JPS6190215A - Automatic steering working wagon - Google Patents

Abstract

PURPOSE:To eliminate the delay in response to the steering control by controlling both front and rear wheels according to the detection parameters of divergence volume and divergence angle against the objective fields. CONSTITUTION:A picture signal S0 picked up by a monitor camera 5 is stored at a frame memory 7. A control device 8 takes an average of the signal S0 and obtains average picture S1. Next the part where the difference of brightness is large into binary, and obtain a binary picture of which only the borderline L between an unharvested area B and harvested area A is bright and others are dark. Further after processing the borderline L so that it makes continuous line, and then calculates the volume and angle of divergence of detected border line L against a objective border line L0 to which the vehicle 1 should follow. After steering operation is made to front and rear wheels 2, 3 and parallelly moving the vehicle 1 without changing its direction, the steering operation is given to wheels 2, 3 according to the divergence angle theta so that the wheels may direct relatively opposite each other to correct the direction of the vehicle 1 towards the borderline L so that borderline L and L0 may coincide each other, in other words so that the vehicle follows the borderline L0.

Description

[Detailed Description of the Invention] [Field of Industrial Application] The present invention is configured such that both front and rear wheels can be steered, and includes means for detecting the boundary between an untreated work area and a treated work area. The present invention relates to an automatic traveling work vehicle, comprising means for controlling the steering of a vehicle body along the boundary based on a result of detecting a shift of the vehicle body with respect to the boundary by the boundary detection means.

[Conventional technology]

In the above-mentioned type of automatic traveling work vehicle, the above-mentioned boundary detection means is configured using a photo-ink brush type or light reflection type scanning sensor, a contact type sensor, etc.
Configured to detect the boundary position along which the vehicle body should follow by sensing whether the state of the work area at a specific point, such as immediately before the direction of travel or the current vehicle body position, is an untreated work area or a treated work area. It was done.

However, the conventional boundary detection means described above detects the deviation of a certain point of the work area from the boundary, and the detection result is immediately used as a steering control parameter, which causes the following disadvantages. was there.

In other words, when the working area is in poor condition and the boundaries are discontinuous, it is easy to lose sight of the boundaries to be followed, so processing such as averaging the boundary detection signals over a predetermined travel section is performed to prevent malfunctions. As a result, there is an inconvenience that the control response becomes slow.

In addition, since it is possible to detect only the deviation from the boundary at the point where the vehicle is actually traveling or one point immediately before it,
Even if the detected boundary is discontinuous, the actual boundary direction is straight and it is sufficient to simply go straight, but unnecessary steering control is performed in an attempt to follow this discontinuous boundary, resulting in There were also inconveniences such as large meandering and control hunting, which worsened straight-line driving performance.

Furthermore, there was also a structural drawback in that the state, such as the direction of the boundary, could not be detected until after the vehicle had actually traveled.

[Problem that the invention seeks to solve]

The present invention has been made in view of the above-mentioned circumstances, and an object of the present invention is to provide means for detecting the shape of the boundary that the vehicle body should follow without actually running the boundary, and to reduce the delay in control response of steering control. Our goal is to provide autonomous work vehicles that are not available today.

[Means for solving problems]

In order to achieve the above object, the automatic traveling work vehicle according to the present invention comprises means for imaging the state of the work area in a predetermined range in front of the vehicle body in the direction of movement, and a means for imaging the state of the work area in a predetermined range in front of the vehicle body in the direction of movement; Means for detecting the boundary as a continuous line by binarizing the image based on the average brightness difference, and means for calculating the deviation amount and deviation angle of the boundary detected by the boundary position detection means from the target boundary that the vehicle body should follow. The present invention is characterized in that the steering control of the front and rear wheels is performed based on detection parameters of the deviation amount and deviation angle with respect to the target boundary, and its operation and effects are as follows.

