KR100698534B1 - Landmark for location recognition of mobile robot and location recognition device and method using same - Google Patents

Abstract

A landmark for position determination of a mobile robot and a position determining apparatus and method using the same are provided to improve a position update rate of the mobile robot by using infrared ray. A landmark(100) for position determination of a mobile robot includes a position determination unit(110) and a region determination unit(120) for identifying another landmark. The position determination unit includes three marks for recognizing position information necessary for the mobile robot. The region determination unit is formed by combining a plurality of marks to recognize additional region information of the mobile robot. The position determination unit includes one mark(B) of an arbitrary position and two marks(C,A) positioned on an X axis and a Y axis with respect to the one mark. And, the region determination unit is constructed by 3x3 marks inside the position determination unit, but the position and number of the marks are changed according to the use purpose.

Description

Landmark for position determination of mobile robot and location recognition device and method using same {Landmark for position determination of mobil robot and apparatus and method using it}

1 is a schematic diagram showing a camera of a mobile robot for imaging a landmark attached to a ceiling of an indoor space;

2 is a schematic diagram showing a ceiling camera for capturing a landmark attached to a mobile robot;

3 is a block diagram of a landmark according to an embodiment of the present invention;

Figure 4a is a plan view showing a position recognition device of a mobile robot according to an embodiment of the present invention.

4B is a sectional view taken along the line A-A 'in FIG. 4A;

<Description of Symbols for Major Parts of Drawings>

100: landmark 110: location recognition unit

120: area recognition unit 200: camera

210: wide-angle lens 220: infrared LED

230: infrared light controller 240: CCD (or CMOS) array

250: image controller

The present invention relates to a marker for recognizing a position (coordinate and azimuth) of a mobile robot (hereinafter referred to as 'landmark') and a location recognition apparatus and method using the same, and more particularly to a land obtained from a camera. A landmark that can accurately and quickly obtain the position of the mobile robot from the mark image, and a position recognition device and method that can detect the area information in addition to the exact position information of the mobile robot by obtaining the landmark image from the infrared camera will be.

In order to control a robot moving in an indoor space, a function of recognizing where the robot is located in an indoor space is required. In general, a method of calculating a magnetic position of a robot using a camera can be divided into two types as follows.

First, as a method of using artificial landmarks, as shown in Figure 1, a landmark 30 having a specific meaning is installed on the ceiling or wall and photographed by the camera 20, and then the landmark 30 is captured in the image. There was a method of calculating the position of the mobile robot 10 by matching the coordinate system of the mobile robot 10 with the coordinate system on the screen (see Republic of Korea Patent No. 485696).

Secondly, as a method of using natural landmarks, the ceiling is photographed with a camera and the robot extracts the linear components and edge information of the structure installed on the ceiling, such as lighting fixtures, and the interface between the ceiling and the wall, and then uses them to capture the ceiling. There was a method of calculating the magnetic position of (see Korean Patent No. 483566).

However, when using artificial landmarks, there is a problem that a lot of the influence of lighting is affected, and color information is distorted by sunlight, causing a lot of misunderstandings, and even when using natural landmarks, the brightness of surrounding light sources is affected. Receiving a lot, and in the step of recording the position of the feature point in the landmark requires the use of odometer information or other robot position reading device requires a lot of memory and the help of additional devices is essential. In particular, there is a problem that it is very difficult to use in the absence of lighting.

Therefore, there is a need for a new robot magnetic position recognition method that can reduce the amount of calculation in the image preprocessing step without being affected by illumination in a robot that recognizes its position using a camera as in the prior art.

The present invention is to solve the above problems, it is possible to quickly and accurately detect the location or area information of the mobile robot from the landmark image captured by the camera and to recognize the landmark irrespective of the indoor lighting The purpose is to provide a landmark for location recognition of the mobile robot.

The present invention also provides an apparatus and method for recognizing a location of a mobile robot capable of acquiring the landmark image by an infrared camera and detecting the location and region information of the mobile robot without undergoing a special preprocessing process. There is a purpose.

A landmark for position recognition of a mobile robot of the present invention for achieving the above object, in the landmark for recognizing the coordinates and azimuth information of the mobile robot, one mark of any position and the X axis and Y axis around the mark Characterized in that it comprises a position recognition portion consisting of two marks located on.

Preferably, the landmark further comprises a region recognition unit consisting of a combination of a plurality of marks to distinguish different landmarks.

An apparatus for recognizing a position of a mobile robot according to the present invention includes an infrared illumination unit for irradiating infrared rays to a landmark composed of a plurality of marks reflecting infrared rays; An infrared camera for capturing the landmark to obtain a binary image; A mark detector for labeling the clustered partial images in the binary image and detecting a mark from the number and / or variance of each label pixel; And a position detection unit for detecting the coordinates and azimuths of the mobile robot from the center coordinates of the detected marks.

