1. //
  2. Start
  3. //
  4. Publications
  5. Paraphrasing Method for Controlling a Ro...
  6. Output formats
  7. //

Paraphrasing Method for Controlling a Robotic Arm Using a Large Language Model

Research output: Contributions to collected editions/works › Article in conference proceedings › Research › peer-review

Standard

Paraphrasing Method for Controlling a Robotic Arm Using a Large Language Model. / Yasuda, Shohei; Komori, Yuka; Nakajima, Kosuke et al.
GCCE 2024 - 2024 IEEE 13th Global Conference on Consumer Electronics. Institute of Electrical and Electronics Engineers Inc., 2024. p. 943-945 (GCCE - IEEE Global Conference on Consumer Electronics).

Research output: Contributions to collected editions/works › Article in conference proceedings › Research › peer-review

Harvard

Yasuda, S, Komori, Y, Nakajima, K, Tanabe, R, Uemura, W & Walter, N 2024, Paraphrasing Method for Controlling a Robotic Arm Using a Large Language Model. in GCCE 2024 - 2024 IEEE 13th Global Conference on Consumer Electronics. GCCE - IEEE Global Conference on Consumer Electronics, Institute of Electrical and Electronics Engineers Inc., pp. 943-945, 13th IEEE Global Conference on Consumer Electronic - GCCE 2024, Kitakyushu, Japan, 29.10.24. https://doi.org/10.1109/GCCE62371.2024.10760305

APA

Yasuda, S., Komori, Y., Nakajima, K., Tanabe, R., Uemura, W., & Walter, N. (2024). Paraphrasing Method for Controlling a Robotic Arm Using a Large Language Model. In GCCE 2024 - 2024 IEEE 13th Global Conference on Consumer Electronics (pp. 943-945). (GCCE - IEEE Global Conference on Consumer Electronics). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/GCCE62371.2024.10760305

Vancouver

Yasuda S, Komori Y, Nakajima K, Tanabe R, Uemura W, Walter N. Paraphrasing Method for Controlling a Robotic Arm Using a Large Language Model. In GCCE 2024 - 2024 IEEE 13th Global Conference on Consumer Electronics. Institute of Electrical and Electronics Engineers Inc. 2024. p. 943-945. (GCCE - IEEE Global Conference on Consumer Electronics). doi: 10.1109/GCCE62371.2024.10760305

Bibtex

@inbook{54ebc76f82ea4e8ab0f181aa62e19415,
title = "Paraphrasing Method for Controlling a Robotic Arm Using a Large Language Model",
abstract = "In recent years, factory production systems have shifted from low-mix high-volume production to high-mix low-volume production and the robots such as arm typed robots and mobile robots are installed in a factory. Integrating robots, sensors and the other devices into a system is costly. To solve the problems in regard to the costs, a method to automatically generate control code for a robot using a large language model (LLM) is considered. Controlling a robot using an LLM makes it possible for non experts in on-site adjustment of robots to adjust motion of a robot installed in factory by giving text-base instructions. In case to use an LLM, we must devise how to write instructions to obtain desired motion of the robot. In this paper, we address pick and place task using a robotic arm and propose a method to learn how to paraphrase instructions to high quality ones for desired controlling a robotic arm using an LLM in reinforcement learning.",
keywords = "large language model, paraphrase, reinforcement learning, robotic arm, Engineering",
author = "Shohei Yasuda and Yuka Komori and Kosuke Nakajima and Ryota Tanabe and Wataru Uemura and Niclas Walter",
note = "Publisher Copyright: {\textcopyright} 2024 IEEE.; 13th IEEE Global Conference on Consumer Electronic - GCCE 2024, GCCE 2024 ; Conference date: 29-10-2024 Through 01-11-2024",
year = "2024",
month = nov,
doi = "10.1109/GCCE62371.2024.10760305",
language = "English",
isbn = "979-8-3503-5508-6",
series = "GCCE - IEEE Global Conference on Consumer Electronics",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "943--945",
booktitle = "GCCE 2024 - 2024 IEEE 13th Global Conference on Consumer Electronics",
address = "United States",
url = "http://ieee-gcce.org/",

}

RIS

TY - CHAP

T1 - Paraphrasing Method for Controlling a Robotic Arm Using a Large Language Model

AU - Yasuda, Shohei

AU - Komori, Yuka

AU - Nakajima, Kosuke

AU - Tanabe, Ryota

AU - Uemura, Wataru

AU - Walter, Niclas

N1 - Conference code: 13

PY - 2024/11

Y1 - 2024/11

N2 - In recent years, factory production systems have shifted from low-mix high-volume production to high-mix low-volume production and the robots such as arm typed robots and mobile robots are installed in a factory. Integrating robots, sensors and the other devices into a system is costly. To solve the problems in regard to the costs, a method to automatically generate control code for a robot using a large language model (LLM) is considered. Controlling a robot using an LLM makes it possible for non experts in on-site adjustment of robots to adjust motion of a robot installed in factory by giving text-base instructions. In case to use an LLM, we must devise how to write instructions to obtain desired motion of the robot. In this paper, we address pick and place task using a robotic arm and propose a method to learn how to paraphrase instructions to high quality ones for desired controlling a robotic arm using an LLM in reinforcement learning.

