Movable body

The movable object uses guide lines and marker-based image processing to overcome positioning challenges in dynamic environments, ensuring accurate self-localization and navigation.

JP2024168090APending Publication Date: 2024-12-05DAIHEN CORP
View PDF 1 Cites 0 Cited by

Patent Information

Application Number
JP2023084498
Authority / Receiving Office
JP · JP
Patent Type
Applications
Current Assignee / Owner
Filing Date
2023-05-23
Publication Date
2024-12-05

AI Technical Summary

Technical Problem

In dynamic environments like factories, conventional SLAM and GPS methods struggle to accurately estimate the self-position of mobile objects due to frequent layout changes and indoor obstructions.

Method used

A movable object that follows visually recognizable guide lines on the floor, utilizing markers with stored position and direction information, combined with image processing and detection techniques to determine its position and orientation, and a movement mechanism to navigate along the guide lines.

Benefits of technology

Enables accurate self-positioning of the mobile object within a building by leveraging markers and image processing, allowing precise navigation along guide lines.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 2024168090000001_ABST
    Figure 2024168090000001_ABST
Patent Text Reader

Abstract

To acquire a self-position of a movable body in a building.SOLUTION: A movable body 1 comprises: a storage unit 11 that stores, for each of a plurality of markers arranged on guidance lines on a floor face, marker information including a position and a direction of the marker; an image acquisition unit 12 that acquires a photographed image of the front of the movable body 1; an image conversion unit 13 that converts the photographed image into a plane image of the photographed image seen from above; a detection unit 14 that detects the guidance lines in the plane image and detects the markers on the detected guidance lines; a first self-position acquisition unit 15 that acquires a self-position of the movable body 1 by using the marker information corresponding to the detected marker and the position and direction of the marker in the plane image; a moving mechanism 17; and a movement control unit 18 that controls the moving mechanism 17 to move the movable body 1 along the guidance line, and controls the moving mechanism 17 by using the self-position. Consequently, the movable body can appropriately acquire its self-position even in a building, such as in a factory.SELECTED DRAWING: Figure 1
Need to check novelty before this filing date? Find Prior Art

Description

[Technical field]

[0001] The present invention relates to a moving object that moves along a visually recognizable guide line provided on a floor surface. [Background technology]

[0002] Conventionally, in an automatic guided vehicle or the like, the self-location is estimated using SLAM (Simultaneous Localization and Mapping) (see, for example, Patent Document 1). In a moving environment in which the layout does not change much, the self-location can be appropriately estimated by using SLAM. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Patent Publication No. 2021-047671 Summary of the Invention [Problem to be solved by the invention]

[0004] On the other hand, in mobile environments where the layout changes frequently, such as factories, there is a problem that the accuracy of self-location decreases when estimating self-location using SLAM. In addition, it is difficult to estimate location using GPS (Global Positioning System) inside buildings such as factories. Therefore, a new method to acquire the self-location of a mobile object inside buildings such as factories has been desired.

[0005] The present invention has been made to solve the above-mentioned problems, and has an object to provide a moving body that is capable of acquiring its own position within a building such as a factory. [Means for solving the problem]

[0006] In order to achieve the above-mentioned object, a moving body according to one embodiment of the present invention is a moving body that moves along a visually recognizable guiding line provided on a floor surface, and is equipped with a memory unit that stores marker information including the position and direction of a plurality of markers whose orientation can be identified and that are arranged on the guiding line, an image acquisition unit that acquires a captured image of the area in front of the moving body, an image conversion unit that converts the captured image into a planar image viewed from above, a detection unit that detects the guiding line in the planar image and detects markers on the detected guiding line, a first self-position acquisition unit that acquires a first self-position of the moving body using marker information corresponding to the marker detected by the detection unit and the position and orientation of the marker in the planar image, a moving mechanism that moves the moving body, and a moving control unit that controls the moving mechanism using the first self-position so that the moving body moves along the guiding line. Effect of the Invention

[0007] According to a moving body according to one aspect of the present invention, it becomes possible to acquire the self-position of the moving body by using markers arranged on a visually recognizable guiding line provided on a floor surface. [Brief description of the drawings]

[0008] [Figure 1] FIG. 2 is a block diagram showing the configuration of a moving body according to an embodiment of the present invention; [Figure 2A] FIG. 13 shows an example of a marker in the embodiment. [Figure 2B] FIG. 13 shows another example of the marker in the embodiment. [Diagram 3] FIG. 2 is a plan view showing a moving area of ​​a moving body in the embodiment; [Figure 4A] FIG. 13 is a diagram showing an example of marker information in the embodiment; [Figure 4B] FIG. 2 is a diagram showing an example of a marker identifier and marker information according to the embodiment; [Diagram 5] FIG. 13 shows an example of a captured image in the embodiment. [Figure 6] FIG. 2 shows an example of a planar image in the embodiment. [Figure 7] A flowchart showing the operation of a moving body according to the embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0009] The moving body according to the present invention will be described below using an embodiment. In the following embodiments, components and steps with the same reference numerals are the same or equivalent, and repeated description may be omitted. The moving body according to this embodiment moves along a visually recognizable guiding line provided on the floor surface, and acquires its own position using a marker placed on the guiding line.

[0010] 1 is a block diagram showing the configuration of a moving body 1 according to this embodiment. The moving body 1 according to this embodiment moves along a visually recognizable guide line provided on a floor surface, and includes a storage unit 11, an image acquisition unit 12, an image conversion unit 13, a detection unit 14, a first self-position acquisition unit 15, a second self-position acquisition unit 16, a movement mechanism 17, and a movement control unit 18. The use of the moving body 1 is not particularly limited, and the moving body 1 may be, for example, a moving body that performs transportation, or may be a moving body for other uses such as security and cleaning.

[0011] Guiding lines are provided on the floor surface of the moving environment of the moving body 1. The floor surface of the moving environment is usually preferably horizontal. The guiding lines may be provided, for example, to guide the moving body 1, or may be used for other purposes, such as dividing lines for dividing a passageway for people or a driving area for a forklift. The guiding lines may be, for example, tape-like such as vinyl tape attached to the floor surface, or may be provided by applying paint to the floor surface. The guiding lines are preferably lines of a certain width, for example. The guiding lines are visually recognizable. That is, the guiding lines are detectable in an image. The guiding lines are preferably a color different from that of the floor surface in order to be visually recognizable. The guiding lines may be, for example, straight lines or curved lines. In this embodiment, the case where the guiding lines are straight lines will be mainly described.

[0012] It is assumed that a plurality of markers are arranged on the guiding line. The markers arranged on the guiding line may mean, for example, that at least a part of the marker is present on the guiding line. The plurality of markers may be, for example, all the same markers, or may be different markers. In this embodiment, the former case will be mainly described, and the latter case will be described later. It is preferable that the markers have a predetermined shape. This is to enable the markers to be detected in a planar image to be described later. As will be described later, when the markers are detected by the Hough transform, the markers may be, for example, circular. In addition, the markers are capable of specifying the direction. The markers may be capable of specifying the direction by the shape of the marker, such as an arrow shape, may have a plurality of regions, and the direction may be specified using a specific position of the region, such as a center of gravity, or may include a figure indicating the direction, such as an arrow.

[0013] In this embodiment, a case where the marker 3 shown in FIG. 2A is used will be mainly described. The marker 3 shown in FIG. 2A is circular and divided into two semicircular regions 3a and 3b by a straight line passing through the center. For example, the region 3a may be blue and the region 3b may be white. Also, for example, the direction of a vector starting from the center of the circular marker 3 and ending at the center of gravity of the region 3a may be the direction of the marker 3. FIG. 3 is a plan view showing an example of a situation in a factory where the marker 3 is placed on a guide line 5. In FIG. 3, the guide line 5 is a demarcation line for demarcating a passage for people near an object 7 in the factory from a driving area for a forklift.

[0014] The storage unit 11 stores a plurality of pieces of marker information. The plurality of pieces of marker information correspond to a plurality of markers arranged on the guiding line, respectively. The marker information is information including the position and direction of the marker corresponding to the marker information. The position may be, for example, a coordinate value in the moving area of ​​the moving body 1. In this embodiment, the case where this position is a position in the world coordinate system will be mainly described. The world coordinate system may be, for example, a coordinate system in the moving area of ​​the moving body 1 (for example, a factory, etc.). The direction may be, for example, a direction based on a reference direction (for example, the north direction). This direction may be indicated by, for example, an azimuth angle. The storage unit 11 may store marker information including a coordinate value in the world coordinate system indicating the position of the marker and an azimuth angle indicating the direction of the marker, as shown in, for example, FIG. 4A. For example, the first marker information shown in FIG. 4A indicates that the coordinate value and azimuth angle of the marker are (X11, Y11) and θ11, respectively.

