Information processing device, information processing method, and storage medium

Abstract

An information processing device 100 according to the present disclosure comprises: a first estimation unit 121 that acquires first measurement information obtained by measuring the shape of an object and estimates an estimated shape of the object on the basis of the first measurement information; and a second estimation unit 122 that acquires second measurement information obtained by measuring the shape of the object after manipulation of the object by a robot and estimates an object shape on the basis of the estimated shape and the second measurement information.

Description

Information processing device, information processing method, and storage medium

[0001] The present disclosure relates to an information processing device, an information processing method, and a storage medium.

[0002] In recent years, robots have been introduced in various situations, and work tasks have been automated. For example, Patent Document 1 describes a system for picking items using a robot. In particular, Patent Document 1 describes picking an item from a group of items consisting of multiple stacked items. In this situation, Patent Document 1 calculates the height of each item by calculating the height of the top surface of the item located on the top shelf and the number of shelves.

[0003] Japanese Patent Application Laid-Open No. 2019-5871

[0004] However, in the technology described in Patent Document 1, the height of each item is calculated from the height of the top surface of the item and the number of layers, so the stacked items must be of the same type, i.e., the same height. Therefore, when items of different types or sizes are stacked, the exact sizes of the items cannot be recognized, which causes a problem in that the robot cannot operate accurately.

[0005] Therefore, one of the objectives of the present disclosure is to provide an information processing device that can solve the above-mentioned problem of the inability of a robot to perform accurate operations on stacked objects.

[0006] An information processing device according to one embodiment of the present disclosure is configured to include a first estimation unit that acquires first measurement information obtained by measuring the shape of an object and estimates an estimated shape of the object based on the first measurement information, and a second estimation unit that acquires second measurement information obtained by measuring the shape of the object after manipulating the object with a robot and estimates the shape of the object based on the estimated shape and the second measurement information.

[0007] Furthermore, an information processing method according to one embodiment of the present disclosure is configured to: acquire first measurement information that measures the shape of an object; estimate an estimated shape of the object based on the first measurement information; acquire second measurement information that measures the shape of the object after manipulating the object with a robot; and estimate the shape of the object based on the estimated shape and the second measurement information.

[0008] Furthermore, a program according to one embodiment of the present disclosure is configured to cause a computer to execute the following processes: acquiring first measurement information obtained by measuring the shape of an object; estimating an estimated shape of the object based on the first measurement information; acquiring second measurement information obtained by measuring the shape of the object after manipulating the object with a robot; and estimating the shape of the object based on the estimated shape and the second measurement information.

[0009] With the above-described configuration, the present disclosure enables a robot to perform accurate manipulation of stacked objects.

[0010] FIG. 1 is a block diagram showing the configuration of an information processing device according to a first embodiment of the present disclosure. FIG. 2 is a diagram showing the state of processing by the information processing device disclosed in FIG. 1. FIG. 3 is a diagram showing the state of processing by the information processing device disclosed in FIG. 1. FIG. 4 is a flowchart showing the operation of the information processing device disclosed in FIG. 1. FIG. 5 is a block diagram showing the hardware configuration of an information processing device according to a second embodiment of the present disclosure. FIG. 6 is a block diagram showing the configuration of an information processing device according to a second embodiment of the present disclosure.

[0011] First Embodiment A first embodiment of the present disclosure will be described with reference to Fig. 1 to Fig. 5. Fig. 1 is a diagram for explaining the configuration of an information processing device, and Fig. 2 to Fig. 5 are diagrams for explaining the processing operation of the information processing device.

[0012] [Configuration] The information processing device 10 in this embodiment has a function of estimating the shape of an object in order to operate the object using a robot. In this embodiment, stacked objects are assumed to be objects to be operated by the robot, and the robot performs an operation of picking up the object and moving it to a target location. As shown in FIG. 1, a camera 20 and a robot 30 are connected to the information processing device 10.

