公开(公告)号：US20240262635A1

公开(公告)日：2024-08-08

申请号：US18635298

申请日：2024-04-15

Applicant: Panasonic Intellectual Property Management Co., Ltd.

Inventor： Tsukasa Okada ,  Tomohide ISHIGAMI ,  Yoshinari MATSUYAMA ,  Yuma YAMAKURA ,  Yuzuka ISOBE

IPC: B65G43/00

CPC classification number: B65G43/00 ,  B65G2203/041

Abstract: A storage device stores a first and a second feature point maps of an object in advance, the first feature point map detected by image processing not based on deep learning, and the second feature point map detected using a deep learning model trained in advance. A processing circuit detects first feature points of the object by the image processing on a captured image. The processing circuit detects second feature points of the object from the captured image using the deep learning model. The processing circuit calculates a position of a target object based on the first feature points and the first feature point map. When the position cannot be calculated based on the first feature points and the first feature point map, the processing circuit calculates the position of the target object based on the first and second feature points, and he first and second feature point maps.

公开(公告)号：US20230256614A1

公开(公告)日：2023-08-17

申请号：US18138913

申请日：2023-04-25

Applicant: Panasonic Intellectual Property Management Co., Ltd.

Inventor： Yuma YAMAKURA

IPC: B25J9/16

CPC classification number: B25J9/1697 ,  B25J9/1653

Abstract: A robot control method is executed in a control device connected to a robot that performs a work on a work object and a sensor mounted on the robot. First, environmental information indicating a peripheral environment of the robot is calculated based on a plurality of pieces of environment sensor information acquired for the peripheral environment by using the sensor at a plurality of positions and angles. Subsequently, first sensor information is acquired by the sensor, and a first step of calculating first control information causing the robot to approach a work goal based on work goal information indicating the work goal, the environmental information, and the first sensor information is executed. Second sensor information is acquired by the sensor, and a second step of calculating second control information causing the robot to approach the work goal based on the work goal information and the second sensor information is executed.