[0015] The process by which information is stored in the storage unit 11 is not important. For example, information may be stored in the storage unit 11 via a recording medium, information transmitted via a communication line or the like may be stored in the storage unit 11, or information inputted via an input device may be stored in the storage unit 11. The storage unit 11 is preferably realized by a non-volatile recording medium, but may also be realized by a volatile recording medium. The recording medium may be, for example, a semiconductor memory, a magnetic disk, an optical disk, or the like.

[0016] The image acquisition unit 12 acquires a captured image of the area in front of the moving object 1. The image acquisition unit 12 may be, for example, an optical device such as a camera that captures an image, or may acquire an image captured by an optical device such as a camera. In this embodiment, a case where the image acquisition unit 12 is a camera will be mainly described. The captured image may be, for example, a color image, or a black and white or grayscale image. When at least one of the guiding line and the marker has a color other than black and white, it is preferable that the captured image is a color image. It is preferable that the image acquisition unit 12 repeats acquisition of the captured image. The image acquisition unit 12 may, for example, repeatedly acquire the captured image periodically or irregularly. The image acquisition unit 12 may also acquire, for example, a video. In this case, one frame constituting the video may be considered to be a captured image.

[0017] The optical axis of the camera for capturing the captured image is preferably usually directed forward in the traveling direction of the moving body 1. The optical axis may extend, for example, horizontally, or may be directed toward the floor so that the depression angle is a positive value. Even in the latter case, it is preferable that the captured image also includes distant areas in the traveling direction. This is to enable detection of markers in distant positions. FIG. 5 is a diagram showing an example of a captured image captured when the moving body 1 is in the position shown in FIG. 3. As shown in FIG. 5, the captured image is an image with perspective.

[0018] The image conversion unit 13 converts the photographed image acquired by the image acquisition unit 12 into a planar image viewed from above. The planar image may be, for example, an image viewed in a direction perpendicular to the floor surface, for example, in the vertical direction. The image conversion unit 13 may convert the photographed image into a planar image by homography conversion, for example. Note that a method for converting a photographed image into a planar image is well known, and detailed description thereof will be omitted. FIG. 6 is a diagram showing an example of a planar image obtained by converting the photographed image shown in FIG. 5. As shown in FIG. 6, the planar image becomes an image without perspective. The image conversion unit 13 may convert each of the photographed images acquired repeatedly into a planar image, for example.

[0019] The detection unit 14 detects the guiding line in the planar image acquired by the image conversion unit 13. The detection unit 14 also detects a marker on the detected guiding line. The detection unit 14 may detect the guiding line by a Hough transform in the planar image, for example. For example, when the guiding line is a straight line, the detection unit 14 may perform a Hough transform to detect the straight line. The detection unit 14 may perform a thinning process on the planar image and then perform a Hough transform. This is because a guiding line is usually a line having a width, and a thinner line is more suitable for detection by a Hough transform than a line having a width. The thinning process may be, for example, an image process in which a line having a width is thinned by narrowing the line width, or may be edge detection. As the former thinning process, for example, algorithms such as Tamura, Hilditch, and Zhang-Suen, which thin an image after binarizing it, are known. In the latter edge detection, the edges on both sides of the width direction of the guiding line are usually detected, but edge detection may be performed so that only one edge is left, for example. In order to retain only one edge, for example, when detecting an edge using a differential value such as a brightness value, only pixels whose differential value is greater than a positive threshold value may be detected as edges, and pixels whose differential value is less than a negative threshold value may not be detected as edges.

[0020] Also, when the captured image is a color image, the detection unit 14 may, for example, convert the color planar image into a grayscale image and then perform thinning processing and guiding line detection processing. When converting to a grayscale image, the detection unit 14 may, for example, convert to grayscale such that the color of the guiding line is a reference color, and the greater the difference between the color and the reference color, the greater the difference between the pixel value of the reference color. For example, when converting to 8-bit grayscale, the pixel value of the reference color may be set to 0, and the greater the difference between the color and the reference color, the closer the pixel value to 255. In this way, it becomes possible to more appropriately detect the guiding line in the converted grayscale planar image.

