JP2021066011A - Method and control system for verifying and updating calibration information for robot control - Google Patents

Abstract

To provide a computing system and a method for calibration verification.SOLUTION: The computing system is configured to perform a first calibration operation, and to control a robot arm to move a verification symbol to a reference location. The robot control system further receives, from a camera, a reference image of the verification symbol, and determines a reference image coordinate for the verification symbol. The robot control system further controls the robot arm to move the verification symbol to the reference location again during an idle period, receives an additional image of the verification symbol, and determines a verification image coordinate. The robot control system determines a deviation parameter value based on the reference image coordinate and the verification image coordinate, determines whether the deviation parameter value exceeds a defined threshold, and performs a second calibration operation if the threshold is exceeded.SELECTED DRAWING: Figure 12A

Description

Mutual reference to related applications This application is a continuation of US Patent Application No. 16 / 732,832 filed on January 2, 2020, the title of the invention "Method and Control System for Verification and Updating Camera Calibration for Robot Continuation". This is a continuation of US Patent Application No. 16 / 525,004 filed on July 29, 2019, the title of the invention "Method and Control System for Verification and Updating Camera Calibration for Robot Control". , US Patent Application No. 16 / 369,630 filed on March 29, 2019, the title of the invention "Method and Control System for Verification and Updating Camera Calibration for Robot Control", which is a continuation of the whole. Incorporated herein. This application further asserts the benefits of US Patent Application No. 62 / 916,798, filed October 18, 2019, the title of the invention, "Method and Control System for Verification for Robot Control," in its entirety. It is also incorporated herein by reference.

The present invention relates to a method and a control system for verifying and updating calibration information for robot control.

As automation becomes more common, robots are used in more environments, such as warehousing and manufacturing environments. For example, robots may be used in warehouses to load or unload goods from pallets, or in factories to lift objects from conveyor belts. The movement of the robot may be constant, or it may be based on the input of images taken by a camera in a warehouse or factory. In the latter situation, a calibration operation may be performed to determine the characteristics of the camera and to determine the relationship between the camera and the environment in which the robot is located. The calibration operation can generate calibration information used to control the robot. In some embodiments, the calibration operation may require manual operation by a person, who either manually controls the movement of the robot or manually controls the camera to image the robot. Can be captured.

One aspect of the embodiments herein relates to performing calibration verification for robot control, such as verifying camera calibration or other system calibration. Calibration verification can be performed by a robotic control system with a communication interface and control circuitry. The communication interface can be configured to communicate with a robot having a base and a robot arm on which a verification symbol is placed and to communicate with a camera having a camera field of view. The control circuit of the robot control system a) executes the first calibration operation (for example, the first camera calibration) to determine the calibration information (for example, the camera calibration information), and b). The first operation command is output to the communication interface, and the communication interface causes the robot to operate the verification symbol at a position in the camera field of view during or after the first calibration operation. To output the first operation command, which is configured to communicate one operation command, which is the reference part of one or more reference points for verifying the first calibration operation. , C) Receiving an image of the verification symbol from the camera via a communication interface, the camera being configured to capture the image of the verification symbol at a reference location, the image being a reference image for verification. Receiving the image of the verification symbol and d) determining the reference image coordinates for the verification symbol, the reference image coordinates are the coordinates at which the verification symbol appears in the reference image, the reference image coordinates are determined. That and e) to output a second operation command based on the calibration information to the communication interface, the communication interface causes the robot to perform the second operation so as to move the robot arm and execute the robot operation. By outputting a second operation command, which is configured to communicate commands, it can be configured to perform calibration verification.

In one embodiment, the control circuit f) detects a pause period during robot operation and g) outputs a third operation command to the communication interface, the communication interface being the robot during the pause period. Outputting a third action command, configured to communicate a third action command to the robot so that the arm moves the verification symbol to at least the reference point, and h) from the camera via the communication interface. Receiving an additional image of the verification symbol, the camera is configured to capture the additional image of the verification symbol at least at the reference point during the pause, and the additional image is the verification image for verification, of the verification symbol. Receiving an additional image and i) determining the verification image coordinates used for verification, the verification image coordinates are the coordinates at which the verification symbol appears in the verification image, the verification image coordinates are determined. And j) the deviation parameter value is determined based on the amount of deviation between the reference image coordinates and the verification image coordinates, and both the reference image coordinates and the verification image coordinates are associated with the reference points and the deviations. The parameter value is the change since the first calibration operation of the camera configured to communicate with the communication interface, or the first calibration of the relationship between the camera and the robot configured to communicate with the communication interface. Judging the deviation parameter value, which indicates the change after the command operation, k) determining whether the deviation parameter value exceeds the specified threshold, and l) determining whether the deviation parameter value exceeds the specified threshold. In response to the decision to do, perform a second calibration operation (eg, a second camera calibration operation) to determine updated calibration information (eg, updated camera calibration information). And are configured to perform further calibration verification.

The above-mentioned features, objectives, and advantages of the present invention, as well as other features, objectives, and advantages, will be apparent from the following description of embodiments of the invention as shown in the accompanying drawings. The accompanying drawings incorporated herein and in part of the specification further illustrate the principles of the invention and serve to enable those skilled in the art to practice and use the invention. The drawings are not at a constant scale.

The block diagram of the system in which the verification of the calibration information is executed according to the embodiment of this specification is illustrated. The block diagram of the system in which the verification of the calibration information is executed according to the embodiment of this specification is illustrated. FIG. 6 illustrates a block diagram of a robot control system configured to perform calibration verification according to an embodiment of the present specification. A block diagram of a camera on which camera calibration is performed according to an embodiment of the present specification is shown. A system illustrating a controlled robot based on calibration information obtained from a calibration operation according to an embodiment of the present specification is illustrated. A system for performing a calibration operation according to an embodiment of the present specification is illustrated. Provided is a flow chart illustrating a method for performing verification of calibration information according to one embodiment of the present specification. Provided is a flow chart illustrating a method for performing verification of calibration information according to one embodiment of the present specification. Illustrates a system in which a verification symbol is placed on a robot and the verification symbol is used to perform verification of calibration information according to one embodiment of the present specification. Illustrates a system in which a verification symbol is placed on a robot and the verification symbol is used to perform verification of calibration information according to one embodiment of the present specification. Illustrative verification symbols according to one embodiment of the present specification are illustrated. An embodiment of a reference point in which each image of the verification symbol is captured according to one embodiment of the present specification is illustrated. An embodiment of a reference point in which each image of the verification symbol is captured according to one embodiment of the present specification is illustrated. An embodiment of a reference point in which each image of the verification symbol is captured according to one embodiment of the present specification is illustrated. An embodiment of a reference point in which each image of the verification symbol is captured according to one embodiment of the present specification is illustrated. An embodiment for determining the reference image coordinates according to the embodiment of the present specification is illustrated. An example of determining the verification image coordinates according to the embodiment of the present specification is illustrated. An exemplary timeline for verifying calibration information according to one embodiment of the specification is illustrated. A flow diagram illustrating an exemplary method for performing verification of calibration information according to one embodiment of the present specification is provided. Illustrates a system according to an embodiment of the present specification in which a group of verification symbols is placed on a robot and the group of verification symbols is used to perform verification of calibration information. Illustrates a system according to an embodiment of the present specification in which a group of verification symbols is placed on a robot and the group of verification symbols is used to perform verification of calibration information. Illustrates a system according to an embodiment of the present specification in which a group of verification symbols is placed on a robot and the group of verification symbols is used to perform verification of calibration information. Illustrates a system according to an embodiment of the present specification in which a group of verification symbols is placed on a robot and the group of verification symbols is used to perform verification of calibration information. Illustrates a system according to an embodiment of the present specification in which a group of verification symbols is placed on a robot and the group of verification symbols is used to perform verification of calibration information. Illustrates a group of verification symbols having different sizes according to one embodiment of the present specification. Provided is a flow chart illustrating a method for performing verification of calibration information according to one embodiment of the present specification. Provided is a flow chart illustrating a method for performing verification of calibration information according to one embodiment of the present specification. A reference image and a verification image associated with the first pose of the robot arm are illustrated, respectively. A reference image and a verification image associated with the first pose of the robot arm are illustrated, respectively. The reference image and the verification image associated with the second pose of the robot arm are illustrated, respectively. The reference image and the verification image associated with the second pose of the robot arm are illustrated, respectively.

The following detailed description is merely exemplary in nature and is not intended to limit the use and use of the present invention or the present invention. Moreover, it is not intended to be limited by any explicit or implied theory presented in the technical fields, background arts, outlines of the invention or detailed description below.

The embodiments described herein relate to verifying and / or updating calibration information used to control a robot, such as a robot used in a warehouse, manufacturing plant, or in any other environment. More specifically, the calibration information may be performed to facilitate control of the robot operating system and can be determined by performing a calibration operation, sometimes referred to as system calibration. System calibration is camera calibration (sometimes called camera calibration or camera calibration operation), robot calibration (sometimes called robot calibration), calibration of another element of the robot operation system. , Or any combination thereof. System calibration is performed, for example, by a robot control system (also called a robot controller) to facilitate the ability of a robot control system to control a robot based on images captured (eg, taken) by a camera. Calibration information to be performed (for example, camera calibration information) can be generated. For example, a robot may be used to lift a package in a warehouse, where the placement of the robot's robot arm or other component can be based on an image of the package captured by the camera. In that case, if the calibration information includes the camera calibration information, the camera calibration information may be used together with the image of the package, for example, to determine the location and orientation of the package with respect to the robot arm of the robot. it can. If the system calibration includes a camera calibration, the camera calibration determines each estimate of the camera's unique parameters (sometimes called internal parameters) and between the camera and its external environment. It can include determining the estimated value of the relationship. The camera's unique parameters can have one or more parameter values such as matrix, vector or scalar values. In addition, examples of unique parameters include projection matrix and strain parameters. In one example, camera calibration can include identifying the position of the camera with respect to a fixed position in the external environment, which is the relationship between the camera and the fixed position in the external environment. It can be expressed as a transformation function (transformation function). In some cases, camera calibration can be performed with the help of a calibration pattern, which can have pattern elements that are placed at defined positions on the calibration pattern. The camera can capture an image of the pattern element of the calibration pattern (also called the calibration image), and camera calibration is performed based on comparing the image of the pattern element with the defined position of the pattern element. Can be done. Camera calibration is described in detail in U.S. Patent Application No. 16 / 295,940 (reference number MJ0021US1) filed on March 7, 2019, in the title of the invention "METHOD AND DEVICE FOR PERFORMING AUTOMATIC CAMERA CALIBRATION FOR ROBOT CONTROL". And the entire contents are incorporated herein by reference.

As mentioned above, one aspect of the disclosure relates to verifying that camera calibration or other calibration operations performed at an early point in time are still accurate at a later point in time. Camera calibration performed at an early point in time produces camera calibration information that reflects the characteristics of the camera at that time, such as the camera's unique parameters or the relationship between the camera and its external environment at that time. be able to. In some cases, the characteristics of the camera may change over time, so early camera calibration may not be able to maintain accuracy over time. In the first example, the camera's unique parameters may change over time. Such changes can be caused, for example, by temperature changes, which change the shape of the camera housing and / or lens. In the second example, the relationship between the camera and its external environment may change over time. For example, the camera may change position or orientation with respect to, for example, the base of the robot, or a position in the warehouse. Such changes include, for example, temperature changes that expand or contract any component used to mount the camera, a person or other object that collides with the camera, or within the external environment of the camera (eg, a warehouse). It can be caused by vibrations, forces due to the camera's own weight (ie, by gravity), or some other factor. These changes may cause the camera calibration information or other calibration information to become out of date, and this camera calibration information or other calibration information may be used to later configure the robot arm or other robots. As a result of positioning the element, errors can occur. In other words, if the characteristics associated with the camera change over time, but the camera calibration information is not updated to reflect such changes, then the robot is out of date or for some other reason. It may operate based on inaccurate camera calibration information, which can cause unwanted errors in the robot's operation. To address the possibility of changes in one or more characteristics of the camera, the robot control system is when the camera calibration information from the camera calibration is no longer accurate enough (or more generally). , When the calibration information from the calibration operation is no longer accurate enough), the verification can be performed automatically. By detecting such conditions, it may provide an indicator of changes in the characteristics of the camera, or some other element of the robotic operating system. If the verification detects that the calibration information is no longer accurate enough, the robot control system performs a calibration operation to perform a more up-to-date singular or multiple characteristics of the camera or another element of the robotic operating system. It is possible to determine the updated calibration information that can reflect the above. The updated calibration information can be used to control the placement of the robot arm, or any other aspect of the robot's movements. Therefore, the robot performs automatic validation of calibration information and / or updates of calibration information based on accurate information about one or more characteristics associated with any other element of the camera or robotic operating system. Make sure that works.

One aspect of an embodiment of the present specification relates to verifying calibration information about a camera by comparing a reference image captured by the camera with a verification image captured by the camera. In some cases, the reference image can be an image of an object captured when the object is in a particular position at an early point in time, and a verification image can be an image of the object captured at a later point in time at the same position. It can be an image. The verification can determine whether the deviation between the reference image and the verification image is too large, such as whether the deviation exceeds a certain threshold. In some embodiments, the object can be a verification symbol. More specifically, the robot arm or other component of the robot can have a verification symbol used to verify the calibration information. Both the reference image and the verification image can be captured or otherwise included, and the robot control system compares the appearance of the verification symbol in the reference image with the appearance of the verification symbol in the verification image. This allows the two images to be compared. For example, after the robot control system performs a calibration operation that generates calibration information at a particular point in time, the robot control system puts a verification symbol on a set of predetermined within the camera's field of view (also called the camera's camera field of view). The robot arm can be controlled (eg, via an action command) to move to, and these can be used as a set of reference points for verification. The camera can capture each reference image of the verification symbol at a set of reference points. In some cases, the reference image can be captured immediately after the calibration operation is performed. The operation of the robot arm, or more specifically, the operation command used to operate the robot arm, can be based on the calibration information from the calibration operation just performed, or from the calibration information. Can be independent. In some cases, the reference image can be captured before the robot initiates robot operation. After the reference image has been captured, the robot can be considered ready to initiate robotic operations to perform the task, and the robot control system will use, for example, the robot based on the image next captured by the camera. The positioning of the arm can be controlled.

As mentioned above, the reference image can be compared to the next captured verification image. In one embodiment, the verification image can be captured during one or more pauses detected by the robot control system. More specifically, once the robot operation has begun, the robot can begin performing robot tasks (eg, by interacting with luggage or other objects). When the robot is performing a robot operation, the robot control system can detect one or more pauses with respect to the robot. In some cases, the pause period can be a period during which the robot is not performing robot work during robot operation. In some cases, the robot control system can schedule robot operations based on detecting or otherwise predicting objects that the robot needs to interact with, and the robots need to interact. The rest period can be detected based on detecting the absence of an object or otherwise predicting it.

During the rest period (s), the robot control system moves the robot arm or other components of the robot to reference points (eg, via motion commands), at each reference point, the respective verification image. Can be controlled to be captured (eg, via a camera command). If the robot has a verification symbol placed on it, the robot control system can, more specifically, move the verification symbol to a reference point and control the robot arm to capture the verification image. The robot control system can then determine how much each verification image deviates from the corresponding reference image at each reference location. In some cases, the deviation between the verification image and each reference image can be expressed as a deviation parameter. If the value of the deviation parameter (also called the deviation parameter value) exceeds a defined threshold for the deviation parameter (sometimes referred to as the defined deviation threshold), the robotic control system will perform additional calibration operations (eg, referred to as the defined deviation threshold). Further camera calibration) can be performed to determine updated calibration information about the camera (eg, updated camera calibration information). When the value of the deviation parameter exceeds the specified deviation threshold, this condition can indicate that the use of previously generated calibration information can result in an undesired amount of error in robot operation. .. Therefore, in some cases, the robot operation may be interrupted or stopped while the further calibration operation is being performed (the interruption may be considered as another pause period). After the further calibration operation is completed, a new set of reference images can be captured and the robot operation can be continued using the updated calibration information. During the subsequent pause period (s), a new set of verification images can be captured and the robot control system compares the new set of reference images with the new set of verification images. This allows further verification of the calibration operation to be performed.

As mentioned above, if the value of the deviation parameter exceeds the defined deviation threshold, the robot control system can perform additional calibration operations. If the value of the deviation parameter does not exceed the deviation threshold, the robot operation can continue after the pause period without the robot control system performing further calibration operations. In this scenario, the camera can capture a new set of verification images at each reference point during subsequent pauses (s). When a new set of verification images is captured, the robot control system verifies the calibration information by determining how much the new set of verification images deviates from each reference image at each reference location. Can be executed again.

As mentioned above, the robot arm can have a verification symbol, such as a ring pattern, placed on it, which may or may not be captured by the reference and verification images. May be included in those images in the manner of. In one embodiment, the robot control system includes the reference image and the respective verification images based on the respective positions where the verification symbols appear in the reference image and based on the respective positions where the verification symbols appear in the verification image. The deviation between can be specified. For example, the robot control system can specify the reference image coordinates for each reference point. The reference image coordinates for a specific location can be the coordinates at which the verification symbol appears in the captured reference image when the verification symbol is placed at that reference location. More specifically, the reference image coordinates can be associated with a particular reference location and refer to the image coordinates where the verification symbol appears in the reference image captured by the camera when the verification symbol is placed at that reference location. Can be done. In the above example, the image coordinates may refer to coordinates in the image, such as pixel coordinates. When the robot control system subsequently places verification symbols at specific reference points and acquires the corresponding verification image, the robot control system can determine the verification image coordinates. In addition, the verification image coordinates can also be associated with the reference location, and can refer to the image coordinates (for example, pixel coordinates) in which the verification symbol appears in the verification image captured by the camera when the verification symbol is placed at the reference location. it can. The robot control system can compare the reference image coordinates associated with a particular reference point with the verification image coordinates associated with the same reference point. This comparison can be performed for each reference location in which the verification image and the reference image are captured.

In one example, the reference image coordinates in which the verification symbol appears in the reference image can be the coordinates of the center of the verification symbol in the reference image (also referred to as the center coordinates of the verification symbol in the reference image). Similarly, the verification image coordinates in which the verification symbol appears in the verification image can be the coordinates of the center of the verification symbol in the verification image (also referred to as the center coordinates of the verification symbol in the verification image). For each reference point where the robot arm and / or the verification symbol was located when the corresponding verification image was captured, the robot control system has the reference image coordinates associated with the reference point and the verification image coordinates associated with the same reference point. The deviation between can be identified. If the robot arm and / or the verification symbol has been placed at multiple reference points, the robot control system will use the respective deviations between each reference image coordinate and each verification image coordinate for the multiple reference points. The amount can be specified. The robot control system can further specify the value of the deviation parameter based on the amount of deviation between the reference image coordinates for each reference point and the verification image coordinates for each reference location.

In one example, the verification symbol can include multiple shapes that are concentric with each other so that the centers of the plurality of shapes within the verification symbol are at the same or substantially the same position. For example, the verification symbol can be a ring pattern containing two or more concentric circles. In some cases, if the reference image coordinates of the verification symbol are the center coordinates of the verification symbol in the reference image, the robot control system will use the verification symbol's center coordinates based on the center coordinates of each of the multiple shapes in the reference image. The center coordinates can be specified, and the center coordinates of a specific shape are the coordinates of the center of the shape. When the verification symbol is a ring pattern, the center coordinates of the first circle forming the ring pattern in the reference image and the center coordinates of the second circle forming the ring pattern are averaged in the reference image. The center coordinates of the ring pattern can be specified. Similarly, the center coordinates of the verification symbol in the verification image can be specified based on the center coordinates of each of the plurality of shapes forming the verification symbol in the verification image. In some cases, the accuracy of verification can be improved by forming a verification symbol using a plurality of shapes. For example, the robustness of verification against image noise can be improved by specifying the center coordinates of the verification symbol by using the center coordinates of each of the plurality of shapes in one image. More specifically, when the image of the verification symbol contains image noise, the image noise may reduce the accuracy with which the robot control system detects the center coordinates of a specific shape of the verification symbol. However, when the center coordinates of the shape are averaged with the center coordinates of another shape and the center coordinates of the verification symbol are specified, the averaged center coordinates can reduce the influence of image noise. As a result, the accuracy in specifying the center coordinates of the verification symbol can be improved.

In one example, the verification symbol can have a plurality of regions, each of which is different in color, and each area of the plurality of regions can have a identifiable defined ratio. For example, the verification symbol can have a first region having a first color (eg, black) and a second region having a second color (eg, white) of the first region. The ratio of the area to the area of the second region is defined or otherwise known. The identifiable ratio can facilitate the identification of verification symbols in the image, especially if the image incorporates other features such as dots of the calibration pattern or is otherwise included. For example, the robot arm moving the verification symbol may have a calibration pattern placed on the robot arm. The robot control system can use the ratio to distinguish between the verification symbol and the dots in the calibration pattern. More specifically, since the ratio of the areas of the plurality of regions of the verification symbol is defined as an identifiable ratio, the robot control system can identify the verification symbol in the image based on the defined ratio. .. During the identification of the verification symbols appearing in the image, the robot control system can distinguish between the verification symbols and the calibration pattern or other features based on the defined ratio. In some cases, the verification symbol can be identified within the image as a portion of the image that has a plurality of regions of different colors and has a defined ratio between the areas of the plurality of regions. If the robotic control system or other system or device determines that a particular part of the image does not have multiple areas of different colors, or what is the specified ratio of each area of the multiple areas? If it determines that it has a different ratio, the robot control system can determine that the portion of the image is not a verification symbol.

In one example, the robot control system can perform verification based on the temperature around the robot. For example, a robot control system can adjust a defined deviation threshold (ie, define a new value for the deviation threshold) based on temperature. For example, temperature affects various parts in the camera and / or in the robot, as some materials may be sensitive to temperature and / or may expand / contract in response to temperature. In some cases. Changes in temperature may change the camera's unique parameters (s) and / or the relationship between the camera and its external environment. In one embodiment, the deviation threshold can be set to have a first value when the temperature is outside the specified range, while the deviation threshold is the first when the temperature is within the specified range. It can be set to have a second value lower than the value of. For example, when the temperature is within a defined normal operating temperature range (eg, within 10 degrees of room temperature), the deviation threshold can be a first value. When the temperature is outside the normal operating temperature range, the deviation threshold can have a second value lower than the first value. Temperatures outside the normal operating temperature range may increase the likelihood of changes in the camera, or in the relationship between the camera and the external environment, and therefore previously generated camera calibration information or any other. A second method is to more easily trigger further calibration operations when the temperature is outside the normal operating range, as the calibration information can increase the likelihood of errors in operating the robot. The value can be lower than the first value.

In one embodiment, the verification of calibration information may rely on only a single reference point. Alternatively, the verification of calibration information can rely on multiple references. The reference location can be any position within the field of view of the camera, or it can be a specific defined position. For example, the reference point can be defined as a position on the surface of at least one virtual sphere that is concave with respect to the camera. At each reference point in this scenario, control the robot arm to position the verification symbol so that it is tangentially positioned with respect to the surface of at least one virtual sphere when facing the camera. Can be done. This positioning allows the verification symbol to be better captured from the front by the camera, or can be captured in another way (the verification symbol directly faces the camera), so that the image of the verification symbol is , It is closer to the plan view, not the perspective view of the verification symbol. For example, if the verification symbol is a ring pattern, positioning the ring pattern tangentially to the surface of the virtual sphere will result in the resulting ring pattern image being still circular rather than appearing elliptical. Can be made visible. The resulting image may show less projection distortion (for scenarios where the ring pattern appears elliptical in the image) or may show no projection distortion at all. The absence of projection distortion can facilitate the accurate identification of the center coordinates of the ring pattern. In some cases, the reference can be divided into a plurality of virtual spheres that are all concave with respect to the camera. Multiple virtual spheres can share a common center and can be of different sizes, so that each virtual sphere has a sphere with a different distance from the camera. In some cases, the camera can be a common center for all virtual spheres.

FIG. 1A illustrates a block diagram of a robot operating system 100 (also referred to as system 100) for performing automatic camera calibration and automatic verification of camera calibration. Some of the examples below discuss performing automatic camera calibration and verifying camera calibration information as determined from automatic camera calibration, but these examples are more In general, it can be applied to any type of auto-calibration operation and to verify any type of calibration information determined from the auto-calibration operation. The robot operation system 100 includes a robot 150, a robot control system 110 (also referred to as a robot controller), and a camera 170. In one embodiment, the system 100 can be located in a warehouse, in a manufacturing plant, or in another facility. The robot control system 110 can be configured to perform camera calibration, which will be discussed in more detail later, to identify camera calibration information, which can be used for robotic operations such as lifting luggage in a warehouse. Will be used later to control the robot 150 to perform. The robot control system 110 can be further configured to perform camera calibration verification, which is also discussed in more detail later, to verify that the camera calibration information is still sufficiently accurate. In some cases, the robot control system 110 is configured to perform camera calibration and control the robot 150 to perform robot operations based on camera calibration information. In some cases, the robot control system 110 can form a single device (eg, a single console or a single computer) that communicates with the robot 150 and the camera 170. In some cases, the robot control system 110 may include a plurality of devices.

In some cases, the robot control system 110 can be a dedicated system that performs camera calibration and / or verification of camera calibration, with the latest camera calibration information in another control system (also called another controller). Can communicate (not shown), after which another control system controls the robot 150 to perform robot operations based on the latest camera calibration information. The robot 150 can be positioned based on the image captured by the camera 170 and based on the camera calibration information. More specifically, in one embodiment, the robot control system 110 generates an operation command based on an image and based on camera calibration information, communicates the operation command to the robot 150, and transmits the operation command to the robot arm. It can be configured to control operation. In some cases, the robot control system 110 is configured to perform camera calibration verification during a pause during robot operation. In some cases, the robot control system 110 is configured to perform verification while performing robot operations on the robot 150.

In one embodiment, the robot control system 110 can be configured to communicate with the robot 150 and the camera 170 via wired or wireless communication. For example, the robot control system 110 is a robot via an RS-232 interface, a universal serial bus (USB) interface, an Ethernet® interface, a Bluetooth® interface, an IEEE802.11 interface, or any combination thereof. It can be configured to communicate with the 150 and / or the camera 170. In one embodiment, the robot control system 110 can be configured to communicate with the robot 150 and / or the camera 170 via a local computer bus such as a peripheral component interconnect (PCI) bus.

In one embodiment, the robot control system 110 can exist separately from the robot 150 and can communicate with the robot via the wireless or wired connections discussed above. For example, the robot control system 110 can be a stand-alone computer configured to communicate with the robot 150 and the camera 170 via a wired or wireless connection. In one embodiment, the robot control system 110 can be an integral component of the robot 150 and can communicate with other components of the robot 150 via the local computer bus discussed above. In some cases, the robot control system 110 can be a dedicated control system (also referred to as a dedicated controller) that controls only the robot 150. In other cases, the robot control system 110 can be configured to control a plurality of robots, including the robot 150. In one embodiment, the robot control system 110, the robot 150 and the camera 170 are located in the same facility (eg, warehouse). In one embodiment, the robot control system 110 can be remote from the robot 150 and the camera 170 and communicates with the robot 150 and the camera 170 via network communication (eg, a local area network (LAN) connection). Can be configured in.

In one embodiment, the robot control system 110 reads (retrieve) an image of the calibration pattern 160 and / or the verification symbol 165 placed on the robot 150 (eg, on the robot arm of the robot) from the camera 170. Alternatively, it can be configured to receive in another way. In some cases, the robot control system 110 can be configured to control the camera 170 to capture such images. For example, the robot control system 110 generates a camera command that causes the camera 170 to capture an image of the camera 170's field of view (also called the camera field of view), and communicates the camera command to the camera 170 via a wired or wireless connection. Can be configured in. The same command can also cause the camera 170 to communicate an image to the robot control system 110, or more generally, a storage device accessible by the robot control system 110. Alternatively, upon receiving the camera command, the robot control system 110 can generate another camera command that communicates the image (s) captured by the camera 170 to the robot control system 110. In one embodiment, the camera 170 automatically captures images in its camera field of view on a regular basis or in response to defined trigger conditions without the need for camera commands from the robot control system 110. Can be captured. In such an embodiment, the camera 170 automatically transmits an image to the robot control system 110, or more generally to a storage device accessible by the robot control system 110, without using camera commands from the robot control system 110. It can also be configured to communicate in a targeted manner.

In one embodiment, the robot control system 110 is configured to control the operation of the robot 150 via motion commands generated by the robot control system 110 and communicated to the robot 150 via a wired or wireless connection. be able to. The robot 150 can be configured to have one or both of the calibration pattern 160 and the verification symbol 165 on the robot 150. For example, FIG. 1B illustrates a robot operation system 100A in which the verification symbol 165 is arranged on the robot 150 in the absence of the calibration pattern 160 of FIG. 1A. In one example, the verification symbol 165 can be part of the robot 150 and can be permanently placed on the robot 150. For example, the verification symbol 165 can be permanently applied onto the robot 150 or can be part of a sticker or board that is permanently attached to the robot 150. In another example, the verification symbol 165 can be another component that is removable from the robot 150. The verification symbol 165 can be permanently placed on the robot 150 or can be another component that is removable from the robot 150.

In one embodiment, the only image used in the system 100 to control the robot 150 may be the image captured by the camera 170. In another embodiment, the system 100 can include multiple cameras and the robot 150 can be controlled by images from the plurality of cameras.

FIG. 1B further illustrates an embodiment in which the robot control system 110 communicates with the user interface device 180. The user interface device 180 can configure an interface with an operator of the robot 150, such as an employee in a warehouse where the robot 150 is located. The user interface device 180 can include, for example, a tablet computer or a desktop computer, which provides a user interface for displaying information related to the operation of the robot 150. As mentioned above, the robot control system 110 can be configured to detect when the deviation parameter value exceeds a defined deviation threshold. In one embodiment, the user interface device 180 may provide an alarm or other warning to notify the operator that the deviation parameter value exceeds a defined deviation threshold.

FIG. 1C illustrates a block diagram of the robot control system 110. As shown in the block diagram, the robot control system 110 includes a control circuit 111, a communication interface 113, and a non-temporary computer-readable medium 115 (eg, memory). In one embodiment, the control circuit 111 is one or more processors, a programmable logic circuit (PLC) or programmable logic array (PLA), a field programmable gate array (FPGA), an application specific integrated circuit (ASIC), or any other. Control circuit can be included.

In one embodiment, the communication interface 113 may include one or more components configured to communicate with the camera 170 of FIG. 1A or FIG. 1B and the robot 150 of FIG. 1A or FIG. 1B. For example, the communication interface 113 may include a communication circuit configured to perform communication over a wired or wireless protocol. As an example, the communication circuit can include an RS-232 port controller, a USB controller, an Ethernet controller, a Bluetooth® controller, a PCI bus controller, any other communication circuit, or a combination thereof. In one embodiment, the control circuit 111 can be configured to generate an operation command (eg, a motor operation command) and output the operation command to the communication interface 113. In this embodiment, the communication interface 113 can be configured to communicate motion commands to the robot 150 in order to control the motion of the robot arm or other components of the robot 150. In one embodiment, the control circuit 111 can be configured to generate a camera command and output the camera command (eg, an image capture command) to the communication interface 113. In this embodiment, the communication interface 113 is configured to communicate camera commands to the camera 170 in order to control the camera 170 to capture or otherwise capture an image of an object in the field of view of the camera. can do. In one embodiment, the communication interface 113 can be configured to receive an image or other data from the camera 170, and the control circuit 111 can be configured to receive an image from the communication interface 113.

In one embodiment, the non-transitory computer-readable medium 115 can include computer memory. Computer memory can include, for example, dynamic random access memory (DRAM), solid state integrated memory, and / or hard disk drive (HDD). In some cases, camera calibration can be performed through computer executable instructions (eg, computer code) stored on a non-transient computer-readable medium 115. In such a case, the control circuit 111 is configured to execute computer executable instructions and perform camera calibration verification (eg, steps exemplified in FIGS. 4A, 4B, and 9). It can include one or more processors.

FIG. 1D illustrates a block diagram of a camera 170 including one or more lenses 171, an image sensor 173, and a communication interface 175. The communication interface 175 can be configured to communicate with the robot control system 110 of FIG. 1A, FIG. 1B, or FIG. 1C, and can be similar to the communication interface 113 of FIG. 1C of the robot control system 110. In one embodiment, the one or more lenses 171 can focus light coming from the outside of the camera 170 on the image sensor 173. In one embodiment, the image sensor 173 can include an array of pixels configured to represent an image via their respective pixel intensity values. The image sensor 173 can include a charge-coupled device (CCD) sensor, a complementary metal oxide semiconductor (CMOS) sensor, a quantum image sensor (QIS), or any other image sensor.

As mentioned above, camera calibration can be performed to facilitate control of the robot based on the images captured by the camera. For example, FIG. 2 illustrates a robot operating system 200 (also referred to as a system 200), in which an image is used to perform a robotic operation, such as lifting an object 292 in a warehouse. Control the robot 250. More specifically, the system 200 can be an embodiment of the system 100 of FIG. 1A and includes a camera 270, a robot 250, and a robot control system 110. The camera 270 can be an embodiment of the camera 170 of FIGS. 1A, 1B, or 1D, and the robot 250 can be an embodiment of the robot 150 of FIG. 1A or FIG. 1B. The camera 270 can be configured to capture an image of an object 292 (eg, a package to be shipped) placed on a conveyor belt 293 in the warehouse, and the robot control system 110 can lift the object 292. , Can be configured to control the robot 250. When one or more objects are present on the conveyor belt 293, the robot control system 110 can be configured to schedule the actions of the robot 250 to lift the objects. In some cases, the robot control system 110 detects a time when an object does not exist on the conveyor belt 293 or a time when an object does not exist within the reach of the robot 250 on the conveyor belt 293 for robot operation. Can be configured to detect the rest period of.

In the embodiment of FIG. 2, the robot 250 can have a base 252 and a robot arm capable of operating with respect to the base 252. More specifically, the robot arm can include a plurality of links 254A to 254E and a robot hand 255 attached to the link 254E. The plurality of links 254A to 254E can be rotatable with respect to each other and / or linear links that can move linearly with respect to each other. Since FIG. 2 relates to a robot 250 used to lift an object, the robot hand 255 can include grips 255A and 255B used to grip the object 292. In one embodiment, the robot control system 110 can be configured to communicate an action command to rotate one or more of the links 254A-254E. The operation command can be a low-level command such as a motor operation command or a high-level command. When the operation command from the robot control system 110 is a high-level command, the robot 150 can be configured to convert the high-level command into a low-level command.

In one embodiment, the camera calibration information identified from the camera calibration is stationary with respect to the relationship between the camera 270 and the robot 250, or more specifically, the camera 270 and the base 252 of the robot 250. Describes the relationship with the world point 294. The world point 294 can represent the world in which the robot 250 is located or another environment, and can be any virtual point (image point) that is stationary with respect to the base 252. In other words, the camera calibration information can include information that describes the relationship between the camera 270 and the world point 294. In one embodiment, the relationship can refer to the position of the camera 270 with respect to the world point 294 and the orientation of the camera 270 with respect to the reference direction for the robot 250. The above relationship between the camera 270 and the world point 294 is sometimes referred to as the camera-world relationship and can be used to represent the relationship between the camera 270 and the robot 250. In some cases, using the camera-world relationship, the relationship between the camera 270 and the object 292 (also called the camera-object relationship) and the relationship between the object 292 and the world point 294 (also called the object-world relationship). ) Can be specified. The camera-object relationship and the object-world relationship can be used to control the robot 250 to lift the object 292.

In one embodiment, the camera calibration information can describe the unique parameters of the camera 270, which can be any parameter whose value is independent of the position and orientation of the camera 270. The unique parameters can characterize the characteristics of the camera 270, such as the focal length of the camera, the size of the image sensor of the camera, or the effect of lens distortion introduced by the camera 270.

An embodiment showing the detailed structure of one embodiment of the robot 350 is illustrated in FIG. 3, which illustrates a robot operating system 300 including a camera 370 and a robot control system 110 that communicates with the robot 350. The camera 370 can be an embodiment of the cameras 170/270 of FIGS. 1A, 1B, 1D, or 2, respectively, and the robot 350 can be the robot 150 / of FIGS. 1A, 1B, or 2, respectively. It can be one embodiment of 250. The camera 370 may be able to capture an image within the camera field of view 330. The robot 350 can include a base 352 and a robot arm that is movable relative to the base 352. The robot arm includes one or more links such as links 354A to 354E and a robot hand 355. In one embodiment, the links 354A-354E can be rotatably attached to each other. For example, the link 354A can be rotatably attached to the robot base 352 via the joint 356A. The remaining links 354B-354E can be rotatably attached to each other via joints 356B-356E. In one embodiment, the base 352 can be used to mount the robot 350, for example, on a mounting frame or mounting surface (eg, warehouse floor). In one embodiment, the robot 350 may include a plurality of motors configured to move the robot arm by rotating the links 354A-354E. For example, one of the motors can be configured to rotate the first link 354A with respect to the joint 356A and the base 302, as indicated by the dashed arrow in FIG. Similarly, other motors among the plurality of motors can be configured to rotate the links 354B to 354E. The plurality of motors can be controlled by the robot control system 110. FIG. 3 further illustrates a robot hand 355 arranged so as to be secured on the fifth link 354E. The robot hand 355 can have a calibration pattern 320 on it, the robot control system 110 captures an image of the calibration pattern 320 via the camera 370, and based on the captured image of the calibration pattern 320, Allows you to perform camera calibration. For example, the robot control system 110 can have the calibration pattern 320 in the camera field 330 when the camera 370 is being used to capture an image of the calibration pattern 320 (also called a calibration image). , The robot arm can be moved so that it can be seen from the camera 370. After the camera calibration has been performed, the robot hand 355 can be removed and replaced with another robot hand, such as a robot hand having a verification symbol placed on it, as discussed in more detail later.

As mentioned above, according to one embodiment, the calibration verification compares the reference image coordinates in which the verification symbol appears in the reference image with the verification image coordinates in which the verification symbol appears in the verification image. Can include. The comparison can determine the deviation between the validation image coordinates and the reference image coordinates, which can be used to determine if further calibration operations should be performed. The verification image can be captured during the pause period of robot operation. 4A and 4B illustrate flow diagrams illustrating method 400 for verification of camera calibration according to one embodiment. While some of the following embodiments discuss verifying camera calibration information as determined from camera calibration, Method 400 determines from any calibration operation performed for the robotic operating system. Can be used to more generally verify the calibration information to be performed. In one embodiment, the method 400 can be performed by the control circuit 111 of the robot control system 110. As mentioned above, the robot control system 110 can include the communication interface 113 of FIG. 1C, which is the robot 150 of FIG. 1A or FIG. 1B, and of FIG. 1A, FIG. 1B, or FIG. 1D. It is configured to communicate with the camera 170. In one embodiment, the robot is a base (eg, base 252 in FIG. 2 or base 352 in FIG. 3) and a robot arm on which a verification symbol is placed (eg, robot arm in FIG. 2 or 3). And can have, and the robot arm is movable with respect to the base.

An exemplary environment in which method 400 is performed is illustrated in FIGS. 5A and 5B, which illustrates a robot operating system 500 / 500A including a robot control system 110 communicating with a camera 570 and a robot 550, respectively. Illustrated. The camera 570 can be an embodiment of the cameras 170/270/370 of FIGS. 1, 2, or 3, respectively, and the robot 550 is the robot of FIGS. 1A, 1B, 2, or 3, respectively. It can be one embodiment of 150/250/350. The robot 550 can include a base 552 and a robotic arm (indicated as 553 in FIGS. 5A and 5B) that is operable with respect to the base 552. The robot arm includes one or more links such as links 554A to 554E. Links 554A-554E may also be embodiments of arm portions of robotic arms 553 that are operably attached to each other. In one embodiment, the links 554A-554E can be rotatably attached to each other. For example, the link 554A can be rotatably attached to the robot base 552. The remaining links 554B-554E can be rotatably attached to each other via a plurality of joints. In one embodiment, the base 552 can be used to attach the robot 552 to, for example, a mounting frame or mounting surface (eg, warehouse floor). The robot 550 can be operated in the same manner as the robot 350 of FIG. For example, the robot 550 can include a plurality of motors configured to move the robot arm by rotating the links 554A-554E with respect to each other. The robot arm can further include a robot hand attached to the link 554E. For example, FIG. 5A illustrates a first robot hand 555, a second robot hand 557, and a third robot hand 559, each of which can be detached from a fifth link 554E. The robot hand 555/557/559 may include, for example, a grip or suction device configured to lift an object (eg, 582A, 582B, 582C) from the conveyor belt 573. When the robot hand 555/557/559 is attached to the fifth link 554E, the attachment can be done in a mixed manner. The attachment / detachment can be performed manually or automatically. In one example, the fifth link 554E can be attached to the first robot hand 555, as illustrated in FIGS. 5A and 5B, and the robot control system 110 is attached to the fifth link 554E as the first robot. The robot 550 can be controlled so that the hand 555 is released and the fifth link 554E is attached to the second robot hand 557. In another embodiment, the fifth link 554E can be permanently attached to the robot hand (eg, robot hand 559).

In one embodiment, the robot 550 can have a verification symbol 530 placed on it. In some cases, the verification symbol 530 can be permanently placed on the robot 550. In some cases, the verification symbol 530 can be placed on the robot arm of the robot 550, such as one of the links 554A-554E, or on the robot hand. For example, FIG. 5A illustrates a verification symbol 530 placed on the first robot hand 555 and a third robot hand 559, while FIG. 5B illustrates a verification symbol 530 placed on the link 554E. .. The verification symbol 530 can be applied directly onto the robot 550, or can be attached to the robot 550 via a sticker, a flat plate, or the like. In the embodiment illustrated in FIG. 5A, the second robot hand 557 or the third robot hand 559 each has a calibration pattern 520/527 placed on it, so that a camera calibration is performed. On the other hand, the first robot hand 555 or the third robot hand 559 performs verification of camera calibration because each has a verification symbol 530 placed on it. May be used for.

Returning to FIG. 4A, in one embodiment, method 400 can be started from step 401, in which control circuit 111 performs a first camera calibration and the camera (eg, FIG. 1). , The camera calibration information associated with the camera 170/270/370/570) of FIG. 2, FIG. 3, or FIG. 5, respectively. More specifically, the camera calibration information can include camera calibration values for the camera. In this embodiment, the control circuit 111 can perform the first camera calibration based on an image of the calibration pattern (also referred to as a calibration image).

For example, to perform the first calibration, the robot 550 of FIG. 5A may be attached to a second robot hand 557 having a calibration pattern 520 or to a third robot hand 559 having a calibration pattern 527. Can be done. FIG. 3 illustrates a similar environment in which the first camera calibration can be performed. During this step, the first robot hand 555, of which the calibration pattern 320 is used to perform camera calibration, can be removed from the fifth link 554E. The first camera calibration can be performed before starting the robot operation. For example, the robot operation can be started from robot work such as the first robot hand 555 interacting with the first object 582A on the conveyor belt. During the first camera calibration, the robot 550 can include a second robot hand 557. The robot control system 110 moves the calibration pattern 520 to various positions within the camera field of view 510 of the camera 570 and captures the respective images of the calibration pattern 520 at such positions by the robot via an operation command. It can control 550 robot arms. The robot control system 110 can execute the first camera calibration based on the captured image of the calibration pattern 520 and identify the camera calibration information regarding the camera 570. In one example, the camera calibration information can include information that describes the relationship between the camera 570 and the robot 550. In one example, the camera calibration information can describe the unique parameters of the camera 570. Camera calibration is described in detail in U.S. Patent Application No. 16 / 295,940 (reference number MJ0021US1) filed on March 7, 2019, in the title of the invention "METHOD AND DEVICE FOR PERFORMING AUTOMATIC CAMERA CALIBRATION FOR ROBOT CONTROL". And the entire contents are incorporated herein by reference.

Returning to FIG. 4A, method 400 can further include step 403, in which the control circuit 111 outputs a first operation command to the communication interface 113 of the robot control system 110, thereby first. The robot arm is controlled to move the verification symbol (eg, 530 in FIG. 5) to one point in the camera field of view (eg, 510) of the camera (eg, 570) during or after the camera calibration. The communication interface 113 communicates an action command to the robot in order for the robot arm to move the verification symbol (eg, 530) to its position in the camera field of view (eg, 510) during or after the first camera calibration. It can be configured as follows. The motion command also allows the robot arm to point the verification symbol so that it faces the camera (eg, 570) or, more generally, is visible to the camera. The position can be used as one of one or more reference points for verification of the first camera calibration. For example, when the verification process acquires an image of the verification symbol over time, the control circuit 111 may use the verification symbol (eg, 530) so that one or more positions can be used as one or more reference points. The robot arm can be controlled to constantly position one or more of the same positions. Further, as described later with respect to steps 405-459, the verification process takes the image after the verification symbol, such as the image obtained immediately after the first camera calibration is performed, the verification symbol (eg, eg). It can be compared with a set of early images of 530). The later image can be used as a verification image, while the image with which the later images are compared can be used as a reference image.

In step 405, the control circuit 111 can receive (eg, read) an image of the verification symbol (eg, 530) from the camera (eg, 170/270/370/570) via the communication interface 113. The image is a reference image for verification. The image may have been captured by the camera while the verification symbol was at or was at the reference. In one embodiment, the communication interface 113 can first receive the reference image from the camera, and then the control circuit 111 can receive the reference image from the communication interface 113. In one embodiment, step 405 is performed without the control circuit 111 generating camera commands for the camera. In one embodiment, step 405 may include the control circuit 111 generating a camera command and communicating the camera command to the camera via the communication interface 113. The camera command can control the camera to capture the image of the verification symbol at the reference point.

5A-6B illustrate aspects of steps 403 and 405. In the embodiment of FIG. 5A, after the first camera calibration has been performed, for example, with the second robot hand 557, the second robot hand 557 has a verification symbol 530 placed on it. It can be exchanged for a third robot hand 559. In this example, the robot control system 110 moves the robot arm of the robot 550 (eg, via one or more motion commands) to move the verification symbol 530 to one or more reference points within the camera field of view 510 of the camera 570. To control. One or more reference points may include any position within the camera field of view 510, or one of a set of positions, etc. placed on the surface of the virtual sphere, as discussed in more detail later. It can be the above specific position. In another example, in the embodiment of FIG. 5B, during or after the first camera calibration, the robot control system 110 moves the robot arm to move the verification symbol 530 to one or more reference points within the camera field of view 510. Can be controlled. In this example, one or more reference points can include any position where the verification symbol 530 was taken (along with the calibration pattern 520) during the first camera calibration, or the first camera calibration. The verification symbol 530 can be one or more specific positions in a set that have been moved after the operation has been performed. Based on the camera calibration information obtained from the first camera calibration, the robot control system 110 can control the movement of the robot arm of the robot 550 in this step by an instruction from the camera 570, or so. The operation can be controlled without using any instructions. In one embodiment, the reference location can be a defined location that can be stored and read in a local or remote storage device. Reference points can be stored in the form of coordinates (eg, Cartesian coordinates), as motor commands for rotating links 554A-554E, or in some other form.

In one embodiment, one or more references in which the robot arm moves the verification symbol (eg, 530) can include multiple references, each of which is concave with respect to the camera. It is a position placed on the surface of a virtual sphere. In such an embodiment, the control circuit 111 is further configured to control the robot arm in order to move the verification symbol tangentially to the surface of the virtual sphere at each reference point of the plurality of reference points. can do. For example, as illustrated in FIGS. 6A, 6B, 6C, and 6D, the robot control system 110 controls the robot arm of the robot 550 to move the verification symbol 530 to reference points 610A-610I. The camera 570 can be controlled so as to capture the respective reference image at each of the reference points 610A to 610I. Reference points 610A to 610I in FIGS. 6A and 6B can be divided among a plurality of virtual spheres in the camera field of view 510. Reference points 610A and 610B can be arranged on the first spherical surface 621 of the first virtual sphere 620, where the first spherical surface 621 is within the camera field of view 510. Reference points 610C, 610D and 610E can be placed on the second spherical surface 631 of the second virtual sphere 630, where the second spherical surface 631 is within the camera field of view 510. Reference points 610F, 610G, 610H and 610I can be placed on the third spherical surface 641 of the third virtual sphere 640, where the third spherical surface 641 is within the camera field of view 510. As illustrated in FIGS. 6A and 6B, the first spherical surface 621, the second spherical surface 631, and the third spherical surface 641 are each concave with respect to the camera 570. The embodiments of FIGS. 6A and 6B show three spheres based on three spheres, but the number of different spheres in which reference points can be placed can be greater than or less than three. You can also do it. In one embodiment, the camera 570 can be at the center of each of the virtual spheres 620, 630, 640.

In one embodiment, as shown in FIGS. 6A-6D, when the verification symbol 530 is moved to a reference point, the robot control system 110 tangents the verification symbol 530 to the spherical surface on which the reference point is located. The robot arm 553 of the robot 550 can be controlled (eg, via motion commands) to position in the direction. For example, FIGS. 6A and 6B illustrate verification symbol 530 tangential to the second spherical surface 631 at reference point 610D, and FIGS. 6C and 6D show the second spherical surface 631 at reference point 610C. The verification symbol 530 facing in the tangential direction with respect to is illustrated. More specifically, the verification symbol 530 can be placed on a plane (eg, a sticker) so that the plane of the verification symbol 530 is relative to the second spherical surface 631 at reference point 610D in FIGS. 6A and 6B. It may be tangentially oriented, or may be tangentially oriented with respect to the second spherical surface 631 at the reference point 610C in FIGS. 6C and 6D. In one embodiment, the robot arm 553 can be in the first pose in FIGS. 6A and 6B and in the second pose in FIGS. 6C and 6D. The pose of the robot arm 553 can refer, for example, to a shape formed by a link or other arm portion of the robot arm 553, or more generally a geometric shape. For example, the pose of the robot arm 553 may refer to a particular permutation of an angle or distance in which the link of the robot arm 553 is rotated or translated (eg, extended or retracted) with respect to the preceding link of the robot arm 553. As an example, the first pose illustrated in FIG. 6A may correspond to a first permutation of angles formed between successive links of a series of links in robot arm 553, which is illustrated in FIG. 6C. The second pose may correspond to a second permutation of angles between successive links of a series of links of robotic arm 553. In such an example, reference point 610D of verification symbol 630 may be associated with a first pose for the robot arm 553 exemplified in FIG. 6A, while reference point 610C of verification symbol 630 is shown in FIG. 6C. As illustrated, it may be associated with a second pose for the robot arm 553.

In one embodiment, the control circuit 111 is configured to control the robot arm to move the verification symbol (eg, 530) so that it faces the camera directly when the verification symbol is moved to the reference location. .. For example, as illustrated in FIG. 6A, the robot control system 110 robots the robot 550 to move the verification symbol 530 so that it faces the camera 570 directly when the verification symbol 530 is moved to reference point 610D. The arm 553 can be controlled. In this example, the robot control system 110 can control the robot hand 555 so that the verification symbol 530 rotates so as to directly face the camera 570. In some cases, the verification symbol can face the camera 570 directly by tangentially facing the spherical surface in the camera field of view 510. When the verification symbol 530 directly faces the camera 570, the camera 570 may be able to capture the verification symbol 530 head-on, thereby eliminating or having little perspective effect on the image of the resulting verification symbol 530.

In one embodiment, the verification symbol (eg, 530) comprises a first region having a first color and a second region having a second color, the area of the first region and the second region. The ratio to the area of the area is defined and stored on a non-transitory computer-readable medium (eg, storage device) of the robot control system 110. In such an embodiment, the control circuit 111 can be configured to identify the verification symbol in the reference image or verification image based on the defined ratio. For example, as illustrated in FIG. 5C, the verification symbol 530 can include a first region 531 (eg, a black region) that is ring-shaped and has a first color, by the first region 531. Includes a second region 533 (eg, white region) that is surrounded and has a second color. The ratio of the area of the black first region 531 to the area of the white second region 533 within the verification symbol 530 can be a specified value that can be identified. By analyzing the colors in the captured image, the robot control system 110 determines whether the portion is a ring-shaped region surrounding the circular region, and determines whether the portion is a ring-shaped region surrounding the circular region, and the area of the ring-shaped region and the area of the circular region. The portion of the image corresponding to verification symbol 530 may be identified by determining if the ratio between them matches the defined ratio. This may allow the robot control system 110 to distinguish the verification symbol 530 from other features captured in the image. For example, as illustrated in FIG. 5A, the robot 550 can be configured to utilize a third robot hand 559 that has a combination of calibration pattern 527 and verification symbol 530. In this example, the reference image can show both the verification symbol 530 and the calibration pattern 527. In this example, the calibration pattern 527 may not have any ring pattern or may have a ring pattern with a ratio different from the defined ratio discussed above. The control circuit 111 determines whether the portion of the reference image has a first image region having a first color and a second image region having a second color, and determines whether the portion of the reference image has a second image region having a second color. By determining whether the ratio of the area to the area of the second image area is equal to the defined ratio, it is determined whether that part of the reference image is the verification symbol 530 or the calibration pattern 527. can do.

In some cases, the robot control system 110 determines whether a particular portion of the captured image has a first area with a first color and a second area with a second color. , It is possible to determine whether or not the ratio of the area of the first region to the area of the second region is within the specified range. In one example, if the defined ratio is 1.5, the robot control system 110 will have the specific area within the range of 1.4 to 1.6. It can be determined that it corresponds to the verification symbol 530. The two colors of the first region and the second region are not limited to black and white, but can be any two different colors that can be identified by the robot control system 110.

にあり、第２の形状５３７の中心が座標

にある場合には、座標

及び座標

は、実質的に同じであるとすることができる。 In one embodiment, the verification symbol (eg, 530) can include a first shape and a second shape that are concentric with each other, and the centers of the first and second shapes are substantially the same. In position. For example, the verification symbol can be formed as a circular ring, which includes a first circle and a second circle that are concentric with each other. More specifically, as shown in FIG. 5C, the verification symbol 530 can include a first shape 535 (eg, outer circle) and a second shape 537 (eg, inner circle). The first shape 535 and the second shape 537 can be concentric with each other so that the center of the first shape 535 and the center of the second shape 537 are substantially in the same position. For example, the center of the first shape 535 is the coordinates.

The center of the second shape 537 is the coordinates

If at, the coordinates

And coordinates

Can be substantially the same.

Returning to FIG. 4A, method 400 can further include step 407, in which control circuit 111 determines the reference image coordinates with respect to the verification symbol, and the reference image coordinates are the verification symbol ( For example, it is the coordinate at which 530) appears. For example, as illustrated in FIG. 6A, the image of verification symbol 530 can be captured at reference point 610D and used as a reference image. The verification symbol 530 can appear in the reference image at specific coordinates, which coordinates are sometimes referred to as reference image coordinates.

In one embodiment, as discussed above, the verification symbol (eg, 530) can include a first shape and a second shape that are concentric with each other, the first shape and the second shape. The centers of each are virtually the same. In such an embodiment, the control circuit 111 identifies the first coordinate of the center of the first shape in the reference image and the second of the center of the second shape in the reference image in step 407. By specifying the coordinates of and specifying the reference image coordinates as the average of the first and second coordinates in the reference image, it is configured to specify the reference image coordinates for such a verification symbol. be able to.

（すなわち、第１の形状７３５の中心座標）と、参照画像７１０内に示される第２の形状７３７の中心の第２の座標

（すなわち、第２の形状７３７の中心座標）とを判断することができる。参照画像７１０が参照箇所Ｎにある検証記号５３０に対応するとき、参照画像７１０に関する参照画像座標

を全体として判断するために、ロボット制御システム１１０は、以下のように、参照画像７１０内の第１の座標

及び第２の座標

の平均を計算することができる。

For example, FIG. 7A shows a reference image 710 captured at a reference point N (where N is an integer) among the reference points. The reference image 710 includes a verification portion 730, which is an image portion within the reference image 710 showing the verification symbol 530 of FIGS. 5A, 5B, or 5C. The robot control system 110 of FIG. 1A or FIG. 1B has a first shape 735 (eg, an outer circle) that is the same as or substantially the same as the first shape 535 of the verification symbol 530 of FIG. 5C from the verification portion 730. Can be configured to identify. The robot control system 110 further identifies from the verification portion 730 a second shape 737 (eg, an inner circle) that is the same as or substantially the same as the second shape 537 of the verification symbol 530 of FIG. 5C. Can be configured. After that, with respect to the reference point N, the robot control system 110 determines the first coordinates of the center of the first shape 735 shown in the reference image 710.

(That is, the center coordinates of the first shape 735) and the second coordinates of the center of the second shape 737 shown in the reference image 710.

(That is, the center coordinates of the second shape 737) can be determined. Reference image coordinates for reference image 710 when reference image 710 corresponds to verification symbol 530 at reference point N.

In order to determine as a whole, the robot control system 110 has the first coordinates in the reference image 710 as follows:

And the second coordinate

Can be calculated on average.

In one embodiment, the reference image coordinates relating to the verification symbol can be the center coordinates thereof, and the center coordinates of the verification symbol 530 are specified based on the center coordinates of the first shape 735 and the second shape 735, respectively. This can improve the robustness of the verification process for image noise. For example, image noise may introduce an error in determining the center coordinates for the first shape 735, but may not introduce an error in specifying the center coordinates for the second shape 737. In some cases, the second shape 737 actually shares the same center position as the first shape 735, but due to image noise, the center coordinates of the second shape 737 are the center of the first shape 735. It may appear in the image differently from the coordinates. In this scenario, simply using the center coordinates of the second shape 737 as the center coordinates of the verification symbol 530 may result in an undesired amount of error. The amount of error can be reduced by using the average of the center coordinates of the first shape 735 and the center coordinates of the second shape 737 as the center coordinates of the verification symbol 530.

In one embodiment, the one or more reference points discussed above may be a plurality of reference points corresponding to a plurality of reference image coordinates. In this embodiment, the reference image coordinates can be one of a plurality of reference image coordinates. For example, as illustrated in FIGS. 6A and 6B, there may be multiple reference points, such as reference points 610A-610I, where the verification symbol 530 is moved or otherwise arranged. For each reference location 610A to 610I of verification symbol 530, the robot control system 110 can read out, or otherwise receive, each reference image of verification symbol 530 captured by the camera 570 at that location. , Each reference image coordinate indicating the position where the verification symbol 530 appears in each reference image can be specified.

Returning to FIG. 4A, method 400 can further include step 409, in which control circuit 111 controls the movement of the robot arm to perform robotic operations based on the calibration information. .. In one embodiment, the step can include the control circuit 111 generating a second operation command based on the camera calibration information and outputting the second operation command to the communication interface 113. .. The communication interface 113 can then communicate a second motion command to the robot in order to control the motion of the robot arm. For example, as illustrated in FIG. 5A, after the first camera calibration, the robot control system 110 is responsible for performing robotic operations, including robotic work, such as lifting objects 582A, 582B, and 582C. Control 550. The operation of the robot 550 can be based on the camera calibration information obtained from the first camera calibration and can be based on the images of the objects 582A, 582B, 582C captured by the camera 570.

In step 411, the control circuit 111 detects a pause period during robot operation. In one aspect, the rest period of the robot can be a period during which the robot is not performing robot work during robot operation. In some cases, if the robot operation is based on lifting an object from the conveyor belt 573, the rest period can be based on the absence of an object on the conveyor belt 573. More specifically, the conveyor belt 573 can be made reachable by the robot arm 553, and the control circuit 111 has no object on the conveyor belt 573 or is closest to the robot 550 on the conveyor belt 573. It is configured to detect a rest period by detecting that the distance to the object exceeds a defined distance threshold. In some cases, control circuit 111 may receive a signal indicating that a pause period is about to occur, which signal may be received from another device or component that monitors robot operation. For example, as illustrated in FIG. 5A, the robot control system 110 moves the second object 582B during robot operation due to the long distance between the second object 582B and the third object 582C. A pause period can be detected between the robotic work involving lifting and the robotic work involving lifting the third object 582C. During this pause period, after the robot 550 lifts the second object 582B, the robot 582C is not yet reachable by the robot 550, so that the robot can have a pause period during which it is not performing robot work. In one example, the robot control system 110 is used when an object on the conveyor belt 573 is not reachable by the robot 550 and / or the robot 550 and the closest object upstream on the conveyor belt 573 (eg, a third object 582C). A pause period can be detected when the robot control system 110 determines that the distance to and from exceeds a certain threshold.

Returning to FIGS. 4A and 4B, the method 400 could further include step 451 in which the control circuit 111 used the verification symbol 530 in step 403 during the pause period (capturing the reference image). Control the robot arm 553 to move it to at least the reference point (used for). In one embodiment, step 451 can include the control circuit 111 generating a third operation command and outputting the third operation command to the communication interface 113. The communication interface 113 can be configured to communicate a third motion to the robot so that the robot arm 553 moves based on the motion command. In some cases, the third action command may include a set of stored motor commands corresponding to the reference location. In some cases, the third operation command can be generated based on the camera calibration information from step 401. In some cases, the third operation command in step 451 does not rely on the camera calibration information from step 401.

In step 453, the control circuit 111 reads an additional image of the verification symbol (eg, 530) from the camera (eg, 570) or otherwise receives it during the rest period, and the additional image is for verification. It is a verification image, and is an image of a verification symbol at least at a reference point during the rest period. That is, the verification image relating to the reference location is captured while the verification symbol (eg, 530) is at the reference location or at the reference location. In one embodiment, step 453 comprises generating a camera command in which the control circuit 111 controls a camera (eg, 570) to capture a verification image. The control circuit 111 can output a camera command to the communication interface 113, and the communication interface can communicate the camera command to the camera (for example, 570). In one embodiment, step 451 can include controlling the robot arm to move the verification symbol to a plurality of reference points and receiving a plurality of each verification image captured by the camera. For example, as illustrated in FIGS. 6A and 6B, during the pause period, the robot control system 110 moves the verification symbol 530 to one of reference points 610A to 610I, and an image of the verification symbol 530 at that location. Can be controlled by the robot arm 553 of the robot 550 so as to capture the image as a verification image. If the dormant period has not yet ended, more specifically, if there is sufficient time remaining within the dormant period, the robot control system 110 will refer to verification symbol 530 from reference points 610A to 610I. The robot arm 553 of the robot 550 can be controlled so as to move to another location of the robot and capture the image of the verification symbol 530 at the other location as another verification image. When the pause period ends, the robot control system 110 can stop capturing the verification image. In that case, during each pause, the robot control system 110 moves the verification symbol 530 to one or more of the reference points 610A to 610I and verifies at each of the one or more reference points of the reference points 610A to 610I. The robot arm 553 of the robot 550 can be controlled so as to capture an image.

Returning to FIG. 4B, method 400 can further include step 455, in which control circuit 111 determines the verification image coordinates used for verification, which are in the verification image. This is the coordinate at which the verification symbol appears. When the verification symbol (eg, 530) is moved to a plurality of reference points (eg, 610A to 610I), the camera (eg, 570) can capture a plurality of verification images corresponding to the plurality of reference points, respectively. , The control circuit 111 corresponds to each of the plurality of verification images, and can specify the plurality of verification image coordinates corresponding to the plurality of reference points. All of the verification images may be captured by the camera (eg, 570) in a single pause (eg, a single pause, but the robot arm sees all references to the verification symbol (eg, 530). It may be captured at locations 610A-610I long enough to be moved) or at multiple different pauses (eg, for each pause, the robotic arm applies verification symbol 530 to all reference points 610A-610I. If not long enough to move to).

を判断し、検証画像７６０の検証部分７８０内に示される第２の形状７８７の中心座標

を判断するように構成することができる。ロボット制御システム１１０はさらに、以下のように、検証画像座標７６０に関する検証画像座標

を、検証画像７６０内の第１の形状７８５の中心座標と第２の形状７８７の中心座標との平均として判断することができる。

In one embodiment, the verification image coordinates can be specified in the same way as the reference image coordinates. For example, the verification image coordinates can be the center coordinates of the verification symbol (eg, 530), and the center coordinates of the first shape of the verification symbol (eg, 530) in the verification image (eg, 760) and the verification symbol. Can be specified as the average with the center coordinates of the second shape of. For example, FIG. 7B shows a verification image 760 captured at reference point N among reference points. The verification image 760 shows a verification portion 780, which portion is an image portion in the verification image 760 showing the verification symbol 530. The robot control system 110 can identify the first shape 785 which is the same as or substantially the same as the first shape 585 of the verification symbol 530 of FIG. 5C from the verification portion 780. The robot control system 110 can further identify from the verification portion 780 a second shape 787 that is the same as or substantially the same as the second shape 587 of the verification symbol 530. Further, the robot control system 110 has the center coordinates of the first shape 785 shown in the verification portion 780 of the verification image 760.

Is determined, and the center coordinates of the second shape 787 shown in the verification portion 780 of the verification image 760.

Can be configured to determine. The robot control system 110 further provides verification image coordinates with respect to verification image coordinates 760 as follows:

Can be determined as the average of the center coordinates of the first shape 785 and the center coordinates of the second shape 787 in the verification image 760.

として表され、参照箇所Ｎにおける検証画像座標が、

として表されると仮定すると、参照箇所Ｎにおける偏差（例えば、距離）は、

として表すことができる。 Returning to FIG. 4B, method 400 can further include step 457, in which control circuit 111 is based on the amount of deviation between the reference image coordinates of step 403 and the verification image coordinates of step 455. , The deviation parameter value is determined, and both the reference image coordinate and the verification image coordinate are associated with the reference point N. In one example, the deviation between the reference image coordinates and the verification image coordinates may be the distance between the reference image coordinates and the verification image coordinates. For example, the reference image coordinates at the reference point N are

The verification image coordinates at the reference point N are expressed as

Assuming that it is expressed as, the deviation (eg, distance) at reference point N is

Can be expressed as.

As discussed above, in an embodiment in which one or more reference points are a plurality of reference points, the control circuit 111 is configured to identify a plurality of verification image coordinates corresponding to the plurality of reference points. The verified image coordinates discussed above are one of a plurality of verified image coordinates. In such an embodiment, the deviation parameter value is based on the respective deviation amounts between the plurality of reference image coordinates and the plurality of verification image coordinates with respect to the plurality of reference points, and each deviation amount of the respective deviation amounts is , (A) The reference image coordinates corresponding to each reference point of the plurality of reference points, and (b) the verification image coordinates corresponding to the same reference point. The plurality of verification image coordinates can be the coordinates in which the verification symbol appears in the plurality of verification images, and the verification image discussed above is one of the plurality of verification images. The control circuit 111 can be configured to control the camera to capture all of the plurality of verification images within one pause and / or capture the plurality of verification images within different pauses. , Can be configured to control the camera.

For example, as shown in FIGS. 6A and 6B, when a plurality of reference points exist, the robot control system 110 can determine a plurality of reference image coordinates corresponding to the plurality of reference points, and a plurality of reference points can be determined. It is possible to determine each of the plurality of verification image coordinates corresponding to the reference points of the above, and it is possible to determine the amount of deviation between the plurality of reference image coordinates and the plurality of verification image coordinates. The deviation parameter value can be based on the respective deviation amount between the plurality of reference image coordinates and the plurality of verification image coordinates. For example, the deviation parameter can be the average of each deviation amount as follows.

In the above equation, N can refer to the Nth reference point, while M can refer to the total number of reference points.

Returning to FIG. 4B, method 400 can further include step 459, at which step the control circuit 111 exceeds a defined threshold (sometimes referred to as a defined deviation threshold) for the deviation parameter value. Decide whether to do it. Further, in step 461, in response to the control circuit 111 determining that the deviation parameter value exceeds a defined threshold, a second camera calibration is performed to provide updated camera calibration information about the camera. Can be identified. For example, a deviation parameter value that exceeds a defined threshold may indicate that the camera calibration information of the camera is out of date and / or is likely to cause an undesired amount of error in robot operation. Therefore, if the deviation parameter value exceeds a defined threshold, a second camera calibration for the camera can be performed to update the camera calibration information for the camera (eg, 570). The second camera calibration can use the same technique as the first camera calibration, but can be based on images captured by the camera after the first camera calibration. In one example, if step 459 indicates that the deviation parameter value exceeds a defined threshold, the robot operation can be stopped or interrupted and then the second camera calibration can be started. Yes, the second camera calibration can be initiated by capturing an image for the second camera calibration. After the second camera calibration is completed and the camera calibration information about the camera is updated, the robot control system 110 can restart the robot operation by using the updated camera calibration information.

In one embodiment, the control circuit 111 responds to determining that the deviation parameter value does not exceed a defined threshold, without performing further camera calibration (eg, to the robot via a communication interface). (By outputting the operation command of 4), it can be configured to control the robot so that the robot operation is continued after the pause period. Such conditions can indicate that the camera calibration information from step 401 is still sufficiently accurate and that the robot operation can continue without receiving an undesired amount of error.

In one embodiment, control circuit 111 identifies the temperature of the environment in which the robot is located and based on the measured temperature, a defined deviation threshold (also referred to as redefining the deviation threshold) or camera calibration for the camera. It can be configured to adjust at least one of the information. For example, the control circuit 111 can identify the temperature of the environment by measuring the temperature or by receiving temperature data from another device or component. In such an embodiment, the control circuit 111 sets a defined threshold to have a first value when the measured temperature is outside the specified range, and the measured temperature is within the specified range. When the threshold is set to have a second value lower than the first, it can be configured to adjust the defined threshold based on the measured temperature. For example, overly high or too low temperatures can cause changes in the camera. More specifically, temperature changes can affect the camera's unique parameters. For example, components within a camera may expand as the temperature rises and contract as the temperature drops, which can affect the camera's unique parameters. Therefore, it may be advantageous to adjust the defined deviation threshold based on the temperature or the amount of temperature change. For example, when the temperature is within the normal operating temperature range (eg, the range defined based on the ambient room temperature), the temperature does not adversely affect the camera and may lower the defined deviation threshold. .. On the other hand, when the temperature is outside the normal operating temperature range, the deviation threshold may be raised because the low temperature or the high temperature adversely affects the camera. In an alternative example, the deviation threshold can be specified to be lower when the temperature is outside the normal operating temperature in order to trigger further camera calibration more often. In this example, the deviation threshold can be defined to be higher in order to reduce the frequency of triggering further camera calibration when the temperature is within normal operating temperature.

FIG. 8 illustrates an exemplary timeline 800 in which camera calibration and camera calibration verification are performed. The following examples discuss verifying camera calibration, but these can more generally be applied to verify any type of calibration operation performed for a robotic operating system. .. Prior to the start of robot operation, the robot control system 110 of FIG. 1A or FIG. 1B performs a first camera calibration during the calibration period 811 and is associated with a camera (eg, camera 570 of FIG. 5A or FIG. 5B). Determine the calibration information. After the first camera calibration is completed, the robot control system 110 captures reference images of verification symbols (eg, verification symbol 530) at various reference points during the reference acquisition period 813 and each reference image (eg, verification symbol 530). , The reference image coordinates in which the verification symbol appears in the reference image 710) of FIG. 7A are determined. When the reference image coordinates are specified, the robot operation can be started after the reference acquisition period 813.

After the start of robot operation, during work period 815, the robot control system 110 controls the robot (eg, robot 550 of FIG. 5A or FIG. 5B) to perform one or more robot tasks, and therefore one implementation. In the form, it may not be possible to collect the verification image (for example, the verification image 760 of FIG. 7B). The robot control system 110 detects a pause period 817 in which the robot is not executing the robot work after the work period 815. Therefore, during the pause period 817, the robot control system 110 will use one or more verification images of verification symbols, respectively, at one or more reference points (eg, 610A and 610B) in the first set of reference points. To capture. After the pause period 817 ends, during the work period 819, the robot control system 110 resumes controlling the robot to perform one or more robot tasks, and therefore may not collect verification images. is there. After the work period 817, the robot control system 110 detects a pause period 821 in which the robot is not executing the robot work. During the pause period 821, the robot control system 110 captures one or more verification images of the verification symbols, respectively, at one or more reference points (eg, 610C to 610E) in the second set of reference points. After the pause period 821, during the robot work period 823, the robot control system 110 may resume controlling the robot to perform one or more robot work, and therefore may not collect verification images. The robot control system 110 detects a pause period 825 in which the robot is not performing robot work after the work period 823. During the pause period 825, the robot control system 110 captures one or more verification images of the verification symbols, respectively, at one or more positions (eg, 610F to 610I) of the third set of reference points.

Verification images (eg, 760) captured during the rest periods 817, 821, and 825 can be captured at different locations within the reference location. For example, one or more positions of the first set, the second set, and the third set can be different from each other and can be prevented from overlapping. Further, during the pause period 825, the robot control system 110 can determine that the verification image capture is complete, which indicates that a sufficient number of verification images have been captured for verification of camera calibration. be able to. In one embodiment, the robot control system 110 can determine that the verification image capture is complete when the verification image is captured at all the reference points (for example, 610A to 610I). In one embodiment, the robot control system 110 can determine that the verification image capture is complete when the number of verification images reaches the specified target total number.

When it is determined that the verification image acquisition is completed, the robot control system 110 specifies the verification image coordinates in which the verification symbol appears in each verification image. After that, the robot control system 110 specifies the deviation parameter value based on the respective deviation amounts of the verification image coordinates from the reference image coordinates. If the deviation parameter exceeds a defined threshold, the robot control system 110 performs another camera calibration. However, in this example, the deviation parameter does not exceed the defined threshold and therefore the robot control system 110 performs robot work during the work period 827 after the rest period 825 without performing further camera calibration. Keep running.

FIG. 9 illustrates an exemplary flow diagram 900 showing the verification process for the timeline of FIG. In step 901, the robot control system 110 of FIG. 1A, FIG. 1B, or FIG. 1C performs a first camera calibration of the camera (eg, camera 570 of FIG. 5A or FIG. 5B) to calibrate the camera. Judge the information. In step 903, the robot control system 110 controls the robot (eg, robot 550 of FIG. 5A or FIG. 5B) to move the verification symbol (eg, verification symbol 530 of FIG. 5A or FIG. 5B) to a reference location. , Each case of the reference image of the verification symbol (for example, the reference image 710 of FIG. 7A) is captured at each reference point via the camera. In step 905, the robot control system 110 starts robot operation of the robot based on the camera calibration information obtained from the first camera calibration.

In step 907, the robot control system 110 detects a pause period during robot operation. In step 909, the robot control system 110 moves the verification symbol (eg, verification symbol 530 of FIG. 5A or FIG. 5B) to one or more of the reference points during the pause period. The robot 550) of FIG. 5A or FIG. 5B is controlled, and one or more verification images (for example, the verification image 760 of FIG. 7B) are captured at one or more reference points among the reference points via the camera. In some cases, the robot control system 110 can control the robot to move the verification symbols to as many reference points as the duration of the pause allows. In step 911, the robot control system 110 determines whether or not the total number of captured verification images has reached the defined target total number. If the total number of captured verification images has not reached the target total number, the robot control system 110 returns to step 907 to capture more verification images, thereby another subsequent subsequent operation during robot operation. Attempts to detect a dormant period.

If the total number of captured verification images has reached the target total number, in step 913, the robot control system 110 performs camera calibration based on the reference image (eg, 710) and the verification image (eg, 760). Execute verification of the operation. Camera calibration verification produces deviation parameters. In step 915, the robot control system 110 determines whether the deviation parameter exceeds a defined threshold. If the deviation parameter does not exceed the threshold, the robot control system 110 can reset all of the captured verification images to 0 in step 919 and continue the robot operation after the pause period. On the other hand, by returning to step 907, an attempt is made to detect another pause period to capture a new set of verification images.

If the deviation parameter exceeds the threshold, the robot control system 110 can stop the robot operation and perform a second camera calibration in step 917. After the second camera calibration in 917, the robot control system 110 can reset the total number of captured verification images to 0 in 921. After step 921, the flow diagram can return to step 903, where the robot control system 110 controls the robot (eg, 550) to move the verification symbol (eg, 530) to the reference location and the camera (eg, 550). Through 570), a new set of reference images of verification symbols (eg, 710) can be captured at each reference location, whereby a new set of reference images can be used for later verification. Will be.

As mentioned above, one aspect of the present disclosure is a common verification symbol (eg, FIG. 6A) located at a physical location on a robot arm, such as the robot arm 553 of the robot 550 of FIGS. 6A-6D. -Receiving both reference images (eg, reference image 710 of FIG. 7A) and verification images (eg, verification image 760 of FIG. 7B) that capture the verification symbol 530) of FIG. 6D or otherwise represent it. including. In one embodiment, the reference image (eg, 710) can be generated at a first time point, such as an early time point, while the verification image (eg, 760) can be generated at a second time point, eg, later time point. It can be a new image generated at the time of. In some cases, the reference image may be generated based on one or more commands (or also referred to as one or more commands) generated by a computing system, such as the robot control system 110 of FIG. 1C. .. In some cases, one or more commands may include operation commands and / or camera commands. The motion command can be for the robot arm to move the verification symbol to the reference point. For example, an action command can cause the robot arm to adopt a particular pose, thereby moving the verification symbol to a reference point associated with the particular pose of the robot arm. The camera command generates a reference image on a camera such as the camera 570 of FIGS. 6A-6D while the robot arm is in a particular pose and / or the verification symbol is in a reference location associated with the particular pose. It can be for letting you. Therefore, the reference image may correspond to a reference location. Similarly, the verification image may be generated based on one or more commands such as motion commands and / or camera commands, which may be the same as the motion commands and / or camera commands discussed above for the reference image. It may be similar. One or more commands for the verification image can be generated by the same computing system that generated the reference image, such as the robot control system 110, or by another computing system. In this embodiment, one or more commands for generating a verification image can move the verification symbol back to the reference point. For example, one or more commands can cause the robot arm to re-adopt a particular pose associated with a reference.

In the above embodiment, the computing system receiving the verification image can compare it to the reference image to determine if the calibration information is still sufficiently accurate. The calibration information can be determined by the calibration operation performed on the robot operating system. Calibration operations, which may also be referred to as system calibration, can include camera calibration, robot calibration, or any other calibration for controlling one or more components of the robot operating system. In one embodiment, the calibration information can include camera calibration information, robot calibration information, or any other calibration information. The comparison discussed above may include, for example, determining a deviation parameter value based on the difference between where the validation symbol appears in the reference image and where the validation symbol appears in the validation image. If the deviation parameter value is too large, such as when it exceeds a defined deviation threshold (eg, a predetermined deviation threshold), the computing system can determine that the calibration information is no longer sufficiently accurate. In such situations, the calibration information may be referred to as reflecting or including miscalibration or misalignment. If the camera calibration information includes miscalibration or misalignment, it will not be possible to accurately describe the camera's unique characteristics (eg, projection or lens distortion characteristics) and / or between the camera and its external environment. (For example, the spatial relationship between the camera and the base of the robot) may not be able to be accurately described. When robot calibration information includes miscalibration or misalignment, it can be unreliable with respect to accurately moving the robot arm or other component in the desired location and / or orientation.

In one embodiment, the method of comparing the reference image with the verification image may include a plurality of verification symbols. For example, FIGS. 10A-10C illustrate groups of a plurality of verification symbols 530A-530C. More specifically, the verification symbol groups 530A to 530C may be a part of the robot operation system 500A, which can be an embodiment of the robot operation system 500. The robot operating system 500A may include a computing system such as a robot 550A (which may be an embodiment of the robot 550), a camera 570 having a camera field of view 510, and a robot controller 110. Like the robot 550, the robot 550A has a robot arm 553 that includes a plurality of arm portions that are operably attached to each other. For example, the plurality of arm portions may include links 554A-554E and include a robot end effector such as a robot hand 555 attached to the link 554E. In some cases, as illustrated in FIGS. 10A-10C, a plurality of arm portions are connected in series from the base 552 of the robot 550A to a robot end effector (eg, robot hand 555) or otherwise arranged. May be good. In such a case, the series of arm portions may form a chain of motion, and the movement of the series of specific arm portions may cause the movement of some or all of the arm portions downstream of that particular arm portion. An arm portion downstream of a particular arm portion may refer to an arm portion following the particular arm portion in a series of arm portions. For example, links 554B-554E, and robot hand 555 may be downstream of link 554A. In other words, the link 554A can be upstream of the links 554B-554E and can be upstream of the robot hand 555. In this embodiment, each arm portion within a series of arm portions or a subset thereof is rotatable, telescopic, and retractable with respect to each arm portion immediately preceding the arm portion in the series of arm portions. It is possible, or it can operate differently. For example, the link 554C may be rotatable with respect to the link 554B, which may be the arm portion immediately preceding the link 554C in the series of arm portions illustrated in FIG. 10A. In the embodiments of FIGS. 10A-10C, the links 554A-554E and the robot hand 555 can be operably attached to each other via joints 556A-556D.

As discussed above, the robot arm (eg, 535) may be moved into different poses, where the pose is the shape formed by the arm portions (eg, links) of the robot arm, or more generally. It may refer to a geometric shape. For example, FIGS. 10A-10C illustrate each of the three different poses for the robot arm 553. In one embodiment, the robots 550A in FIGS. 10A-10C are configured to rotate, translate (eg, extend or retract or retract), or otherwise move the links 554A-554E and the robot hand 555 with respect to each other. It can include one or more actuators (eg, motors) that are In such an embodiment, each of the poses of FIGS. 10A-10C may be associated with a particular permutation of motion output by one or more actuators. For example, in a permutation, the various arm portions of the robot arm 553 are rotated with respect to the respective arm portions immediately preceding the various arm portions, and / or the various arm portions are of various arm portions. A translated distance can be described for each arm portion immediately preceding. As an example, the poses in FIGS. 10A-10C are the rotation direction and amount of the link 554B with respect to the link 554A, the rotation direction and amount of the link 554C with respect to the link 554B, the rotation direction and amount of the link 554D with respect to the link 554C, respectively. It can be associated with a different permutation of five angular values that describe the direction and amount of rotation of link 554E with respect to link 554D and the direction and rotation of robot hand 555 with respect to link 554E.

As mentioned above, FIGS. 10A-10C illustrate a group of plurality of verification symbols 530A-530C arranged on one or more arm portions of the robot arm 553. More specifically, the verification symbol 530A may be placed on the link 554B, while the verification symbol 530B may be placed on the link 554C and the verification symbol 530C may be placed on the robot hand 555. In some cases, the robot (eg, robot 550) can have any number of verification symbols, which may be placed on the robot in any way. For example, the verification symbols 530A to 530C may be randomly placed at each location on the robot 550A. In some cases, the number and relative arrangement of verification symbols (eg, 530A-530C) may be subject to one or more defined constraints. For example, their relative arrangement requires that adjacent verification symbols (eg, 530B and 530C) be separated by a specified minimum distance (also called symbol spacing), such as a specified minimum distance of 5 cm. Can be subject to specified constraints. Such constraints can reduce the likelihood that a computing system (eg, robot controller 110) will confuse a particular verification symbol (eg, 530B) with respect to an adjacent verification symbol (eg, 530C).

11A-11C illustrate another example that includes a plurality of groups of verification symbols 1130A-1130C. More specifically, the verification symbols 1130A to 1130C may be part of a robot operating system 1100 including a computing system such as a robot 1150, a camera 1170 having a camera field of view 1110, and a robot controller 110. Each of the robot operation system 1100 and the camera 1170 can be an embodiment of the robot operation system 500 and the camera 570, respectively. The robot 1150 may have a robot arm 1153 including a plurality of arm portions such as links 1154A-1154E and a robot hand 1155 (or other robot end effector). The plurality of arm portions may be operably attached to each other, for example, via joints 1156A-1156D. FIG. 11A shows that the robot arm 1153 is in the first pose, and FIG. 11B shows that the robot arm 1153 is in the second pose. Similar to FIGS. 10A-10C, the plurality of arm portions may be connected in series or otherwise arranged from the base 1152 of the robot 1150 to the robot hand 1155. A series of arm portions can form a movement chain, in which the movement of one arm portion of the series can propagate to the downstream arm portion within the chain. As illustrated in FIG. 11A, the verification symbol 1130A may be located on the link 1154C, while the verification symbol 1130B may be located on the link 1154D and the verification symbol 1130C may be located on the robot hand 1155.

In one embodiment, one or more verification symbols in the group of verification symbols (eg, 530A to 530C, or 1130A to 1130C) can have a circular shape. For example, each of the verification symbols 530A-530C of FIGS. 10A-10C or the verification symbols 1130A-1130C of FIGS. 11A-11C is a ring pattern, or more specifically a circular ring, as discussed above with respect to FIG. 5C. Can be. In the example of FIG. 5C, the ring pattern may have concentric regions (eg, 513 and 533) or concentric circles (eg, 535 and 537). The concentric circular region or concentric circle may include, for example, an inner circle region and an outer circle region, or an inner circle and an outer circle. In the example illustrated in FIG. 11C, the verification symbols 1130A, in one example, can be formed as a circular ring having an outer circle having an inner circle and a radius _{r 2,1130A} having a radius _{r 1,1130A.} In this embodiment, verification symbol 1130B is another may be a circular ring having an outer circle having an inner circle and a radius _{r 2,1130B} having a radius _{r 1,1130B.} Verification symbol 1130C may also be shaped as a circle having an outer circle having an inner circle and a radius _{r 2,1130C} having a radius _{r 1,1130C.}

In one embodiment, groups of verification symbols (eg, 530A-530C, or 1130A-1130C) may be molded as respective circular rings with different sizes. For example, as illustrated in FIG. 11C, the verification symbols 1130A-1130C may have different radii for each outer circle region or outer circle. _{That is, they may have r 2,1130A} , r _2,1130B , and r _2,1130C , all of which are different from each other. In one embodiment, the circular rings for verification symbols 1130A-1130C have different ratios between their inner circle regions or their respective radii of the inner circle and their respective outer circle regions or their respective radii of the outer circle. Can have. That is, the ratio r _2,1130A / r _1,1130A , the ratio r _2,1130B / r _1,1130B , and the ratio r _2,1130C / r _1,1130C may all be different from each other. As discussed in more detail below, computing systems (eg, robotic control systems 110) are based on the size of each circular ring forming the verification symbols 1130A / 1130B / 1130C and / or within the circular ring. It may be configured to identify the verification symbols 1130A / 1130B / 1130C based on their respective ratios between the radius of the circle and the radius of the outer circle of the circular ring.

In one embodiment, some or all of the verification symbols (eg, 530a-530C of FIGS. 10A-10C, or 1130A-1130C of FIGS. 11A-11B) are permanently on the robot arm (eg, 533 or 1130). It may be attached to or otherwise arranged. Such embodiments may include calibration patterns used to perform camera calibration (eg, 520 in FIGS. 5A and 5B), which provides sufficiently accurate results with respect to camera calibration. To obtain, it has a size large enough to accommodate a pattern that is very complex and / or large enough to accommodate a sufficient number of pattern elements. However, such a large size of the calibration pattern (eg, 520) may interfere with normal robot operation because the large size of the calibration pattern (eg, 520) may interfere with normal robot operation, and thus may be a permanent portion of the robot arm or otherwise. Can be too large to be a persistent part. In such an example, the calibration pattern 520 may be removed from the robot arm (eg, 535), for example, before resuming normal robot operation. In this embodiment, some or all of the verification symbols (eg, 530A-530C or 1130A-1130C) may be less complex and / or smaller than the calibration pattern (eg, 520). The smaller size of the verification symbols may allow them to stay on the robot arm (eg, 535 or 1153) during normal robot operation, while there is no interference with normal robot operation, or Only minimal interference may be presented. Therefore, in such an example, some or all of the verification symbols (eg, 530A-530C, or 1130A-1130C) may be permanently or separately on the robot arm (eg, 533 or 1133). Can be continuously placed like this. Whether such an arrangement allows the robot controller or other computing system to perform calibration verification more frequently and / or faster and whether updated camera calibration needs to be determined. Provides the advantage of being able to evaluate.

12A and 12B show a method 1200 relating to the use of a plurality of verification symbols to verify calibration information such as camera calibration information. In one embodiment, method 1200 is performed by a computing system, such as the robot control system 110 of FIGS. 10A-10C, or 11A-11B, or more specifically, the robot control system 110 of FIG. 1C. It can be executed by the control circuit of the computing system, such as the control circuit 111 of. As shown in FIG. 1C, the computing system is configured to communicate with a camera having a camera field of view, such as camera 570 of FIG. 10A or camera 1170 of FIG. 11A, which has a camera field of view 510 or 1110, respectively. Interface 113 may be included. The communication interface 113 may be further configured to communicate with a robot, such as the robot 550A of FIGS. 10A-10C, or the robot 1150 of FIGS. 11A-11C. As mentioned above, the robot 550A / 1150 may include robot arms 553/1153 having multiple arm portions that are operably attached to each other and are located on each arm portion of the plurality of arm portions. It may include a group of verification symbols. In the embodiments of FIGS. 10A-10C, the verification symbol group may include verification symbols 530A-530C, which are located on the link 554B, link 554C, and robot hand 555, respectively. In the embodiments of FIGS. 11A-11C, the group of verification symbols may include verification symbols 1130A-1130C, which may be placed on links 1154C, 1154D, and robot hand 1155, respectively.

In one embodiment, method 1200 can include step 1201, in which a robot arm (eg, a robot arm) for the control circuit 111 of a robot control system or other computing system to perform a robot operation. Outputs an operation command for controlling the operation of 533/1153). The operation command may be based on, for example, calibration information. Calibration information such as camera calibration information can be determined from the first calibration operation such as the first camera calibration. In some cases, step 1201 may be the same as or similar to step 409 of method 400, in which the control circuit 111 controls the movement of the robot arm to perform the robot operation. For example, robotic operation may include removing a box or other object in a warehouse. In this example, the control circuit 111 is based on the image of the box generated by the camera (eg, camera 570 of FIGS. 10A-10C, or camera 1170 of FIGS. 11A-11B) and with calibration information, camera. It may be configured to make a judgment based on the spatial relationship between the box and / or the spatial relationship between the robot (eg, robots 550A-1150) and the box. In one embodiment, the method 1200 can include a step in which the control circuit 111 performs a first calibration operation to determine the calibration information. Such a step of performing the first calibration operation can be similar to step 401 of method 400 of FIG. 4A and can be performed before step 1201. As an example, the first calibration operation may be a camera calibration involving determining an estimated value of a camera calibration parameter based on a calibration image generated by the camera.

In one embodiment, method 1200 can include step 1203, in which control circuit 111 or other component of the computing system determines a group of reference image coordinates. The group of reference image coordinates can be, for example, the coordinates in which a group of verification symbols (eg, 530A to 530C / 1130A to 1130C) appears in the reference image, and the reference image is a verification symbol (eg, 530A to 530C /). It can be an image to represent a group of 1130A-1130C). In one embodiment, a group of reference image coordinates can be used to verify the calibration information.

For example, FIG. 13A illustrates a reference image 1120 representing the group of verification symbols 1130A-1130C of FIG. 11A. In the embodiment of FIG. 13A, the group of reference image coordinates may include a first reference image coordinate, a second reference image coordinate, and a third reference image coordinate. In such an embodiment, the first reference image coordinates can identify the location where the verification symbol 1130A appears in the reference image 1120, and the second reference image coordinates are the locations where the verification symbol 1130B appears in the reference image 1120. The third reference image coordinate can identify the place where the verification symbol 1130C appears in the reference image 1120. In a more specific example, each of the first reference image coordinates, the second reference image coordinates, and the third reference image coordinates may be ^{pixel coordinates [uv] T.} More specifically, FIG. 13A shows the three reference image coordinates of the verification symbols 1130A, 1130B, and 1130C, which are [u _{ref_1} v _{ref_1} ] ^T _1130A , [u _{ref_1} v _{ref_1} ] ^T _1130B , and [u _{ref_1} v, respectively. _{ref_1} ] _Illustrated as ^{T 1130C.} In this embodiment, the label ref_N (eg, ref_1) is associated with a reference image generated when the robot arm 1153 is in the Nth pose, such as the first pose (when N = 1). Can point to coordinates. As discussed in more detail below, reference image 1120 of FIG. 13A may correspond to a first pose, which may be an exemplary pose of robot arm 1153 shown in FIG. 11A, or more generally. , Can be associated with the first pose. Different poses can be arranged with verification symbols 1130A-1130C in different groups at each location within the camera field of view 1110. For example, the pause in Figure 11A, the verification symbol 1130A～1130C, respectively, 3D _{locations, [x ref_1 y ref_1 z ref_1} ] T 1130A, [x ref_1 y ref_1 z ref_1] T 1130B, [x ref_1 y ref_1 z ref_1 ] _Can be placed at ^{T 1130C.} In such an example, these 3D points _{[x ref_1 y ref_1 z ref_1]} T 1130A, [x ref_1 y ref_1 z ref_1] T 1130B, [x ref_1 y ref_1 z ref_1] T 1130C , the pixels in the reference image 1120 It can be projected onto the coordinates [u _{ref_1} v _{ref_1} ] ^T _1130A , [u _{ref_1} v _{ref_1} ] ^T _1130B , [u _{ref_1} v _{ref_1} ] ^T _{1130C, or otherwise mapped.} In one embodiment, the pixel coordinates [u _{ref_1} v _{ref_1} ] ^T _1130A , [u _{ref_1} v _{ref_1} ] ^T _1130B , and [u _{ref_1} v _{ref_1} ] ^T _1130C each have their respective verification symbols 1130A / 1 in the reference image 1120. The center where / 1130C appears can be identified.

In one embodiment, in step 1203, the control circuit 111 receives a reference image (eg, 1120) from the robot control system 110 or the communication interface 113 of another computing system and / or the non-transitory computer-readable medium 115. Can be included. For example, the reference image 1120 of FIG. 13A can be generated by the camera 1170 when the robot arm 1153 is in the pose of FIG. 11A. The computing system 110 can receive the reference image 1120 from the camera 1170 via the communication interface 113 and can store the reference image 1120 in the non-temporary computer-readable medium 115. In step 1203, control circuit 111, in one example, can acquire or otherwise receive reference image 1120 from a non-transient computer-readable medium 115. The non-transient computer-readable medium 115 can also store a verification image (discussed below), and the control circuit 111 can receive the verification image from the non-temporary computer-readable medium 115.

In one embodiment, the control circuit 111 has verification symbols (eg, 1130A to 1130C) in a reference image (eg, 1120) based on a defined model that describes the geometry of the robot arm (eg, 1153). Can be configured to identify at least one verification symbol (eg, 1130A) in a group of. For example, the defined model is which links, robot end effectors, or other arm parts form the robot arm, their respective sizes (eg, length), and how they are connected. , And / or which arm portion has at least one verification symbol (eg, 1130A) placed on it. In such an embodiment, the control circuit determines, based on the model, a region within the reference image (eg, 1120) where at least one verification symbol is expected to appear, and at least one within the region of the reference image. It can be configured to search for one verification symbol (eg, 1130A). In one embodiment, the model can memorize the position of the verification symbol (eg, 1130A) on the robot arm (eg, 1153), or can be described more generally. The position of the verification symbol (also referred to as the symbol position) can be the approximate location of the verification symbol on the robot arm (eg, 1153).

For example, one or more of the motion commands in which the reference image (eg, 1120) is used to generate the pose associated with the reference image, or more specifically, the pose of the robot arm that appears in the reference image. When stored with parameter values, one or more parameter values and models can be used to estimate the pose of the robot arm (eg, 1153) when the robot arm is moved according to an action command. As discussed in more detail below, one or more parameter values, in one embodiment, are one or more actuators (eg, one or more motors) used to move a robot arm (eg, 1153). ) May belong to one or more actuator parameters used to control. The estimated pose can be used to estimate the location of the verification symbol (eg, 1130A) on the robot arm (eg, 1153), and the estimated location can be used to make the verification symbol a reference image (eg, 1130A). It is possible to estimate the location that is likely to appear in 1120).

In the above embodiment, the control circuit 111 may be configured to focus on a region (s) of a reference image (eg, 1120) where the verification symbol or the verification symbols are expected to appear. .. Such techniques prevent the control circuit 111 from searching the entire reference image (eg, 1120) for the verification symbol (eg, 1130A-1130C) and therefore the verification symbol (eg, 1120) within the reference image (eg, 1120). It may be possible to identify (1130A to 1130C) more quickly. The model in the above embodiment can also be used to search for validation symbols in the validation image (discussed below).

