JP7306311B2 - recognition device - Google Patents

Description

The present invention relates to recognition devices.

As a conventional recognition device, for example, the technology described in Patent Document 1 is known. The recognition device described in Patent Document 1 includes a range sensor that irradiates a laser beam and measures the distance from the reflected light of the irradiated laser beam to a surrounding object, and the distance data measured by the range sensor. , coordinate transformation to a group of observation points by reflected light reflected from the front surface of the pallet, extract a straight line resulting from scanning the front surface of the pallet from the group of observation points, and based on the group of observation points and the straight line, and an arithmetic device for identifying the center position of the front surface.

JP 2017-178567 A

In the prior art described above, the position of the pallet is recognized by specifying the center position of the front surface of the pallet using the group of observation points based on the light reflected from the front surface of the pallet. However, the plurality of observation points forming the observation point group contain variations due to, for example, sensor errors. Therefore, it is difficult to precisely recognize the position of the pallet, which is the object to be recognized.

SUMMARY OF THE INVENTION An object of the present invention is to provide a recognition device capable of recognizing the position of an object to be recognized with high accuracy.

One aspect of the present invention is a recognition device that recognizes a recognition target existing in a traveling direction of a moving body, the detection unit being provided in the moving body and configured to detect the distance and angle of the recognition target with respect to the moving body; A point cloud acquisition unit that acquires a detection point cloud corresponding to the front surface of the recognition target based on detection data from the detection unit, and a point cloud acquisition unit that acquires the front surface of the recognition target based on the detection point cloud acquired by the point cloud acquisition unit. A straight line calculation unit that calculates a straight line that represents a straight line, a point cloud correction unit that corrects the detected point cloud acquired by the point cloud acquisition unit using the straight line calculated by the straight line calculation unit, and a point cloud corrected by the point cloud correction unit a position recognizing unit for recognizing the position of the object to be recognized based on the detected point cloud; The detection point cloud is corrected by projecting in the angular direction where the detection unit is positioned on the straight line calculated by the unit.

In such a recognition device, the detection unit detects the distance and angle of the object to be recognized with respect to the moving object, and based on the detection data of the detection unit, a detection point group corresponding to the front surface of the object to be recognized is acquired. Then, a straight line representing the front surface of the recognition object is calculated based on the detection point group, and the detection point group is corrected using the straight line. Then, the position of the recognition target object is recognized using the corrected detection point group. Here, the positions of the plurality of detection points forming the detection point group may shift due to, for example, detection errors of the detection unit. Therefore, each detection point is corrected to an appropriate position by projecting a plurality of detection points forming a detection point group in the angular direction in which the detection unit is positioned on a straight line. As a result, the position of the object to be recognized is recognized with high accuracy.

The moving body may be a forklift, and the recognition target may be a pallet provided with a fork accommodating portion into which the forks of the forklift are inserted.

In such a configuration, the pallet is provided with a fork accommodating portion into which the fork of the forklift is inserted. For this reason, the detection data of the distance of the pallet to the forklift tends to deviate, and as a result, the positions of the plurality of detection points forming the detection point group tend to shift. Therefore, each detection point is corrected to an appropriate position by projecting a plurality of detection points forming a detection point group in the angular direction in which the detection unit is positioned on a straight line. As a result, the position of the pallet can be recognized with high accuracy.

The recognition device extracts a plurality of end points along the width direction of the pallet corresponding to the direction perpendicular to the inserting direction of the fork, from among the plurality of detection points forming the detection point cloud acquired by the point cloud acquisition unit. Further comprising an extraction unit, the plurality of endpoints include a detection point located at the end of the front surface of the pallet and a detection point located at the boundary between the front surface of the pallet and the fork housing unit, and the point group correction unit includes: A plurality of endpoints may be projected on a straight line in the angular direction where the detector is located.

In such a configuration, among the plurality of detection points forming the detection point group, only the plurality of end points along the width direction of the pallet are projected onto the straight line. Therefore, it is possible to simplify the correction processing of the detected point group.