AB - In recent years, factory production systems have shifted from low-mix high-volume production to high-mix low-volume production and the robots such as arm typed robots and mobile robots are installed in a factory. Integrating robots, sensors and the other devices into a system is costly. To solve the problems in regard to the costs, a method to automatically generate control code for a robot using a large language model (LLM) is considered. Controlling a robot using an LLM makes it possible for non experts in on-site adjustment of robots to adjust motion of a robot installed in factory by giving text-base instructions. In case to use an LLM, we must devise how to write instructions to obtain desired motion of the robot. In this paper, we address pick and place task using a robotic arm and propose a method to learn how to paraphrase instructions to high quality ones for desired controlling a robotic arm using an LLM in reinforcement learning.

KW - large language model

KW - paraphrase

KW - reinforcement learning

KW - robotic arm

KW - Engineering

UR - http://www.scopus.com/inward/record.url?scp=85213354505&partnerID=8YFLogxK

U2 - 10.1109/GCCE62371.2024.10760305

DO - 10.1109/GCCE62371.2024.10760305

M3 - Article in conference proceedings

AN - SCOPUS:85213354505

SN - 979-8-3503-5508-6

T3 - GCCE - IEEE Global Conference on Consumer Electronics

SP - 943

EP - 945

BT - GCCE 2024 - 2024 IEEE 13th Global Conference on Consumer Electronics

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 13th IEEE Global Conference on Consumer Electronic - GCCE 2024

Y2 - 29 October 2024 through 1 November 2024

ER -

DOI

Recently viewed

Researchers

  1. Inge Nehring
  2. Lea Gathen

Publications

  1. Anomaly detection in formed sheet metals using convolutional autoencoders
  2. Machine Learning and Knowledge Discovery in Databases
  3. Is sensitivity for the complexity of mathematics teaching measurable?
  4. On the origin of passive rotation in rotational joints, and how to calculate it
  5. What Makes for a Good Theory? How to Evaluate a Theory Using the Strength Model of Self-Control as an Example
  6. Mirrored piezo servo hydraulic actuators for use in camless combustion engines and its Control with mirrored inputs and MPC
  7. Implicit and explicit horizons
  8. Credit constraints and exports
  9. Evaluation of mechanical property predictions of refill Friction Stir Spot Welding joints via machine learning regression analyses on DoE data
  10. How numeric advice precision affects advice taking
  11. Sliding Mode Control for a Vertical Dynamics in the Presence of Nonlinear Friction
  12. Scientific and local ecological knowledge, shaping perceptions towards protected areas and related ecosystem services
  13. Expectations on Hierarchical Scales of Discourse
  14. Using an adaptive memory strategy to improve a multistart heuristic for sequencing by hybridization
  15. Manufacturing of irregular shapes through force control in incremental sheet forming with active medium
  16. Can not wanting to know be responsible?
  17. Local lens for SDG implementation: lessons from bottom-up approaches in Africa
  18. The feasibility of using Apple's ResearchKit for recruitment and data collection
  19. DigiSchreib
  20. Investigating Factors on R estorative Sleep Quality and its Relationship with Personal Work Performance - An Analysis of Diary Data
  21. Machine Learning Analysis in the Diagnostics of the Dynamics of Ball Bearing with Different Radial Internal Clearance
  22. Resonating self-tracking practices? Empirical insights into theoretical reflections on a 'sociology of resonance'
  23. Managing and accounting for corporate biodiversity contributions mapping the field
  24. Networking
  25. Economic Values from Ecosystems
  26. The Use of Anti-Windup Techniques in Didactic Level Systems
  27. Analysis of life cycle datasets for the material gold
  28. Export entry, export exit, and productivity in German manufacturing industries
  29. New methods for the analysis of links between international firm activities and firm performance
  30. EU Migration and Asylum Policies
  31. Working hour arrangements and working hours
  32. C.S.ルイス 「ライオンと魔女」の謎を解く―ナルニアガイド
  33. Relativity in Social Cognition: Basic processes and novel applications of social comparisons
  34. Consumers' Responses to CSR Activities
  35. Influence of transition metal dopants and temperature on the dehydrogenation and rehydrogenation kinetics of NaAlH4
  36. The Effects of Nonindependent Rater Sets in Multilevel–Multitrait–Multimethod Models
  37. Attention on the source of influence reverses the impact of cross-contextual imitation
  38. Organic Synthesis – Art or Science?
  39. Traits of butterfly communities change from specialist to generalist characteristics with increasing land-use intensity
  40. Use of the concept of Bildung in the international science education literature, its potential, and implications for teaching and learning
  41. Beyond Personalization and Anonymity: