Information processing device and robot system

Abstract

An information processing device according to the present invention comprises a calculation unit that, when performing interference avoidance calculation between a robot or tool and an object on the basis of three-dimensional data acquired by a sensor which measures a three-dimensional space, performs the interference avoidance calculation while excluding a workpiece to be worked from the three-dimensional data, on the basis of the three-dimensional data and information indicating the position of the workpiece in the three-dimensional space.

Description

Information Processing Apparatus and Robot System

[0001] The present disclosure relates to an information processing apparatus and a robot system.

[0002] There is known a robot system configured to detect a target object from image information acquired by a visual sensor, and handle the target object using a robot based on the detection result. Patent Document 1 and Patent Document 2 describe configuration examples of such a robot system.

[0003] Japanese Unexamined Patent Application Publication No. 2023-172790 Japanese Unexamined Patent Application Publication No. 2023-094786

[0004] A robot system that detects a workpiece from three-dimensional data acquired by a visual sensor that measures a three-dimensional space and handles the workpiece by a robot may be configured to perform interference avoidance calculation between the robot or a hand and an object using the three-dimensional data. However, in the case of such a configuration, it may be determined that the workpiece to be worked on by the robot interferes with the robot or the hand, leading to a situation where the operation by the robot is interrupted. Even in a case where the robot system adopts a configuration of performing interference avoidance calculation using three-dimensional data acquired by a visual sensor, a technique that enables the interference avoidance calculation to be performed accurately is desired.

[0005] One aspect of the present disclosure is an information processing apparatus including a calculation unit that, when performing interference avoidance calculation between a robot or a tool and an object based on the three-dimensional data, based on three-dimensional data acquired by a sensor that measures a three-dimensional space and information indicating a position of a workpiece in the three-dimensional space, excludes the workpiece to be worked on from the three-dimensional data to perform the interference avoidance calculation.

[0006] These and other objects, features and advantages of the present invention will become more apparent from the detailed description of the exemplary embodiments of the present invention illustrated in the accompanying drawings.

[0007] This figure shows the configuration of a robot system including an image processing device according to one embodiment. This is a functional block diagram relating to the image processing device and the robot control device. This is a flowchart showing the interference avoidance calculation process according to this embodiment. This figure schematically shows the representation of a three-dimensional space based on a three-dimensional point cloud acquired by a vision sensor. This figure schematically shows a distance image acquired by a vision sensor. This figure shows the situation in the first modified example where the portion including the detected workpiece is extracted from the distance image as a binarized image. This figure conceptually shows the handling of voxel data in the second modified example.

[0008] Next, embodiments of the present disclosure will be described with reference to the drawings. In the drawings, similar components or functional parts are given the same reference numerals. For ease of understanding, the scale of these drawings has been appropriately changed. Furthermore, the embodiments shown in the drawings are just one example of how to carry out the present invention, and the present invention is not limited to the illustrated embodiments.

[0009] Figure 1 shows the configuration of a robot system 100 including an image processing device 20 according to one embodiment. As shown in Figure 1, the robot system 100 comprises a robot 10, a robot control device 50 that controls the robot 10, a teaching device 40 connected to the robot control device 50, a vision sensor 70, and an image processing device 20. The image processing device 20 is connected to the robot control device 50. The robot system 100 can, for example, detect a workpiece W (only a part is labeled) placed inside a container 90 using the vision sensor 70, and handle the workpiece W (removal, transfer, etc.) with a hand 15 mounted on the robot 10.

[0010] In this embodiment, robot 10 is a vertical articulated robot, but other types of robots such as horizontal articulated robots, parallel link robots, and dual-arm robots may be used depending on the work purpose. Figure 1 shows an example in which a hand 15 is attached to the wrist of robot 10, but various types of tools (end effectors) can be attached to the wrist of robot 10 depending on the work purpose.

