ROBOT SAFETY MONITORING SYSTEM

Description

BACKGROUND1. Field

[0001] One or more embodiments relate to safety monitoring equipment using a stereo camera, and more particularly, to a system including a robot and a robot safety monitoring system for controlling mechanical equipment in a dangerous situation after detecting an abnormal approach of a person or an object to the mechanical equipment.2. Description of the Related Art

[0002] As safety in industrial sites becomes more important, the need for monitoring equipment using sensors and cameras has increased. Such monitoring equipment is a system that detects and monitors whether a person or any object enters a hazardous area by using a sensor and a camera installed around mechanical equipment. This system has already been used in several ways.

[0003] A first way, which refers to a method using a line sensor, is more frequently used in a space with an entrance than in an open space. In general, in this method, when a line sensor is installed at an entrance and a person passes through the entrance, the mechanical equipment is stopped. Thus, the first way is cost effective, but there is a limitation in usage in open spaces.

[0004] A second way refers to a method using a lidar sensor. In general, in the second way, monitoring is performed while rotating a line sensor in a certain angle range. In this method, a monitoring speed is determined according to a rotation speed, and detection is possible only in a two-dimensional (2D) plane rather than a three-dimensional (3D) space.

[0005] Finally, there is a method using a 3D camera, which is the most useful method because data about a 3D space can be obtained. However, a Time of Flight (TOF) camera is sensitive to the surrounding brightness and has a narrow field of view (FOV).

[0006] Existing stereo cameras are inexpensive and have a wide FOV, but provide poor detection performance with respect to objects parallel to the baselines of the stereo cameras.

[0007] FIG. 1 is a view for explaining an FOV. Referring to FIG. 1, an FOV refers to a shooting range of a camera. As shown in FIG. 1, the FOV may include a vertical FOV, a horizontal FOV, and a diagonal FOV. An imaging area may be defined by the vertical FOV, the horizontal FOV, and the diagonal FOV. An angle corresponding to half the FOV may be referred to as half-of-FOV (HFOV).

[0008] FIG. 2 is a diagram showing the structure of a conventional stereo camera. FIG. 3 shows distance information when the same subject is photographed with a conventional stereo camera. FIG. 4 shows a one-to-one matching result according to a pattern during stereo matching through a conventional stereo camera.

[0009] Referring to FIG. 2, depth information may be obtained using two images 4 and 5 obtained after photographing a subject 3 through two cameras 1 and 2, respectively.

[0010] Referring to FIG. 3, when the same subject is photographed, the locations of the subject shown on a left image 8 and a right image 9 have the same height along an epipolar line, and only locations thereof in a horizontal direction are different from each other. To obtain the depth information, stereo matching is performed along the epipolar line. After finding the same portion from the left image 8 and the right image 9, the depth information is obtained using a disparity 10 between the locations. In this case, it may be determined that the smaller the location disparity is, the greater the depth is, and the larger the location disparity is, the closer the distance is.

[0011] However, this stereo matching has a structural disadvantage. Because scan is performed in a parallel direction along the epipolar line, detection of the distance information for a pattern in a direction parallel to the epipolar line is weak.

[0012] FIG. 4 explains this disadvantage in detail. It may be seen from the upper image of FIG. 4 that, in the case of a vertical pattern, when a right image 12 is scanned along the epipolar line 13 in order to find the same block as a solid block in a left image 11, the same solid block is one.

[0013] In this case, a result is reliable because one-to-one matching is established. On the other hand, in the case of a horizontal pattern in the lower image of FIG. 4, several blocks that are the same as the solid block in the left image 11 exist as viewed along the epipolar line 13 of the right image 12. Thus, one-to-one matching is not established, and thus, a result of stereo matching is unreliable. In this case, because an epipolar line 7 of FIG. 2 is parallel to a baseline 6 of the stereo camera, when the subject 3 is placed parallel to the baseline 6 or a pattern is parallel to the base line 6, a method using the conventional stereo camera may have degraded detection performance.