[0013] As will be described later, the camera 20 captures an image capable of measuring the shape and distance of an object in response to a command from the information processing device 10. For example, the camera 20 is installed above a space in which the object 50 is placed, and captures a distance image from above the object 50. However, the camera 20 may capture any image as long as it is an image capable of measuring the shape and distance of an object. Furthermore, instead of the camera 20, a measuring device capable of measuring the shape and distance of an object may be provided.

[0014] In this embodiment, the robot 30 is configured as a robot arm. The robot arm has an operation unit at the tip of the arm that adsorbs and holds an object. As will be described later, the robot 30 operates to hold and move an object in response to commands from the information processing device 10, and to move and place the object at a desired location. Note that the robot 30 is not limited to adsorbing and holding an object, and may hold an object in any structure, such as by grasping and holding it.

[0015] The information processing device 10 is composed of one or more information processing devices each including a calculation device and a storage device. As shown in FIG. 1 , the information processing device 10 includes a motion control unit 11, a measurement unit 12, a first estimation unit 13, and a second estimation unit 14. The functions of the motion control unit 11, the measurement unit 12, the first estimation unit 13, and the second estimation unit 14 can be realized by the calculation device executing a program for realizing each function stored in the storage device. The information processing device 10 also includes a motion plan storage unit 16 and an object shape storage unit 17. The motion plan storage unit 16 and the object shape storage unit 17 are each configured using a storage device. Each component will be described in detail below.

[0016] The motion plan storage unit 16 stores animation plan information of the robot 30. For example, the motion plan information is planned based on a preset initial position and a target position of the object 50, and includes information for controlling the robot 30 to realize a motion plan such as picking up the object 50 from the initial position, moving it to the target position, and placing it there. Note that the motion plan information can be planned and changed each time the object shape of the object 50 is estimated, as will be described later.

[0017] The object shape memory unit 17 stores shape information of the object 50 to be operated. For example, the shape information is stored each time an image of the object 50 is measured and the object shape of each object is estimated. Here, as shown in FIG. 2 (2-1), the object 50 in this embodiment is two objects 51 and 52, i.e., a first object 51 and a second object 52, stacked in the height direction (z direction) on a base G, and placed at a predetermined initial position on the base G. However, the objects 50 are not limited to being stacked in pairs, and more objects may be stacked, or may be placed side by side in a horizontal direction.

[0018] The operation control unit 11 controls the operation of the robot 30 based on the operation plan information, and performs an operation on the object 50. Accordingly, the operation control unit 11 instructs the measurement unit 12 to measure the object 50. For example, the operation control unit 11 instructs the measurement unit 12 to take images of the object 50 and acquire measurement information before and after the robot 30 performs an operation to pick up the object 50. As an example, the operation control unit 11 instructs the measurement unit 12 to take a first image and measure the object 50 before performing the picking operation on the object 50, as shown in FIG. 2, and then instructs the measurement unit 12 to take a second image and measure the object 50 after performing the picking operation on the object 50, as shown in FIG. 4. Note that the operation control unit 11 may further instruct the measurement unit 12 to take a further image and measure the object 50 after performing the picking operation on the object 50.

[0019] In response to a command from the operation control unit 11, the measurement unit 12 captures an image of the object 50 using the camera 20 and measures the shape of the object 50 from the image. For example, when the measurement unit 12 receives an instruction to capture and measure the object 50 for the first time before picking it up, the measurement unit 12 captures a first image using the camera 20 from above the object 50 at an initial position where the object 50 is set in advance. The measurement unit 12 then measures first measurement information including the shape and height position of the top surface of the object 50 from the first captured image. As an example, for an object 50 in which two objects 51 and 52 are stacked as shown in FIG. 2 (2-1), the measurement unit 12 captures an image from above using the camera 20 as shown in FIG. 2 (2-2), and measures the shape 50a of the top surface of the object 50 and the height position 50b of the top surface from the image as first measurement information. At this time, the measurement unit 12 measures the shape 50a of the top surface of the object 50, such as the length of each side located on the periphery of the shape 50a and the angle between each side, to measure the shape itself and size of the top surface, such as a square or a rectangle. The measurement unit 12 also measures the height 50b from the base G to the top surface as the height position 50b of the top surface of the object 50. Then, the measurement unit 12 passes the first measurement information to the first estimating unit 13.