The position recognition unit may calculate the center position of the front surface of the pallet based on the detected point group corrected by the point group correction unit.

In such a configuration, each endpoint is corrected to an appropriate position by projecting the plurality of endpoints on a straight line in the angular direction in which the detection unit is positioned. Therefore, the center position of the front face of the pallet can be accurately calculated from the plurality of end points.

According to the present invention, the position of a recognition target can be recognized with high accuracy.

1 is a block diagram schematically showing the configuration of an automatic cruise control device provided with a recognition device according to one embodiment of the present invention; FIG. 1 is a side view of a reach-type forklift equipped with an automatic travel control device; FIG. FIG. 4 is a perspective view of a pallet recognized by a recognition device; FIG. 4 is a schematic plan view showing how laser light is emitted from a laser sensor toward a pallet; It is a figure which shows an example of the straight line calculated by the detection point group and straight line calculation part which are acquired by a point cloud acquisition part. 5 is a flowchart showing a procedure of straight line calculation processing executed by a straight line calculation unit; FIG. 10 is a diagram showing how RANSAC is used to extract a straight line near the front surface of the pallet from a plurality of detection points forming a detection point group; FIG. 10 is a diagram showing how a straight line with a minimum error is extracted from a plurality of detection points existing near a straight line extracted by RANSAC using the least squares method. FIG. 6 is a diagram showing how endpoints are extracted from a plurality of detection points forming the detection point group shown in FIG. 5; FIG. 4 is a cross-sectional view showing positions where laser light emitted from a laser sensor hits the pallet and detection points necessary for recognizing the pallet; FIG. 5 is a diagram showing how a plurality of end points among a plurality of detection points forming a detection point group are projected onto a straight line by a point group correction unit; FIG. 11 is a front view showing a method of calculating the center position of the front surface of the pallet by the position recognition unit; 4 is a schematic plan view showing a travel route generated by a route generation unit; FIG. FIG. 4 is a cross-sectional view showing an example in which erroneous detection points are obtained by a laser sensor because a laser beam emitted from a laser sensor hits two spots on a pallet; FIG. 10 is a cross-sectional view showing a comparison between how end points are projected onto a straight line in the optical axis direction of a laser beam and how the end points are projected vertically onto a straight line in a point group correction unit;

BEST MODE FOR CARRYING OUT THE INVENTION Hereinafter, embodiments of the present invention will be described in detail with reference to the drawings.

FIG. 1 is a block diagram schematically showing the configuration of an automatic cruise control system equipped with a recognition device according to one embodiment of the present invention. In FIG. 1, an automatic travel control device 1 is mounted on a reach-type forklift 2 (moving body) as shown in FIG.

The forklift 2 includes a vehicle body 3, a pair of left and right legs 4 (see FIG. 4) arranged on the front side of the vehicle body 3, a mast 5 arranged between the legs 4 and movable in the front-rear direction, and the mast 5. A pair of left and right forks 6 (see FIG. 4) attached so as to be able to move up and down, a front wheel 7 provided at the tip of each leg 4, and a rear wheel 8 provided at the lower left side of the vehicle body 3. , and a caster wheel 9 disposed on the lower right side of the vehicle body 3 . The fork 6 is a cargo handling member for lifting the pallet 10 (see FIG. 3). The vehicle body 3 has a driver's seat 11 and a head guard 12 arranged above the driver's seat 11 .

The pallet 10 is a flat pallet having a square shape in plan view as shown in FIG. The pallet 10 is a loading platform for loading cargo. The pallet 10 has a front surface 10a, a rear surface 10b facing the front surface 10a in the front-rear direction (X direction), and two side surfaces 10c perpendicular to the front surface 10a and the rear surface 10b and facing in the left-right direction (Y direction). are doing. The front surface 10a faces the forklift 2 when the forks 6 of the forklift 2 lift the pallet 10 .

The pallet 10 is provided with fork pockets 13 and 14 (fork accommodating portions) into which the respective forks 6 are inserted. Two fork pockets 13 and 14 are provided on each pallet 10 . The fork pocket 13 extends in the longitudinal direction from the front surface 10a of the pallet 10 to the rear surface 10b. The fork pocket 14 extends laterally from one side surface 10c of the pallet 10 to the other side surface 10c. The fork pockets 13, 14 cross each other vertically. The shape of the fork pockets 13 and 14 is rectangular when viewed from the front. Note that the pallet 10 may not be provided with the fork pockets 14 .

The front-rear direction of the pallet 10 is the front-rear direction when viewed from the forklift 2 positioned on the front surface 10 a side of the pallet 10 . The front-rear direction of the pallet 10 corresponds to the insertion direction of the forks 6 in the pallet 10 . The left-right direction of the pallet 10 is the left-right direction when viewed from the forklift 2 located on the front surface 10 a side of the pallet 10 . The horizontal direction of the pallet 10 is the width direction of the pallet 10 and corresponds to the direction perpendicular to the inserting direction of the fork 6 .

Returning to FIG. 1 , the automatic travel control device 1 is a device that automatically travels the forklift 2 to the front of the pallet 10 . The automatic cruise control device 1 includes laser sensors 15 and 16 , a driving section 17 and a controller 18 .

The laser sensor 15 is provided on the upper part of the forklift 2, as shown in FIG. The laser sensor 15 is attached to the front end of the head guard 12, for example. The laser sensor 15 detects an object existing around the forklift 2 by irradiating a laser beam around the forklift 2 and receiving reflected light of the laser beam. The objects are walls, pillars, etc., and are registered in map data (described later). A laser range finder, for example, is used as the laser sensor 15 . The laser light emitted from the laser sensor 15 may be a 2D laser or a 3D laser.

The laser sensor 15 irradiates the periphery of the forklift 2 with laser light in a fan shape. Specifically, the laser sensor 15 irradiates a laser beam in a prescribed angular range centered on the straight forward direction of the forklift 2 . A laser beam emitted from the laser sensor 15 hits an object, and the laser beam reflected by the object is received by the laser sensor 15 . A laser sensor 15 detects the distance and angle of the object with respect to the forklift 2 . The distance and angle of the object with respect to the forklift 2 can be detected from the position and angle at which the laser beam emitted from the laser sensor 15 hits the object.

The laser sensor 16 is provided below the forklift 2, as shown in FIG. The laser sensor 16 is attached, for example, to the tip (front end) of one leg 4 . The laser sensor 16 is a detection unit that detects the distance and angle of the pallet 10 with respect to the forklift 2 by irradiating the pallet 10 in front of the forklift 2 with laser light and receiving the laser light reflected by the pallet 10 . . The distance and angle of the pallet 10 with respect to the forklift 2 can be detected from the position and angle at which the laser beam emitted from the laser sensor 16 hits the pallet 10 .

As shown in FIG. 4, the laser sensor 16 irradiates the periphery of the forklift truck 2 with laser light in a fan shape. Specifically, the laser sensor 16 irradiates a laser beam in a prescribed angular range centered on the forward straight traveling direction of the forklift 2 . As the laser sensor 16, a laser range finder is used like the laser sensor 15, for example. A 2D laser is used as the laser emitted from the laser sensor 16 .

Although not shown, the drive unit 17 has, for example, a travel motor that rotates the rear wheels 8 that are driving wheels, and a steering motor that steers the rear wheels 8 that are steering wheels.

The controller 18 is composed of a CPU, RAM, ROM, input/output interfaces, and the like. The controller 18 includes a self-position estimation unit 20, a point group acquisition unit 21, a straight line calculation unit 22, an end point extraction unit 23, a point group correction unit 24, a position recognition unit 25, a route generation unit 26, and a driving unit. and a control unit 27 .

Here, the laser sensor 16, the point group acquisition unit 21, the straight line calculation unit 22, the end point extraction unit 23, the point group correction unit 24, and the position recognition unit 25 constitute a recognition device 28 of this embodiment. The recognition device 28 is a device that recognizes the pallet 10, which is the object to be recognized, existing in the traveling direction of the forklift 2. As shown in FIG.

The self-position estimation unit 20 estimates the self-position of the forklift 2 using the detection data of the laser sensor 15 and the map data of the surrounding environment of the forklift 2 . The self-position estimation unit 20 estimates the self-position of the forklift 2 using a SLAM (simultaneous localization and mapping) technique. SLAM is a self-localization technique that uses sensor data and map data to estimate self-localization. SLAM uses a laser sensor or the like to simultaneously estimate its own position and create an environment map.

Specifically, the self-position estimating unit 20 matches the detection data of the laser sensor 15 with the map data of the surrounding environment of the forklift 2 to estimate the self-position of the forklift 2 . The self-position of the forklift 2 is represented by position coordinates (XY coordinates) and orientation (angle).

The point group acquisition unit 21 acquires a detection point group corresponding to the front surface 10 a of the pallet 10 based on the detection data of the laser sensor 16 . A detection point group is composed of a plurality of detection points. A detection point is a point (reflection point) at which the laser beam emitted from the laser sensor 16 hits the pallet 10 . A detection point is represented by position coordinates (XY coordinates).

At this time, in the fork pocket 13 of the pallet 10 , the laser beam hits a position on the far side of the pallet 10 (a position farther from the laser sensor 16 ) than the front face 10 a of the pallet 10 . Therefore, as shown in FIG. 5A, a detection point group Pg is obtained in which the density of detection points P1 generated on the front surface 10a of the pallet 10 is higher than the density of detection points P2 generated on the fork pocket 13. be done.

The straight line calculator 22 calculates a straight line representing the front surface 10 a of the pallet 10 based on the detected point group acquired by the point group acquirer 21 . A straight line representing the front surface 10a of the pallet 10 is a line extending in the left-right direction of the pallet 10 . At this time, as shown in FIG. 5(b), a straight line S is calculated such that the error of each detection point P constituting the detection point group Pg is minimized.

FIG. 6 is a flowchart showing the procedure of straight line calculation processing executed by the straight line calculation unit 22. As shown in FIG. In FIG. 6, the straight line calculator 22 first uses RANSAC (Random Sample Consensus) to extract a straight line close to the front surface 10a of the pallet 10 from a plurality of detection points forming a detection point group (step S101).

RANSAC is a technique for extracting straight lines from a point group. Specifically, RANSAC sets a straight line connecting any two points in a point group, obtains the number of points existing in the vicinity of the straight line, and extracts the straight line with the largest number of points existing in the vicinity.

For example, in a detection point group Pg as shown in FIG. The number of detection points Ps existing near the straight line S1 connecting the two detection points Ps selected in FIG. The number of detection points Ps present in the vicinity of the straight line S1 connecting the two detection points Ps selected in FIG. 7C is even greater. Therefore, as shown in FIG. 8A, the straight line S1 connecting the two detection points Ps selected in FIG.

Subsequently, the straight line calculator 22 uses the least squares method to extract a straight line that minimizes the error from a plurality of detection points existing near the straight line extracted by RANSAC (step S102). Specifically, the straight line calculator 22 extracts a straight line that minimizes the sum of distances to all detection points existing near the straight line extracted by RANSAC.

For example, as shown in FIG. 8(a), when the least squares method is applied to a plurality of detection points P existing near the straight line S2 extracted by RANSAC, the result shown in FIG. 8(b) Thus, a straight line S closer to the front surface 10a of the pallet 10 than the straight line S2 (see the two-dot chain line) extracted by RANSAC is obtained.

The endpoint extraction unit 23 extracts a plurality of endpoints along the left-right direction (width direction) of the pallet 10 from among the plurality of detection points forming the detection point group acquired by the point cloud acquisition unit 21 . Here, the plurality of end points include detection points located at the ends of the front surface 10 a of the pallet 10 and detection points located at the boundary between the front surface 10 a of the pallet 10 and the fork pockets 13 .

Specifically, as the plurality of end points Pt, as shown in FIG. 9, end points Pt1 located at both ends of the front surface 10a of the pallet 10 and edges of the fork pockets 13 on the front surface 10a of the pallet 10 on the left-right direction outer side of the fork pocket 13 and an end point Pt3 positioned at a boundary point between the front surface 10a of the pallet 10 and the inner edge of the fork pocket 13 in the left-right direction. Adjacent end points Pt are separated from each other.

The point cloud correction unit 24 corrects the detection point cloud acquired by the point cloud acquisition unit 21 using the straight line calculated by the straight line calculation unit 22 . The point cloud correction unit 24 calculates the plurality of endpoints extracted by the endpoint extraction unit 23 from among the plurality of detection points forming the detection point cloud acquired by the point cloud acquisition unit 21 and the straight line calculation unit 22. The detected point cloud is corrected by projecting it onto a straight line.

Here, when the laser beam irradiated from the laser sensor 16 reaches the fork pocket 13 of the pallet 10, the laser beam is positioned behind the front surface 10a of the pallet 10 as shown in FIG. 10(a). The light hits the inner wall surface of the pallet 10 and is reflected. At this time, the position of the obtained detection point P is the inner wall surface of the pallet 10 which is farther from the laser sensor 16 than the front surface 10 a of the pallet 10 . However, the detection point P necessary for recognizing the position of the pallet 10 is the point located on the front surface 10a of the pallet 10, as shown in FIG. 10(b). Therefore, it is necessary to correct the detected point cloud acquired by the point cloud acquisition unit 21 .

Therefore, the point group correction unit 24 aligns a plurality of end points of the plurality of detection points forming the detection point group on the straight line calculated by the straight line calculation unit 22 in the optical axis direction of the laser light emitted from the laser sensor 16. The detected point cloud is corrected by projecting to . The optical axis direction of the laser light corresponds to the angular direction in which the laser sensor 16 is positioned when viewed from the end point (detection point). That is, the plurality of endpoints are projected onto the straight line calculated by the straight line calculator 22 along a virtual line that linearly connects the laser sensor 16 and the endpoints.

As a result, as shown in FIG. 11, even if the plurality of endpoints Pt extracted by the endpoint extractor 23 do not exist on the straight line S calculated by the straight line calculator 22, the plurality of endpoints Pt are located on the straight line S. It is projected upward in the direction of the optical axis of the laser beam. That is, the plurality of end points Pt are positioned on the straight line S representing the front surface 10a of the pallet 10. As shown in FIG.

The position recognition section 25 recognizes the position of the pallet 10 based on the detected point group corrected by the point group correction section 24 . Specifically, the position recognizing unit 25 calculates the center position of the front surface 10 a of the pallet 10 based on the plurality of end points projected onto the straight line calculated by the straight line calculating unit 22 . The center position of the front surface 10a of the pallet 10 is the center position of the front surface 10a of the pallet 10 in the left-right direction (width direction).

At this time, as shown in FIG. 12, the average value of the center point A between the two end points Pt1, the center point B between the two end points Pt2, and the center point C between the two end points Pt3 is calculated. . Then, the average value of the center points A to C is obtained as the center position G of the front surface 10a of the pallet 10. FIG.

The average value of two of the center points A to C may be used as the center position G of the front surface 10a of the pallet 10, or any one of the center points A to C may be used as the center position G of the front surface 10a of the pallet 10. good.

Based on the self-position of the forklift 2 estimated by the self-position estimation unit 20 and the center position of the front surface 10a of the pallet 10 calculated by the position recognition unit 25, the route generation unit 26 generates a path from the forklift 2 to the front of the pallet 10. to generate a travel route R of For example, as shown in FIG. 13 , the travel route R is a route that allows the forks 6 of the forklift 2 to be inserted into the fork pockets 13 in front of the central portion of the pallet 10 in the left-right direction.