[For production]

In other words, images are taken of a certain range of the work area in front of the vehicle in the direction of travel, and two images are taken based on the brightness difference between the images.
By converting it into a value, the boundary between the untreated work area and the treated work area is detected as a continuous line, for example, an approximate straight line, and the amount and angle of deviation between the detected boundary and the target boundary that the vehicle body should follow are determined. By controlling the front and rear wheels based on the detected deviation amount and deviation angle, there is no delay in control response, and the follow-up response and convergence to the boundary are improved.

〔Effect of the invention〕

Due to the above structure, the following excellent effects have been achieved.

In other words, the boundary that the vehicle should follow is determined not as a point but as a continuous line before traveling to that position.In other words, the direction of the boundary and the degree of deviation from that boundary are quantitatively detected, so the direction of travel is corrected. It is now possible to predict in advance the steering direction and amount to
The ability to track boundaries was significantly improved without any delay in control response.

Further, since the steering control is performed by predicting the boundary position with respect to the vehicle body, even if the boundary condition is bad and discontinuous, the direction and position can be corrected and the steering control can be performed. Therefore, straight-line running performance has also been significantly improved.

〔Example〕

Embodiments of the present invention will be described below based on the drawings.

As shown in Figures 5 and 6, the front wheel (2).

(2) and the rear wheels (3), a lawn mower (4) equipped with an internal disc-shaped cutting blade is suspended vertically in the middle of the vehicle body (1), which is configured so that both of the rear wheels (3) and (3) can be operated by steering. At the same time, a tracing sensor (^) is used as a boundary detection means configured as described later to detect the boundary (L) between the unmown area (B) and the mowed area (C) of the lawn indicating the running course of each process. This constitutes a lawn mowing vehicle as an automatically traveling vehicle capable of automatically traveling along the boundary (L).

The following sensor (A) is configured by using a monitor camera (5) as an imaging means, whose imaging field of view is centered on the target boundary (L0) along which the vehicle body (1) is to travel forward in the traveling direction. Car body (1
) The sensor indicator frame extends forward and upward (
6), and binarizes the image captured by this monitor camera (5) based on the average brightness difference, thereby determining the amount of deviation (a) of the detection boundary (L) with respect to the target boundary (L0). Find the deviation angle (θ) and set the detection boundary (L)
and the target boundary (L0), that is, the driving direction is corrected so that the detection boundary (L) is located at the center of the field of view in the longitudinal direction with respect to the vehicle body (1) of the monitor camera (5). It controls the steering operation.

Hereinafter, the means for detecting the boundary (L) by binarizing the image captured by the monitor camera (5) will be explained using the block diagram shown in FIG. 1, the explanatory diagram of the image signal shown in FIG. The explanation will be based on the flowchart shown in .

First, an image signal (S0) captured by the monitor camera (5) is temporarily stored in a frame memory (7), and a control device (8) configured by a microcomputer
The image signal (SO) (shown in FIG. 2 (a)) stored in the frame memory (7) is converted into, for example, the brightness of the center pixel of the image by the average value of the area partitioned by a predetermined number of dots around it. order. By performing processing such as subsequent replacement, the images are averaged to obtain a blurred averaged image (S,) as shown in FIG. 2 (Ij).

Next, by binarizing the portions of the averaged image (Sl) where the brightness changes are large, that is, the pixel portions where the brightness changes are large, as shown in FIG. A binarized image (S2) is obtained in which only the boundary (L) portion with the mowed field (C) is bright and the other portions are dark.

Furthermore, after processing the boundary (L) detected by the binarized image (S2) so that it becomes a continuous line, for example, an approximate straight line, the vehicle body (1) is aligned as shown in FIG. The deviation amount (a) and deviation angle (θ) of the detection boundary (L) with respect to the power target boundary (L0) are calculated.

Then, based on the deviation amount (a) calculated by the calculation, the front and rear wheels (2) and (3) are steered in the same direction, so that the vehicle body (1) is parallel without changing its direction. After moving, based on the deviation angle (θ), the front and rear wheels (2) and (3) are steered in relatively opposite directions to find the target boundary (position) of the vehicle body (1). ) and correct the orientation with respect to the detection boundary (L
) and the target boundary (L, ) coincide within the field of view of the monitor camera (5), that is, the vehicle body (1) is controlled to follow the target boundary (L0).