[0021] The detection unit 14 may detect the marker in the planar image by, for example, a Hough transform or by template matching. In the planar image, the resolution is lower in the area farther from the moving body 1. Therefore, in the Hough transform, it may be difficult to detect a marker located farther from the moving body 1, but in the case of template matching, a marker located farther from the moving body 1 can be more reliably detected. From this viewpoint, it is preferable to detect the marker by template matching. In addition, when the size of the marker is determined, the marker can be detected by using a template image of a predetermined size corresponding to the marker. In addition, since the marker is arranged on the guiding line, the detection unit 14 may detect the marker by template matching only within a predetermined range based on the detected guiding line. In the case where the marker has a color other than black and white, for example, even if the detection of the guiding line is performed using the above-mentioned grayscale image, the detection of the marker may be performed using a color planar image. Detecting the marker may mean, for example, identifying the position of the marker in the planar image. Furthermore, the detection unit 14 may also identify the orientation of the marker in addition to the position of the marker in the planar image.

[0022] The first self-location acquisition unit 15 acquires the first self-location of the moving object 1 using marker information corresponding to the marker detected by the detection unit 14 and the position and orientation of the marker in the planar image. The first self-location acquisition unit 15 may also specify the marker information corresponding to the detected marker using the second self-location. Note that the second self-location may be the self-location of the moving object 1 acquired by a method different from that of the first self-location acquisition unit 15, as described later.

[0023] For example, when the mounting position of the camera that captures the captured image in the moving body 1 and the angle of view of the camera are known, the first self-position acquisition unit 15 can acquire the relative positional relationship between the local coordinate system of the marker detected in the planar image and the local coordinate system of the moving body 1 by using the position and orientation of the detected marker in the planar image. The position and orientation of the detected marker in the planar image may be specified by the detection unit 14, for example, as described above. The relative positional relationship may be, for example, a homogeneous transformation matrix indicating the transformation between both local coordinate systems. In addition, the first self-position acquisition unit 15 can specify the position of the detected marker by using the relative positional relationship and the second self-position. For example, when the second self-position is a position in the world coordinate system, the first self-position acquisition unit 15 can specify the position of the detected marker in the world coordinate system. Then, the first self-position acquisition unit 15 can specify marker information corresponding to the detected marker by specifying marker information including a position closest to the specified position of the marker. In this way, the second self-location is used to identify marker information corresponding to the detected marker, and therefore may have lower accuracy than the first self-location. Note that, for example, the orientation of the detected marker may also be used to identify the marker information.

[0024] In addition, the first self-location acquisition unit 15 can acquire the first self-location of the moving body 1 by using the position and direction included in the specified marker information and the relative positional relationship between the local coordinate system of the marker detected in the planar image and the local coordinate system of the moving body 1. More specifically, the first self-location acquisition unit 15 can specify the relative positional relationship between the world coordinate system and the local coordinate system of the detected marker by the position and direction included in the specified marker information, and can specify the relative positional relationship between the world coordinate system and the local coordinate system of the moving body 1, that is, the position and orientation of the moving body 1 in the world coordinate system, by using the relative positional relationship and the relative positional relationship between the local coordinate system of the detected marker and the local coordinate system of the moving body 1. The position and orientation of the moving body 1 in the world coordinate system specified in this way may be the first self-location. Therefore, the first self-location may include not only the position of the moving body 1 but also its orientation. The orientation of the moving body 1 may be indicated by an angle based on a reference direction such as an azimuth angle.

[0025] In addition, when two or more markers are detected in the planar image, the first self-location acquisition unit 15 may acquire the first self-location using, for example, one specific marker, or may acquire the first self-location using each marker. In the former case, the first self-location may be acquired using the marker located closest to the moving body 1. In the latter case, the first self-location may be acquired by averaging a plurality of self-locations acquired using a plurality of markers. The average may be, for example, a simple average or a weighted average. In the latter case, the weight may be, for example, a weight that decreases as the distance from the moving body 1 to the marker increases.

