公开(公告)号：US20240286277A1

公开(公告)日：2024-08-29

申请号：US18569237

申请日：2022-07-11

Applicant: BRIDGESTONE CORPORATION

Inventor： Hajime KITANO ,  Yasumichi WAKAO ,  Hitoshi YASUI ,  Masahiro YAMAGUCHI ,  Hirohito SUGINO ,  Yusuke FUJISAWA

IPC: B25J9/16 ,  B25J9/10 ,  B25J13/08

CPC classification number: B25J9/163 ,  B25J9/1075 ,  B25J9/161 ,  B25J13/081 ,  B25J13/087

Abstract: A flexible material provided at a robot is conductive and an electrical characteristic of the flexible material changes in response to a change of state. The electrical characteristic between plural detection points of the robot is detected by a detection unit. An estimation unit uses a learning model to estimate a robot state from the electrical characteristic of the robot. The learning model is trained so as to input the electrical characteristic and output the robot state. The learning model is trained using, as training data, electrical characteristics when changes of state occur at the flexible material and robot states after the changes of state of the flexible material of the robot. The estimation unit inputs the electrical characteristic to the learning model and outputs the robot state corresponding to the inputted electrical characteristic.

公开(公告)号：US20240286278A1

公开(公告)日：2024-08-29

申请号：US18570640

申请日：2022-07-12

Applicant: BRIDGESTONE CORPORATION

Inventor： Hajime KITANO ,  Yasumichi WAKAO ,  Hitoshi YASUI ,  Masahiro YAMAGUCHI ,  Hirohito SUGINO ,  Yusuke FUJISAWA

IPC: B25J9/16 ,  B25J13/08 ,  B25J15/12 ,  B25J19/02

CPC classification number: B25J9/163 ,  B25J9/161 ,  B25J9/1612 ,  B25J13/083 ,  B25J15/12 ,  B25J19/02

Abstract: An estimating device including, a detecting section detecting electrical characteristics between a plurality of predetermined detection points of a flexible material, the electrical characteristics of the flexible material varying in accordance with changes in applied pressure, and that is disposed can cover a portion of a projecting portion, an estimating section that inputs time-series electrical characteristics to a learning model that is trained by using, as learning data, time-series electrical characteristics at times when pressure is applied to the flexible material, and applied stimulus state information expressing applied stimulus states in which pressure is applied to the flexible material, such that the time-series electrical characteristics are inputs of the learning model and the learning model outputs the applied stimulus state information, and the estimating section estimates applied stimulus state information expressing an applied stimulus state corresponding to the inputted time-series electrical characteristics.