[0020] When the first estimating unit 13 receives first measurement information including the shapes 50a and heights 50b of the stacked objects 50 from the measuring unit 12, the first estimating unit 13 estimates an estimated shape of the object 50 from the first measurement information. That is, as shown in FIG. 3 (3-1), the first estimating unit 13 assumes that the object 50 measured using the first measurement information is a single rectangular parallelepiped object 50' and estimates its estimated shape. As an example, the first estimating unit 13 estimates the estimated shape of a single rectangular parallelepiped object 50' by using the shape 50a included in the first measurement information as the bottom shape of the object 50' and the height 50b included in the first measurement information as the height of the object 50'.

[0021] The above-described operation control unit 11 then creates an operation plan based on the estimated shape of the object 50' and controls the operation of the robot 30 to perform a picking operation according to the operation plan. In this case, the operation control unit 11 controls the position of the robot 30 so that the robot 30 holds the object 50' at a height position 50b of the upper surface of the estimated shape of the object 50', as shown in FIGS. 3 (3-1) and (3-2). The operation control unit 11 then suction-holds the object 50' with the robot 30, resulting in only the first object 51 located at the top of the stacked objects 50' being held and moved by the robot 30, as shown in FIG. 4 (4-1). Note that, as described above, the operation control unit 11 instructs the robot 30 to take and measure a second image after performing the picking operation on the object 50.

[0022] Furthermore, when the measurement unit 12 receives an instruction from the operation control unit 11 to take a second photograph and measurement after picking the object 50, the measurement unit 12 takes a second image from above the object 50 using the camera 20 at the location before the object 50 was picked, i.e., the initial position where the object 50 is set to be placed. Then, the measurement unit 12 measures second measurement information including the shape and height position of the top surface of the object 50 from the image taken the second time. As an example, as shown in FIG. 4 (4-1), when two objects 51 and 52 are stacked on top of each other and the first object 51 is picked from the stack of objects 50, the measurement unit 12 takes an image from above using the camera 20 of the object 50 remaining after the first object 51 is picked, i.e., the second object 52, and measures the shape 50c of the top surface and the height position 50d of the top surface of the second object 52 from the image as second measurement information. At this time, the measurement unit 12 measures the length of each side located on the periphery of the shape 50c of the top surface of the second object 52, the angle between each side, and the like, to measure the shape itself and size of the top surface, such as a square or a rectangle. The measurement unit 12 also measures the height 50d from the base G to the top surface as the height position 50d of the top surface of the second object 52. Then, the measurement unit 12 passes the second measurement information to the second estimation unit 14.

[0023] When the second estimation unit 14 receives second measurement information including the shape 50c and height 50d of the object 50 after the picking operation, i.e., the second object 52, from the measurement unit 12, the second estimation unit 14 estimates the object shape of the second object 52 from the second measurement information. That is, the second estimation unit 14 estimates the estimated shape of the object 50 measured using the second measurement information, and in particular in this embodiment, the second estimation unit 14 estimates the object shape of the remaining object 50 as a single second object 52. As an example, as shown in FIG. 4 (4-2), the second estimation unit 14 estimates the object shape of a single rectangular parallelepiped second object 52, where the shape 50c included in the second measurement information is the bottom shape of the second object 52 and the height 50d included in the second measurement information is the height h2 of the second object 52.

