JP2514405B2 - Automatic traveling device - Google Patents

Description

Description: TECHNICAL FIELD The present invention relates to an automatic traveling device that allows a vehicle to travel automatically while searching for a traveling path.

2. Description of the Related Art Conventionally, in this type of automatic traveling device, a video camera mounted on a vehicle so that a dedicated guideline for guiding the traveling of the vehicle on a road surface is provided in advance, and the road surface in front of the vehicle can be imaged. While following the guideline, the vehicle is controlled according to the guideline by steering the vehicle (Japanese Patent Publication No. 58-58).
-42482 and JP-A-62-140109).

However, such a conventional automatic traveling device cannot guide the traveling of the vehicle on the road surface where the guideline is not provided.

Further, in the past, for example, in a lawnmower work vehicle, while capturing an area in the traveling direction of the vehicle with a video camera mounted on the vehicle, continuous edge information is emphasized by emphasizing the difference in brightness between the work site and the unworked site. To detect the boundary between the work site and the unworked site by appropriately performing the image processing of the captured image so that the vehicle steering control is performed so that the vehicle travels along the detected boundary. (See JP-A-62-70916).

However, unlike the above-mentioned automatic traveling apparatus, the automatic traveling apparatus has a function of traveling along the line while searching for a guideline for traveling by itself. Guidance is merely a matter of simply following one guideline.

The present invention has been made in consideration of the above points, and makes the vehicle travel control so that the vehicle travels on the searched road while searching the road by imaging the front of the vehicle with the imaging device. In addition, when the vehicle is approaching an intersection, a straight road, a spelling road, or the like, the imaging device is appropriately switched to wide-angle or telephoto so that the road ahead of the vehicle can be appropriately imaged according to the road conditions. The present invention provides an automatic traveling device capable of

Configuration The automatic traveling device according to the present invention has
Means for recognizing a road ahead of the vehicle by image processing of an image obtained by picking up an image of the front by an imaging device attached to the vehicle, and means for controlling the running of the vehicle so as to drive on the recognized road. And a means for setting information for designating an intersection, a straight road, or a spelling road on the planned traveling route, and detecting the fact that the vehicle is approaching an intersection, a spelling road or a straight road on the planned traveling route, and detecting the information. And a means for appropriately switching the image pickup characteristic of the image pickup device according to the output information so that the image pickup device has a wide angle on an intersection or a spelling road and a telephoto on a straight road.

An embodiment of the present invention will be described below with reference to the accompanying drawings.

FIG. 1 shows a basic configuration of an automatic traveling apparatus according to the present invention, in which a video camera 1 mounted on a vehicle so as to be able to capture an area in the traveling direction of the vehicle, and an image captured by the video camera 1 A driveable area recognition unit 2 that recognizes a driveable area, such as a road, in the traveling direction of the vehicle by performing image processing on the obtained image;
A target route setting unit 3 that sets a target route for vehicle travel within the travelable region recognized by the travelable region recognition unit 2, a vehicle speed sensor 5 that detects a traveling speed v of the vehicle, and a yaw rate (V) that accompanies traveling of the vehicle ( Y angular velocity of change in one direction) Υ
The running state of the vehicle at that time is recognized according to the respective sensor outputs of the yaw rate sensor 6 for detecting the tire angle and the tire angle sensor 7 for detecting the tire angle δ due to the steering of the vehicle, and based on the recognized running state of the vehicle. Control unit 4 for obtaining a control target amount required for the vehicle to travel on a target route by a predetermined calculation process, a steering control unit 8 for steering the vehicle in accordance with the obtained control target amount, and a steering drive. And the part 9. Actually, the travelable area recognition unit 2 and the target route setting unit 3
And the control unit 4 is replaced by a computer control device. Further, the steering control unit 8 can be included in the computer control device.

FIG. 2 shows a specific configuration example of the travelable area recognition unit 2.

Here, under the control of the CPU 211 or the CPU 212, the input images for one image sequentially transmitted from the video camera 1 are temporarily sent to the buffer memory 23 through the image input unit 22.
Alternately stored in 1 or 232. Thereafter, the input images for one image stored in the buffer memory 231 or 232 are sequentially read out, and the image processing unit 24 extracts, for example, a road edge, which will be described later, to determine the travelable area of the vehicle. Image processing for recognition is performed. Then
The image information of the travelable area recognized by the image processing is stored in an image memory group including a plurality of memories 251 to 253.
25 or a plurality of memories 261 to 263 are stored in each memory portion of the image memory group 26 while being sequentially updated, and the image memo group 25 or the image memory group 26 is continuously driven along with a certain distance of the vehicle. The image information of the feasible area is stored. The image information of the travelable area accumulated in the image memory group 25 or the image memory group 26 is read and given to the target route setting unit 3.

