Generation of inference model by machine learning using pile images

Patent metadata

Field	Value
Publication number	US-2026073249-A1
Application number	US-202519322713-A
Country	US
Kind code	A1
Filing date	Sep 9, 2025
Priority date	Sep 12, 2024
Publication date	Mar 12, 2026
Grant date	—

Abstract

A system includes circuitry configured to: generate a plurality of workpiece images each of which shows a workpiece viewed from a different viewpoint; generate, based on the plurality of workpiece images, one or more virtual pile images showing a plurality of piled workpieces; and generate, by machine learning using the one or more virtual pile images, an inference model configured to infer workpiece information regarding one or more of the workpieces shown in the pile image.

First claim

What is claimed is:

1 . A system comprising circuitry configured to:
generate a plurality of workpiece images each of which shows a workpiece viewed from a different viewpoint; generate, based on the plurality of workpiece images, one or more virtual pile images showing a plurality of piled workpieces; and generate, by machine learning using the one or more virtual pile images, an inference model configured to infer workpiece information regarding one or more of the workpieces shown in the pile image.

2 . The system according to claim 1 , wherein the circuitry is configured to:
generate the plurality of workpiece images for each of a plurality of classes of workpieces; generate the one or more virtual pile images showing the plurality of classes of workpieces that are piled; and generate, based on the one or more virtual pile images, the inference model so as to infer the workpiece information for each of the plurality of classes of workpieces.

3 . The system according to claim 1 , wherein the circuitry is configured to generate the plurality of workpiece images based on a 3D model of the workpiece.

4 . The system according to claim 3 , wherein the circuitry is configured to:
acquire a plurality of captured images obtained by capturing an actual workpiece from different viewpoints; and generate the 3D model of the workpiece from the plurality of captured images of the workpiece.

5 . The system according to claim 4 , wherein the circuitry is configured to generate the 3D model of the workpiece by image synthesis using a neural radiance field based on the plurality of captured images of the workpiece.

6 . The system according to claim 3 , wherein the circuitry is configured to:
approximate the 3D model of the workpiece with a plurality of particles connected by elastic parameters to deform the 3D model; and generate the plurality of workpiece images based on the deformed 3D model.

7 . The system according to claim 3 , wherein the circuitry is configured to:
attach a ground truth label of the workpiece information of the workpiece to the 3D model of the workpiece; associate the ground truth label attached to the 3D model of the workpiece with each of the plurality of workpiece images of the workpiece; generate the one or more virtual pile images based on the plurality of workpiece images with which the ground truth label is associated; and generate the inference model by the machine learning using the one or more virtual pile images with which a plurality of the ground truth labels are associated.

8 . The system according to claim 7 , wherein the circuitry is configured to:
select, in response to a user operation, one or more types of information items from a plurality of types of information items prepared in advance for the workpiece information; connect one or more heads corresponding to the selected one or more types of information items to an output layer of a network constituting the inference model; and generate the inference model including the network to which the one or more heads are connected.

9 . The system according to claim 8 , wherein the circuitry is configured to:
select, as the one or more types of information items, an information item regarding at least one of a relative position and a relative region that are determined relative to the workpiece; and connect the head corresponding to the information item regarding at least one of the relative position and the relative region to the output layer.

10 . The system according to claim 9 ,
wherein the relative position is a working position where a task is executed on the workpiece, and wherein the head corresponding to the information item regarding the relative position is a head configured to recognize the working position.

11 . The system according to claim 9 ,
wherein the relative position is a skeleton of the workpiece, and wherein the head corresponding to the information item regarding the relative position is a head configured to recognize the skeleton.

12 . The system according to claim 9 ,
wherein the relative region is associated with one or more part-classes set for the workpiece, and wherein the head corresponding to the information item regarding the relative region is a head configured to recognize the one or more part-classes.

13 . The system according to claim 8 , wherein the circuitry is configured to:
for each of a plurality of classes of workpieces, connect the one or more heads corresponding to the workpiece and the selected one or more types of information items to the output layer, and configure the inference model so as to output a class indicating a type of the workpiece from the output layer, and to switch the one or more heads for inferring the workpiece information according to the output class.

14 . The system according to claim 1 , wherein the circuitry is configured to configure the inference model so as not to present the workpiece information of a workpiece whose recognition score obtained by object detection does not satisfy a predetermined criterion.

15 . The system according to claim 1 , wherein the circuitry is configured to:
input a real pile image showing a plurality of real workpieces into the generated inference model to infer the workpiece information regarding one or more of the real workpieces; and execute a task on at least one of the one or more real workpieces based on the inferred workpiece information.

16 . The system according to claim 15 , wherein the circuitry is configured to cause a machine to execute the task.

17 . The system according to claim 16 ,
wherein the machine is a robot, and wherein the task circuitry is configured to:
generate a path of the robot for executing the task; and
cause the robot to execute the task based on the generated path.

18 . The system according to claim 5 , wherein the circuitry is configured to generate, based on the 3D model of the workpiece, the plurality of workpiece images each of which shows the workpiece viewed from a viewpoint different from all of the viewpoints of the plurality of captured images of the workpiece.

19 . A processor-executable method comprising:
generating a plurality of workpiece images each of which shows a workpiece viewed from a different viewpoint; generating, based on the plurality of workpiece images, one or more virtual pile images showing a plurality of piled workpieces; and generating, by machine learning using the one or more virtual pile images, an inference model configured to infer workpiece information regarding one or more of the workpieces shown in the pile image.

20 . A non-transitory computer-readable storage medium storing processor-executable instructions to:
generate a plurality of workpiece images each of which shows a workpiece viewed from a different viewpoint; generate, based on the plurality of workpiece images, one or more virtual pile images showing a plurality of piled workpieces; and generate, by machine learning using the one or more virtual pile images, an inference model configured to infer workpiece information regarding one or more of the workpieces shown in the pile image.

Assignees

• Yaskawa Electric Corp

Inventors

• Masumura Ryo
• KUNICHI Daisuke
• Kashiyama Marino

Classifications

• G06T17/00

  Three-dimensional [3D] modelling for computer graphics · CPC title

• G06T11/00

  Two-dimensional [2D] image generation · CPC title

• G06N5/022 Primary

  Knowledge engineering; Knowledge acquisition · CPC title

• G06T15/20 Primary

  Perspective computation · CPC title