[0024] Furthermore, the second estimation unit 14 estimates the object shape of the first object 51 from the second measurement information and the estimated shape of the first object 51. For example, as shown in FIG. 4 (4-2), the second estimation unit 14 can calculate the actual height h1 of the first object 51 being picked by subtracting the height 50d (h2) of the second object 52 from the height 50b of the estimated shape of the object 50′ assumed as one object measured from the first measurement information as described above, and estimates and corrects the object shape of the first object 51.

[0025] In the above, the second estimating unit 14 estimates the object shape of the second object 52 from the second measurement information, but the object shape of the second object 52 may be estimated in the same manner as the first object 51 described above. In other words, the second estimating unit 14 may first estimate the estimated shape of the second object 52 from the second measurement information, and then estimate the object shape of the second object 52 based on an image captured after picking the second object 52 in the same manner as the method of estimating the object shape of the first object 51 described above.

[0026] The above-described operation control unit 11 then creates an operation plan based on the estimated object shapes of the first object 51 and the second object 52, and controls the operation of the robot 30 to perform a picking operation according to the operation plan. In this case, as shown in FIG. 4 (4-2), the operation control unit 11 first creates an operation plan to move the first object 51 to a target position and place it thereon, depending on the height h1 of the first object 51 being picked, and controls the operation of the robot 30. In other words, the operation control unit 11 creates an operation plan in consideration of the height h1 of the first object 51, and controls the operation of the robot 30 to properly place the first object 51 on the base G without dropping or crushing it.

[0027] Furthermore, the operation control unit 11 controls the position of the robot 30 so that the second object 52 is held at a height position 50c (h2) of the upper surface of the object shape of the second object 52. Then, the operation control unit 11 causes the robot 30 to suction-hold the second object 52, and the second object 52 is held by the robot 30 and moved.

[0028] Here, the operation control unit 11 temporarily suspends the operation control of the robot 30 when issuing an instruction to take a second image and measure the second image after performing a picking operation on the first object 51. In other words, the operation control unit 11 temporarily suspends the operation control of the robot 30 when, as described above, the operation control unit 11 picks the first object 51, photographs and measures the second object 52 left behind, and estimates the object shapes of the first object 51 and the second object 52. Then, after estimating the object shapes of the first object 51 and the second object 52, the operation control unit 11 calculates a new operation plan for the robot 30, and then resumes the operation control of the robot 30 based on the new operation plan.

[0029] [Operation] Next, the operation of the information processing device 10 described above will be described mainly with reference to the flowchart in FIG.

[0030] The information processing device 10 controls the operation of the robot 30 based on the operation plan information and starts operating the object 50. At this time, the information processing device 10 first captures and measures an image of the object 50 for the first time before performing a picking operation on the object 50 (step S1). Specifically, as shown in FIG. 2 (2-2), the information processing device 10 captures an image from above the object 50, which is made up of two stacked objects 51 and 52, and measures the shape 50a and height position 50b of the top surface of the object 50 from the image as first measurement information. Then, as shown in FIG. 3, the information processing device 10 determines that the object 50 is a single object 50' from the first measurement information, and estimates the estimated shape of the single rectangular parallelepiped object 50' by taking the shape 50a included in the first measurement information as the bottom surface of the object 50' and the height 50b included in the first measurement information as the height of the object 50' (step S2).

[0031] Next, the information processing device 10 creates an operation plan based on the estimated shape of the object 50' and controls the operation of the robot 30 to perform a picking operation according to the operation plan. In this case, the information processing device 10 controls the position of the robot 30 so that the object 50' is held at a height position 50b of the upper surface of the estimated shape of the object 50', as shown in Figures 3 (3-1) and (3-2). As a result, the information processing device 10 causes only the first object 51 located at the top of the stack of objects to be held and moved by the robot 30, as shown in Figure 4 (4-1) (step S3).