Here, by providing the two CPUs 211 and 212 and the two buffer memories 231 and 232 in parallel, for example, while reading out the previously stored input image from the buffer memory 231 under the control of one CPU 211, Under the control of the other CPU 212, the next input image is stored in the buffer memory 232 so that the input image input processing can be performed in real time.

Similarly, by providing two image memory groups 25 and 26 in parallel, it is possible to perform the writing or reading processing of the image information alternately performed in each image memory group 25 and 26 in real time. ing.

In FIG. 2, 27 indicates each memory select section, and 28 indicates each decode section. Further, S-BUS indicates a system bus, D-BUS indicates a high speed data bus, and M-BUS indicates a high speed memory access bus.

In the vehicle configured as described above, the recognition of the travelable area of the vehicle in the travelable area recognition unit 2 is performed as follows.

First, an input image sent from a video camera 1 for imaging a road surface in front of a vehicle is subjected to an edge detection process by differentiating the input image. A suitable automatic threshold value setting circuit automatically sets an optimum threshold value according to the degree of shading of the input image at that time, and binarizes the edge image.

At this time, the binarization of the input image may be performed first, and then the differentiation processing for edge detection may be performed. Further, instead of performing the binarization, the multivalue may be performed by expressing the shading of the image.

Then, based on the edge-detected and binarized or multi-valued processed image, a line segment on the XY coordinate is ρ−.
By performing a Hough transform process, which is a well-known method of performing coordinate transformation represented by points on the θ coordinate, it is possible to combine continuous point sequences or remove independent discrete points, For example, information on continuous road edges as shown in FIG. 3 is obtained.

Here, θ is the angle of a perpendicular line drawn from the straight line on the XY coordinates to the origin of the coordinates, and ρ is the length of the perpendicular line. For example, the line segment L on the XY coordinates shown in FIG.
Is represented as O1 on the ρ-θ coordinate as shown in FIG.

In this case, based on the binarized processed image, an edge tracking process may be performed to extract an edge portion of the image having continuity. In addition, a plurality of processes such as a Hough transform process and an edge tracking process for obtaining continuity of an image edge are performed in parallel, and comprehensive judgment is made from the results of each process, so that a road with higher accuracy can be obtained. Edge information can be obtained. Further, by performing the above-described processing for extracting continuous image edges while growing the area of the input image as the vehicle travels, it becomes possible to extract road edge information with higher accuracy. Become.

Finally, since the image captured by the video camera 1 is a perspective projection image, the perspective image as shown in FIG. 3 eliminates the influence of perspective projection as shown in FIG. Projection conversion processing, which is a well-known means for converting into road edge images, is performed, and the space between consecutive road edges is recognized as a vehicle travelable area.

The projection conversion characteristics are set in advance in the travelable area recognition unit 2 in accordance with the characteristics of the perspective projection of the video camera 1.

Next, when a road that becomes a travelable area in the traveling direction of the vehicle is recognized by the travelable area recognition unit 2, a target route setting unit 3 sets a target that becomes an optimal travel route of the vehicle in the recognized road. A route is set.

As will be described later, the target route is preferably set in consideration of the road shape and the vehicle speed, and is set to be suitable for the running condition of the vehicle at that time, but basically, the recognized road is Depending on whether it is narrow or wide, it is uniformly set as follows.

That is, in the case where the target route setting unit 3 determines that the road width is wide gauge over a certain width, for example, as shown in FIG. 5, in the case of a left-hand road, the left edge of the road is separated from the reference edge of the road. For example, the target example road OC along the reference edge is set with a predetermined separation width w of about 1.5 m.

If the target route setting unit 3 determines that the gauge is a narrow gauge with a road width less than a certain value, the target route is set at the center of the road, though not particularly shown.

Then, the position on the XY coordinates of the set target route is stored in the internal memory of the target route setting unit 3 while being updated as the vehicle travels. At this time, the scale on the XY coordinates is determined by the magnification of the video camera 1.