[0026] The second self-location acquisition unit 16 acquires the second self-location of the moving object 1 by a method different from that of the first self-location acquisition unit 15. As described above, the second self-location may have a lower accuracy than the first self-location. The second self-location acquisition unit 16 may acquire the second self-location by, for example, odometry, wireless communication, measurement of the distance to a surrounding object, capturing an image of the surroundings, or other method of acquiring the self-location. As a method of acquiring the self-location by wireless communication, for example, a method using GPS, a method using indoor GPS, a method using the nearest wireless base station, and the like are known. In addition, as a method of acquiring the self-location by, for example, using the measurement of the distance to a surrounding object or capturing an image of the surroundings, for example, SLAM or the like may be used. In addition, the second self-location acquisition unit 16 may acquire the second self-location including the orientation of the moving object 1. For example, when the second self-location is acquired by odometry, the first self-location may be set as the second self-location when the first self-location is acquired. That is, the second self-location may be reset to the first self-location. This is because when the second self-location is acquired by odometry, the first self-location has higher accuracy than the second self-location. Then, in the planar image, from when a marker cannot be detected until the next marker is detected, the second self-location acquired by the second self-location acquisition unit 16 may be used for movement control.

[0027] The moving mechanism 17 moves the moving body 1. In this embodiment, the moving mechanism 17 is mainly described as a mechanism that moves the moving body 1 on a floor surface. The moving mechanism 17 may or may not be capable of moving the moving body 1 in all directions. Being capable of moving in all directions means being capable of moving in any direction. The moving mechanism 17 may have, for example, a running part (for example, wheels, etc.) and a driving means (for example, a motor, an engine, etc.) that drives the running part. In addition, when the moving mechanism 17 is capable of moving the moving body 1 in all directions, the running part may be an omnidirectional wheel (for example, an omniwheel, a mecanum wheel, etc.). As the moving mechanism 17, a known one can be used, and therefore a detailed description thereof will be omitted.

[0028] The movement control unit 18 controls the movement mechanism 17 so that the moving body 1 moves along the guiding line. The detection result of the guiding line in the planar image allows the movement control unit 18 to know the position of the guiding line in the local coordinate system of the moving body 1. Therefore, by using this, the movement control unit 18 can realize the movement of the moving body 1 along the guiding line. In addition, when a plurality of guiding lines are included in the planar image, the movement control unit 18 may perform movement control so that the moving body 1 moves along the guiding line extending in the traveling direction. In addition, when the moving body 1 moves on the guiding line, the movement control unit 18 may perform movement control so that the moving body 1 moves along the guiding line extending in the traveling direction, for example, at the center in the left-right direction of the planar image.

[0029] Moreover, the movement control unit 18 controls the movement mechanism 17 using the first self-position acquired by the first self-position acquisition unit 15. This movement control may be, for example, control of the direction of the moving body 1, start of movement, stop, etc., using the first self-position. For example, when the moving body 1 reaches a predetermined position, that is, when the first self-position reaches a predetermined position, the movement control unit 18 may control the movement mechanism 17 so that the moving body 1 stops. Furthermore, when a movement route is indicated in advance, the movement control unit 18 may control the movement mechanism 17 so that the first self-position is along the movement route. Note that in a situation where a marker is not included in the planar image, since the first self-position cannot be acquired, the movement control unit 18 may perform movement control using the second self-position.

[0030] Next, the operation of the moving object 1 will be described with reference to the flowchart of FIG. (Step S101) The image acquisition unit 12 judges whether or not to acquire a photographed image. If the photographed image is to be acquired, the process proceeds to step S102. If not, the process of step S101 is repeated until it is determined that the photographed image is to be acquired. The image acquisition unit 12 may, for example, periodically determine that the photographed image is to be acquired.

[0031] (Step S102) The image acquisition unit 12 acquires a captured image. The image acquisition unit 12 may acquire the captured image by, for example, photographing an image, or may acquire the captured image by receiving a photographed image. The captured image may be stored in a recording medium (not shown) or the like.

[0032] (Step S103) The image conversion unit 13 converts the captured image into a planar image. The image conversion unit 13 may convert all captured images into planar images, or may convert some captured images into planar images. This is because, when captured images are captured frequently, it is not necessary to convert all captured images into planar images. The planar image may be stored in a recording medium (not shown) or the like.

[0033] (Step S104) The detection unit 14 performs a thinning process on the planar image. This thinning process may be performed after the planar image is converted into a grayscale image as described above.

[0034] (Step S105) The detection unit 14 detects guiding lines in the planar image after the thinning process.

[0035] (Step S106) The detection unit 14 detects markers on the guiding line detected in step S105 in the planar image that has not been subjected to thinning processing.

[0036] (Step S107) The second self-position acquisition unit 16 acquires the second self-position.

[0037] (Step S108) The first self-position acquisition unit 15 judges whether or not a marker was detected in step S106. If a marker was detected, the process proceeds to step S109, and if not, the process proceeds to step S110.