The drive control unit 27 controls the drive unit 17 so that the forklift 2 travels toward the pallet 10 according to the travel route R generated by the route generation unit 26 .

By the way, as shown in FIG. 14, the laser light emitted from the laser sensor 16 has a beam H. As shown in FIG. The light beam H is the width of the laser beam. For this reason, the laser beam emitted from the laser sensor 16 may hit two points, the front surface 10 a of the pallet 10 and the inner wall surface of the pallet 10 forming the fork pocket 13 . In this case, the detection points obtained by the laser sensor 16 are not the point F1 where the laser beam hits the front surface 10a of the pallet 10 and the point F2 where the laser beam hits the inner wall surface of the pallet 10, but the points between the points F1 and F2. An arbitrary point F on the optical axis of the laser beam is erroneously detected. Further, the detection error of the laser sensor 16 itself can also be a factor causing the position of the detection point obtained by the laser sensor 16 to shift.

Therefore, when correcting the detection point group by the point group correction unit 24, as shown in FIG. It is conceivable to project perpendicularly onto the straight line S. However, in this case, since the end point Pt projected onto the straight line S is not on the optical axis of the laser beam, the position of the end point Pt is shifted in the horizontal direction of the pallet 10 . Therefore, the center position G of the front surface 10a of the pallet 10 cannot be calculated correctly. As a result, when the fork 6 of the forklift 2 is inserted into the fork pocket 13 of the pallet 10 , the fork 6 interferes with the pallet 10 .

In order to deal with such a problem, in the present embodiment, as shown in FIG. It is projected in the optical axis direction of the laser light emitted from the sensor 16 . Therefore, the end point Pt is corrected to an appropriate position on the optical axis of the laser beam. Thereby, the center position G of the front surface 10a of the pallet 10 can be calculated correctly.

As described above, according to this embodiment, the distance and angle of the pallet 10 with respect to the forklift 2 are detected by the laser sensor 16, and based on the detection data of the laser sensor 16, the detection point group corresponding to the front surface 10a of the pallet 10 is detected. is obtained. Then, a straight line representing the front surface 10a of the pallet 10 is calculated based on the detected point group, and the detected point group is corrected using the straight line. Then, the position of the pallet 10 is recognized using the corrected detection point group. Here, the positions of the plurality of detection points forming the detection point group may shift due to, for example, detection errors of the laser sensor 16 . Further, since the pallet 10 is provided with a fork pocket 13, the detection data of the distance of the pallet 10 from the forklift 2 tends to deviate. easier. Therefore, each detection point is corrected to an appropriate position by projecting a plurality of detection points forming a detection point group on a straight line in the angular direction in which the laser sensor 16 is positioned. Thereby, the position of the pallet 10 is recognized with high accuracy.

Further, in the present embodiment, a plurality of end points along the left-right direction of the pallet 10 are extracted from among the plurality of detection points forming the detection point group. Only a plurality of end points of the plurality of detection points are projected onto the straight line. Therefore, it is possible to simplify the correction processing of the detected point group.

Further, in the present embodiment, the center position of the front surface 10a of the pallet 10 is calculated based on the corrected detection point group. At this time, each endpoint is corrected to an appropriate position by projecting the plurality of endpoints on the straight line in the angular direction where the laser sensor 16 is positioned. Therefore, the central position of the front surface 10a of the pallet 10 can be accurately calculated from the plurality of end points. This prevents the forks 6 from interfering with the pallet 10 when the forks 6 of the forklift 2 are inserted into the fork pockets 13 of the pallet 10 .

In addition, this invention is not limited to the said embodiment. For example, in the above-described embodiment, a straight line representing the front surface 10a of the pallet 10 is calculated from the detected point group using RANSAC and the method of least squares, but the method is not particularly limited to such a form. For example, the straight line representing the front surface 10a of the pallet 10 may be calculated using only RANSAC, or the straight line representing the front surface 10a of the pallet 10 may be calculated using only the least squares method.

Further, in the above embodiment, a plurality of end points along the left-right direction of the pallet 10 are extracted from the plurality of detection points forming the detection point group, and the plurality of end points are aligned on a straight line by the laser beam emitted by the laser sensor 16. Although the detected point group is corrected by projecting in the axial direction, it is not particularly limited to such a form. For example, by projecting a plurality of detection points forming the detection point group on a straight line in the optical axis direction of the laser beam from the laser sensor 16, the detection point group is corrected, and then a plurality of detection points forming the corrected detection point group are projected. , a plurality of end points along the horizontal direction of the pallet 10 may be extracted.

In the above embodiment, the distance and angle of the pallet 10 with respect to the forklift 2 are detected by the laser sensor 16 that emits laser light. may be used to detect the distance and angle of the pallet 10 relative to the forklift 2 .

In the above embodiment, the pallet 10 is a flat pallet, and the center position of the front surface 10a of the pallet 10 is calculated. Any pallet having a fork receiving portion to be inserted may be used. Such a pallet may be, for example, a mesh pallet having at least one pair of legs.

In the above embodiment, the position of the pallet 10 scooped up by the forklift 2 is recognized. It can be an object. In this case, the present invention is not limited to recognizing the center position of the front surface of the recognition target object, and can be applied to, for example, recognizing edges and corners of the front surface of the recognition target object.

In the above embodiment, the position of the pallet 10 in front of the forklift 2 is recognized when the forklift 2 moves forward toward the pallet 10. It can also be applied to the case of recognizing the position of a recognition object that exists behind.

2... Forklift (moving body), 6... Fork, 10... Pallet (recognition target object), 10a... Front surface, 13... Fork pocket (fork storage part), 16... Laser sensor (detection part), 21... Point cloud acquisition part , 22... straight line calculation unit, 23... end point extraction unit, 24... point group correction unit, 25... position recognition unit, 28... recognition device, Pg... detection point group, P... detection point, Pt... end point, S... straight line, G...Center position.

Claims (4)

A recognition device for recognizing a recognition target existing in a moving direction of a moving object,
a detection unit provided in the moving body for detecting the distance and angle of the recognition target object with respect to the moving body;
a point cloud acquisition unit that acquires a detection point cloud corresponding to the front surface of the recognition target based on the detection data of the detection unit;
a straight line calculation unit that calculates a straight line representing the front surface of the recognition target based on the detection point cloud acquired by the point cloud acquisition unit;
a point cloud correction unit that corrects the detected point cloud acquired by the point cloud acquisition unit using the straight line calculated by the straight line calculation unit;
a position recognition unit that recognizes the position of the recognition target based on the detection point cloud corrected by the point cloud correction unit;
The point cloud correction unit projects a plurality of detection points forming the detection point cloud acquired by the point cloud acquisition unit in an angular direction in which the detection unit is positioned on the straight line calculated by the straight line calculation unit. A recognition device that corrects the detected point group by The moving body is a forklift,
2. The recognition device according to claim 1, wherein the object to be recognized is a pallet provided with a fork accommodating portion into which a fork of the forklift is inserted. End points for extracting a plurality of end points along the width direction of the pallet corresponding to a direction perpendicular to the inserting direction of the fork, from among the plurality of detection points forming the detection point group acquired by the point cloud acquisition unit. further comprising an extractor,
The plurality of end points include a detection point located at the end of the front surface of the pallet and a detection point located at the boundary between the front surface of the pallet and the fork housing,
3. The recognition device according to claim 2, wherein the point group correction unit projects the plurality of end points onto the straight line in an angular direction in which the detection unit is positioned. 4. The recognition device according to claim 3, wherein the position recognition unit calculates the center position of the front surface of the pallet based on the detected point group corrected by the point group correction unit.

Images