[0032] Next, after picking the first object 51, the information processing device 10 captures a second image from above the object 50 at the location before picking, i.e., the location where the remaining object 50 is placed, as shown in FIG. 4 (4-1). Then, as shown in FIG. 4 (4-1), the information processing device 10 measures second measurement information including the shape 50c of the top surface of the remaining object 50 and the position of the height 50d of the top surface from the second image (step S4). That is, in this case, the information processing device 10 measures the shape 50c of the top surface of the remaining second object 52 and the height position 50d of the top surface as the second measurement information. At this time, the information processing device 10 temporarily stops controlling the operation of the robot (step S5).

[0033] Next, the information processing device 10 estimates the object shapes of the first object 51 and the second object 52 based on the second measurement information including the shape 50c and height 50d of the second object 52 and the estimated shape of the first object 51 estimated as described above (step S6). Specifically, as shown in FIG. 4 (4-2), the information processing device 10 estimates the object shape of the second object 52, which is a rectangular parallelepiped, with the shape 50c included in the second measurement information as its bottom surface and the height 50d as its height h2. Furthermore, as shown in FIG. 4 (4-2), the information processing device 10 can calculate the height h1 of the first object 51 being picked by subtracting the height 50d (h2) of the second object 52 from the height 50b of the estimated shape of the object 50' assumed as a single object measured from the first measurement information as described above, and estimates the object shape of the first object 51.

[0034] The information processing device 10 then creates an operation plan based on the estimated object shapes of the first object 51 and the second object 52 (step S7) and resumes operation control of the robot 30 to perform a picking operation according to the operation plan (step S8). In this case, as shown in FIG. 4 (4-2), the information processing device 10 first creates an operation plan to place the first object 51 being picked at a desired position according to the height h1 of the first object 51, and controls the operation of the robot 30. That is, the information processing device 10 creates an operation plan taking into account the height h1 of the first object 51, and controls the operation of the robot 30 to properly place the first object 51 on the base G without dropping or crushing it. The information processing device 10 also controls the position of the robot 30 so that the second object 52 is held at a height position 50c (h2) of the upper surface of the object shape of the second object 52. The operation control unit 11 then causes the robot 30 to suction-hold the second object 52, and the second object 52 is held and moved by the robot 30.

[0035] In addition, if, after the robot 30 picks up the second object 52 described above, another object remains in the location before picking, the information processing device 10 takes an image of the remaining object as described above and measures its shape and height, and then re-estimates the object shape of the picked second object 52, in particular its height, from the measurement results.

[0036] As described above, according to this embodiment, first, an image of the object is photographed and measured to estimate its estimated shape, and then, after picking the object, an image of the remaining object is photographed and measured to estimate the object's shape. Therefore, even when multiple objects are stacked, the height of each object can be measured appropriately. As a result, the robot can accurately manipulate the objects.

[0037] Unlike the above, the information processing device 10 may first photograph and measure an image of the first object 51 in a situation where the first object 51 and the second object 52 are stacked, and after picking up the first object 51, photograph an image of the first object 51 again and estimate the object shape of the first object 51 based on the image. In this case, for example, after picking up the first object 51, it is preferable to photograph the first object 51 from the side to obtain an image that allows the height of the first object 51 to be measured, and estimate the height of the first object 51. Then, in addition to such photographing, the remaining second object 52 may be photographed in the same manner as described above, and the object shape of the second object 52 may be estimated.

[0038] <Embodiment 2> Next, a second embodiment of the present disclosure will be described with reference to Fig. 7 and Fig. 8. Fig. 7 and Fig. 8 are block diagrams showing the configuration of an information processing device in embodiment 2. Note that this embodiment shows an outline of the configuration of the information processing device described in the above embodiment.

[0039] First, the hardware configuration of the information processing device 100 in this embodiment will be described with reference to Fig. 7. The information processing device 100 is configured as a general information processing device, and is equipped with the following hardware configuration, for example: CPU (Central Processing Unit) 101 (arithmetic unit); ROM (Read Only Memory) 102 (storage device); RAM (Random Access Memory) 103 (storage device); programs 104 loaded into RAM 103; a storage device 105 that stores the programs 104; a drive device 106 that reads and writes data from and to a storage medium 110 external to the information processing device; a communication interface 107 that connects to a communication network 111 external to the information processing device; an input / output interface 108 that inputs and outputs data; and a bus 109 that connects the various components.

[0040] 6 shows an example of the hardware configuration of the information processing device 100, and the hardware configuration of the information processing device is not limited to the above-described case. For example, the information processing device may be configured with only a part of the above-described configuration, such as excluding the drive device 106. Furthermore, the information processing device may use a GPU (Graphics Processing Unit), a DSP (Digital Signal Processor), an MPU (Micro Processing Unit), an FPU (Floating Point Number Processing Unit), a PPU (Physics Processing Unit), a TPU (Tensor Processing Unit), a quantum processor, a microcontroller, or a combination thereof, instead of the above-described CPU.

[0041] The information processing device 100 can be equipped with a first estimating unit 121 and a second estimating unit 122 shown in FIG. 7 by having the CPU 101 acquire and execute the program group 104. The program group 104 is stored in advance in the storage device 105 or the ROM 102, for example, and is loaded into the RAM 103 and executed by the CPU 101 as needed. The program group 104 may be supplied to the CPU 101 via the communication network 111, or may be stored in advance in the storage medium 110, and the drive device 106 may read and supply the programs to the CPU 101. However, the first estimating unit 121 and the second estimating unit 122 described above may be constructed using dedicated electronic circuits for realizing such means.

[0042] The first estimating unit 121 acquires first measurement information obtained by measuring the shape of an object, and estimates an estimated shape of the object based on the first measurement information. For example, the first estimating unit 121 measures the shapes of stacked objects and estimates the estimated shape.

[0043] The second estimating unit 122 acquires second measurement information obtained by measuring the shape of an object after the object is manipulated by the robot, and estimates the object shape based on the estimated shape and the second measurement information. For example, the second estimating unit 122 acquires second measurement information obtained by measuring the shape of a second object after the robot manipulates a first object among the stacked objects, and estimates the object shape of the first object based on the estimated shape and the second measurement information. Furthermore, the second estimating unit 122 acquires second measurement information obtained by measuring the shape of the remaining object that was not manipulated after the robot manipulates one of the stacked objects, and estimates the object shape of the manipulated object based on the estimated shape of the stacked objects and the second measurement information.

[0044] With the above-described configuration, the present disclosure first estimates the shape of stacked objects by photographing and measuring images of the objects, and then estimates the shape of the manipulated object after the objects are manipulated by the robot by photographing and measuring images of the manipulated object and any remaining objects that have not been manipulated. Therefore, even when multiple objects are stacked, the shape of each object can be appropriately measured, and the robot can accurately manipulate the objects.

[0045] The above-described program can be stored and supplied to a computer using various types of non-transitory computer-readable media. Non-transitory computer-readable media include various types of tangible storage media. Examples of non-transitory computer-readable media include magnetic recording media (e.g., flexible disks, magnetic tapes, hard disk drives), magneto-optical recording media (e.g., magneto-optical disks), CD-ROMs (Read Only Memory), CD-Rs, CD-R / Ws, and semiconductor memories (e.g., mask ROMs, PROMs (Programmable ROMs), EPROMs (Erasable PROMs), flash ROMs, and RAMs (Random Access Memory)). The program may also be supplied to a computer by various types of transitory computer-readable media. Examples of transitory computer-readable media include electrical signals, optical signals, and electromagnetic waves. The transitory computer-readable media can be supplied to a computer via wired communication paths such as electric wires and optical fibers, or via wireless communication paths.