[0011] In this embodiment, the vision sensor 70 functions as a three-dimensional vision sensor capable of measuring three-dimensional space and acquiring positional information in three-dimensional space. Hereinafter, the positional information in three-dimensional space acquired by the vision sensor 70 will also be referred to as three-dimensional data. As the three-dimensional vision sensor, for example, a stereo camera that performs measurement using passive stereo measurement or active stereo measurement, or a TOF (Time of Flight) camera that measures the distance to an object using the optical time-of-flight method can be used. Here, it is assumed that the vision sensor 70 is fixed in the workspace so as to image the workpiece W from above, as shown in Figure 1. Alternatively, the vision sensor 70 may be mounted on the end-effector of the robot 10. The vision sensor 70 may also have the function of a two-dimensional camera.

[0012] The visual sensor 70 is assumed to be calibrated, and the internal parameters that associate the camera coordinate system fixed to the visual sensor 70 (imaging surface) with the two-dimensional coordinates set on the image (imaging surface), and the external parameters that associate the world coordinate system fixed to the workspace with the camera coordinate system are assumed to be known in the robot system 100. These calibration data may be stored, for example, in the memory unit of the image processing device 20.

[0013] The image processing device 20 controls the visual sensor 70 and has the function of executing various image processing, including processing for detecting objects, and various interference avoidance calculations. The image processing device 20 may have a hardware configuration as a general computer, including a processor 21, memory (ROM, RAM, non-volatile memory, etc.), storage unit 22, operation unit 23, display unit 24, input / output interface, network interface, etc. (see Figure 2). The image processing device 20 may be configured as a dedicated image processing device, or it may be configured as a PC (personal computer) or other general-purpose information processing device. The display unit 24 is, for example, a liquid crystal display. The operation unit 23 may include, for example, a keyboard and various pointing devices such as a mouse.

[0014] In Figure 1, the image processing device 20 is shown as a separate device from the robot control device 50 and is located in the robot system 100. However, the functions of the image processing device 20 may also be incorporated into the robot control device 50.

[0015] The robot control device 50 controls the operation of the robot 10 according to the operation program or commands from the teaching device 40. The robot control device 50 may have a hardware configuration as a general computer, including a processor, memory (ROM, RAM, non-volatile memory, etc.), storage device, operation unit, input / output interface, network interface, etc.

[0016] The teaching device 40 is used as an operating terminal for teaching (programming) and setting various settings for the robot 10. The teaching device 40 may be a teaching control panel, or it may be composed of a tablet computer or the like. The teaching device 40 may have a hardware configuration as a general computer, including a processor, memory (ROM, RAM, non-volatile memory, etc.), storage device, operation unit, display unit 43, input / output interface, network interface, etc. The display unit 43 may be composed of, for example, a liquid crystal display.

[0017] Figure 2 is a functional block diagram relating to the image processing device 20 and the robot control device 50. As shown in Figure 2, the robot control device 50 includes an motion control unit 151. The motion control unit 151 controls the movement of the robot 10 according to the motion program or according to commands from the teaching device 40. The robot control device 50 also includes a servo control unit (not shown) that performs servo control on the servo motors of each axis according to commands for each axis generated by the motion control unit 151.

[0018] As shown in Figure 2, the image processing device 20 includes a visual sensor control unit 121, a detection unit 122, a labeling processing unit (processing unit) 124, and an interference avoidance calculation unit (calculation unit) 125. As shown in Figure 2, these functional blocks may also be realized by the processor 21 executing software.

[0019] Figure 2 illustrates the storage unit 22, operation unit 23, and display unit 24 as hardware components of the image processing device 20. The storage unit 22 consists of, for example, non-volatile memory, a hard disk drive, etc., and stores workpiece model data, calibration data, and various other data necessary for controlling the visual sensor and image processing.

[0020] The vision sensor control unit 121 controls the operation of the vision sensor 70. For example, the vision sensor control unit 121 can receive operation commands for the vision sensor 70 from the robot control device 50 and control the vision sensor 70.

[0021] The detection unit 122 can detect a workpiece based on image information (3D data) acquired by the visual sensor 70, for example, by a pattern matching method. For example, the detection unit 122 can detect the position and orientation of a workpiece by matching the contour pattern of the workpiece extracted from the 3D data with the contour pattern obtained from the workpiece model data.