As mentioned above, the groups of verification symbols (eg, 1130A-1130C) may be molded as their respective annulus in one embodiment. In such an embodiment, the control circuit 111 recognizes or must recognize the verification symbol (eg, 1130A) in the reference image (eg, 1120) by identifying the circular ring forming the verification symbol. Can be configured to identify. If the group of verification symbols is molded as each circular ring with a different size, as shown above with respect to FIG. 11C, the control circuit 111 will have the size of each circular ring forming the verification symbol ( For example, it can be configured to identify a verification symbol (eg, 1130A) based on _{radius r 2,1130A).} In some cases, if the verification symbol (eg, 1130A) is formed as a circular ring having at least a first circular region or a first circle and a second circular region or a second circle, the control circuit 111 It can be configured to identify the verification symbol based on the ratio between the radius of one circular region or first circle and the radius of the second circular region or second circle. For example, the control circuit 111 can be configured to identify the circular ring and identify the verification symbol 1130A based on _{ensuring that the ring has a ratio of r 2,1130A} / r _1,1130A. ..

As further mentioned above, the reference image of step 1203 (eg, 1120 in FIG. 13A) is when the robot arm (eg, 1153) is in a first pose, such as the pose illustrated in FIG. 11A. , Can be generated by a camera (eg, 1170 in FIG. 11A). The reference image can be generated by the camera during the first period, or more generally, at the first point in time. The first period may refer to a period used to generate a reference image or otherwise associated (eg, a period of milliseconds, seconds, or minutes). For example, the first period may include time for camera movement to capture the reference image, and in some examples, further includes time for robot movement to position the verification symbol within the camera field of view. It's fine. In some cases, the first period during which the reference image is generated may be, for example, hours, days, or weeks before step 1201 and / or step 1203. In one embodiment, the computing system, or more specifically, the control circuit 111 that performs steps 1201 and 1203, may be uninvolved in generating the reference image (eg, 1120). In one embodiment, a computing system, or more specifically, a control circuit 111 that performs steps 1201 and 1203, can be involved in the generation of a reference image (eg, 1120). For example, the computing system may output action commands during the first period for moving the robot arm (eg, 1153) into the first pose in steps preceding steps 1201 and / or 1203. In such an example, this preceding step can be part of method 1200. The first pose sets the group of verification symbols (eg, 1130A to 1130C) to the sections discussed above [x _{ref_1} y _{ref_1} z _{ref_1} ] ^T _1130A , [x _{ref_1} y _{ref_1} z _{ref_1} ^{] T} _1130B , [x _ref1 ]. y _{ref_1} z _{ref_1} ] It can be moved to the first group of each location associated with the first pose, such as ^T _1130C. In some cases, such a step may be similar to step 403 in FIG. 4A. In the above example, the computing system, or more specifically the control circuit 111, may further output camera commands in this step, which causes the robot arm (eg, 1153) to make a first pose. While at, have the camera (eg, 1170) generate a reference image (eg, 1120). In one embodiment, the computing system receives a reference image (eg, 1120) from the camera and stores the reference image on the non-transient computer-readable medium 115 of FIG. 1C or another non-transient computer-readable medium. can do. In some cases, the computing system may cause the robot arm (eg, 1153) to return to the first pose and / or the verification symbols (eg, 1130A to 1130C) to return to the first group at their respective locations. Further information that enables it may be stored. For example, a computing system may memorize a first group of each location, or more specifically, its 3D coordinates, and / or a robot arm (eg, 1153). The parameter value of the operation command for moving to the pause can be memorized. In one embodiment, the coordinates and / or operation commands can be stored in the non-transitory computer-readable medium 115 in such a manner that the stored information is associated with the reference image (eg, 1120) discussed above.

In one embodiment, the motion commands discussed above for moving the robot arm to a first pose can include one or more parameter values that describe the motion of the robot arm (eg, 1153). As mentioned above, in some cases, one or more parameter values belong to one or more actuator parameters that control one or more actuators that create motion for a robotic arm (eg, 1153). obtain. In such cases, one or more parameter values can be referred to as one or more actuator parameter values (also referred to as robot joint values). For example, one or more actuator parameter values are, for example, the respective rotation amounts of the arm portions of the robot arm with respect to each other, the respective locations and / or orientations of the arm portions with respect to each other, and / or each of the joints connecting the arm portions. (For example, 1156A to 1156D) can be described. For example, one or more actuator parameter values of an action command can describe their respective angular values so that the motors in the robot 1150 can have different arm parts (eg, for example) with respect to their immediate previous arm parts. The links 1154A to 1154E and the robot hand 1155) are rotated.

In one embodiment, the action command discussed above can have any parameter value (s) (eg, random parameter value (s)) and is triggered by the action command. The first pose can be any pose. In one embodiment, the operation commands discussed above allow some or all of the verification symbols (eg, 1130A to 1130C) to have the desired appearance within the reference image (eg, 1120). It may be a command. For example, as discussed above, some or all of the groups of verification symbols (eg, 1130A-1130C) may have a circular shape, such as a concentric circular region or a ring shape formed by concentric circles. In such an example, when at least one of the verification symbols (eg, 1130A) is in a particular orientation with respect to the camera (eg, 1170), the at least one verification symbol (eg, 1130A) is completely. Instead of appearing circular, it may appear elliptical in the resulting reference image. The oval appearance can lead to inaccurate calibration verification. For example, if the reference image coordinates for the verification symbol 1130A are where the center of the symbol appears in the reference image, the reference image coordinates accurately determine when the verification symbol 1130A appears in an elliptical shape in the reference image. Can be more difficult. Further, identifying the verification symbol 1130A in the reference image (eg, distinguishing the verification symbol 1130A from other features in the reference image) identifies the ring pattern in the reference image, and the ring pattern is a symbol. If it depends on verifying that it has a specific ratio between the concentric circles associated with (eg, the ratio r _2,1130A / r _{1,1130A associated with the verification symbol 1130A), this identification is a ring.} When the pattern looks oval in the reference image, it can be more difficult to perform accurately. Therefore, if the control circuit 111 includes outputting an operation command associated with generating a reference image, the control circuit 111 completes the group of verification symbols (eg, 1130A-1130C) in the reference image. Attempts can be made to generate motion commands for positioning in or in a manner that makes them appear substantially circular.

As an example, the control circuit 111 generates an action command that causes a group of verification symbols (eg, 1130A to 1130C) to move the robot arm (eg, 1153) into a pose directly facing the camera (eg, 1170). be able to. For example, the pose points at least one of the verification symbols (eg, 1130A to 1130C) in a tangential direction to the surface of the virtual sphere that is concave with respect to the camera (eg, 1170). You may let it. In FIG. 11A, the illustrated poses for the robot arm 1153 are oriented tangentially to the surface of the virtual sphere 1121, which is concave with respect to the camera 170, to the verification symbols 1130A and 1130B. It can result in having, and the verification symbol 1130C can have an orientation tangential to the surface of the virtual sphere 1123, which is also concave with respect to the camera 1170. In such a pose, which may be the first pose discussed above, the groups of verification symbols (eg, 1130A-1130C) may appear as their respective circular shapes in the reference image (eg, 1120). More specifically, the groups of verification symbols (eg, 1130A-1130C) in such embodiments appear in the reference image without eccentricity, or are less than or equal to the defined eccentricity threshold, respectively. It can be positioned in such a way that it appears in the eccentricity of. In the above embodiment, the imagined circles 1121 and 1123 can be centered on a camera (eg, 1170). In one embodiment, the control circuit 111 is configured to generate a random action command and search through the random action command to find one that can generate the orientation discussed above for a group of verification symbols. May be done. The found operation command can be output by the control circuit 111 to generate a reference image (eg, 1120).

Returning to FIGS. 12A-12B, method 1200 in one embodiment includes step 1205, in which the control circuit 111 has a first pose, such as the first pose illustrated in FIG. 10A or FIG. 11A. It outputs motion commands to control the robot arm to move it into a pose, and the first pose produces a reference image (eg, 1120) during the first period, as discussed above. It's a pose. In some cases, the operation command can be output to the robot (for example, 550A / 1150) via the communication interface 113. In one embodiment, the operation command in step 1205 is added to the operation command in step 1201, and thus can be referred to as an additional operation command. Additional action commands may be output during a second period, or more generally, a second time point following the first period. The second period can refer to a period used to generate a validation image or otherwise associated (eg, a period of milliseconds, seconds, or minutes). For example, the second period may include time for robot movement to position the verification symbol within the camera field of view and / or time for camera operation to capture the verification image. In some cases, the second period (or more generally, the second time point) is hours, days, or weeks during the first period (or more generally, the first time point). May continue over. Additional action commands can be used to generate a validation image during the second period, as discussed in more detail below. In one embodiment, an additional action command is a robot arm (eg, first pose in FIG. 11A) in which a group of verification symbols (eg, 1130A to 1130C) is in a pose directly facing the camera (eg, 1170). , 1153) can be moved. For example, a group of verification symbols may have their respective orientations in contact with one or more virtual spheres that are concave with respect to the camera. In such a pose, the groups of verification symbols (eg, 1130A-1130C) may each appear as a circular shape in the verification image (eg, 1160 in FIG. 13B).

In one embodiment, if method 1200 includes a step of outputting an action command for generating a reference image during the first period, as discussed above, then the reference image is generated during the first period. The action command for doing so may be the first additional action command, while the action command in step 1205 for generating the verification image during the second period is the second additional action command. There may be. In some cases, the first additional action command may be a faster action command, while the second additional action command may be a slower action command. In some cases, the first additional motion command can have one or more actuator parameter values (or robot joint values) to control the robot arm to move to the first pose, and a second. Additional action commands can also have one or more actuator parameter values. More specifically, the first additional operation command and the second additional operation command may have the same actuator parameter value. As an example, if the robot (eg, 1150) includes multiple motors that rotate various arm portions (eg, links 1154A to 1154E, and robot hand 1155) with respect to each other, then one or more actuator parameter values , Each may include a plurality of respective angular values that control how much rotation is output by the plurality of motors. In this embodiment, the first additional motion command and the second additional motion command both control how much rotation is output by the plurality of motors, each of the same plurality of angles. May include a value.

In one embodiment, the first additional action command and / or the second additional action command may be output during each idle period, such as the idle period discussed above with respect to step 411 of FIG. 4A. it can. In some cases, if the calibration information is determined by performing a calibration operation, the first additional action command is the earliest idle period immediately after the calibration operation is performed or following the calibration operation. Can be output inside. In some situations, the second additional action command is that a specified period of time has passed since the calibration operation was performed, a collision event involving the robot, or between the camera and the robot or part of it. It may respond to specified trigger conditions, or some other trigger conditions, such as any other event that may result in the possibility of displacement or misalignment of the robot (eg, a natural disaster such as an earthquake). If generating a verification image involves the control circuit 111 outputting a camera command, in some examples the camera command may also be output in response to a defined trigger condition.

In one embodiment, the first pose of step 1205 with respect to the robot arm (eg, 1153) relates to a group of verification symbols (eg, 1130A to 1130C) placed on the robot arm, respectively, as discussed above. Can be associated with a particular group of references. For example, a group of each of the reference points, 3D points _{[x ref_1 y ref_1 z ref_1]} T 1130A, [x ref_1 y ref_1 z ref_1] T 1130B, may be _{[x ref_1 y ref_1 z ref_1]} T 1130C. When a reference image (eg, 1120) is generated, the group of verification symbols (eg, 1130A-1130C) may be located in the group of each reference point associated with the first pose. In step 1205, if the additional motion command returns the robot arm to the first pose, the group of verification symbols (eg, 1130A to 1130C) is the group of references (eg, [x _{ref_1} y _{ref_1} z _{ref_1} ] ^T _1130A. , [X _{ref_1} y _{ref_1} z _{ref_1} ] ^T _1130B , [x _{ref_1} y _{ref_1} z _{ref_1} ] ^T _1130C ). In such an embodiment, groups of verification symbols (eg, 1130A to 1130C) can be placed in groups of respective reference points when reference images (eg, 1120) are generated, and verification images (eg, 1160). ) Is generated, it can be placed again in each reference group.

Returning to FIGS. 12A-12B, the method 1200 in one embodiment can include step 1207, at which step the control circuit 111 receives a verification image such as the verification image 1160 in FIG. 13B. As mentioned above, the reference image (eg, 1160) can be an image to represent a group of verification symbols (eg, 1130A-1130C). In this embodiment, the verification image (eg, 1160) may be a further image for also representing a group of verification symbols (eg, 1130A-1130C), such as the first pose illustrated in FIG. 11A. , May be generated when the robot arm (eg, 1153) is moved to the first pose as a result of the additional action command in step 1205.

In one embodiment, method 1200 can include step 1209, in which control circuit 111 determines a group of verification image coordinates. In this embodiment, the group of verification image coordinates can be the respective coordinates in which the group of verification symbols (eg, 1130A to 1130C) appears in the verification image (eg, 1160 in FIG. 13B). In one embodiment, the group of verification image coordinates may be for verifying calibration information, such as camera calibration information. Similar to the above discussion of reference image coordinates in step 1203, the group of verification image coordinates in one example may include a first verification image coordinate, a second verification image coordinate, and a third verification image coordinate. In a more specific example, each of the first verification image coordinates, the second verification image coordinates, and the third verification image coordinates can be, for example, pixel coordinates that identify the center of the respective verification symbol. For example, FIG. 13B shows three verification image coordinates, or more specifically, pixel coordinates [u _{verify_1} v _{verify_1} ] ^T _1130A , [u _{verify_1} v _{verify_1} ] ^T _1130B , [u _{verify_1} v _{verify_1} ] ^t _1130A . The centers of the verification symbols 1130A to 1130C appear in the verification image 1160. Similar to the reference image coordinate discussion, the label verify_N (eg, verify_1) was associated with a validation image generated when the robot arm was in the Nth pose, such as the first pose (N = 1). Can point to coordinates.

In one embodiment, the control circuit 111 can perform steps 1203 to 1209 multiple times for a plurality of reference images and a plurality of verification images (eg, five reference images and five verification images). The plurality of reference images and the plurality of verification images may correspond to a plurality of respective poses. For example, FIGS. 10A-10C illustrate a series of three poses for the robot arm 553. In this example, the robot controller 110 or the control circuit 111 of any other computing system has a first reference image and a first verification image associated with both the first pose, as shown in FIG. 10A. A second reference image and a second verification image with both second poses associated, as shown in FIG. 10B, and a third pose and both, as shown in FIG. 10C. An associated third reference image and a third verification image may be received. In another example, the reference image 1120 of FIG. 13A may be the first reference image and the verification image 1160 of FIG. 13B may be the first verification image, both of which are robotic arms. The 1153 may be associated with the first pose illustrated in FIG. 11A. In this example, the control circuit 111 can further receive the second reference image 1122 of FIG. 14A and the second verification image 1162 of FIG. 14B, both of which are shown in FIG. 11B. May be associated with the pose of. In this embodiment, the reference image coordinates [u _{ref_1} v _{ref_1} ] ^T _1130A , [u _{ref_1} v _{ref_1} ] ^T _1130B , and [u _{ref_1} v _{ref_1} ] ^T _1130C in FIG. 13A are a group of first reference image coordinates. at best, whereas in Figure 13B the verification image coordinates ^{_{[u verify_1 v verify_1] T 1130A}} , [u verify_1 v verify_1] T 1130B, [u verify_1 v verify_1] T 1130C is a group of the first verification image coordinates May be good. The control circuit 111 of this embodiment further determines a group of second reference image coordinates [u _{ref_2} v _{ref_2} ] ^T _1130A , [u _{ref_2} v _{ref_2} ] ^T _{1130C of the second reference image 1122 of FIG. 14A.} the second group of the verification image coordinates _{[u verify_2 v verify_2]} ^T _1130A of the second verification image 1162 in FIG. _{14B, [u verify_2 v verify_2]} T 1130B, configured to determine _{[u verify_2 v verify_2]} ^T _1130C Can be done. In the above embodiment, the control circuit 111 can be configured to output different operation commands for moving the robot arm (eg, 1153) into a plurality of respective poses in some examples. A plurality of reference images and / or a plurality of verification images are associated with a plurality of respective poses.

Returning to FIGS. 12A-12B, in one embodiment, method 1200 may include step 1211 where the control circuit 111 is a group of reference image coordinates (eg, [u _{ref_1} v _{ref_1} ] in FIG. 13A]. ^{_{T 1130A, [u ref_1 v ref_1}} ] T 1130B, [u ref_1 v ref_1] T 1130C) with a group of verification image coordinates (e.g., in Figure ^{_{13B [u verify_1 v verify_1] T}} 1130A, [u verify_1 v verify_1] T 1130B , [ _{Uverify_1} v _{verify_1} ] ^T _1130C ), and determine the group of each deviation parameter value based on the respective deviation amount. For example, each group of deviation parameter values in the context of FIGS. 13A and 13B may include a first deviation parameter value, a second deviation parameter value, and a third deviation parameter value. The first deviation parameter values are the first reference image coordinates [u _{ref_1} v _{ref_1} ] ^T _1130A for the verification symbol 1130A in the reference image 1120 and the first verification image coordinates for the verification symbol 1130A in the verification image 1160. [U _{verify_1} v _{verify_1} ] It may be based on the amount of deviation from ^T _1130A. For example, the first deviation parameter value is equal to, or more generally, the distance between the first reference image coordinates and the first validated image coordinates, as discussed above for step 457 in FIG. 4B. It may be based on distance. _{Similarly, the second deviation parameter value is the second reference image coordinates [u ref_1} v _{ref_1} ] ^T _1130B for the verification symbol 1130B in the reference image 1120 and the second reference image coordinates 1130B for the verification symbol 1130B in the verification image 1160. Verification image coordinates [u _{verify_1} v _{verify_1} ] It ^{may be based on the amount of deviation from T} _1130B (for example, even if they are equal). Further, the third deviation parameter value is the third verification of the third reference image coordinate [u _{ref_1} v _{ref_1} ] ^T _1130C for the verification symbol 1130C in the reference image 1120 and the verification symbol 1130C in the verification image 1160. It may be based on the amount of deviation from the image coordinates [u _{verify_1} v _{verify_1} ] ^T _1130C. In the above embodiment, each group of deviation parameter values is associated with a group of verification symbols 1130A-1130C. That is, the first deviation parameter value is associated with the verification symbol 1130A, while the second deviation parameter value is associated with the verification symbol 1130B and the third deviation parameter value is associated with the verification symbol 1130C.

In one embodiment, some or all of each group of deviation parameter values may be based on a single pair of reference and validation images, both of which have a common pose for the robotic arm. May be associated. For example, the first deviation parameter value discussed above may be associated with the validation symbol 1130A or may be based on a single pair of reference image 1120 and validation image 1160, both of which are shown in FIG. 11A. Associated with common poses, such as the pose of.

In one embodiment, some or all of each group of deviation parameter values may be based on multiple pairs of each reference image and each verification image, each pair having multiple poses for the robot arm. Associated with each pose of. As an example, the first deviation parameter value discussed above associated with verification symbol 1130A is the first pair of reference image 1120 (FIGS. 13A and 13B) and verification image 1160, and (FIGS. 14A and 14B). It may be based on the second pair of reference image 1122 and verification image 1162. The first pair may be associated with the first pose of FIG. 11A, while the second pair may be associated with the second pose of FIG. 11B. More specifically, the first deviation parameter value in this example is the _{amount of deviation between [u ref_1} v _{ref_1} ] ^T _1130A and [u _{verify_1} v _{verify_1} ] ^T _1130A (associated with the first pose). For example, it can be obtained based on distance) and can be based on the amount of deviation between _{[u ref_2} v _{ref _2} ] ^T _1130A and [u _{verify _2} v _{verify _2} ] ^T _{1130A (associated with the second pose).} In one example, the first deviation parameter value may be equal to or based on the average of the two deviation quantities. More generally, each group of deviation parameter values in this example is between a group of first reference image coordinates (associated with a first pose) and a group of first validation image coordinates, respectively. It may be based on the amount of deviation, and may be further based on the amount of deviation between the group of second reference image coordinates (associated with the second pose) and the group of second verification image coordinates. ..