[0014] US 2015 / 217455 A1 discloses a conventional robot safety monitoring system and method, wherein a single stereo camera is used to detect an object in a monitoring area.SUMMARY

[0015] The invention is defined by the appended set of claims. The description that follows is subjected to this limitation. Any disclosure lying outside the scope of said claims is only intended for illustrative as well as comparative purposes.BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The above and other aspects, features, and advantages of certain embodiments of the inventive concept will be more apparent from the following description taken in conjunction with the accompanying drawings, in which: FIG. 1 is a view for explaining a field of view (FOV); FIG. 2 is a diagram showing the structure of a conventional stereo camera; FIG. 3 shows distance information when the same subject is photographed with a conventional stereo camera; FIG. 4 shows a one-to-one matching result according to a pattern during stereo matching through a conventional stereo camera; FIG. 5 is a view illustrating an arrangement in a T shape of two cameras according to an embodiment; FIG. 6 is a view illustrating a detailed arrangement of a stereo camera set according to an embodiment; FIG. 7 is a view illustrating an FOV of a camera module according to an embodiment; FIG. 8 is a view illustrating connection of a stereo camera set to a processor according to an embodiment; FIG. 9 is a perspective view illustrating an arrangement of a robot safety monitoring system around a robot according to an embodiment; and FIG. 10 is a view illustrating a stereo camera set according to another embodiment. DETAILED DESCRIPTION

[0017] Reference will now be made in detail to embodiments, examples of which are illustrated in the accompanying drawings, wherein like reference numerals refer to the like elements throughout. In this regard, the present embodiments may have different forms and should not be construed as being limited to the descriptions set forth herein. Accordingly, the embodiments are merely described below, by referring to the figures, to explain aspects of the present description. As used herein, the term "and / or" includes any and all combinations of one or more of the associated listed items. Expressions such as "one or more of," when preceding a list of elements, modify the entire list of elements and do not modify the individual elements of the list.

[0018] In the description of the invention, even though shown in other embodiments, the same reference characters or numerals are used for the same components.

[0019] Hereinafter, the invention will be described in detail by explaining exemplary embodiments of the invention with reference to the attached drawings. Like reference numerals in the drawings denote like components, and thus their description will be omitted.

[0020] It will be understood that although the terms "first," "second," etc. may be used herein to describe various components, these components should not be limited by these terms. These components are only used to distinguish one component from another.

[0021] As used herein, the singular forms "a," "an "and "the "are intended to include the plural forms as well, unless the context clearly indicates otherwise.

[0022] It will be further understood that the terms "comprises" and / or "comprising" used herein specify the presence of stated features or components, but do not preclude the presence or addition of one or more other features or components.

[0023] Sizes of components in the drawings may be exaggerated for convenience of explanation. In other words, since sizes and thicknesses of components in the drawings are arbitrarily illustrated for convenience of explanation, the following embodiments are not limited thereto.

[0024] When a certain embodiment may be implemented differently, a specific process order may be performed differently from the described order. For example, two consecutively described processes may be performed substantially at the same time or performed in an order opposite to the described order.

[0025] The terms used in the present specification are merely used to describe particular embodiments, and are not intended to limit the invention. In the present specification, it is to be understood that the terms such as "including" or "having," etc., are intended to indicate the existence of the features, numbers, steps, actions, components, parts, or combinations thereof disclosed in the specification, and are not intended to preclude the possibility that one or more other features, numbers, steps, actions, components, parts, or combinations thereof may exist or may be added.

[0026] A stereo camera set according to an embodiment will now be described with reference to FIGS. 5 through 8.

[0027] FIG. 5 is a view illustrating an arrangement of two cameras according to an embodiment in a T shape. FIG. 6 is a view illustrating a detailed arrangement of a stereo camera set according to an embodiment. FIG. 7 is a view illustrating a field of view (FOV) of a camera module according to an embodiment. FIG. 8 is a view illustrating connection of a stereo camera set according to an embodiment to a processor.

[0028] FIGS. 5 through 8, a robot safety monitoring system according to an embodiment includes a stereo camera set 100 for photographing a robot and a monitoring area around the robot, and a processor 200 connected to the stereo camera set 100. According to the invention, the processor 200 sets the monitoring area, determines whether an object exists in the monitoring area, and controls the robot when an object exists in the monitoring area.

[0029] The stereo camera set 100 may include a first camera 110 and a second camera 120 disposed perpendicular to the first camera 110. A first camera image 110a and a second camera image 120a are illustrated in FIG. 5. Referring to FIGS. 5 and 6, because the stereo camera set 100 has a T shaped configuration in which the first camera 110 is disposed to extend in a first direction and the second camera 120 is disposed to extend a direction perpendicular to the first direction, any one of the two cameras obtains a pattern that is not parallel to a baseline even in any situation, so a situation where there is no one-to-one matching at a specific angle does not occur. Thus, the reliability of a stereo matching result may be improved, and the detection performance of an object using the stereo camera may be maintained more stably. In addition, the stereo camera set 100 includes the first and second cameras 110 and 120 arranged in a T shape, and, when any one of the first and second cameras 110 and 120 is damaged, the first and second cameras 110 and 120 may be selectively replaced rather than being entirely replaced, and thus repair and replacement may be easy and economical efficiency may be improved.

[0030] Referring to FIG. 6, the stereo camera set 100 according to an embodiment includes a first camera 110 including a plurality of first camera modules 111 spaced apart from each other, and a second camera 120 including a plurality of camera modules 121 second cameras spaced apart from each other. In this case, based on the first direction, the first and second cameras 110 and 120 have FOVs having different directions.

[0031] Because the first and second cameras 110 and 120 have FOVs in different directions, a situation in which one-to-one matching is not established at a specific angle does not occur, so the reliability of the stereo matching result may be improved, and an object detection performance using the stereo camera may be kept more stably.

[0032] According to the invention, a first distance D1 between two of the first camera modules 111 is greater than a second distance D2 between one of two of the first camera modules 111 and one of the second camera modules 121 which is closest to the one of the two of the first camera modules 111. When the first distance D1 is less than the second distance D2, an FOV of the first camera modules 111 and an FOV of the second camera modules 121 may overlap each other. Accordingly, by making the first distance D1 be larger than the second distance D2, a field of vision in a range where the FOVs of the camera modules do not overlap each other or are not away from each other may be secured.

[0033] According to the invention, the first distance D1 and the second distance D2 may maintain a preset ratio. In this case, the second distance D2 is 95% or less of the first distance D1. More specifically, the second distance D2 is 50 % to 95 % of the first distance D1. When the second distance D2 is greater than 95% of the first distance D1, an ineffective area may be formed due to an increase in a distance between the cameras, and thus detection performance may be deteriorated. Accordingly, by designing the second distance D2 not to exceed 95% of the first distance D1, loss of a sensing area and deterioration of sensing performance may be both prevented.

[0034] In more detail, the ratio may be set by being divided into three steps. In a maximum allowable range, which is step 1, the second distance D2 may be 95% or less of the first distance D1. Step 1 may be set as a threshold of loss of the sensing area and degradation of sensing performance.

[0035] In an appropriate allowable range, which is step 2, the second distance D2 may be 85% or less of the first distance D1. When the camera modules are disposed within the appropriate allowable range, the sensing performance may be improved to the extent that the sensing area is not lost.

[0036] In a highest appropriate allowable range, which is step 3, the second distance D2 may be 70% or less of the first distance D1. When the camera modules are disposed within the highest appropriate allowable range, the sensing performance may be maximized to the extent that the sensing area is not lost.

[0037] According to an embodiment, referring to FIG. 6, the first distance D1 may be 50 mm, and the second distance D2 may be 35 mm. In this case, the second distance D2 may be 70% of the first distance D1. When the first distance D1 and the second distance D2 are arranged to have a ratio of the highest appropriate allowable range of 70% as described above, the sensing area may not be lost, and still the sensing performance may be maximized.