Preferably, the infrared camera is configured integrally with the infrared illuminating unit.

The position recognition method of the mobile robot according to the present invention comprises: (a) a landmark including a position recognition part that reflects infrared rays, consisting of one mark at an arbitrary position and two marks positioned on the X and Y axes about the same; Imaging the landmark while irradiating infrared light to obtain a binary image; (b) labeling the clustered partial images in the binary image and detecting a mark from each number of label pixels and / or variance; And (c) detecting the coordinates and azimuths of the mobile robot from the center coordinates of the detected marks.

The present invention relates to a landmark used for recognizing position information (coordinates and azimuths) of a mobile robot, and a location recognition apparatus and method using the same. First, a landmark for position recognition of a mobile robot according to the present invention will be described. Afterwards, a position recognition apparatus and method for a mobile robot using the same will be described in detail with reference to the accompanying drawings.

The landmark for position recognition of the mobile robot of the present invention is attached to the ceiling of the robot's moving space as shown in FIG. 1, and is captured from a camera installed in the robot, or is attached to the top of the robot as shown in FIG. 2. It is captured from the installed camera and used for location recognition of the mobile robot.

Looking at the landmark 100 according to an embodiment of the present invention in detail with reference to Figure 3, the position recognition unit 110 consisting of three marks to recognize the essential position information, that is, coordinates and orientation of the mobile robot, The area recognizing unit 120 for identifying different landmarks 100 is made of a combination of a plurality of marks to recognize additional area information of the mobile robot.

The position recognition unit 110 is composed of one mark B at an arbitrary position and two marks C and A positioned on the X and Y axes about the mark B. The three marks configured as described above provide the reference point and the reference coordinate on the landmark 100.

The area recognition unit 120 is configured as a mark of 3 × 3 inside the position recognition unit 110, as shown in Figure 3, the position or number of the marks forming the position recognition unit 110 is changed depending on the purpose of use It is possible. The different landmarks 100 are identified by assigning IDs corresponding to the number and positions of the marks constituting the area recognition unit 120 configured as described above. In the case of the 3x3 mark shown in FIG. 3, it can be seen that 512 IDs are assigned. At this time, the position of the mark constituting the area recognition unit 120 may be determined according to the reference coordinates provided by the position recognition unit 110, and since the binary coding is possible for each ID, the area information of the mobile robot can be quickly obtained. I can recognize it.

On the other hand, all the marks constituting the landmark 100, for example, can be coated with an infrared reflecting paint or the like, or a reflective sheet to diffusely reflect light of a specific wavelength band, especially infrared rays in the 800nm to 1200nm region. Therefore, by using an infrared camera, it is possible to quickly recognize the position of the mobile robot without special image preprocessing by detecting only infrared rays reflected from the mark even in the presence of disturbance light as well as at night.

In this case, the mark may be configured only in a circle shape of a predetermined size, or may be configured in a circle shape on a plane or a shape protruding like a hemisphere on a plane. The shape of the mark in the form of a circle or hemisphere is because the number of pixels, dispersion or center coordinates can be easily obtained in detecting the mark.

These marks may be configured in the same manner, but by distinguishing the marks of the gas recognition unit 110 and the area recognition unit 120 with different sizes and / or colors, it may be easier to distinguish the two.

The mark constituting the landmark 100 of the present invention described above may be utilized in a conventional mobile robot position recognition apparatus that does not use an infrared camera, and its use is not limited to the position recognition apparatus of the present invention described below. .

In the mobile robot position recognition apparatus and method of the present invention, it is basically assumed that the space in which the robot moves or the space to which the landmark is attached is not curved and is parallel, and will be described in the operation sequence below.

(a) First, infrared light is irradiated from the infrared LED 220 to the landmark 100, and the image reflected back from the mark forming the position recognition unit 110 is captured by a camera to obtain a binary image. That is, the mark of the image acquired from the camera 200 is set to a bright color close to white, and a predetermined threshold brightness value is selected and converted into a binary image.

Looking at the camera 200 in detail, as shown in Figures 4a and 4b, a plurality of infrared LEDs 220, infrared light controller 230, CMOS array 250 and the image controller around the wide-angle lens 210 (Vision Controller; 250). The camera 200 configured as described above is installed on a mobile robot or a ceiling to obtain an image of the landmark 100 of the present invention attached to the ceiling or wall of the moving space of the robot or the upper part of the mobile robot.

(b) Next, the partial image displayed brightly in the binary image is labeled, and a mark is detected from each number of label pixels and / or dispersion. In this case, labeling is a procedure of creating a label list by individually recognizing the clustered images and numbering them so as to know the position and size of the clustered partial images brightly displayed in the binary image. After this labeling, the center coordinates of each label are obtained and the mark is detected from the number and / or variance of pixels of the label.