[0038] (Step S109) The first self-location acquisition unit 15 acquires a first self-location using marker information corresponding to the detected marker and the position and orientation of the marker in the planar image. Note that the marker information corresponding to the detected marker may be specified using the second self-location acquired by the second self-location acquisition unit 16.

[0039] (Step S110) The movement control unit 18 controls the moving mechanism 17 so as to move along the guiding line detected in step S105. Movement control using the first self-position may also be performed. Note that if the first self-position is not acquired, that is, if the marker is not detected in the planar image, the movement control unit 18 may perform movement control using the second self-position acquired in step S107. Then, the process returns to step S101. Note that by repeatedly performing the movement control in step S110, the moving object 1 can perform the desired movement.

[0040] Note that the order of the processes in the flowchart of Fig. 7 is an example, and the order of the steps may be changed as long as the same results can be obtained. In addition, in the flowchart of Fig. 7, the process ends when the power is turned off or an interrupt is issued to end the process.

[0041] Next, the operation of the moving body 1 according to this embodiment will be described using a specific example. In this specific example, it is assumed that a plurality of pieces of marker information shown in FIG. 4A are stored in the storage unit 11. It is also assumed that the moving body 1 moves along a guide line 5 in the factory shown in FIG. It is also assumed that movement instructions indicating a movement route along the guide line and a stop position are input in advance to the moving body 1, and the movement control unit 18 performs movement control in accordance with the movement instructions.

[0042] When the moving object 1 starts moving, first, the image acquisition unit 12 acquires a photographed image and passes the acquired photographed image to the image conversion unit 13 (steps S101 and S102). The photographed image is assumed to be, for example, the one shown in FIG. 5. Upon receiving the photographed image, the image conversion unit 13 converts the photographed image into a planar image viewed from above and passes it to the detection unit 14 (step S103). The planar image is, for example, the one shown in FIG. 6.

[0043] Upon receiving the planar image, the detection unit 14 performs a thinning process on the planar image, detects a guiding line in the planar image that has been subjected to the thinning process, and passes the detection result of the guiding line to the movement control unit 18 (steps S104 and S105). The detection unit 14 also detects a marker present on the detected guiding line in the planar image received from the image conversion unit 13 (step S106). More specifically, the detection unit 14 identifies the position and orientation of the marker in the planar image, and passes the identification result to the first self-position acquisition unit 15. In the case of the planar image shown in FIG. 6, the position and orientation of the marker 3 present on the guiding line 5 is passed to the first self-position acquisition unit 15.

[0044] Next, the second self-location acquisition unit 16 acquires the second self-location at that time and passes it to the first self-location acquisition unit 15 and the movement control unit 18 (step S107). Upon receiving the second self-location, the first self-location acquisition unit 15 judges whether the marker has been detected (step S108). For example, the first self-location acquisition unit 15 may judge that the marker has been detected when it receives the position and orientation of the detected marker in the planar image from the detection unit 14, and may judge that the marker has not been detected when it does not receive the position of the marker, etc. When the marker has been detected, the first self-location acquisition unit 15 acquires the relative positional relationship between the local coordinate system of the moving object 1 and the local coordinate system of the marker using the position and orientation of the marker in the planar image, and specifies the position of the marker in the world coordinate system using the relative positional relationship and the second self-location. Then, the first self-location acquisition unit 15 reads out marker information including the position closest to the specified position from the storage unit 11. This marker information includes the position and direction of the detected marker. The first self-position acquisition unit 15 acquires a first self-position indicating the position and direction of the moving body 1 in the world coordinate system by using this marker information and the relative positional relationship between the local coordinate system of the moving body 1 and the local coordinate system of the marker, and passes it to the movement control unit 18 (step S109). The movement control unit 18 controls the movement mechanism 17 so that the moving body 1 moves along the guiding line using the detection result of the guiding line received in advance. In addition, the movement control unit 18 performs movement control using the received first self-position as necessary (step S110). By repeating such processing every time a captured image is acquired, the moving body 1 moves according to a movement instruction. Note that the movement control unit 18 may perform movement control using the second self-position when the first self-position is not acquired.