[0038] Referring to FIG. 7, a horizontal FOV FOV1 and a vertical FOV FOV2 of the first and second camera modules 111 and 121 may be the same as each other. In other words, the horizontal FOV FOV1, the vertical FOV FOV2, and a diagonal FOV FOV3 of the first and second camera modules 111 and 121 are all the same as each other, but the second camera 120 may be disposed perpendicular to the first camera 110 while having the same FOV direction as the first camera 110.

[0039] According to an embodiment, the horizontal FOV FOV1 may be 1 to 2 times the vertical FOV FOV2. When the horizontal FOV FOV1 is less than one time the vertical FOV FOV2, a circular sensing area is not formed around the robot R. Even when the horizontal FOV FOV1 is greater than twice the vertical FOV FOV2, a circular sensing area is not formed around the robot R.

[0040] Accordingly, in order to form the circular sensing area around the robot R, the horizontal FOV FOV1 may need to be 1 to 2 times the vertical FOV FOV2.

[0041] In more detail, the ratio may be set by being divided into three steps. In the maximum allowable range, which is step 1, the horizontal FOV FOV1 may be 1 to 2 times the vertical FOV FOV2. Step 1 may be set as a threshold value for forming a sensing area in a circular shape around the robot R.

[0042] In step 2, the horizontal FOV FOV1 may be 1.25 to 1.75 times the vertical FOV FOV2. In step 2, an object in the sensing area of the circular shape set about the robot R may be effectively sensed.

[0043] In step 3, the horizontal FOV FOV1 may be 1.3 to 1.5 times the vertical FOV FOV2. In step 3, the sensing area may be provided more compactly, so that the sensing performance in the sensing area in a circular shape set around the robot R.

[0044] According to an embodiment, referring to FIG. 7, the horizontal FOV FOV1 may be about 70 degrees to about 100 degrees, and the vertical FOV FOV2 may be about 45 degrees to about 65 degrees. In detail, according to an embodiment, in order to reduce the loss of the sensing area set around the robot R, the horizontal FOV FOV1 may be about 70 degrees to about 90 degrees, and the vertical FOV FOV2 may be about 50 degrees to about 60 degrees. For example, according to an embodiment, the horizontal FOV FOV1 may be 85.2 degrees, and the vertical FOV FOV2 may be 58 degrees. In this case, the horizontal FOV FOV1 may be 1.468 times the vertical FOV FOV2. Due to this arrangement of the horizontal FOV FOV1 and the vertical FOV FOV2 in the step 3's range of 1.468 times, the sensing area may be provided compactly, so that the sensing performance of the sensing area set around the robot R may be maximized.

[0045] Referring to FIG. 6, vertical and horizontal widths of the stereo camera set 100 may be the same as each other or different from each other. For example, a ratio between the vertical width and the horizontal width of the stereo camera set 100 may be 0.8:1 to 1.2:1. According to an embodiment, the vertical and horizontal widths of the stereo camera set 100 may be provided the same as each other to thereby have improved aesthetics. For example, the vertical width and the horizontal width of the stereo camera set 100 may be both 200 mm. Horizontal and vertical lengths of the first camera 110 may be different from each other. For example, the horizontal length of the first camera 110 may be greater than the vertical length thereof. In detail, the horizontal length of the first camera 110 may be about 2 to about 5 times the vertical length thereof. Preferably, the horizontal length of the first camera 110 may be about 2.5 to about 4 times the vertical length thereof. The vertical length of the second camera 120 may be greater than the horizontal length thereof. In detail, the vertical length of the second camera 120 may be about 2 to about 5 times the horizontal length thereof. Preferably, the vertical length of the first camera 120 may be about 2.5 to about 4 times the horizontal length thereof. For example, according to an embodiment, the first camera 110 may be formed with a width of 90mm and a height of 25mm. The second camera 120 may be formed with a width of 25mm and a height of 90mm. Accordingly, according to an embodiment, the sensing performance in the sensing area set around the robot R may be maximized.

[0046] According to the present embodiment, a process of matching two captured images may be needed for objects photographed through the first and second cameras 110 and 120 disposed perpendicular to each other so that the photographed objects appear as if photographed by a single camera.