The method for detecting a mark in the label list may be in various forms. For example, as a first method, a restriction on the number of pixels constituting the label can be applied. That is, since the mark has a circular circle shape and a uniform size, only a label having a certain number of pixels is selected as a mark candidate, and a label smaller or larger than a certain number of pixels is deleted from the label list.

As a second method, since marks are clustered in a circle, mark candidates can be deleted by labeling a non-clustered label from the label list by setting a predetermined variance value corresponding to the boundary value using the variance of the center coordinates among the labels. Can be selected.

As described above, the two methods of detecting the mark in the label may be selectively used or may be used in parallel if necessary.

On the other hand, if there is only a mark of the position recognition unit 110 in the landmark 100, three marks can be detected through the above method. However, if there is a mark of the area recognition unit 120 of the same size in addition to the mark of the position recognition unit 110, the mark corresponding to the position recognition unit 110 can be separated and detected from the entire mark by performing the following additional steps. have.

That is, the mark of the position recognition unit 110 may be separated and detected by finding three labels having similar distances between the labels among the selected mark candidates and having a position close to a right angle. For example, by finding the dot product of the vector connecting each label and finding the label when the dot product is closest to the maximum value of the dot product, only the mark of the position recognition unit 110 can be detected separately from all the marks.

When this is explained using an equation, when the indices of labels corresponding to A, B, and C of FIG. 3 are defined as i, j, and k, the maximum effective value of the dot product of the vectors between the labels is δ _th . Then, among the indexes whose inner value is within the range, the index having the smallest difference in size is found through the following equation.

If the existence and position of the mark are recognized through the above equation, the ID of the mark can be easily obtained by calculating the position point through the sum of these position values and checking the existence of the label at the position.

(c) Finally, position information (coordinates and azimuths) and area information of the mobile robot are detected using the detected mark.

First, an ID determined according to the number and position of the marks corresponding to the area recognition unit 120 among the detected marks can be quickly obtained, and the area information of the mobile robot assigned to the ID, that is, the outline of the location of the mobile robot can be obtained. The location can be recognized.

Next, detailed position information of the mobile robot, that is, coordinates and azimuths, may be obtained using the center coordinates of the three marks A, B, and C constituting the position recognition unit 110 detected above.

According to one embodiment of the present invention, the coordinates of the mobile robot can be obtained by using any point obtained from the center coordinates of each of the three marks A, B, and C shown in FIG. 3 as a reference coordinate. At this time, any one point may use the center of gravity obtained by the center coordinates of the three marks, and in this case, the result of averaging the errors of the center coordinates of the three marks can be minimized. Will be.

The orientation of the mobile robot can be obtained based on one direction vector obtained by three center coordinates (for example, a direction vector of a vector of vectors A and C centered on B).

The amount of vector that can know both the coordinates and the bearing information of the mobile robot can be obtained by using the calibration formula, which is described in detail in the following papers.

[1] RI Hartley. An algorithm for self calibration from several views. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition , pages 908-912, Seattle, WA, June 1994. IEEE.

[2] D. Liebowitz and A. Zisserman. Metric rectification for perspective images of planes. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition , pages 482-488, Santa Barbara, California, June 1998. IEEE Computer Society.

The calibration equation is represented by the following equation.

, 회전행렬과 수평 이동 벡터를 각각 R_O, t₀라 하고, s는 임의의 스케일 값이고 A는 캘리브레이션 행렬이다. 그리고 로봇이 회전하고 이동한 위치에서의 픽셀 좌표를

, 회전한 각도 량에 해당하는 행렬을 R₁, 수평 이동 벡터 량을 t₁이라 하면 아래 식을 얻을 수 있다. Using the above equation, the projected pixel coordinates corresponding to the position of the robot

The rotation matrix and the horizontal movement vector are denoted by R ₀ , t ₀ , s is an arbitrary scale value, and A is a calibration matrix. And then the pixel coordinates at the position

If the matrix corresponding to the rotated angle is R ₁ and the horizontal movement vector is t ₁ , the following equation can be obtained.

Coordinate value M is obtained from Equation 3 above, and the calculated value is substituted into Equation 4. In Equation 4, R ₁ may be calculated through a vector sum of recognized marks. After all, since all values except t ₁ in Equation 4 are known, the movement amount vector t ₁ can be calculated. That is, the calculated vector amount of the robot can be obtained by calculating the following equation.

As described above, the vector amount which can simultaneously know the coordinates and the orientation of the mobile robot can be obtained through vector calculation using the detected three marks of the position recognition unit 110 and the calibration equation, and by using this, a low-cost micro Processor implementations are possible.

