vi crosses immediately before that. It is difficult to assume that a pedestrian crosses just before Mv. Therefore, in this embodiment, the threshold value of the number d of pedestrians near the vehicle detected per unit time (1H) is set to 0.0001 to facilitate estimation as a general road.

  When d> 0.0001 person / 1H, the evaluation point of the general road is set to 1, and the evaluation point of the expressway is set to 0. In the case of d ≦ 0.0001 person / 1H, the evaluation point of the general road is set to 0 and the evaluation point of the expressway is set to 1. The evaluation when the time Tim after the start of the sample is less than 1 hour is as described above.

(E) Number of oncoming vehicles e
As shown in FIG. 6, the oncoming vehicle ii is easily detected on the general road, but on the highway, in many cases, as shown in FIG. 7, the traveling lane and the oncoming lane of the host vehicle Mv are guardrails xi. Since it is partitioned, it is difficult to detect the oncoming vehicle number e. Therefore, in the present embodiment, the threshold of the number of oncoming vehicles e detected per unit time (1H) is set to one, and when e> 1 / 1H, the evaluation point of the general road is 1, the evaluation point of the expressway Is set to 0. In the case of e ≦ 1 vehicle / 1H, the evaluation point of the general road is set to 0 and the evaluation point of the expressway is set to 1. The threshold when the time Tim after the start of the sample is less than 1 hour is 1 unit · Tim / 1H.

(F) Number of vehicle traffic signals f
As shown in FIG. 6, the vehicle traffic signal vii can be recognized normally on a general road. However, on highways, it is rare that a traffic signal is installed at the entrance of the tunnel. Therefore, in this embodiment, the threshold of the number of vehicle traffic signals f detected per unit time (1H) is set to 0.01, and when f> 0.01 / 1H, the evaluation point of a general road is 1 , Set the highway evaluation point to 0. In the case of f ≦ 1 car / 0.01H, the evaluation point of the general road is set to 0, and the evaluation point of the expressway is set to 1. The threshold when the time Tim after the start of the sample is less than 1 hour is 0.01 units · Tim / 1H.

(G) Number of traffic lights for red / yellow lighting vehicles g
As described above, the vehicle traffic signal on the highway is mainly installed at the entrance of the tunnel, and the red light is lit only when a disaster occurs in the tunnel. For this reason, almost all blue lights are on. On the other hand, traffic lights on general roads are repeatedly switched in a cycle of blue light → yellow light → red light. Further, in a traffic signal equipped with three direction (forward, right turn, left turn) arrow lights, the red light → yellow light is switched back and forth as one cycle. Therefore, in the present embodiment, the threshold of the number of traffic signals for vehicles g that detects lighting of a red light or a yellow light per unit time (1H) is one, and when g> 1 / 1H, the evaluation of the general road Set the point to 1 and the evaluation point of the expressway to 0. When g ≦ 1 vehicle / 1H, the evaluation point for the general road is set to 0 and the evaluation point for the expressway is set to 1. The threshold when the time Tim after the start of the sample is less than 1 hour is 1 unit · Tim / 1H.

(H) Number of pedestrian crossings h
There is no pedestrian crossing on the expressway, but there is a possibility of misrecognizing a puddle or a puddle as a pedestrian crossing. Therefore, in this embodiment, the threshold value of the number of pedestrian crossings h detected per unit time (1H) is set to 1, and when h> 1 / 1H, the evaluation point of the general road is 1, and the evaluation point of the expressway is 0. In the case of h ≦ 1 / 1H, the evaluation point of the general road is 0, and the evaluation point of the expressway is 1. The threshold when the time Tim after the start of the sample is less than 1 hour is 1 · Tim / 1H.

(I) Number of intersections i
There is no intersection (for example, a branch road in which the white line on the shoulder side of the expressway turns almost at right angles) on the highway. For this reason, in the present embodiment, the threshold of the number of intersections i detected per unit time (1H) is set to 1 to facilitate detection of ordinary roads.

  When i> 1 / 1H, the general road evaluation point is 1, and the highway evaluation point is 0. When i ≦ 1 / 1H, the general road evaluation point is 0, The evaluation point is 1. The threshold when the time Tim after the start of the sample is less than 1 hour is as described above.

(J) Ratio j [%] where the lane width is 3 [m] or more continuously for a predetermined section
Most of the lane width, which is the distance between the left and right section lines that divide the lane of the expressway, is 3 [m] or more. Therefore, when the ratio j of the section having a predetermined unit distance (for example, 250 to 300 [m]) and the lane width of 3 [m] or more exceeds 99 [%] (j> 99 [%]), the high speed Assume that the road evaluation point is 1 and the general road evaluation point is 0. When j ≦ 99 [%], the evaluation point of the expressway is 0, and the evaluation point of the general road is 1. (k) The number k of times when the radius of curvature of the curve is R250 or more
The curve radius of curvature of the expressway is determined by the speed limit, topography, etc., but has a minimum of about R250 [m]. On the other hand, in general roads, there are many curved roads having a radius of curvature of R250 [m] or less, but curved roads of R250 [m] or more are rare. For this reason, in the present embodiment, the threshold value of the number k of passages of curved roads of R250 [m] or more among curved roads passing per unit time (1H) is 1, and when k> 1 / 1H, a general road The evaluation point is 0, the highway evaluation point is 1, and when k ≦ 1 / 1H, the general road evaluation point is 1, and the highway evaluation point is 0. The threshold when the time Tim after the start of the sample is less than 1 hour is the same as described above.