[0047] In order to match images obtained from two cameras, as shown in FIG. 8, the two cameras may be connected to one processor 200 through a cable 300 and then may obtain frames at the same time. After that, 2D point matching or 3D point cloud matching may be used.

[0048] When the stereo camera matching is completed, the stereo camera set 100 including the first and second cameras 110 and 120 disposed perpendicular to each other is configured, and then the robot safety monitoring system shown in FIG. 8 may be configured. A robot safety monitoring equipment according to an embodiment may include the stereo camera set 100, the cable 300 connecting the stereo camera set 100 to the processor 200, and the processor 200.

[0049] According to the invention, the processor 200 is configured to match images obtained through the plurality of first camera modules and the plurality of second camera modules, obtain detection information of an object based on a result of the matching and then determine whether an object exists in the monitoring area by using the stereo camera set, and control the robot when an object exists in the monitoring area. According to an embodiment, the processor 200 may include an image processor 210 for matching the images obtained through the first and second cameras 110 and 120 and obtaining detection information of an object, based on a result of the matching, and a robot controller 220 for determining presence or absence of an object in a monitoring area and controlling the robot R. Based on this configuration, the processor 200 detects an object through an image and controls an operation of the robot R when an unintended object approaches the robot R so that the robot R may be prevented from operating in a dangerous environment and allowed to operate in a safe environment. Thus, a safer working environment may be provided to the operating robot R.

[0050] The processor 200 may enable data communication between the image processor 210 and the robot controller 220.

[0051] A robot safety monitoring system installed in a driving environment of the robot R and a monitoring area, according to an embodiment, will now be described with reference to FIG. 9. For contents not shown in FIG. 9, reference may be made to FIGS. 5 through 8.

[0052] FIG. 9 is a perspective view illustrating an arrangement of a robot safety monitoring system according to an embodiment around a robot.

[0053] Referring to FIG. 9, in the robot safety monitoring system according to an embodiment, the stereo camera set 100 may be disposed over the robot R, and may be disposed in a direction facing the robot R. In this case, the robot safety monitoring system according to an embodiment may further include a height adjuster 400 for adjusting the arrangement height of the stereo camera set 100. According to the present embodiment, the height adjuster 400 may be a pillar. The stereo camera set 100 may be disposed on the ceiling irrespective of the height adjuster 400.

[0054] As such, the stereo camera set 100 may be installed at a position high enough to sufficiently monitor the surroundings of the robot R while looking at the robot R. Because a distance from the processor 200 increases as the stereo camera set 100 is installed higher, the length of the cable 300 may become sufficiently long to be connected to the stereo camera set 100.

[0055] According to an embodiment, a distance h to the floor on which the stereo camera set 100 and the robot R are disposed may be 5 m or less, and a width w of the sensing area may be 5 m or less. When the distance h to the floor on which the stereo camera set 100 and the robot R are disposed and the width w of the sensing area deviate from the ranges of the distance and the width, the sensing area may not be set normally, and thus the sensing performance of an object may be deteriorated. When the robot R is disposed within the above range, the sensing performance of the stereo camera set 100 may be secured to a minimum. Preferably, the distance h to the floor on which the stereo camera set 100 and the robot R are disposed may be 0.5m to 4m, and the width w of the sensing area may be 4m or less. In this case, according to an embodiment, the sensing performance in the sensing area set around the robot R may be maximized.

[0056] The monitoring area according to the invention include a warning area 500, a danger area 600, and an object area 700. Respective sizes of the warning area 500, the danger area 600, and the object area 700 are shown in FIG. 9.

[0057] In more detail, the warning area 500 includes the danger area 600 and the object area 700, and, when an object exists in an area other than the object area 700 among the warning area 500, the processor 200 slows down the driving speed of the robot R.

[0058] In this case, according to one or more embodiments, the robot safety monitoring system may further include an alarm unit (not shown) connected to the processor 200 and generating a warning sound, and, when an object exists in the area other than the object region 700 among the warning region 500, the alarm unit (not shown) may generate the warning sound by the processor 200.