In FIG. 5, point P indicates the current position of the vehicle. For example, the mounting position of the video camera 1 in the vehicle is set in advance so that the center lower end of the imaging surface of the video camera 1 is point P. ing. In the figure, the locus from the point P to the point O is until the vehicle at the point P joins the target route OC by steering control of the vehicle under the control of the control unit 4, as described later. It shows the traveling route of. The point O is the position where the vehicle joins the target route OC at that time.

Further, in the present invention, it is possible to detect the traveling state of the vehicle and set the optimum target route of the vehicle on the road as follows according to the detected traveling state.

That is, the target route setting section 3 reads, for example, the traveling speed of the vehicle detected by the vehicle speed sensor 5 and, if the vehicle speed at that time is within a low speed range equal to or less than a preset threshold value, FIG. As shown in a), the target route OC is set so as to follow the shape of the road.

Similarly, if the vehicle speed at that time is within a high-speed range exceeding a preset threshold value, as shown in FIG.
When traveling on a winding road, a target route OC having a gentle curvature is set in the road so that the lateral acceleration acting on the vehicle is reduced as much as possible.

Next, when a target route on the road is set, the control unit 4 calculates a control target amount for causing the vehicle to join the target route by an arithmetic process as follows.

Now, for example, as shown in FIG.
Let's consider a case in which is merged with the target route OC.

First, based on the current vehicle speed v (m / s) of the vehicle detected by the vehicle speed sensor 5, a distance L (m) (L = v × T) on the X axis after T seconds of the vehicle at the point P is calculated. The deviation yl between the target route OC and the point C separated by a distance L from the point P on the X-axis, that is, a value proportional to the position on the target route OC after T seconds is calculated.

Similarly, the predicted path A of the vehicle based on the yaw rate Υ (rad / s) of the vehicle detected by the yaw rate sensor 6
C is calculated, and the deviation y of the predicted route AC from the point C on the X-axis
m, that is, a value proportional to the position on the predicted route AC after T seconds is obtained according to the following equation.

^{ym = (- v × T 2} /2) × Υ ... (1) As a sign of the yaw rate Upsilon, for example the predicted path
Positive when AC turns left.

Then, a yaw rate Υ ′ to be corrected of the vehicle is obtained according to the following equation in accordance with the difference between the obtained deviations yl and ym.

Υ ′ = (ym−yl) × 2 / (v × T ² ) (2) Finally, the tire angle δ of the vehicle at the point P detected by the tire angle sensor 7 is obtained, and is calculated according to the following equation. A tire angle control target amount δ ′ for joining the vehicle to the target route OC is determined.

δ ′ = δ + (Υ ′ / v) × W · (1 + Kv ² ) (3) where W is a wheel base and K is a constant coefficient determined by vehicle characteristics such as tire characteristics and wheel base.

Then, the steering control unit 8 issues a drive command to the steering drive unit 9 according to the control target amount δ ′ given from the control unit 4, whereby the steering drive unit 9 appropriately drives the steering to move the vehicle to the target route. Steer to join the OC.

In the relationship of FIG. 7, when the distance L (target merging distance) on the X axis is set, the traveling speed v of the vehicle detected by the vehicle speed sensor 5 under the control of the control unit 4.
The set distance L can be made variable according to That is, the lower the traveling speed v, the shorter the distance L is set, so that the traveling route until the vehicle at the point P merges with the target route OC is shortened, so that the vehicle merges with the target route OC. Have it done promptly. Further, the higher the traveling speed v is, the longer the distance L is set so that the traveling route until the vehicle at the point P merges with the target route OC becomes longer so that the vehicle joins the target route OC. Let it be done gently.

Furthermore, when traveling on a winding road, the smaller the curvature is, the shorter the distance L is set to set the target route of the vehicle.
It is also possible to promptly join the OC.

Also, from the point P when the vehicle joins the target route OC
Using a curve model of the travel route to reach the point, the travel route having a predetermined curve pattern is determined by approximate analysis according to the route curvature obtained by the control unit 4 according to the target merge distance L and the vehicle speed v. It is also possible to smoothly join the target route OC with the pattern of the traveling route thus extracted. As a curve model of the traveling route, for example, the function y can be used.
= To x-sinx etc. function y = x ³ is used.

FIG. 8 shows a travel route pattern when a curve model of the travel route by the function y = x-sinx is used.

The above-described processing is repeatedly performed at predetermined time intervals on the order of several seconds set in advance, so that the vehicle can automatically travel along the target route OC.