[0045] As described above, according to the moving body 1 of this embodiment, the self-location of the moving body 1 can be appropriately acquired by using a plurality of markers arranged on the guiding line. In addition, if the plurality of markers arranged on the guiding line are all the same, it is not necessary to prepare different markers, and the load when arranging a plurality of markers can be reduced. In addition, since the second self-location may be lower in accuracy than the first self-location, the second self-location acquisition unit 16 can also acquire the second self-location by a simple configuration such as odometry. In addition, by detecting the guiding line by the Hough transform in the plan view, the guiding line can be detected in a shorter time and with higher accuracy. In addition, by performing a thinning process on the planar image before the Hough transform, the guiding line can be made easier to find. In addition, by detecting the marker by template matching in the planar image, it becomes possible to more reliably detect a marker that is far away.

[0046] In the present embodiment, the case where the moving body 1 includes the second self-location acquisition unit 16 has been mainly described, but this is not necessarily the case. The moving body 1 may not include the second self-location acquisition unit 16. In this case, for example, the multiple markers arranged on the guiding line may all be the same markers, and the multiple markers may be arranged on the guiding line such that at least one marker is included in the captured image when the moving body moves along the guiding line. In this way, the first self-location acquisition unit 15 can acquire the first self-location using at least one marker included in the planar image, and the movement control unit 18 can perform movement control using the first self-location. In this case, it is preferable that marker information corresponding to the marker included in the planar image can be specified at the start of the movement. The marker information may be specified manually, for example. In this way, the first self-location acquisition unit 15 can acquire the first self-location even at the start of the movement. Furthermore, after starting to move, when a certain marker is no longer included in the planar image, there is a period during which two markers are included in the planar image, and therefore the first self-location acquisition unit 15 can identify marker information corresponding to the marker that is newly included in the planar image during that period. In this way, the first self-location acquisition unit 15 can constantly acquire the first self-location using the marker, and therefore the moving body 1 can move even without the second self-location acquisition unit 16.

[0047] In addition, when the moving object 1 does not have the second self-location acquisition unit 16, the multiple markers arranged on the guiding line may be different from each other, and the storage unit 11 may store a marker identifier for identifying the marker and the marker information of the marker in association with each other. For example, as shown in FIG. 4B, the storage unit 11 may store the marker identifier and the marker information in association with each other. In FIG. 4B, for example, the position and the direction of the marker identified by the marker identifier M11 are (X11, Y11) and θ11, respectively. Then, the first self-location may be acquired using the marker information associated with the marker identifier of the detected marker. In this case, it is preferable that the multiple markers are each identifiable by, for example, color, shape, pattern, or the like. As an example, when the first marker 3 is the one shown in FIG. 2A, the second marker 3 may be the one shown in FIG. 2B. In the marker 3 shown in FIG. 2B, for example, the area 3a may be blue and the area 3c may be red. In this way, by changing the combination of the two colors, each of the multiple markers 3 may be able to be distinguished.

[0048] When the multiple markers are different from each other, the detection unit 14 may also specify the marker identifier of the marker detected in the planar image. For example, the detection unit 14 may acquire feature amounts related to the color, shape, pattern, etc. of the detected marker, and may specify the marker identifier corresponding to the acquired feature amount using information that associates the feature amounts related to the color, shape, pattern, etc. of the marker with the marker identifier. The first self-location acquisition unit 15 may acquire the first self-location using marker information associated with the marker identifier identified by the detected object 14. In this case, although there may be a situation in which the marker is not included in the captured image, it is preferable that the marker is always captured by the moving body 1 moving along the guiding line. In addition, in an area where the self-location is required for the movement control of the moving body 1 (for example, an area where the moving body 1 stops, etc.), the marker is arranged on the guiding line, and the marker is preferably included in the captured image.

[0049] In addition, in the present embodiment, the case where the guiding line is a straight line has been mainly described, but the guiding line may be a curved line. For example, the curved guiding line may be a curved guiding line with a constant curvature. In this case, the detection unit 14 can also detect the curved guiding line with a constant curvature by, for example, the Hough transform.

[0050] Also, the first self-location acquisition unit 15 may acquire the first self-location by integrating the self-location acquired using the marker and the second self-location, for example. The first self-location acquisition unit 15 may perform the integration using, for example, a Kalman filter or the like. Also, the first self-location acquisition unit 15 may acquire the first self-location by averaging the self-location acquired using the marker and the second self-location. The average may be, for example, a simple average or a weighted average. In the latter case, the weight may be, for example, a weight that increases as the reliability increases. The reliability of the self-location acquired using the marker may be, for example, a reliability that decreases as the distance from the moving object 1 to the marker increases. Also, when the second self-location is acquired by odometry, the reliability of the second self-location may be, for example, a reliability that decreases as the amount of movement after the first self-location is acquired and the second self-location is reset at the first self-location increases.