[0059] According to the invention, when an object exists in an area other than the object area 700 among the danger area 600, the processor 200 stops the robot R. In this case, the danger area 600 is included in the warning area 500 and may be narrower than the warning area 500. The size of the danger area 600 may be set to correspond to the size and speed of the robot R.

[0060] When the size of the robot R is relatively large, the size of the danger area 600 may also be relatively large. When the speed of the robot R is relatively high, the probability of problems in the work stability of the robot R due to an approach of an abnormal object is higher, so the size of the danger area 600 may also become larger than when the speed of the robot R is low.

[0061] When an object enters the warning area 500, the processor 200 may slow down the driving speed of the robot R to prepare for a dangerous situation in which an abnormal object exerts a physical force on the robot R. When an object crosses the warning area 500 and enters the danger area 600, which is an area closer to the robot R, the processor 200 may stop an operation of the robot R to more actively prepare for a dangerous situation.

[0062] The object area 700 may be included in the warning area 500 or the danger area 600. The object area 700 may be necessary to set the part where the object is located differently from the warning area 500 or the danger area 600 when there is an object essential for driving and working of the robot R in the warning area 500 or in the danger area 600. In other words, unlike in an object located inside the warning area 500 or the danger area 600, in an object located inside the object area 700, deceleration and stoppage of the robot R and generation of a warning sound may not occur.

[0063] According to an embodiment, the object area 700 may include a first object area 710 including the robot R, and a second object area 720 including the height adjuster 400 for adjusting the height of the stereo camera set 100. In this case, the danger area 600 may include the first object area 710.

[0064] Referring to FIG. 9, the robot R is present in the danger area 600, and the height adjuster 400 for supporting the stereo camera set 100 and installing the stereo camera set 100 high is present in the warning area 500. However, in this case, an object is always sensed as being present in the danger area 600 and the warning area 500, and thus the robot R is unable to operate normally. In order to prevent this situation from happening, the robot R and the height adjuster 400 may be set as an object area, so that the height adjuster 400 may prevent deceleration and stoppage of the robot R and generation of a warning sound.

[0065] A stereo camera set according to another embodiment will now be described with reference to FIG. 10. For contents not described with reference to FIG. 10, in particular, contents of first and second distances D1' and D2' and FOVs FOV1', FOV2', and FOV3' may refer to the above-described contents.

[0066] FIG. 10 is a view illustrating a stereo camera set 100' according to another embodiment.

[0067] Referring to FIG. 10, a first camera 110' and a second camera 120' of the stereo camera set 100' may be disposed to cross each other. In this case, a plurality of first camera modules 111' of the first camera 110' may be disposed to intersect a plurality of second camera modules 121' of the second camera 120'.

[0068] In this case, because the first and second cameras 110' and 120' have different FOVs, a situation in which one-to-one matching is not established at a specific angle does not occur, so the reliability of the stereo matching result may be improved, and an object detection performance using the stereo camera may be kept more stably.

[0069] Compared to the T-shaped stereo camera set structure, as in the present embodiment, a cross-type stereo camera set structure may be a structure in which the top, the bottom, the left, and the right are symmetrically arranged. Therefore, objects approaching in various directions may be equally sensed through the structure of the stereo camera set 100' arranged around the robot R, thereby improving sensing performance.

[0070] A robot safety monitoring method according to an embodiment will now be described.

[0071] The robot safety monitoring method according to an embodiment includes setting the robot R and the monitoring area around the robot R, determining presence or absence of an object in the monitoring area, and controlling the robot R according to the presence or absence of the object.

[0072] The monitoring area may include a warning area, a danger area, and an object area, each of which may be set, modified, and deleted. By allowing a user to set, modify, and delete each monitoring area, various operations of the robot R may be stably monitored through the setting, modification, and deletion of the monitoring area, and thus the robot R may more flexibly cope with changes in the working environment. An embodiment of the invention may include a computer program stored in a medium in order to set, modify, and delete each area using a computer device.