As described above, in the automatic traveling apparatus according to the present invention, the vehicle travels a self-traveling area by recognizing the road edge based on the image of the road surface in front of the vehicle captured by the image capturing apparatus, and an appropriate target is set within the traveling area. A route is set, an optimum control target amount for merging the vehicle with the target route is obtained according to the traveling state of the vehicle at that time, and vehicle traveling control is performed accurately according to the control target amount. It has become possible.

At that time, since a target route is set within the travelable area of the vehicle, and a traveling route for merging the vehicle with the target route is determined, a two-stage route formation process is performed. It is possible to accurately perform the automatic driving of.

In the automatic traveling apparatus configured as described above, in particular, in the present invention, the video camera 1 is provided with the telephoto camera 11 and the wide-angle camera 12, and is provided from a separately provided navigation system (see FIG. 9). According to the information RD that indicates the intersections, straight roads, and spelling roads, the telescopic camera 11 and the wide-angle camera 12 can be selectively switched under the control of the drivable area recognition unit 2. Is characterized by.

As will be described later, the navigation system detects the changes in the traveling distance and the traveling direction of the vehicle and sequentially obtains the position on the XY coordinates by a calculation process, and displays the vehicle on a screen on which a road map is projected in advance. The current position is displayed. Then, the navigation system sets the planned traveling route on the road map displayed on the screen in advance, and the information RD that indicates an intersection, a straight road, a spelling road, etc. on the planned traveling route.
It is possible to input in advance, and when it is detected that the vehicle is approaching the designated intersection from the current position of the vehicle displayed on the road map on the screen, the predetermined information RD It is supposed to be output.

At this time, if the starting point and the destination point on the map are input and designated, the computer system in the navigation system automatically sets, for example, the shortest planned route from the starting point to the target point. You can also

Then, for example, when the drivable area recognition unit 2 receives the information RD designating an intersection from the navigation system, the drivable area recognition unit 2 switches to the wide-angle camera 12 in accordance with the information RD and extensively searches for the designated intersection. When the drivable area recognition unit 2 receives the information RD indicating a straight road, the telescopic camera 11 is switched to optimally image the straight road looking ahead. Further, when the drivable area recognition unit 2 receives the information RD indicating the spelling and the road, the wide-angle camera 12 is switched to optimally image the winding road.

It is possible to provide the telephoto camera 11 with a zoom function so that the zoom function can be appropriately operated according to the length of a straight line on a straight road, for example.

FIG. 9 shows an example of the configuration of a navigation system. For example, a photoelectric, electromagnetic, or mechanical contact type distance sensor 91 that outputs a pulse signal for each unit mileage according to the rotation of a vehicle tire, and A yaw rate sensor including a gyroscope that outputs a signal proportional to the amount of change in the angular velocity in the yaw direction as the vehicle travels 92
The number of pulse signals from the distance sensor 91 is counted to measure the traveling distance of the vehicle, and the yaw rate sensor 92
A change in the traveling direction of the vehicle is obtained in accordance with the output signal of the vehicle, a position on the XY coordinates for each unit traveled distance of the vehicle is sequentially obtained, and a centralized control of the entire system, a ROM for the program, and Signal processing device (computer control device) 93 consisting of control RAM etc.
And a traveling locus storage device 94 for sequentially storing the data of the position on the XY coordinates which is changed by the signal processing device 93 and holding it as finite continuous position information corresponding to the current position of the vehicle. A map information storage medium 95 in which a plurality of pre-digitized map information is stored in file units, a storage medium reproducing device 96 for selectively reading out necessary map information from the storage medium 95, and the read-out information. The map image is displayed on the screen according to the map information, and the current position of the vehicle, the running trajectory up to that point and the current traveling direction are updated on the same screen based on the position data stored in the running trajectory storage device 94. Display device to display 97
In addition to giving an operation command to the signal processing device 93, it causes the display device 97 to select and specify the map to be displayed and set the starting point of the vehicle on the displayed map, and to travel on the displayed map. While setting the route,
It is configured by an operating device 98 capable of inputting in advance information RD indicating a crossing, a straight road, and a spelling road on the planned traveling route.

With such a configuration, as shown in FIG. 10, the selectively read map is displayed on the screen of the display device 97 and the vehicle travels from the starting point set on the map. In accordance with the scale of the map preset by the signal processing device 93, a display mark M1 indicating the current position of the vehicle on the XY coordinates, a display mark M2 indicating the traveling direction of the vehicle at the current position, and a starting point. S
The running locus display mark M3 from the current position to the current position is simulated and displayed according to the running state of the vehicle.