[0022] The labeling processing unit 124 has the function of labeling the workpiece with respect to the 3D data acquired by the visual sensor 70, based on the detection result by the detection unit 122. Here, labeling a workpiece with respect to 3D data means adding or associating data (label data) to distinguish the workpiece with respect to the 3D data.

[0023] The interference avoidance calculation unit 125 uses the 3D data acquired by the vision sensor 70 to determine whether the robot 10 or hand 15 will interfere with an object. If interference is determined to occur, it performs an interference avoidance calculation to modify the path of the robot 10 so that the robot 10 or hand 15 does not interfere with the object. The interference avoidance calculation can be performed, for example, by optimizing the path to obtain the shortest path while avoiding obstacles under predetermined constraints such as the robot's speed. The interference avoidance calculation unit 125 can exclude the workpiece that the robot 10 is working on from the 3D data based on the label data generated by the labeling processing unit 124 and then perform the interference determination. This prevents a situation where, when the robot 10 is working on a certain workpiece (workpiece to be worked on), it is determined that the robot 10 or hand 15 will interfere with that workpiece, causing the robot 10 to stop working.

[0024] Figure 3 is a flowchart illustrating the interference avoidance calculation process according to this embodiment. This interference avoidance calculation process is performed under the control of the processor 21 of the image processing device 20. Here, the interference avoidance calculation process is described assuming that the 3D data is represented as a 3D point cloud.

[0025] First, a 3D point cloud is acquired as 3D data within a predetermined imaging range including the container 90 by the vision sensor 70 (3D vision sensor) (step S1). Figure 4 is a schematic diagram showing the representation of the 3D space based on the 3D point cloud D1 acquired here. Note that in Figure 4, the side walls of the container 90 are partially omitted to make the workpieces inside the container 90 easier to understand. As shown in Figure 4, multiple workpieces, including workpieces W1 and W2, are captured inside the container 90.

[0026] Next, the detection unit 122 detects the workpieces using a pattern matching method that combines the 3D point cloud and the workpiece model data (step S2). This detects the position and orientation of each workpiece, including workpieces W1 and W2, within the 3D point cloud D1.

[0027] Next, the labeling processing unit 124 labels the workpieces based on the detection results (step S3). Here, as an example, the labeling processing unit 124 performs the process of assigning labels (numbers) to the pixels (connected pixels) that make up each workpiece in the 3D point cloud D1 (labeling). In this case, in the 3D point cloud D1 shown in Figure 4, the pixels (connected pixels) of workpiece W1 are assigned a number indicating workpiece W1 (for example, number "1"), and the pixels (connected pixels) of workpiece W2 are assigned a number indicating workpiece W2 (for example, number "2"). In this way, the workpiece to be worked on can be identified within the 3D point cloud D1. In step S3, the 3D data (3D point cloud D1) acquired by the visual sensor 70 is also saved.

[0028] Furthermore, methods other than directly assigning labels (numbers) to the pixels (connected pixels) that constitute each workpiece within the 3D point cloud D1, as described above, may be used for labeling workpieces in the 3D point cloud. For example, a dataset with the same 3D spatial size as the 3D point cloud D1 obtained by measurement may be prepared separately, and workpiece identification numbers may be assigned to the pixels at the location of each workpiece within that dataset. In this case, the dataset can function as label data for identifying workpieces in the 3D point cloud D1.

[0029] Next, the interference avoidance calculation unit 125 removes the workpiece to be retrieved from the 3D point cloud D1 based on the label generated in step S3, and performs interference determination and interference avoidance calculation between the robot 10 or hand 15 and the object based on the 3D point cloud D1 (step S4). For example, in the labeling of workpieces, the workpieces are assigned numbers 1, 2, ... in order of height as their position. Then, in step S4, the workpiece at the highest position among the detected workpieces is determined to be the one to be retrieved. In this case, the data of the workpiece to be retrieved (the workpiece with the highest position and number "1") is removed from the 3D point cloud D1, and interference determination and interference avoidance calculation between the robot 10's hand 15 and the object are performed. Therefore, the situation in which the workpiece to be retrieved is determined to interfere with the robot 10's hand 15 is avoided.

[0030] The robot control device 50 (motion control unit 151) can cause the robot 10 (hand 15) to retrieve the target workpiece based on the results of the interference avoidance calculation process described above. The robot control device 50 (motion control unit 151) can perform the workpiece retrieval process in the following steps: (Step a1) By executing the interference avoidance calculation process (Figure 3), the robot control device 50 detects the workpieces in the container 90 and performs an interference avoidance calculation by excluding the workpiece to be worked on (for example, the workpiece at the highest position) from the 3D data. (Step a2) The robot control device 50 (motion control unit 151) causes the robot to retrieve the workpiece based on the results of the interference avoidance calculation. (Step a3) Steps a2 and a3 are repeated until it is determined that the retrieval work for all workpieces in the container 90 has been completed.

[0031] Next, two modified examples (the first modified example and the second modified example) of the interference avoidance calculation process described above will be explained with reference to Figure 3. For the sake of clarity, the step numbers in Figure 3 will be referred to as appropriate below.

[0032] (First Modification) The first modification is an example in which a depth image is adopted as the data format for the 3D data, and a binarized image obtained by cutting out a small region containing the detected workpiece from the depth image is used as label data to represent the detected workpiece.

[0033] In the first modified example, the workpiece is detected based on the depth image (step S2). The detection unit 122 can, for example, detect the workpiece by pattern matching based on the contour pattern of the workpiece extracted from the depth image and the contour pattern extracted from the workpiece model data.

[0034] Next, the labeling processing unit 124 labels the workpieces in relation to the distance image (step S3). The specific details of this process will be explained with reference to Figures 5A and 5B. Figure 5A is a schematic diagram showing the distance image G1 obtained by imaging the container 90 from above with the visual sensor 70. The distance image is an image that represents the distance to the object, for example, by the intensity of the grayscale. In the distance image G1, the bottom surface of the container 90 and each workpiece (only some are labeled with codes W1 and W2) are represented by different degrees of grayscale.

[0035] The labeling processing unit 124 can recognize the position and orientation of each workpiece within the distance image G1 based on the detection results from the detection unit 122. Based on the detection results from the detection unit 122, the labeling processing unit 124 extracts and saves a small portion of the distance image G1 containing the detected workpiece as a binarized image. Figure 5B shows the situation where the small portions containing the detected workpieces W1 and W2 have been extracted as binarized images L1 and L2, respectively. In binarized images L1 and L2, the parts where the workpiece exists are represented by the value '1', and the parts where the workpiece does not exist are represented by the value '0'. In addition, binarized images L1 and L2 each hold the label (number) of the workpiece.

[0036] The depth image G1 and the binarized images L1 and L2, which serve as label data, are linked by sharing a common coordinate system. Specifically, the relative position and orientation based on a common coordinate system (e.g., the world coordinate system) are stored in the form of transformation matrices in the depth image G1 and the binarized images L1 and L2, respectively. This allows the position of each pixel in the depth image G1 to correspond to the position of each pixel in the binarized images L1 and L2 using a common coordinate system. In this way, in the first modified example, the binarized image from which the workpiece's region is extracted functions as label data for identifying the workpiece in the depth image.

[0037] Next, the interference avoidance calculation unit 125 performs interference avoidance calculations using the label data (step S4). For example, when the workpiece to be extracted is W1, the interference avoidance calculation unit 125 can use the binarized image L1 to exclude pixels in the distance image G1 where the workpiece W1 exists from the interference determination calculation.

[0038] Therefore, even in this modified example, interference detection and interference avoidance calculations can be performed while avoiding situations in which the workpiece to be removed is determined to be interfering with the robot 10 or the hand 15.

[0039] In this modified example, the label data is a small, binarized image extracted from the workpiece, thus reducing the required data size for label data and lowering the memory consumption required for labeling.

[0040] In typical labeling, the size of the label assigned to a single pixel (or voxel) in 3D data requires, for example, one byte of data. However, according to this modification, the amount of information in the label per pixel can be reduced to a minimum of one bit.