[0073] According to the invention, the robot safety monitoring method further includes, before determining presence or absence of the object, matching an image obtained through the stereo camera set 100 and obtaining detection information of the object, based on a result of the matching.

[0074] The invention may include a computer program stored in a medium to set a monitoring area, determine presence or absence of an object, and control a robot. The computer program may execute the setting of the monitoring area, determination of presence or absence of the object, and control of the robot corresponding to the setting of the monitoring area and the determination of presence or absence of the object according to the computer program stored in the medium.

[0075] Specific technical contents described in the embodiment are embodiments, and do not limit the technical scope of the embodiment. In order to concisely and clearly describe the description of the invention, descriptions of conventional general techniques and configurations may be omitted. Furthermore, the connecting lines, or connectors shown in the various figures presented are intended to represent exemplary functional relationships and / or physical or logical couplings between the various elements. It should be noted that many alternative or additional functional relationships, physical connections or logical connections may be present in a practical device. Moreover, no item or component is essential for application of the invention unless the item or component is specifically described as "essential" or "critical".

[0076] In the description and claims, "above" or similar referents may refer to both the singular and the plural unless otherwise specified. Furthermore, recitation of ranges of values herein are merely intended to serve as a shorthand method of referring individually to each separate value falling within the range, unless otherwise indicated herein, and each separate value is incorporated into the specification as if it were individually recited herein. The operations that constitute a method described herein can be performed in any suitable order unless otherwise indicated herein or otherwise clearly contradicted by context. Embodiments are not limited to the described order of the operations. The use of any and all examples, or exemplary language (e.g., "such as") provided herein, is intended merely to better illuminate the invention and does not pose a limitation on the scope of the invention unless otherwise claimed. Robot safety monitoring systems according to embodiments provide an effect capable of detecting an object no matter what angle the object enters by vertically arranging two cameras in order to overcome structural limitations of a stereo camera.

[0077] In addition, the robot safety monitoring systems according to embodiments may provide sufficient robot safety monitoring to users with only a camera without installing a mechanical fence.

[0078] Moreover, because the robot safety monitoring systems according to embodiments do not utilize a mechanical fence, the robot safety monitoring systems according to embodiments may freely set, modify, and delete the monitoring area even after the robot safety monitoring systems are initially installed, and thus may flexibly deal with changes in the work environment.

[0079] Furthermore, in the robot safety monitoring systems according to embodiments, when any one of first and second cameras arranged in a T shape is damaged, only one of the two cameras rather than the entire first and second cameras may be selectively replaced, so repair and replacement may be easy and improved economical efficiency may be provided.

[0080] The effects of the invention are not limited to the above-mentioned effects, and other effects not mentioned will be clearly understood by a person skilled in the art from the accompanying claims.

[0081] It should be understood that embodiments described herein should be considered in a descriptive sense only and not for purposes of limitation. Descriptions of features or aspects within each embodiment should typically be considered as available for other similar features or aspects in other embodiments. While one or more embodiments have been described with reference to the figures, it will be understood by those of ordinary skill in the art that various changes in form and details may be made therein without departing from the scope of the invention as defined by the following claims.

Claims

1. A system comprising: a robot (R); and a robot safety monitoring system comprising: a stereo camera set (100, 100') configured to photograph the robot (R) and a monitoring area around the robot (R); and a processor (200) connected to the stereo camera set (100, 100'), wherein the processor (200) is configured to set the monitoring area; wherein the stereo camera set (100, 100') comprises: a first stereo camera (110, 110') including a plurality of first camera modules (111, 111') spaced apart from each other; characterized in that the stereo camera set (100, 100') further comprises: a second stereo camera (120, 120') including a plurality of second camera modules (121, 121') spaced apart from each other, wherein based on a first direction, the first stereo camera (110, 110') and the second stereo camera (120, 120') have different fields of view (FOV1, FOV2, FOV1', FOV2'), and wherein a first distance (D1) between two of the plurality of first camera modules (111, 111') is greater than a second distance (D2) between one of the two of the plurality of first camera module (111, 111') and one of the plurality of second camera modules (121, 121') which is closest to the one of the two of the plurality of first camera modules (111, 111'); and wherein the second distance (D2) is 50 % to 95 % of the first distance (D1); wherein the processor (200) is further configured to match images obtained through the plurality of first camera modules (111, 111') and the plurality of second camera modules (121, 121'), obtain detection information of an object based on a result of the matching and then determine whether an object exists in the monitoring area by using the stereo camera set (100, 100'), and control the robot (R) when an object exists in the monitoring area, wherein the monitoring area comprises a warning area (500), a danger area (600), and an object area (700), wherein the warning area (500) comprises the danger area (600) and the object area (700), and when an object exists in an area other than the object area (700) among the warning area (500), the processor (200) is further configured to decrease a driving speed of the robot (R); and when an object exists in an area other than the object area (700) among the danger area (600), the processor (200) is further configured to stop the robot (R) from moving.