In some cases, the reference image coordinates in the first reference image and the reference image coordinates in the second reference image are common in a set of reference images, such as the two reference images 1120, 1122 discussed above. Can be part of a set of reference image coordinates indicating where the verification symbol (eg, 1130A) appears. The set of reference images and the set of reference image coordinates in this embodiment may correspond to the respective set of poses for the robot arm (eg, 1153), such as the two poses in FIGS. 11A and 11B, respectively. Similarly, the verification image coordinates in the first verification image and the verification image coordinates in the second verification image are the places where the verification symbol appears in the set of verification images such as the verification images 1160 and 1162 discussed above. Can be part of a set of verification image coordinates that indicate. The set of verification images and the set of verification image coordinates can also correspond to the set of poses. In such a case, the deviation parameter value associated with the verification symbol may be based on the respective deviation amount between the set of reference image coordinates and the set of verification image coordinates.

Returning to FIGS. 12A-12B, method 1200 can include step 1213, in which the control circuit 111 has at least one deviation parameter value in each group of deviation parameter values defined deviation. Determine if the threshold is exceeded. In some cases, step 1213 may be similar to step 459 in FIG. 4B. In one embodiment, step 1213 may include determining whether each deviation parameter value in each group of deviation parameter values exceeds each deviation threshold. For example, the control circuit 111 determines whether the deviation parameter value associated with the verification symbol 1130A exceeds the defined deviation threshold, and the deviation parameter value associated with the verification symbol 1130B exceeds the defined deviation threshold. It can be determined whether and / or whether the deviation parameter value associated with the verification symbol 1130C exceeds the defined deviation threshold. In some cases, each deviation threshold can have the same value and therefore can form a common deviation threshold for the validation symbol or have different values.

In one embodiment, the method may include step 1215, in which control circuit 111 determines that at least one deviation parameter value in each group of deviation parameter values exceeds a defined deviation threshold. In response to (a) printing a notification that at least one of the groups of each deviation parameter value exceeds a defined deviation threshold, and (b) updated calibration information (eg, updating). At least one of performing a calibration operation to determine the calibration information) can be performed. For example, step 1215 may include outputting notifications to a user interface device, such as an electronic display that communicates with the robot controller 110. The electronic display may, for example, display an indicator that at least one deviation parameter value, or at least one deviation parameter value, exceeds a defined deviation threshold. In one embodiment, performing the calibration operation in step 1215 may be similar to or identical to step 461 in FIG. 4B. In one embodiment, if the calibration information in step 1201 is determined by performing a first calibration operation, the calibration operation in step 1215 follows the first calibration operation, followed by a second calibration. It can be a calibration operation.

In one embodiment, at least one deviation parameter value that exceeds a defined deviation threshold is a change to a camera (eg, 1170 of FIGS. 11A-11B) and / or a camera environment or robotic operating system (eg, 1100). ) Can be shown to be changed. In some cases, the change to the camera may be an internal change, for example, when the camera lens or camera image sensor changes shape or size due to temperature changes or physical damage. .. In some cases, changes to the camera may include changes to the location where the camera (eg, 170) is mounted, eg, due to vibrations in the structure (eg, ceiling) where the camera is mounted. .. In some cases, changes in the camera environment or to the robot operating system may result from vibrations in the structure (eg, floor) on which the robot is mounted, such as the position of the base (eg, 1152) of the robot (eg, 1150) or. It can include changes in orientation. In some cases, changes to the camera environment or robotic operating system can be changes in the arm portion of the robot arm (eg, between links 1154A to 1154E of the robot arm 1153), or in the relationship of the arm portion itself. For example, one of the arm portions (eg, link 1154D or robot hand 1155) may be curved or otherwise deformed or damaged due to an event unplanned by the computing system 110. An unplanned event can be a collision event, or some other unexpected event that can lead to potential changes in the robot (eg, 1150) or other elements of the robotic operating system. The calibration verification discussed above may provide a fast and efficient technique for detecting changes to the camera (eg, 1170) and / or changes to the camera environment or robotic operating system 1100. For example, changes in a camera (eg, 1170) and / or a robot (eg, 1150) can be compared with reference image coordinates (s) and corresponding verification image coordinates (s). It can be detected by determining the difference between them. In many cases, such comparisons can be made without placing significant demand on the computing resources of the computing system 110. For example, comparisons can be made with calculations that acquire only a limited amount of processor execution time and / or a limited amount of memory. Therefore, the comparison can facilitate accurate monitoring of the accuracy of the calibration information in a computationally efficient manner.

In one embodiment, at least one deviation parameter value that exceeds a defined deviation threshold is a calibration error, such as a camera calibration error in which the camera calibration information from the first camera calibration is no longer sufficiently accurate. Can indicate that there is. In one embodiment, method 1200 comprises the control circuit 111 determining the type of calibration error (also referred to as the type of misalignment) that causes at least one deviation parameter value to exceed a defined deviation threshold. Can be done. The type of calibration error is caused, for example, by whether a loss of accuracy for calibration information (eg, camera calibration information) is caused by a change to the robot, or otherwise represents a change to the robot. It can indicate whether or not the loss of accuracy is caused by a change to the camera, or otherwise by something that represents a change to the camera. For example, changes to a camera (eg, 1170) may include internal changes to the camera and / or changes to where the camera is mounted, as discussed above. Changes to the robot, as discussed above, are changes to the location or orientation of the base (eg, 1152) of the robot (eg, 1150), to the relationship between the arm portions of the robot arm (eg, 1153). It can include changes and / or changes to the arm portion itself.

In one embodiment, the determination of the type of calibration error can be based on a comparison between each group of deviation parameter values, and more specifically, each group of deviation parameter values is substantially uniform. It can be based on whether the deviation threshold specified in the embodiment is exceeded. For example, if a group of deviation parameter values associated with different verification symbols (eg, 1130A-1130C) all exceed a defined deviation threshold and are performed in a substantially uniform manner, the control circuit 111 loses accuracy. However, it can be determined that it is caused by a camera (eg, 1170) or, more specifically, by a change to the camera. This is because the appearance of each of the verification symbols (eg, 1130A-1130C) in the reference or verification image depends on the internal characteristics and / or the positioning of the camera (eg, 1170). More specifically, the reference image coordinates and the verification image coordinates of the verification symbol (for example, 1130A to 1130C) in the reference image or the verification image may all depend on the internal characteristics or the positioning of the camera. Therefore, changes to internal characteristics or positioning of the camera (eg, 1170) can often affect the respective deviation parameter values for all verification symbols (eg, 1130A to 1130C) and are more specific. In many cases, all deviation parameter values can be increased in a substantially uniform manner. By comparison, if part of the robot (eg, 1150), such as the arm, is damaged, malfunctions, or otherwise changes, all other parts of the robot change in exactly the same way (eg, damage or all malfunctions). )Unlikely. Therefore, if there is a change in the part of the robot where at least one deviation parameter value will exceed the specified deviation threshold, the other deviation parameter values in the group of deviation parameter values will be below the specified deviation threshold. It may remain, or a group of deviation parameter values may all exceed the defined deviation threshold, but in a non-uniform manner. Therefore, in one embodiment, at least one of each group of deviation parameter values associated with different verification symbols (eg, 1130A-1130C) exceeds the defined deviation threshold, but each deviation parameter. If all groups of values do not exceed a deviation threshold defined in a substantially uniform manner, the control circuit 111 will lose accuracy due to a change to the robot (eg, 1150), or more specifically to the robot. It can be determined that it is caused.

In one embodiment, the control circuit 111 uses a defined uniformity threshold to assess whether a group of deviation parameter values all exceed the defined deviation threshold in a substantially uniform manner. be able to. For example, the control circuit 111 may determine whether at least one of the deviation parameter values exceeds a defined deviation threshold, and between the deviation parameter values (or each of them exceeding a defined deviation threshold). It can be further determined whether the difference (between quantities) is within the defined uniformity threshold. The uniformity threshold can be dynamically or pre-defined (eg, based on the current operating conditions of the robotic operating system). As an example of using the defined uniformity threshold, the control circuit 111 has a deviation parameter associated with the verification symbol 1130C, although the respective deviation parameter values for verification symbols 1130A to 1130C all exceed the specified deviation threshold. If the value exceeds the specified uniformity threshold and differs from the deviation parameter value associated with verification symbol 1130A and / or exceeds the specified uniformity threshold and differs from the deviation parameter value associated with verification symbol 1130B. When making a determination, the control circuit 111 can determine that a change in the robot 1150, such as a change in at least the robot hand 1155 or another arm portion on which the verification symbol 1130C is located, causes a loss of accuracy. In the above example, the control circuit 111 directly compares the deviation parameter values. In another embodiment, the control circuit 111 compares the respective quantities of deviation parameter values that exceed the defined deviation thresholds, and whether each of these quantities differs beyond the defined uniformity threshold. be able to. In another embodiment, the control circuit 111 has a first deviation parameter value in a group of deviation parameter values that exceeds a defined deviation threshold, but one or more of the groups of deviation parameter values have been defined. If it determines that the deviation threshold is not exceeded, the control circuit 111 also determines that the calibration error (also called misalignment) is such as the arm portion on which the verification symbol associated with the first deviation parameter value is placed. , Can be determined to be caused by a change to a robot (eg, 1150). In another embodiment, if the control circuit 111 determines that the groups of deviation parameter values all exceed the defined deviation thresholds and they do not exceed the defined uniformity thresholds and differ from each other, then The control circuit 111 can determine that the calibration error is caused by a change in the camera (eg, 1170).

In some cases, the robot controller 110 or the control circuit 111 of another computing system can communicate with a conveyor belt, such as the conveyor belt 1173 of FIGS. 11A and 11B. In such cases, the control circuit 111 can be configured to stop the conveyor 1173 belt in response to determining that at least one deviation parameter value exceeds a defined deviation threshold. Stopping the conveyor belt 1173 can prevent the robot arm 1153 from having unwanted interactions with objects on the conveyor belt 1173, based on inaccurate calibration information.

In one embodiment, the control circuit 111 is provided with calibration information such that the link 1154C on which the verification symbol 1130A is arranged, the link 1154D on which the verification symbol 1130B is arranged, or the verification symbol 1130C is arranged. If sufficiently accurate for the robot hand 1155), the calibration information should also be determined to be sufficiently accurate for one or more arm portions upstream of that particular arm portion. Can be configured. As mentioned above, the plurality of arm portions can be arranged as a series of arm portions from the base of the robot to the robot end effector. If the former arm portion precedes the latter arm portion in a series of arm portions, the arm portion may be upstream of another arm portion. For example, link 1154D in FIGS. 11A-11B can be upstream of link 1154E and robot hand 1155. In one example, if the control circuit 111 determines that the calibration information (eg, camera calibration information) is sufficiently accurate for, for example, the robot hand 1155, then the calibration is performed on links 1154E, 1154D, 1154C, It can be determined that it is sufficiently accurate for the upstream arm portions such as 1154B and 1154A. In this example, the control circuit 111 states that the calibration information is sufficiently accurate for the arm portion if the deviation parameter value associated with the verification symbol placed on the arm portion is below the defined deviation threshold. You can judge. In one embodiment, if the control circuit 111 determines that there is a calibration error for a particular arm portion such that the calibration information for that arm portion is not sufficiently accurate, then the control circuit 111 may have some or all. It can be determined that there is a calibration error for the downstream arm portion. For example, if the control circuit 111 determines that the calibration information is not sufficiently accurate for a particular robot portion such as the link 1154D, the control circuit 111 will provide the calibration information for the downstream arm portion such as the link 1154E and the robot hand 1155. It can be judged that it is not accurate enough.

In one embodiment, one or more steps of method 1200, such as steps 1203-1215, can be performed by the robot controller 110 or other computing system in response to user commands. For example, a user (eg, a system operator) can manually trigger a calibration verification operation that includes steps 1203-1215. In one embodiment, steps 1203-1215 can be performed during the rest period. The rest period can be a period during which no robotic operation, such as lifting an object from a conveyor belt or pallet, is being performed. In one embodiment, one or more steps of method 1200, such as steps 1203-1215, can be performed by the robot controller 110 or other computing system in response to defined trigger conditions. As discussed above, trigger conditions can include unplanned events such as collisions involving robots (eg 1150), earthquakes or other natural disasters, which include robots (eg 1150) and / Or can result in changes in the camera (eg, 1170). In some cases, the trigger condition can include a specific period that elapses after an earlier calibration operation, such as the calibration operation used to determine the calibration information in step 1201. In such an example, the previous calibration operation may be the first calibration operation, while the calibration operation in step 1215 may be the second calibration operation.

Further Discussion of Various Embodiments Embodiment A1 is a communication interface configured to communicate with a robot having a base and a robot arm having a verification symbol placed on it and to communicate with a camera having a camera field of view. Related to robot control systems equipped with. The robot control system performs a first camera calibration (or more generally, a calibration operation) and is associated with the camera calibration information (or more generally, the robot control system) associated with the camera. A control circuit configured to determine the calibration information) is further provided. The control circuit a) causes the robot arm to move the verification symbol to a location within the camera field of view during or after the first camera calibration by outputting a first action command to the robot via the communication interface. Control is to control the robot arm, which is a reference point of one or more reference points for verification of the first camera calibration, and b) via a communication interface. The camera receives the image of the verification symbol from the camera, the camera is configured to capture the image of the verification symbol at the reference point, and the image receives the image of the verification symbol, which is the reference image for verification. That, c) to determine the reference image coordinates for verification, and the reference image coordinates are the coordinates where the verification symbol appears in the reference image, to determine the reference image coordinates, and d) to determine the communication interface. By outputting a second operation command based on the camera calibration information to the robot via the camera, the operation of the robot arm is controlled so as to execute the robot operation based on the camera calibration information, and e) the robot. By detecting the pause period during operation and f) outputting a third action command to the robot via the communication interface, the robot arm is moved to move the verification symbol to at least the reference point during the pause period. Controlling and g) receiving additional images of the verification symbol from the camera via the communication interface during the pause period, the camera being configured to capture additional images of the verification symbol at least at its reference points. The further image is a verification image for verification, receiving a further image of the verification symbol and h) determining the verification image coordinates used for verification, the verification image coordinates being verified. Judging the verification image coordinates, which are the coordinates at which the verification symbol appears in the image, and i) determining the deviation parameter value based on the amount of deviation between the reference image coordinates and the verification image coordinates. Both the reference image coordinates and the verification image coordinates are associated with the reference point, and the deviation parameter value is the change of the camera after the first camera calibration, or between the camera and the robot after the first camera calibration. Judging the deviation parameter value, which indicates the change in the relationship, i) determining whether the deviation parameter value exceeds the specified threshold, and j) deviation. Performing a second camera calibration in response to determining that the parameter value exceeds a defined threshold to determine updated camera calibration information (or, more generally, a second). To determine the updated calibration information by performing the calibration operation of), and is further configured to perform.

Embodiment A2 includes the robot control system of embodiment A1, and the control circuit gives the robot a fourth action command via the communication interface in response to the determination that the deviation parameter value does not exceed a defined threshold. Is configured to control the robot so that it continues to operate after a pause without performing further camera calibration.

The embodiment A3 includes the robot control system of the embodiment A1 or A2, and one or more reference points are a plurality of reference points corresponding to a plurality of reference image coordinates, and the reference image coordinates are a plurality of reference images. It is one of the coordinates. In this embodiment, the control circuit is further configured to determine a plurality of verification image coordinates corresponding to the plurality of reference points, the verification image coordinates being one of the plurality of verification image coordinates, and a deviation. The parameter value is based on the amount of deviation between the plurality of reference image coordinates and the plurality of verification image coordinates for the plurality of reference points, and each deviation amount of the respective deviation amounts is (a) a plurality of reference points. It is between the reference image coordinates corresponding to each reference point of (b) and the verification image coordinates corresponding to the same reference point.

The embodiment A4 includes the robot control system of the embodiment A3, and the plurality of verification image coordinates are the coordinates where the verification symbol appears in the plurality of verification images, and the verification image is one of the plurality of verification images. The control circuit is configured to control the camera and capture all of the plurality of verification images within the pause period.

The embodiment A5 includes the robot control system of the embodiment A3, and the plurality of verification image coordinates are the coordinates in which the verification symbol appears in the plurality of verification images, and the verification image is one of the plurality of verification images. The control circuit is configured to control the camera and capture a plurality of verification images within different pauses, the pause being one of the different pauses.

The embodiment A6 includes a robot control system according to any one of the embodiments A1 to A5, and the verification symbol includes a first region having a first color and a second region having a second color. , The ratio of the area of the first region to the area of the second region is defined and stored on the storage device of the robot control system as the defined ratio.

The A7 embodiment includes the robot control system of the A6 embodiment, the control circuit being configured to identify a verification symbol in a reference image or verification image based on a defined ratio.

The embodiment A8 includes the robot control system of the embodiment A7, the robot arm has a calibration pattern arranged on it, the reference image includes a verification symbol and a calibration pattern, and the control circuit is a reference. It is determined whether the image portion has a first image region having a first color and a second image region having a second color, and the area of the first image region and the second image region. It is configured to determine whether the portion of the reference image is a verification symbol or a calibration pattern by determining whether the ratio of to the area of the image region is equal to the defined ratio.

The embodiment A9 includes a robot control system according to any one of the embodiments A1 to A8, and the verification symbols include a first shape and a second shape that are concentric with each other, and the first shape and the second shape. The centers of each are substantially the same.

The embodiment A10 includes the robot control system of the embodiment A9, in which the control circuit a) determines the first coordinate of the center of the first shape in the reference image and b) the second in the reference image. To determine the reference image coordinates by determining the second coordinate of the center of the shape of, and c) determining the reference image coordinates as the average of the first and second coordinates in the reference image. It is composed of. In this embodiment, the control circuit d) identifies the first coordinate of the center of the first shape in the verification image and e) determines the second coordinate of the center of the second shape in the verification image. It is configured to specify the verification image coordinates by specifying and f) specifying the verification image coordinates as the average of the first and second coordinates in the verification image.

The embodiment A11 includes a robot control system according to any one of the embodiments A1 to A10, and the control circuit is configured to identify a reference image or a verification symbol in a verification image by identifying a circular ring. The verification symbol is formed as a circular ring.

Embodiment A12 includes a robot control system according to any one of embodiments A1 to A11, in which the control circuit determines the temperature of the environment in which the robot is located and determines a defined threshold or calibration based on the measured temperature. It is further configured to adjust at least one of the threshold information.

The A13 embodiment includes the robot control system of the A12 embodiment, the control circuit sets a defined threshold value to have a first value when the temperature is outside the specified range, and the temperature is within the specified range. At one point, the threshold is configured to adjust a defined threshold based on temperature by setting the threshold to have a second value lower than the first.

The embodiment A14 includes any one of the robot control systems of embodiments A1 to A13, and one or more reference points such that the control circuit is configured to move the verification symbol via the robot arm refers to the camera. Includes multiple references located on the surface of a concave sphere.

The A15 embodiment includes the robot control system of the A14 embodiment, in which the control circuit moves the robot arm so that the verification symbol is tangentially oriented with respect to the surface of the sphere at each reference point of the plurality of reference points. Further configured to control.

The embodiment A16 includes a robotic control system according to any one of embodiments A1 to A15, in order to move the verification symbol so that it faces the camera directly when the verification symbol is moved to a reference point. It is configured to control the robot arm.

The embodiment A17 includes a robot control system according to any one of the embodiments A1 to A16, and the control circuit detects a period during which the robot is not performing the robot work during the robot operation, thereby setting a pause period for the robot operation. It is configured to detect.

Embodiment A18 includes the robotic control system of embodiment A17, the control circuit being configured to control the robot arm to interact with an object on a conveyor belt reachable by the robot arm. The pause period by detecting the absence of an object on the conveyor belt or by detecting that the distance between the robot and the closest object on the conveyor belt exceeds a defined distance threshold. Is configured to detect.

Embodiment B1 relates to a computing system including a communication interface and a control circuit. The communication interface comprises (i) a camera having a camera field of view and (ii) a group of verification symbols arranged on each arm portion of the plurality of arm portions having a plurality of arm portions operably attached to each other. It is configured to communicate with a robot that has a robot arm. The control circuit is to output an operation command for controlling the operation of the robot arm in order to execute the robot operation when the robot arm is in the camera field of view, and the operation command is based on the calibration information. The reference image coordinates are the coordinates where the verification symbol group appears in the reference image, and the reference image is the verification symbol. An image to represent a group, which is generated by the camera during the first period when the robot arm is in the first pose, and during the second period following the first period. It is an additional image to output an additional motion command to control the robot arm to move to the first pose and to represent a group of verification symbols, and the robot arm is the result of the additional motion command. As a result, when the robot is moved to the first pose, the verification image generated by the camera is received and the verification image coordinate group is determined, and the verification image coordinate group is included in the verification image. Judging that the group of verification symbols is each coordinate in which it appears, and determining each group of deviation parameter values, which is based on the amount of deviation between the group of reference image coordinates and the group of verification image coordinates. To determine that each group of deviation parameter values is associated with a group of validation symbols, and at least one deviation parameter value of each group of deviation parameter values is specified. Responding to the determination of whether the deviation threshold is exceeded and the determination that at least one deviation parameter value in each group of deviation parameter values exceeds the defined deviation threshold, each deviation At least one of a group of parameter values outputs a notification that the specified deviation threshold is exceeded, and performs a calibration operation to determine updated calibration information. It is configured to do and do at least one. The control circuit can execute the method, for example, by executing an instruction on a non-transitory computer-readable medium.

The first embodiment B2 includes the computing system according to the first embodiment, in which the first pause is associated with the first additional action command output during the first period, and the first additional action command. However, the robot arm has one or more operating parameter values for controlling the robot arm to move to the first pose, and the reference image shows that the robot arm is in the first pose as a result of the first additional motion command. Generated by the camera when in. Further, in this embodiment, the additional operation command output during the second period is the second additional operation command, and also includes one or more operation parameter values.

Embodiment B3 includes the computing system of Embodiment B2, where each verification symbol in the group of verification symbols has a circular shape and is one or more of a first additional action command and a second additional action command. The operating parameter value of is such that the group of verification symbols appears in the reference image and in the verification image without the eccentricity or with the eccentricity of each amount below the defined eccentricity threshold. Position the group of verification symbols with.

Embodiment B4 includes the computing system of any one of embodiments B1 to B3, where the control circuit is one for an additional action command that moves each verification symbol in the group of verification symbols so that it faces the camera directly. It is configured to judge the above operating parameter values.

Embodiment B5 includes the computing system of Embodiment B4, where one or more operating parameter values tangentially make a group of verification symbols tangential to one or more virtual spheres that are concave with respect to the camera. Make it face.

The control circuit identifies the circular ring when embodiment B6 includes any one of the computing systems of embodiments B1 to B5 and at least one of the verification symbols in the group of verification symbols is formed as a circular ring. By doing so, it is configured to identify at least one verification symbol in the reference image and the verification image.

The control circuit forms at least one verification symbol when embodiment B7 includes the computing system of embodiment B6 and the groups of verification symbols are formed as respective circular rings with different sizes. It is configured to identify at least one verification symbol based on the size of each circular ring.

Embodiment B8 includes any one of the computing systems of Embodiments B1 to B7, where the control circuit is a group of validation symbols in a reference image based on a defined model that describes the geometry of the robot arm. It is configured to identify at least one verification symbol of.

Embodiment B9 includes the computing system of Embodiment B8, the control circuit determines the region in the reference image where at least one verification symbol is expected to appear based on the model, and within the region of the reference image. It is configured to search for at least one verification symbol of.

The embodiment B10 includes any one of the computing systems of embodiments B1 to B9, in which the control circuit has a deviation defined in at least one deviation parameter value based on a comparison between each group of deviation parameter values. It is configured to determine the type of calibration error that causes the threshold to be exceeded, and the type of calibration error is whether the loss of accuracy with respect to the calibration information represents a change in the robot, or the loss of accuracy in the camera. Indicates whether it represents a change.

The embodiment B11 includes the computing system of the embodiment B10, and the control circuit determines whether all the groups of deviation parameter values exceed the specified deviation threshold value, and whether each group of deviation parameter values exceeds the specified deviation threshold value. It is configured to determine if they differ from each other beyond a defined uniformity threshold. The control circuit in this embodiment is calibrated in response to the determination that all groups of deviation parameter values do not exceed a defined deviation threshold and do not differ from each other beyond a defined uniformity threshold. The type of threshold error is configured to determine that it is a calibration error that represents a change in the camera.

Embodiment B12 includes the computing system of Embodiment B11, and the control circuit determines that one or more of the groups of deviation parameter values does not exceed a defined deviation threshold, or each deviation parameter. In response to the determination that the groups of values are different from each other beyond the defined uniformity threshold, it is further configured to determine that the type of calibration error is a calibration error that represents a change in the robot.

Embodiment B13 includes any one of the computing systems of embodiments B1 to B12. In this embodiment, the calibration information is associated with the first calibration operation, and the calibration operation for generating the updated calibration information is a second calibration operation following the first calibration operation. The control circuit is configured to output an additional operation command and a camera command to receive the verification image in response to the specified trigger condition. The specified trigger condition includes at least one of a specified period of time that has elapsed since the first calibration operation, or an event that is not planned by the computing system and causes a change in the robot or camera.

The embodiment B14 includes any one of the computing systems of embodiments B1 to B13, and when a plurality of robot arm portions are arranged as a series of arm portions from the base of the robot to the robot end effector, the control circuit. However, it is determined whether the deviation parameter value for the first verification symbol in the group of verification symbols exceeds the specified deviation threshold value, and the first verification symbol is arranged from among the plurality of arm parts. In response to identifying the first arm portion with and determining that the deviation parameter value for the first verification symbol does not exceed the defined deviation threshold, the calibration information is for the first arm portion. , And determining that the series of arm portions is accurate with respect to at least one additional arm portion preceding the first arm portion.

The embodiment B15 includes any one of the computing systems of embodiments B1 to B14, and when the computing system communicates with a conveyor belt used for robot operation, the control circuit has at least one deviation parameter value. , The conveyor belt is configured to stop in response to a determination that the specified deviation threshold is exceeded.

The embodiment B16 includes any one of the computing systems of embodiments B1 to B15, the reference image is the first reference image associated with the first pose of the robot arm, and the verification image is the first. The first validation image associated with the pose, the group of reference image coordinates is the group of first reference image coordinates associated with the first pose, and the group of validation image coordinates is the first. A group of first verified image coordinates associated with the pose. In the present embodiment, the control circuit is to determine the group of the second reference image coordinates, and the group of the second reference image coordinates and the group of the verification symbols appear in the second reference image, respectively. Coordinates, the second reference image is generated by the camera when the robot arm is in the second pose, following the determination and the second reference image being generated, the robot arm To output additional motion commands to control the robot arm to move to the second pose and to receive the second verification image, the second verification image is also a group of verification symbols. Also represents, as a result of further action commands, when the robot arm is moved to the second pose, it is to determine the receiving and the group of second verification image coordinates generated by the camera. , The second group of verification image coordinates is the coordinate at which the group of verification symbols appears in the second verification image. In this embodiment, each group of deviation parameter values is further based on the respective amount of deviation between the group of second reference image coordinates and the group of second verification image coordinates.

Although various embodiments have been described above, it should be understood that these embodiments are presented as mere explanations and examples of the present invention, not as a limitation. It will be apparent to those skilled in the art that various changes in form and detail can be made within the invention without departing from the spirit and scope of the invention. Therefore, the scope of the present invention should not be limited by any of the exemplary embodiments described above, but only by the appended claims and their equivalents. .. It will also be appreciated that each of the embodiments discussed herein, and each feature of each cited document cited herein, can be used in combination with the features of any other embodiment. All patents and publications discussed herein are hereby incorporated by reference in their entirety.

Claims (20)

It ’s a computing system,
A communication interface comprising (i) a camera having a camera field of view and (ii) a plurality of arm portions operably attached to each other, and arranged on each arm portion of the plurality of arm portions. With a robot arm, with a group of verification symbols, configured to communicate with the robot, with a communication interface,
With a control circuit,
The control circuit provides when the robot arm is in the camera field of view.
In order to execute the robot operation, it is to output an operation command for controlling the operation of the robot arm, and the operation command is based on the calibration information.
To determine a group of reference image coordinates, the group of reference image coordinates is the coordinate at which the group of verification symbols appears in the reference image, and the reference image represents the group of verification symbols. And when the robot arm is in the first pose, it is generated by the camera during the first period.
To output additional motion commands to control the robot arm to move to the first pose during the second period following the first period.
An additional image for representing the group of verification symbols and a verification image generated by the camera when the robot arm is moved to the first pose as a result of the additional motion command. To receive and
It is to determine the group of the verification image coordinates, that the group of the verification image coordinates is each coordinate in which the group of the verification symbols appears in the verification image.
Determining a group of deviation parameter values based on the amount of deviation between the group of reference image coordinates and the group of verification image coordinates. , Being associated with the group of verification symbols
Determining whether at least one deviation parameter value in each of the above groups of deviation parameter values exceeds a defined deviation threshold.
In response to the determination that at least one of the groups of deviation parameter values exceeds the defined deviation threshold, at least one of the groups of deviation parameter values said. To output a notification that the specified deviation threshold is exceeded, and to perform a calibration operation to determine the updated calibration information, and to perform at least one of them.
A computing system that is configured to do. The first pose is associated with a first additional action command output during the first period.
The first additional motion command has one or more action parameter values for controlling the robot arm to move to the first pose.
The reference image is generated by the camera when the robot arm is in the first pose as a result of the first additional motion command.
The computing system according to claim 1, wherein the additional operation command output during the second period is the second additional operation command and also includes the one or more operation parameter values. Each verification symbol in the group of verification symbols has a circular shape and has a circular shape.
The first additional operation command and the one or more operation parameter values of the second additional operation command are such that in the reference image and in the verification image, the group of verification symbols is accompanied by an eccentricity. The computing system of claim 2, wherein the group of verification symbols is positioned without or in a manner such that it appears with an eccentricity of each amount below a defined eccentricity threshold. Claimed, the control circuit is configured to determine one or more operating parameter values for the additional operation command that move each verification symbol in the group of verification symbols so that it faces the camera directly. The computing system according to 1. The compute according to claim 4, wherein the one or more operating parameter values cause the group of verification symbols to point tangentially to one or more virtual spheres that are concave with respect to the camera. Ring system. When at least one of the verification symbols in the group of verification symbols is formed as a circular ring, the control circuit identifies the circular ring so that the at least one in the reference image and in the verification image. The computing system according to claim 1, which is configured to identify a verification symbol. When the group of verification symbols is formed as each circular ring having a different size, the control circuit is based on the size of each circular ring forming the at least one verification symbol. The computing system according to claim 6, which is configured to identify one verification symbol. The control circuit is configured to identify at least one verification symbol of the group of verification symbols in the reference image, based on a defined model that describes the geometry of the robot arm. Item 1. The computing system according to item 1. The control circuit
Determining the region in the reference image where the at least one verification symbol is expected to appear based on the model.
The computing system according to claim 8, wherein the computing system is configured to search for and perform the at least one verification symbol in the region of the reference image. The control circuit is configured to determine the type of calibration error that causes the at least one deviation parameter value to exceed the defined deviation threshold, based on a comparison between each group of deviation parameter values. Ori,
The type of calibration error according to claim 1, wherein the loss of accuracy with respect to the calibration information represents a change in the robot, or whether the loss of accuracy represents a change in the camera. Computing system. In the control circuit, whether or not all the groups of the respective deviation parameter values exceed the specified deviation threshold value, and the groups of the respective deviation parameter values differ from each other beyond the specified uniformity threshold value. Judging whether or not
The type of calibration error in response to the determination that all of the respective groups of deviation parameter values exceed the defined deviation threshold and are not different from each other beyond the defined uniformity threshold. The computing system according to claim 10, wherein the computing system is configured to determine that it is a calibration error representing a change in the camera. The control circuit determines that one or more of the respective groups of deviation parameter values does not exceed the defined deviation threshold, or the respective groups of deviation parameter values are said to have the defined uniformity. The computer according to claim 11, further configured to determine that the type of calibration error is a calibration error representing a change in the robot in response to the determination that the thresholds are exceeded and differ from each other. Ing system. The calibration information is associated with the first calibration operation.
The calibration operation for generating the updated calibration information is a second calibration operation following the first calibration operation.
The control circuit is configured to output the additional operation command and a camera command to receive the verification image in response to a defined trigger condition.
The specified trigger condition is
A defined period of time that has passed since the first calibration operation, and events that are not planned by the computing system and result in changes to the robot or camera.
The computing system of claim 1, comprising at least one of. When the plurality of robot arm portions are arranged as a series of arm portions from the base of the robot to the robot end effector, the control circuit
Determining whether the deviation parameter value for the first verification symbol of the verification symbol group exceeds the defined deviation threshold.
Identifying the first arm portion on which the first verification symbol is arranged from the plurality of arm portions, and
In response to the determination that the deviation parameter value with respect to the first verification symbol does not exceed the defined deviation threshold, the calibration information is provided with respect to the first arm portion and in the series of arm portions. The computing system of claim 1, wherein the computing system is configured to determine that it is accurate with respect to at least one additional arm portion preceding the first arm portion. When the computing system communicates with a conveyor belt used to operate the robot, the control circuit responds to a determination that the at least one deviation parameter value exceeds the defined deviation threshold. The computing system according to claim 1, which is configured to stop the conveyor belt. The reference image is a first reference image associated with the first pose of the robot arm.
The verification image is a first verification image associated with the first pose.
The group of reference image coordinates is a group of first reference image coordinates associated with the first pose.
The group of verification image coordinates is a group of first verification image coordinates associated with the first pose.
The control circuit
The second reference image coordinate group is determined, and the second reference image coordinate group is the coordinate at which the verification symbol group appears in the second reference image, and the second reference image coordinate group is determined. The reference image of is generated by the camera when the robot arm is in the second pose.
Following the generation of the second reference image, an additional motion command for controlling the robot arm to move the robot arm to the second pose is output.
By receiving the second verification image, the second verification image also represents the group of verification symbols, and as a result of the further action command, the robot arm is moved to the second pose. When it is generated by the camera,
To determine the group of the second verification image coordinates, that the group of the second verification image coordinates is the coordinate at which the group of the verification symbols appears in the second verification image.
Is configured to do
The computing according to claim 1, wherein each of the groups of deviation parameter values is further based on the amount of deviation between the group of the second reference image coordinates and the group of the second verification image coordinates. Ing system. A non-transitory computer-readable medium with internally stored instructions that, when executed by a control circuit of a computing system, the control circuit.
To output an operation command based on calibration information, the computing system includes (i) a camera having a camera field of view and (ii) a plurality of arm portions operably attached to each other. The robot is configured to communicate with a robot having a robot arm including a group of verification symbols arranged on each of the plurality of arm portions, and the operation command executes the robot operation. To control the operation of the robot arm
To determine a group of reference image coordinates, the group of reference image coordinates is the coordinate at which the group of verification symbols appears in the reference image, and the reference image represents the group of verification symbols. And when the robot arm is in the first pose, it is generated by the camera during the first period.
To output additional motion commands to control the robot arm to move to the first pose during the second period following the first period.
An additional image for representing the group of verification symbols, and a verification image generated by the camera when the robot arm is moved to the first pose as a result of the additional motion command. To receive and
It is to determine the group of the verification image coordinates, that the group of the verification image coordinates is each coordinate in which the group of the verification symbols appears in the verification image.
Determining a group of deviation parameter values based on the amount of deviation between the group of reference image coordinates and the group of verification image coordinates. , Being associated with the group of verification symbols
Determining whether at least one deviation parameter value in each of the above groups of deviation parameter values exceeds a defined deviation threshold.
In response to the determination that at least one of the groups of deviation parameter values exceeds the defined deviation threshold, at least one of the groups of deviation parameter values said. To output a notification that the specified deviation threshold is exceeded, and to perform a calibration operation to determine the updated calibration information, and to perform at least one of them.
A non-transitory computer-readable medium that allows you to do so. The first pose is associated with a first additional action command output during the first period.
The first additional motion command has one or more action parameter values for controlling the robot arm to move to the first pose.
The non-transient computer according to claim 17, wherein the additional operation command output during the second period is the second additional operation command and also includes the one or more operation parameter values. Readable medium. When the instruction is executed by the control circuit, the control circuit exceeds the defined deviation threshold by causing the control circuit to exceed the at least one deviation parameter value based on a comparison between the respective groups of deviation parameter values. Lets you further determine the type of calibration error to make
17. The type of calibration error of claim 17, wherein the loss of accuracy with respect to the calibration information indicates whether the loss of accuracy represents a change in the robot, or whether the loss of accuracy represents a change in the camera. Non-temporary computer-readable medium. The method performed by the computing system,
The computing system outputs operation commands based on calibration information, wherein the computing system is (i) a camera having a camera field of view and (ii) a plurality of robots mounted so as to be operable with each other. It is configured to communicate with a robot, including a robot arm, comprising an arm portion and comprising a group of verification symbols arranged on each of the plurality of arm portions, said operation command. Is to control the operation of the robot arm in order to execute the robot operation.
The computing system determines a group of reference image coordinates, wherein the reference image coordinate group is each coordinate in which the verification symbol group appears in the reference image, and the reference image is the reference image. An image to represent a group of verification symbols and to be generated by the camera during the first period when the robot arm is in the first pose.
During the second period following the first period, the computing system outputs additional action commands for controlling the robot arm to move to the first pose.
Receiving a verification image by the computing system, wherein the verification image is an additional image for representing the group of verification symbols, and the robot arm is the result of the additional action command. What is generated by the camera when moved to the first pose
The computing system determines a group of verification image coordinates, that the group of verification image coordinates is the coordinate at which the group of verification symbols appears in the verification image.
The computing system determines each group of deviation parameter values based on their respective deviation amounts between the group of reference image coordinates and the group of verification image coordinates. That the group of deviation parameter values is associated with the group of verification symbols
Determining by the computing system that at least one deviation parameter value in each of the groups of deviation parameter values exceeds a defined deviation threshold.
In response to the determination that at least one of the respective groups of deviation parameter values exceeds the defined deviation threshold, the computing system determines that each of the groups of deviation parameter values. At least one of outputting a notification that the specified deviation threshold is exceeded and performing a calibration operation to determine updated calibration information. How to do and include.

Images