Therefore, as shown in Figure 4, for example, there are discontinuous boundaries (as shown in Figure (A)), locally curved boundaries (as shown in Figure 4), and uneven and unclear lawns. Even if a boundary (shown in Q9 in the same figure) is detected, a continuous boundary (L
), making it possible to perform steering control without unnecessary steering operations or deviation of the driving direction from the original boundaries as in the past.

In Figure 1, (9) and (10) are the front wheels (2), respectively.
, (2) and the hydraulic cylinders that actually steer the rear wheels (3), (3), (11), (1
2) are electromagnetic valves that drive the hydraulic cylinders (9) and (10), respectively, and (13) is a motor that operates the shift position of the continuously variable transmission (14). Also, (R,)
, (RZ) is a potentiometer for detecting the steering amount of the front wheels (2), (2) and the rear wheels (3), (3) and feeding it back to the control device (8), and (R3) is a similar potentiometer. This is a potentiometer for detecting the shift position of the transmission device (14) and feeding it to the control device (8).

By the way, averaging the original image signal (S0) is as follows:
It detects large brightness changes due to the influence of reflected light from mown grass leaves, small bald areas of grass that are difficult to distinguish from mown areas (C) in uncut areas (B), and uneven areas. This is to reduce the detection error of the boundary (L) in advance.

The averaging process may be performed by using an optical filter for blurring instead of the arithmetic processing, or by simply using the camera (5) in a so-called out-of-focus state.

In addition, in order to find the boundary (L), the binary image (S2
) can be processed using the least squares method or the like from each adjacent pixel (dot), but instead of binarizing, the differential value of the brightness change may be processed as a weighting coefficient.

Furthermore, in order to obtain the boundary (L) as a continuous line, calculation may be performed using the coordinates of the image of the boundary line portion by the least squares method or Hough transformation.

[Brief explanation of drawings]

The drawings show an embodiment of the automatic traveling work vehicle according to the present invention, and FIG. 1 is a block diagram showing the configuration of the control system, and FIG. 2 (
A) + (0), G1%) is an explanatory diagram of the image signal, 3rd
The figure is a flowchart showing the operation of the control device, Figures 4 (a) and (b), Q9 are explanatory diagrams of unclear boundaries, Figure 5 is a plan view showing the overall configuration of the lawn mowing vehicle, and Figure 6 is a plan view showing the overall configuration of the lawn mowing vehicle. The figure is a side view thereof. (1)...Vehicle body, (2)...Front wheels, (
3)... Rear wheel, (5)... Imaging means,
(A)... Boundary detection means, (B)...
Untreated working area, (C)... Treated working area, (L
)...Detection boundary, (L0)...Target boundary, (a)...Difference amount, (θ)...Difference angle.

Claims (1)

[Claims] [1] Both the front and rear wheels (2) and (3) can be steered, and the boundary between the untreated work area (B) and the treated work area (C) ( L), and the vehicle body (1) moves along the boundary (L) based on the detection result of the displacement of the vehicle body (1) with respect to the boundary (L) by the boundary detection means (A). The automatic traveling work vehicle is equipped with means for steering control in order to move, and the boundary detection means (A) comprises means for capturing an image of the state of the work site in a predetermined range in front of the vehicle body (1) in the direction of movement. (5) means for detecting the boundary as a continuous line by binarizing the image based on the average brightness difference of the image captured by this imaging means (5);
A means is provided for calculating a deviation amount (a) and a deviation angle (θ) with respect to a target boundary (L_0) that the vehicle body (1) of L) should follow,
The front and rear wheels (2
), (3) An automatic driving work vehicle characterized by performing steering control. [2] Detected deviation amount (a) with respect to the target boundary (L_0)
) and the deviation angle (θ), the steering control for the deviation amount (a) is based on the front and rear wheels (
2) and (3) are steered in the same direction, and the steering control for the deviation angle (θ) is performed by steering the front and rear wheels (2) and (3) in relatively opposite directions. The self-driving work vehicle according to claim 1, characterized in that it has turning steering.