2. The system of claim 1, wherein all of the plurality of first camera modules (111, 111') and second camera modules (121, 121') have same diagonal fields of view (FOV3, FOV3'), and wherein the plurality of first camera modules (111, 111') are arranged in a direction perpendicular to a direction in which the plurality of second camera modules (121, 121') are arranged.

3. The robot safety monitoring system of any one of the preceding claims, wherein all of the plurality of first camera modules (111, 111') and second camera modules (121, 121') have same horizontal fields of view (FOV1) and vertical fields of view (FOV2).

4. The system of claim 3, wherein the horizontal field of view (FOV1) is 1.2 times to 3 times the vertical field of view (FOV2).

5. The system of any one of the preceding claims, wherein the processor (200) comprises: an image processor (210) configured to match the images obtained through the plurality of first camera modules (111) and second camera modules (121) and obtain the detection information of an object based on a result of the matching; and a robot controller (220) configured to determine presence or absence of an object in the monitoring area and control the robot (R).

6. The system of any one of the preceding claims, wherein the stereo camera set (100, 100') is disposed above the robot (R) in a direction facing the robot (R).

7. The system of any one of the preceding claims, wherein the first camera (110') and the second camera (120') are arranged to cross each other in the middle.

8. A robot safety monitoring method comprising: setting a robot (R) and a monitoring area around the robot (R); determining whether an object exists in the monitoring area by using a stereo camera set (100, 100'), and controlling the robot (R) when an object exists in the monitoring area; wherein the stereo camera set (100, 100') comprises: a first stereo camera (110, 110') including a plurality of first camera modules (111, 111') spaced apart from each other; and a second stereo camera (120, 120') including a plurality of second camera modules (121, 121') spaced apart from each other, wherein based on a first direction, the first stereo camera (110, 110') and the second stereo camera (120, 120') have different fields of view (FOV1, FOV2, FOV1', FOV2'); wherein a first distance (D1) between two of the plurality of first camera modules (111, 111') is greater than a second distance (D2) between one of the two of the plurality of first camera module (111, 111') and one of the plurality of second camera modules (121, 121') which is closest to the one of the two of the plurality of first camera modules (111, 111'); and wherein the second distance (D2) is 50 % to 95 % of the first distance (D1); wherein the method further comprises: before the determining whether an object exists in the monitoring area by using a stereo camera set (100, 100'), and controlling the robot(R) when an object exists in the monitoring area, matching images obtained through the plurality of first camera modules (111, 111') and the plurality of second camera modules (121, 121') and obtaining detection information of an object based on a result of the matching, wherein the monitoring area comprises a warning area (500), a danger area (600), and an object area (700), wherein the warning area (500) comprises the danger area (600) and the object area (700), and the method further comprising: decreasing a driving speed of the robot (R) when an object exists in an area other than the object area (700) among the warning area (500); and stopping the robot (R) from moving when an object exists in an area other than the object area (700) among the danger area (600).

9. The robot safety monitoring method of claim 8, wherein each of the warning area (500), the danger area (600), and the object area (700) is set, modified, and deleted.

10. A computer program stored comprising instructions which, when the program is executed by a system of any one of claim 1 to 7, cause the system to carry out the method of any one of claims 8 to 9.