TY - GEN
T1 - A Voice-Controlled Motion Reproduction Using Large Language Models for Polishing Robots
AU - Tanaka, Yuki
AU - Katsura, Seiichiro
N1 - Funding Information:
This work was partially supported by Strategic Information and Communications RandD Promotion Programme (SCOPE) Grant Number 201603011
Funding Information:
This work was partially supported by Strategic Information and Communications R&D Promotion Programme (SCOPE) Grant Number 201603011.
Publisher Copyright:
© 2023 IEEE.
PY - 2023
Y1 - 2023
N2 - In recent years, the shortage of professionally skilled people in industrial fields has been a major social problem. To solve this problem, the transfer of skills to robots has been attracting much attention. However, they are not familiar with robot control, and hard to teach robots their skills by numerical commands or program source code. For more user-friendly human-robot interaction, a lot of studies have been conducted. In previous researches, robot task processes are pre-defined and not changed in task execution. We developed a robot system using the motion-copying system and GPT-3, one of the Large Language Models. This system can not only copy the motion but also modify saved motion in execution by using natural language commands. We evaluated the proposed system by applying it to polishing robots and confirmed that the surface of used workpieces was changed following to input commands.
AB - In recent years, the shortage of professionally skilled people in industrial fields has been a major social problem. To solve this problem, the transfer of skills to robots has been attracting much attention. However, they are not familiar with robot control, and hard to teach robots their skills by numerical commands or program source code. For more user-friendly human-robot interaction, a lot of studies have been conducted. In previous researches, robot task processes are pre-defined and not changed in task execution. We developed a robot system using the motion-copying system and GPT-3, one of the Large Language Models. This system can not only copy the motion but also modify saved motion in execution by using natural language commands. We evaluated the proposed system by applying it to polishing robots and confirmed that the surface of used workpieces was changed following to input commands.
KW - human-robot interaction
KW - large language models
KW - motion control
KW - motion reproduction system
KW - natural language processing
KW - polishing robot
KW - robot teaching
KW - transfer of skills
UR - http://www.scopus.com/inward/record.url?scp=85158139970&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85158139970&partnerID=8YFLogxK
U2 - 10.1109/ICM54990.2023.10101966
DO - 10.1109/ICM54990.2023.10101966
M3 - Conference contribution
AN - SCOPUS:85158139970
T3 - Proceedings - 2023 IEEE International Conference on Mechatronics, ICM 2023
BT - Proceedings - 2023 IEEE International Conference on Mechatronics, ICM 2023
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2023 IEEE International Conference on Mechatronics, ICM 2023
Y2 - 15 March 2023 through 17 March 2023
ER -