(L) Number of guide signs peculiar to expressways
There are specific traffic signs that are not installed on general roads, such as interchanges, guide signs to parking areas and service areas. The guidance sign xii shown in the highway image of FIG. 7 displays a green horizontal signboard with a notice of “exit” and a notice distance such as “2 km”, “1 km”, “500 m”, etc. In the case of guidance for a parking area or a service area, a letter “P” and a notice distance are displayed. By recognizing these images, highway guide signs are recognized. However, even on general roads, if a sign indicating the interchange entrance is displayed on a green landscape sign, such as a sign indicating the entrance of an expressway, it can be mistaken for an expressway guide sign. There is sex.

  Therefore, in the present embodiment, the threshold of the number of guide signs l that is specific to a highway recognized per unit time (1H) is set to 0.1, and when l> 0.1 / 1H, the evaluation point of a general road is set to 0. , The evaluation point of the expressway is 1, and when l ≦ 0.1 / 1H, the evaluation point of the general road is 1, and the evaluation point of the expressway is 0. The threshold when the time Tim after the start of the sample is less than 1 hour is the same as described above.

(M) Ratio m [%] that guard rails are continuous for a predetermined distance on both sides
As shown in the image of the expressway in FIG. 7, on the expressway, both sides of the lane are partitioned by guardrails (x, xi) on most routes except for face-to-face traffic in the provisional two lanes. However, even on ordinary roads, there are cases where guardrails are installed on the mountain side as well as on Tanigawa.

  Therefore, in this embodiment, when the guardrail has a predetermined unit distance on both sides (for example, about 250 to 300 [m]), and the continuous section exceeds 99 [%] (m> 99 [%]), Assume that the highway evaluation point is 1, and the general road evaluation point is 0. When m ≦ 99 [%], the evaluation point for the expressway is 0, and the evaluation point for the general road is 1.

  Then, it progresses to step S13 and weights according to the priority set beforehand with respect to each evaluation point. Note that the processing in this step corresponds to the weighting means of the present invention.

  The priority ranks the characteristic elements that need to ensure the safety of the object in the higher rank and the characteristic elements that are merely estimated roads in the lower rank. In the present embodiment, the feature elements a to m shown in FIGS. 8 to 9 are the order of priority (a> to> m). Incidentally, the feature elements a to e ranked higher are priorities for ensuring the safety of the object, and are applied to estimation of general roads. The feature elements f to i are priorities for estimating the general road, and the feature elements j to m for simply estimating the highway are ranked in the lower order.

  Note that the priority order can be arbitrarily changed. In this embodiment, the weighting coefficient of the highest priority number of pedestrians a is set to 1, and lower-order feature elements are weighted by sequentially multiplying, for example, a gain of 98 [%]. Therefore, the weighting coefficient of the ratio m, which is the feature element having the lowest priority and the guard rails are continuous for a predetermined distance on both sides, is 78 [%].

  After that, the process proceeds to step S14, and the general road evaluation points and the expressway evaluation points of the respective characteristic elements a to m weighted in advance are individually added (aggregated) to obtain the general total evaluation points and the total highway evaluation points. calculate. The processing in this step corresponds to the road type total evaluation means of the present invention.

  And it progresses to step S6 of the road classification estimation routine shown in FIG. In step S6, first, it is checked whether or not the difference between the total evaluation points is within a preset error range. If it is within the error range, the estimation is impossible, the process jumps to step S10, the road type estimation flag Fa is set to 0, and the routine is exited.

  On the other hand, if the error range is exceeded, the process proceeds to step S7. If the general road total evaluation point <the highway total evaluation point, the highway is estimated, and the process proceeds to step S8 where the road type estimation flag Fa is set to 2. Set and exit the routine.

  If the general road total evaluation point> the highway total evaluation point, it is estimated that the road is a general road, the process proceeds to step S9, the road type estimation flag Fa is set to 1, and the routine is exited. Note that the processing of steps S7 to S9 described above corresponds to the road type estimation means of the present invention.

  The value of the road type estimation flag Fa set by the road type identification unit 16 described above is read by the travel support control unit 11, and an automatic driving mode corresponding to the road type is set and executed. The automatic operation mode is set according to the automatic operation mode setting routine shown in FIG.

  In this routine, first, in steps S21 and S22, the value of the road type estimation flag Fa is referred to. If Fa = 2, it is estimated that the road is a highway, so the process proceeds to step S23, the highway mode is executed, and the process proceeds to step S26. If Fa = 1, it is estimated that the road is a general road, so the process proceeds to step S24, the general road mode is executed, and the process proceeds to step S26. If Fa = 0, it is determined that the road type cannot be estimated, and the process proceeds to step S25. After canceling the automatic driving, the process proceeds to step S26.

  If it progresses to step S26, the information of the automatic driving mode performed will be alert | reported to a driver | operator, and a routine will be exited. The information on the automatic driving mode is a display indicating that the highway mode or the general road mode is executed, and the driver is notified through the notification means 26 to be recognized. In addition, when the automatic driving is canceled, the driver is notified of the fact through the notification means 26 to be recognized.

  In this driving support control unit 11, all functions provided for automatic driving in the highway mode (lane departure prevention control, lane keeping control, lane change control, automatic start control, ACC control, automatic brake control, etc.) Is executed. On the other hand, in the general road mode, only limited automatic driving functions (ACC control, automatic brake control, etc.) are executed.

  As described above, in the present embodiment, first, based on the traveling environment information from the in-vehicle camera unit 21, a plurality of types of objects for estimating the road types of the general road and the highway are recognized, and each of these objects is recognized. Each feature element is obtained based on each of the feature elements, and each of the feature elements is compared with a preset threshold value to obtain an evaluation point for each of the feature elements. Subsequently, since the evaluation points obtained for each feature element are weighted according to the priority of the feature element, for example, the number of pedestrians a in FIG. 8 is 1, and the lane width is predetermined. When the highway evaluation point of the ratio j of 3 [m] or more is determined to be 1 in the continuous section, the general road evaluation point is prioritized by weighting.

  Further, the general road evaluation point and the highway evaluation point of each weighted characteristic element are grouped and added, and compared to estimate the general road or the highway. It is possible to estimate with high accuracy the type of travel road on which the road travels is a general road or a highway. Moreover, in this embodiment, since the road type can be estimated without depending on the car navigation device, high versatility can be obtained.

  The present invention is not limited to the above-described embodiment. For example, two or more threshold values for comparing each feature element are set, and for example, even a general road is estimated whether it is a suburb or an urban area. In automatic driving at, functional restrictions may be made more lenient than automatic driving during city driving.

1 ... Driving assistance device,
11 ... Driving support control unit,
15 ... In-car communication line,
16 ... road type identification part,
17 ... storage means,
21 ... In-vehicle camera unit,
21a ... main camera,
21b ... sub camera,
22, Automatic operation switch,
23 ... Running state detection sensor,
26. Informing means,
31 ... Throttle actuator,
32 ... Electric power steering motor,
33 ... Brake actuator,
a ... Number of pedestrians
b ... Number of pedestrian groups,
c ... Number of bicycles,
d ... Number of pedestrians near the vehicle,
e ... Number of oncoming vehicles,
f ... Number of vehicle traffic lights,
g ... Number of yellow traffic lights
h ... Number of pedestrian crossings,
i ... Number of intersections,
j. m ... ratio,
k ... times,
l ... Number of guide signs,
Fa: Road type estimation flag,
Mv ... own vehicle,
Tim ... Time after starting the sample,
i-xii ... road type estimation object,

Claims (4)

Road type identifying means for identifying the road type on which the vehicle travels;
In a vehicle driving support device having a plurality of automatic driving modes corresponding to the road type, and driving support control means for setting the automatic driving mode corresponding to the road type estimated by the road type identification means,
Having imaging means for imaging the traveling environment in front of the host vehicle;
The road type identifying means is
Road type estimation target acquisition means for acquiring a road type estimation target based on image information of the traveling environment imaged by the imaging means;
A physical quantity per unit time or unit distance of each road type estimation object acquired by the road type estimation object acquisition means is set as a characteristic element representing the characteristic of each road type, and Road type evaluation means for comparing the threshold set for each feature element and evaluating the road type for each feature element;
Road type total evaluation means for calculating the total evaluation of the road type by totaling the evaluation of the road type for each feature element evaluated by the road type evaluation means;
A road type estimation means for estimating the road type by comparing the total evaluation of the road type calculated for each road type by the road type total evaluation means,
The vehicle driving support device according to claim 1, wherein the driving support control unit executes the automatic driving mode corresponding to the road type estimated by the road type estimating unit. The road type identification unit further includes a weighting unit that weights the evaluation of the road type performed for each feature element in the road type evaluation unit according to priority.
2. The vehicle travel support apparatus according to claim 1, wherein the road type total evaluation unit aggregates the evaluations weighted by the weighting unit. The priority is characterized in that the feature elements that need to ensure the safety of the road type estimation object are ranked higher, and the feature elements that only estimate the road type are ranked lower. The vehicle travel support device according to claim 2. When the comparison value of the total evaluation of the road type that is totaled for each road type by the road type total evaluation unit is within a preset error range, the driving support control unit can estimate the road type. The vehicle driving support device according to any one of claims 1 to 3, wherein the automatic driving is canceled by determining.

Images