[0041] (Second Modification) The second modification is an example in which 3D data is represented in the data format of voxel data, and voxel data extracted from the voxel data containing the detected workpiece is used as label data to represent the detected workpiece.

[0042] The workpiece detection process based on 3D data in this modified example is equivalent to the workpiece detection process based on 3D point clouds described with reference to Figure 3 (step S2).

[0043] Next, the labeling processing unit 124 labels the workpiece based on the voxel data as three-dimensional data (step S3). The specific details of this process will be explained with reference to Figure 6. Figure 6 is a conceptual diagram showing how voxel data is handled in the second modified example. In Figure 6, the voxel data V1 represents the entire three-dimensional data acquired by the visual sensor 70.

[0044] The labeling processing unit 124 can recognize the position and orientation of each workpiece in the voxel data V1 based on the detection result from the detection unit 122. The labeling processing unit 124 cuts out and saves a small-sized portion including the detected workpiece in the voxel data V1 based on the detection result from the detection unit 122. FIG. 6 shows a situation where small-sized portions including the detected workpieces W1 and W2 are cut out as voxel data L11 and L12, respectively. In the small-sized voxel data L11 and L12, for example, it is assumed that voxels at locations where workpieces are present are represented by a value of '1', and voxels in portions where no workpiece is present are represented by a value of '0'. Further, the small-sized voxel data L11 and L12 each hold a label (number) of the workpiece.

[0045] The entire voxel data V1 and the cut-out small-sized voxel data L11 and L12 are associated by sharing a common coordinate system. Specifically, the voxel start position and size based on a common coordinate system are recorded for each of the entire voxel data V1 and the small-sized voxel data L11 and L12. Thereby, the position of each voxel in the entire voxel data V1 and the position of each voxel in the small-sized voxel data L12 and L13 are associated with each other by the common coordinate system. As described above, in the second modified example, the small-sized voxel data obtained by cutting out the existing region of the workpiece functions as label data for identifying the workpiece in the entire voxel data.

[0046] Next, interference avoidance calculation using the label data is performed by the interference avoidance calculation unit 125 (step S4). For example, when the workpiece to be taken out is W1, the interference avoidance calculation unit 125 uses the small-sized voxel data L11 to exclude the region where the workpiece W1 exists in the entire voxel data V1 from the interference determination calculation.

[0047] Therefore, also in the case of the present modified example, it is possible to perform interference determination and interference avoidance calculation while avoiding a situation where it is determined that the workpiece to be taken out interferes with the robot 10 or the hand 15.

[0048] In the case of this modified example, since the label data is small-sized voxel data obtained by cutting out the workpiece portion, the data size required as label data can be reduced, and the memory consumption required for labeling can be reduced.

[0049] In general labeling, the size of a label assigned to one pixel (or voxel) in 3D position information requires a data amount of, for example, 1 byte, but according to this modified example, the information amount of the label per pixel can be reduced to the minimum of 1 bit.

[0050] As described above, according to the present embodiment, it is possible to prevent a situation in which it is determined that the workpiece that is the work target interferes with the robot or the hand in interference avoidance calculation.

[0051] The above-described embodiment has a configuration in which the image processing apparatus 20 detects a workpiece from 3D data measured by a 3D visual sensor, and labels the workpiece on the 3D data based on the detection result. On the other hand, in the robot system 100, an application example is also assumed in which the arrangement state and shape information of the workpiece can be used as known information. For example, this is a case where workpieces are always supplied to the robot system 100 in a fixed arrangement state, and the shape information of the workpieces can be obtained as CAD data, for example. FIG. 2 shows a state in which the arrangement information of the workpiece and the CAD data are stored as known information in the storage unit 22 in such an application example.

[0052] In such an application example, the interference avoidance calculation unit 125 excludes the data of the workpiece to be taken out from the 3D data acquired by the visual sensor 70 based on the arrangement information and shape information of the workpiece in the work space, and can perform interference avoidance calculation between the robot 10 or the hand 15 and the object. Therefore, also in the case of such an application example, it is possible to prevent a situation in which it is determined that the workpiece that is the work target interferes with the robot or the hand in the interference avoidance calculation.

[0053] The configuration of the above-described embodiment can be applied to scenes of interference avoidance calculation between an industrial machine and an object in various types of work performed by the industrial machine.

[0054] It should be understood that not all of the functional blocks shown in the functional block diagram in Figure 2 are essential.

[0055] The arrangement of the functional blocks in the functional block diagram shown in Figure 2 is illustrative, and there are various possible variations in the arrangement of the functional blocks in the robot system 100. For example, some of the functions (labeling processing unit, interference avoidance calculation unit, etc.) that are located in the image processing device 20 may be located in the robot control device 50 or the teaching device 40.

[0056] In the functional block diagram of Figure 2, each functional block described as a function of the image processing device, robot control device, or teaching control panel may be realized by one or more processors of these devices executing various software stored in a memory device, or in this case, part of the function may be made up of hardware such as discrete circuits (i.e., the functional block may be realized by a combination of a processor and discrete circuits), or the functions shown in the functional block diagram may be realized by a hardware-based configuration such as an ASIC (Application Specific Integrated Circuit).

[0057] The computer programs for executing various processes such as interference avoidance calculation and workpiece retrieval in the above-described embodiments, or the computer programs for executing processes in each part of the processor of the robot control device, may be provided in the form of program products recorded on various computer-readable recording media (for example, semiconductor memories such as ROM, EEPROM, and flash memory, magnetic recording media, or optical recording media such as CD-ROM and DVD-ROM).

[0058] While this disclosure has been described in detail, it is not limited to the individual embodiments described above. These embodiments can be added, replaced, modified, partially deleted, etc., in any way that does not depart from the gist of this disclosure or from the spirit of this disclosure derived from the claims and their equivalents. Furthermore, these embodiments can be implemented in combination. For example, the order of operations and processes in the embodiments described above are given as examples only and are not limited thereto. The same applies when numerical values ​​or mathematical formulas are used in the description of the embodiments described above.

[0059] The following additional notes are provided with respect to the above embodiments and modifications. (Note 1) An information processing device (20) comprising a calculation unit (125) that performs interference avoidance calculations between a robot or tool and an object based on three-dimensional data acquired by a sensor that measures three-dimensional space and information indicating the position of a workpiece in the three-dimensional space, while excluding the workpiece to be worked on from the three-dimensional data. (Note 2) The information processing device (20) according to Note 1, comprising a detection unit (122) that detects a workpiece based on the three-dimensional data, wherein the information indicating the position of the workpiece in the three-dimensional space includes the workpiece detection result by the detection unit (122). (Note 3) The information processing device (20) according to Note 1, comprising a storage unit (22) that stores information representing the arrangement position and shape of the workpiece in the three-dimensional space as information indicating the position of the workpiece in the three-dimensional space. (Note 4) The information processing device (20) according to Note 2, comprising a processing unit (124) that generates label data for labeling the detected workpiece in the three-dimensional data based on the detection result by the detection unit, wherein the information indicating the position of the workpiece in the three-dimensional space includes the label data. (Note 5) The information processing device (20) according to Note 4, wherein the three-dimensional data is a distance image, and the processing unit (124) generates a binarized image of the portion containing the detected workpiece extracted from the distance image as the label data. (Note 6) The information processing device (20) according to Note 4, wherein the three-dimensional data is voxel data, and the processing unit (124) generates voxel data of the portion containing the detected workpiece extracted from the voxel data as the label data.(Note 7) A robot system (100) comprising: a sensor (70) that measures a three-dimensional space and acquires three-dimensional data; a robot (10) equipped with a tool; a calculation unit (125) that performs interference avoidance calculations between the robot or the tool and an object based on the acquired three-dimensional data and information indicating the position of the workpiece in the three-dimensional space, excluding the workpiece to be worked on from the three-dimensional data; and an action control unit (151) that controls the robot based on the result of the interference avoidance calculation. (Note 8) The robot system (100) according to Note 7, further comprising a detection unit (122) that detects a workpiece based on the three-dimensional data, wherein the information indicating the position of the workpiece in the three-dimensional space includes the result of workpiece detection by the detection unit (122). (Note 9) The robot system (100) according to Note 7, further comprising a storage unit (22) that stores information representing the arrangement position and shape of the workpiece in the three-dimensional space as information indicating the position of the workpiece in the three-dimensional space. (Note 10) The robot system (100) according to Note 8, comprising a processing unit (124) that generates label data for labeling the detected workpiece in the three-dimensional data based on the detection result by the detection unit, wherein the information indicating the position of the workpiece in the three-dimensional space includes the label data. (Note 11) The robot system (100) according to Note 10, wherein the three-dimensional data is a distance image, and the processing unit (124) generates a binarized image of the portion containing the detected workpiece extracted from the distance image as the label data. (Note 12) The robot system (100) according to Note 10, wherein the three-dimensional data is voxel data, and the processing unit (124) generates voxel data of the portion containing the detected workpiece extracted from the voxel data as the label data.