[0046] Although the present disclosure has been described above with reference to the above-described embodiments, the present disclosure is not limited to the above-described embodiments. Various modifications that are understandable to those skilled in the art can be made to the configuration and details of the present disclosure within the scope of the present disclosure. Furthermore, at least one or more of the functions of the first estimating unit 121 and the second estimating unit 122 described above may be executed by an information processing device installed and connected anywhere on a network, that is, may be executed by so-called cloud computing.

[0047] <Supplementary Notes> Some or all of the above embodiments can also be described as in the following supplementary notes. Below, an overview of the configurations of an information processing device, an information processing method, and a program according to the present disclosure will be described. However, the present disclosure is not limited to the following configurations. (Supplementary Note 1) An information processing device comprising: a first estimation unit that acquires first measurement information obtained by measuring a shape of an object and estimates an estimated shape of the object based on the first measurement information; and a second estimation unit that acquires second measurement information obtained by measuring the shape of the object after manipulating the object with a robot and estimates the object shape based on the estimated shape and the second measurement information. (Supplementary Note 2) The information processing device according to Supplementary Note 1, wherein the first estimation unit acquires the first measurement information obtained by measuring the shape of a first object and estimates the estimated shape of the first object based on the first measurement information; and the second estimation unit acquires the second measurement information obtained by measuring the shape of a second object after manipulating the first object with a robot and estimates the object shape of the first object based on the estimated shape and the second measurement information. (Supplementary Note 3) The information processing device according to Supplementary Note 2, wherein, after manipulating the first object with a robot, the second estimation unit acquires the second measurement information obtained by measuring the shape of the second object located at a position where the first object was located before the manipulation, and estimates the object shape of the first object based on the estimated shape and the second measurement information. (Supplementary Note 4) The information processing device according to Supplementary Note 3, wherein the second estimation unit estimates the object shapes of the first object and the second object based on the estimated shape and the second measurement information. (Supplementary Note 5) The information processing device according to Supplementary Note 3 or 4, wherein the first estimation unit acquires the first measurement information including a height of the first object, and the second estimation unit acquires the second measurement information including a height of the second object, and estimates the object shapes of the first object and the second object using the heights respectively included in the estimated shape and the second measurement information. (Supplementary Note 6) The information processing device according to Supplementary Note 4 or 5, further comprising: a motion control unit that calculates a motion plan for the robot based on the estimated object shapes of the first object and the second object, and controls the motion of the robot based on the motion plan.(Supplementary Note 7) The information processing device according to Supplementary Note 6, wherein the operation control unit calculates the operation plan when acquiring the second measurement information and estimating the object shapes of the first object and the second object. (Supplementary Note 8) The information processing device according to Supplementary Note 6 or 7, wherein the operation control unit stops operation control of the robot when acquiring the second measurement information, estimates the object shapes of the first object and the second object, calculates a new operation plan, and then resumes operation control of the robot based on the new operation plan. (Supplementary Note 9) An information processing method comprising acquiring first measurement information that measures the shape of an object, estimating an estimated shape of the object based on the first measurement information, acquiring second measurement information that measures the shape of the object after manipulating the object with a robot, and estimating the object shape based on the estimated shape and the second measurement information. (Supplementary Note 10) The information processing method according to Supplementary Note 9, comprising: acquiring first measurement information measuring a shape of a first object; estimating the estimated shape of the first object based on the first measurement information; acquiring second measurement information measuring a shape of a second object after manipulating the first object with a robot; and estimating the object shape of the first object based on the estimated shape and the second measurement information. (Supplementary Note 11) The information processing method according to Supplementary Note 10, comprising: acquiring second measurement information measuring a shape of the second object located at a position where the first object was located before the manipulation of the first object with a robot after manipulating the first object; and estimating the object shape of the first object based on the estimated shape and the second measurement information. (Supplementary Note 12) The information processing method according to Supplementary Note 11, comprising estimating the object shapes of the first object and the second object based on the estimated shape and the second measurement information. (Supplementary Note 13) The information processing method according to Supplementary Note 12, further comprising: calculating an operation plan for the robot based on the estimated object shapes of the first object and the second object; and controlling the operation of the robot based on the operation plan.(Supplementary Note 14) The information processing method according to Supplementary Note 13, wherein when the second measurement information is acquired, motion control of the robot is stopped, object shapes of the first object and the second object are estimated to newly calculate the motion plan, and then motion control of the robot is resumed based on the new motion plan. (Supplementary Note 15) A computer-readable storage medium storing a program for causing a computer to execute processes of acquiring first measurement information that measures the shape of an object, estimating an estimated shape of the object based on the first measurement information, acquiring second measurement information that measures the shape of the object after manipulating the object with the robot, and estimating the object shape based on the estimated shape and the second measurement information.