Further, when the planned travel route is set on the map displayed on the screen by the input operation of the operation device 98, for example, as shown in FIG. 11, target points are set at the main intersections and branch points in the planned travel route on the map. While setting a, b, c, ..., it is possible to give an instruction such as turning right or left at each target point.

Then, the signal processing device 93, for example, when the display mark M1 of the current position of the vehicle approaches the position D which is a certain distance before the target point a, the navigation such as “advancing the Y-shaped road forward to the right” is performed. Information is emitted to the driver through, for example, a voice generating device (not shown), and information RD for instructing a Y-shaped intersection is provided to the travelable area recognition 2.

Further, as described above, the map information storage medium 95 is used without inputting the designation information RD of the designated intersection or the like by designating the intersection or the like on the planned traveling route by the input operation of the operation device 98. The position of an intersection on the map and its designated information RD are registered in advance together with the map information, and under the control of the signal processing device 93, the current position of the vehicle at the predetermined intersection on the map displayed on the screen. When the display mark of “3” comes, the instruction information RD registered in advance according to the position may be given to the travelable area recognition unit 2.

In the navigation system, the distance sensor
It is possible to obtain the traveling distance of the vehicle based on the output of the vehicle speed sensor 5 in the automatic traveling device shown in FIG. 1 without providing 91 in particular. Further, the yaw rate sensor 6 in the automatic traveling apparatus shown in FIG. 1 can be used together without separately providing the yaw rate sensor 92.

As described above, in the automatic traveling device according to the present invention, the road itself to be traveled can be searched based on the image obtained by capturing the region in the traveling direction of the vehicle by the image capturing device. When approaching an intersection on a planned route, a straight road, a spelling road, etc., the wide angle and the telephoto of the image pickup device are appropriately switched, and the intersection, the straight road,
By imaging the spelling road, etc., it is possible to optimize the imaging of the road according to the road condition, and appropriately recognize the intersection, the straight road, the spelling road, etc. from the imaged image. It has an excellent advantage that it can.

[Brief description of drawings]

FIG. 1 is a block configuration diagram showing an embodiment of an automatic traveling device according to the present invention, FIG. 2 is a block diagram showing a concrete configuration example of a travelable area recognition unit in the embodiment, and FIG. 3 is a video camera. FIG. 4 is a diagram showing an example of a road recognized from among the images picked up by FIG. 4, FIG. 4 is a diagram showing an image when the image of FIG. 3 is subjected to projective transformation processing, and FIG. 5 is a target set on the road. 6 is a diagram showing an example of a route, FIGS. 6 (a) and 6 (b) are diagrams showing target routes set on the road at low speed and high speed of the vehicle, respectively, and FIG. 7 is a target route and a predicted route of the vehicle. FIG. 8 is a diagram showing an example of a traveling route of a vehicle when the vehicle merges with a target route, FIG. 9 is a block diagram showing one configuration example of a navigation system, and FIG. Figure 11 shows an example of the display screen. Diagram showing the state of inputting navigation information on the planned travel route in the navigation system,
FIG. 12 is a diagram showing a line segment on the XY coordinate, and FIG. 13 is a diagram showing a point on the ρ-θ coordinate when the line segment of FIG. 12 is Hough transformed. 1 ... Video camera, 2 ... Driving area recognition unit, 3 ...
… Target route setting unit, 4 …… Control unit, 5 …… Vehicle speed sensor,
6 ... Yaw rate sensor, 7 ... Tire angle sensor, 8 ...
... Steering control unit, 9 ... Steering drive unit

Claims (1)

(57) [Claims] 1. A means for recognizing a road ahead of the vehicle by image processing of an image obtained by picking up an image of the front by an image pickup device attached to the vehicle, and a vehicle traveling so as to travel on the recognized road. Means to perform control, means to set each instruction information of intersection on the planned travel route, spelling road or straight road, and means that the vehicle is approaching the intersection on the planned travel route, spelling road or straight road Means for detecting and outputting predetermined instruction information, and according to the output instruction information, the image pickup characteristic of the image pickup device is appropriately switched so as to be wide angle at an intersection or a spelling road and telephoto on a straight road. And an automatic traveling device configured by means.