In addition, schematic area information of the mobile robot and detailed position information (coordinates and azimuth) can be converted into code information, and the converted code information is transmitted to the mobile robot, thereby performing the necessary operation.

As described above, the detailed description of the present invention has been described with respect to specific embodiments, which are merely exemplary and various modifications are possible without departing from the scope of the technical idea of the present invention. Obviously, the scope of the present invention should not be limited to the described embodiments, but should be determined by the equivalents of the claims and the equivalents of the following claims. do.

According to the landmark for location recognition of the mobile robot of the present invention configured as described above, and the location recognition apparatus and method using the same, the preprocessing process of the image is omitted, regardless of the illumination of the moving space of the robot using an infrared image. Not only can the position update rate of the mobile robot be improved, but it can be applied to a robot moving at a high speed (30 cm / s or more).

In addition, it is possible to recognize the exact position of the mobile robot by the position recognition unit consisting of three marks, and mobile robots can be applied in complex or spacious indoor spaces by assigning IDs to landmarks by the area recognition unit consisting of a plurality of marks. There is an advantage.

Claims (20)

In the landmark for recognizing the coordinates and orientation information of the mobile robot, A landmark for position recognition of a mobile robot, characterized in that it comprises a position recognition unit consisting of one mark at an arbitrary position and two marks positioned on the X-axis and Y-axis about the mark. The method of claim 1, A landmark for position recognition of a mobile robot, comprising a plurality of marks, the region recognition unit for identifying different landmarks by assigning IDs corresponding to the number and position of each mark. delete The method of claim 2, ID of the area recognition unit, the landmark for position recognition of the mobile robot, characterized in that determined based on the position recognition unit. The method of claim 4, wherein The area recognition unit is a landmark for position recognition of the mobile robot, characterized in that configured to the inside of the three marks forming the position recognition unit. The method according to claim 1 or 2, The mark is a landmark for position recognition of the mobile robot, characterized in that for reflecting light of a specific wavelength range. The method of claim 6, The landmark for position recognition of the mobile robot, characterized in that the light is infrared. The method according to claim 1 or 2, The mark is a landmark for position recognition of the mobile robot, characterized in that formed in the shape of a circle of a predetermined size. The method according to claim 1 or 2, The mark is a landmark for position recognition of the mobile robot, characterized in that formed in the form protruding on the plane or on the plane. The method of claim 2, The mark constituting the position recognition unit and the area recognition unit is a landmark for position recognition of the mobile robot, characterized in that configured in different sizes and / or colors. An infrared illumination unit for irradiating infrared rays to a landmark consisting of a plurality of marks reflecting infrared rays; An infrared camera for capturing the landmark to obtain a binary image; A mark detector for labeling the clustered partial images in the binary image and detecting a mark from the number and / or variance of each label pixel; And And a position detector configured to detect coordinates and azimuths of the mobile robot from the center coordinates of the detected marks. The method of claim 11, The infrared camera, the position recognition device of the mobile robot, characterized in that it is configured integrally with the infrared illumination unit. The method of claim 12, The landmark is installed on top of the mobile robot, The infrared camera is a location recognition device for a mobile robot, characterized in that installed in a predetermined space capable of imaging the mobile robot. The method according to any one of claims 11 to 13, The landmark, the position recognition device of a mobile robot, characterized in that it comprises a position recognition unit consisting of one mark of any position and two marks located on the X-axis and Y-axis around it. The method of claim 14, The landmark further includes an area recognition unit formed of a combination of a plurality of marks to distinguish different landmarks, The position detecting unit further detects area information of the mobile robot from the detected mark. The method of claim 15, The area recognition unit recognizes different landmarks by assigning IDs corresponding to the number and positions of the respective marks. (a) A landmark is taken while irradiating infrared rays on a landmark including a position recognition unit consisting of one mark at an arbitrary position and two marks positioned on the X-axis and the Y-axis, and reflecting infrared rays. Obtaining an image; (b) labeling the clustered partial images in the binary image and detecting a mark from each number of label pixels and / or variance; And (c) detecting coordinates and azimuths of the mobile robot from the center coordinates of the detected marks; Position recognition method of the mobile robot comprising a. The method of claim 17, In the step (b), the mark candidate is selected from the number and / or variance of each label pixel, and the three robots corresponding to the position recognition unit are detected from the inner product of the vector following the selected label. Location recognition method. The method of claim 17, In the step (a), to obtain a binary image further comprising a region recognition unit consisting of a combination of a plurality of marks to distinguish different landmarks, In the step (c), the area information of the mobile robot is further detected from the mark of the area recognition unit. The method of claim 19, The area information is a location recognition method of a mobile robot, characterized in that the ID given corresponding to the number and location of each mark constituting the area recognition unit for identification of different landmarks.

Images