[0060] 10 Robot 15 Hand 20 Image processing device 21 Processor 22 Memory unit 23 Operation unit 24 Display unit 40 Teaching device 43 Display unit 50 Robot control device 70 Vision sensor 90 Container 100 Robot system 121 Vision sensor control unit 122 Detection unit 124 Labeling processing unit 124 125 Interference avoidance calculation unit 151 Motion control unit

Claims

1. An information processing device comprising a calculation unit that performs interference avoidance calculations between a robot or tool and an object based on three-dimensional data acquired by a sensor that measures three-dimensional space and information indicating the position of a workpiece in the three-dimensional space, while excluding the workpiece to be worked on from the three-dimensional data.

2. The information processing apparatus according to claim 1, comprising a detection unit for detecting a workpiece based on the three-dimensional data, wherein the information indicating the position of the workpiece in the three-dimensional space includes the result of workpiece detection by the detection unit.

3. The information processing apparatus according to claim 1, comprising a storage unit that stores information representing the arrangement position and shape of a workpiece in the three-dimensional space as information indicating the position of a workpiece in the three-dimensional space.

4. The information processing apparatus according to claim 2, comprising a processing unit that generates label data for labeling the detected workpiece in the three-dimensional data based on the detection result by the detection unit, wherein the information indicating the position of the workpiece in the three-dimensional space includes the label data.

5. The information processing apparatus according to claim 4, wherein the three-dimensional data is a distance image, and the processing unit generates a binarized image of the portion of the region containing the detected workpiece extracted from the distance image as the label data.

6. The information processing apparatus according to claim 4, wherein the three-dimensional data is voxel data, and the processing unit generates the voxel data of the portion extracted from the voxel data that includes the detected workpiece as the label data.

7. A robot system comprising: a sensor that measures a three-dimensional space and acquires three-dimensional data; a robot equipped with a tool; a calculation unit that performs interference avoidance calculations between the robot or the tool and an object based on the acquired three-dimensional data and information indicating the position of a workpiece in the three-dimensional space, while excluding the workpiece to be worked on from the three-dimensional data; and an motion control unit that controls the robot based on the results of the interference avoidance calculation.

8. The robot system according to claim 7, comprising a detection unit that detects a workpiece based on the three-dimensional data, wherein the information indicating the position of the workpiece in the three-dimensional space includes the result of workpiece detection by the detection unit.

9. The robot system according to claim 7, further comprising a storage unit that stores information representing the arrangement position and shape of a workpiece in the three-dimensional space, as information indicating the position of a workpiece in the three-dimensional space.

10. The robot system according to claim 8, comprising a processing unit that generates label data for labeling the detected workpiece in the three-dimensional data based on the detection result by the detection unit, wherein the information indicating the position of the workpiece in the three-dimensional space includes the label data.

11. The robot system according to claim 10, wherein the three-dimensional data is a distance image, and the processing unit generates a binarized image of the portion of the region containing the detected workpiece extracted from the distance image as the label data.

12. The robot system according to claim 10, wherein the three-dimensional data is voxel data, and the processing unit generates the voxel data of the portion extracted from the voxel data that includes the detected workpiece as the label data.

Images