[0051] In addition, when detecting guiding lines using a Hough transform, the result of the Hough transform may be unstable. In order to avoid such a situation, a process for stabilizing the result may be performed. The process for stabilizing the result of the Hough transform may be, for example, filtering using a Kalman filter or the like, or may be weighted addition for removing outliers or reducing the influence of the outliers.

[0052] Furthermore, when the moving body 1 is capable of moving in multiple directions, such as an omnidirectional dolly, the image acquisition unit 12 may be able to acquire captured images of the area ahead in each of the multiple moving directions. In this case, for example, the moving body 1 may be provided with a camera for capturing captured images in each of the multiple directions. The image acquisition unit 12 may then acquire captured images of the area ahead in the moving direction according to the current moving direction.

[0053] In addition, in the above embodiments, each process or function may be realized by centralized processing in a single device or a single system, or may be realized by distributed processing in multiple devices or multiple systems.

[0054] In the above embodiment, each component may be configured by dedicated hardware, or a component that can be realized by software may be realized by executing a program. For example, each component may be realized by a program execution unit such as a CPU reading and executing a software program recorded on a recording medium such as a hard disk or a semiconductor memory. During execution, the program execution unit may execute the program while accessing a storage unit or a recording medium. The program may be executed by being downloaded from a server or the like, or may be executed by reading a program recorded on a predetermined recording medium (for example, an optical disk, a magnetic disk, a semiconductor memory, etc.). The program may be used as a program constituting a program product. The computer that executes the program may be single or multiple. That is, centralized processing may be performed, or distributed processing may be performed.

[0055] The above-mentioned embodiments are merely examples for specifically implementing the present invention, and are not intended to limit the technical scope of the present invention. The technical scope of the present invention is indicated by the claims, not by the description of the embodiments, and is intended to include modifications within the literal scope of the claims and the scope of equivalent meanings. [Explanation of symbols]

[0056] REFERENCE SIGNS LIST 1 moving object, 3 marker, 5 guiding wire, 11 memory unit, 12 image acquisition unit, 13 image conversion unit, 14 detection unit, 15 first self-position acquisition unit, 16 second self-position acquisition unit, 17 movement mechanism, 18 movement control unit

Claims

1. A moving object that moves along a visually recognizable guide line provided on a floor surface, a storage unit that stores marker information including a position and a direction of each of a plurality of markers that are arranged on the guiding line and whose orientation can be specified; an image acquisition unit that acquires a captured image of a scene ahead of the moving object; an image conversion unit that converts the captured image into a planar image viewed from above; A detection unit that detects a guiding line in the planar image and detects a marker on the detected guiding line; a first self-location acquisition unit that acquires a first self-location of the moving object by using the marker information corresponding to the marker detected by the detection unit and the position and orientation of the marker in the planar image; A moving mechanism that moves the moving body; a movement control unit that controls the movement mechanism so that the moving body moves along the guide line, and controls the movement mechanism using the first self-position.

2. the plurality of markers arranged on the guiding line are all the same markers, a second self-location acquisition unit that acquires a second self-location of the moving object by a method different from that of the first self-location acquisition unit; The moving body according to claim 1 , wherein the first self-location acquisition unit identifies the marker information corresponding to the detected marker by using the second self-location.

3. the plurality of markers arranged on the guiding line are all the same markers, The moving body according to claim 1 , wherein the plurality of markers are arranged on the guiding line such that at least one marker is included in the captured image when the moving body moves along the guiding line.

4. The plurality of markers arranged on the guiding line are different from each other, the storage unit stores a marker identifier for identifying a marker and marker information of the marker in association with each other; The detection unit identifies a marker identifier of a marker detected in the planar image, The moving body according to claim 1 , wherein the first self-location acquisition unit acquires the first self-location by using marker information associated with the specified marker identifier.

5. The moving body according to claim 1 , wherein the detection unit detects guiding lines in the planar image by a Hough transform.

6. The moving body according to claim 5 , wherein the detection unit performs a thinning process on the planar image and then performs a Hough transform.

7. The moving body according to claim 1 , wherein the detection unit detects the marker by template matching.

Citation Information

Patent Citations

  • Control system and control method of automatic guided vehicle

    JP2021047671A