[0048] REFERENCE SIGNS LIST 10 Information processing device 11 Motion control unit 12 Measurement unit 13 First estimation unit 14 Second estimation unit 16 Motion plan storage unit 17 Object shape storage unit 100 Information processing device 101 CPU 102 ROM 103 RAM 104 Program group 105 Storage device 106 Drive device 107 Communication interface 108 Input / output interface 109 Bus 110 Storage medium 111 Communication network 121 First estimation unit 122 Second estimation unit

Claims

1. a first estimation unit that acquires first measurement information obtained by measuring a shape of an object and estimates an estimated shape of the object based on the first measurement information; a second estimation unit that acquires second measurement information obtained by measuring a shape of an object after the object is manipulated by the robot, and estimates the object shape based on the estimated shape and the second measurement information, Information processing device.

2. 2. The information processing device according to claim 1, the first estimating unit acquires the first measurement information obtained by measuring a shape of a first object, and estimates the estimated shape of the first object based on the first measurement information; the second estimation unit acquires the second measurement information obtained by measuring a shape of the second object after the robot manipulates the first object, and estimates the object shape of the first object based on the estimated shape and the second measurement information. Information processing device.

3. 3. The information processing device according to claim 2, the second estimation unit acquires the second measurement information obtained by measuring a shape of the second object located at a position of the first object before the manipulation, after the robot manipulates the first object, and estimates the object shape of the first object based on the estimated shape and the second measurement information. Information processing device.

4. 4. The information processing device according to claim 3, the second estimating unit estimates object shapes of the first object and the second object based on the estimated shapes and the second measurement information; Information processing device.

5. 4. The information processing device according to claim 3, the first estimation unit acquires the first measurement information including a height of the first object; the second estimating unit acquires the second measurement information including a height of the second object, and estimates an object shape of the first object and the second object using the heights included in the estimated shape and the second measurement information. Information processing device.

6. 5. The information processing device according to claim 4, a motion control unit that calculates a motion plan for the robot based on the estimated object shapes of the first object and the second object, and controls the motion of the robot based on the motion plan; Information processing device.

7. 7. The information processing device according to claim 6, the operation control unit calculates the operation plan when acquiring the second measurement information and estimating object shapes of the first object and the second object. Information processing device.

8. 7. The information processing device according to claim 6, the operation control unit stops the operation control of the robot when the second measurement information is acquired, estimates object shapes of the first object and the second object, calculates a new operation plan, and then resumes the operation control of the robot based on the new operation plan. Information processing device.

9. An information processing device, acquiring first measurement information obtained by measuring a shape of an object, and estimating an estimated shape of the object based on the first measurement information; acquiring second measurement information obtained by measuring a shape of the object after the object is manipulated by the robot, and estimating the shape of the object based on the estimated shape and the second measurement information; Information processing methods.

10. An information processing device, acquiring first measurement information obtained by measuring a shape of an object, and estimating an estimated shape of the object based on the first measurement information; acquiring second measurement information obtained by measuring a shape of the object after the object is manipulated by the robot, and estimating the shape of the object based on the estimated shape and the second measurement information; A program that executes a process.