LLM-driven agent for speech-enabled control of industrial robots: A case study in snow-crab quality inspection

This study investigates the integration of large language models (LLMs) into a voice- and vision-based robotic control system in autonomous industrial applications. The main objective is to demonstrate that an LLM-based agent can interpret natural instructions, dynamically plan movements, and execut...

Full description

Saved in:
Bibliographic Details
Main Authors: Ibrahim Kadri, Sid Ahmed Selouani, Mohsen Ghribi, Rayen Ghali, Sabrina Mekhoukh
Format: Article
Language:English
Published: Elsevier 2025-09-01
Series:Results in Engineering
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2590123025027276
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849330485251014656
author Ibrahim Kadri
Sid Ahmed Selouani
Mohsen Ghribi
Rayen Ghali
Sabrina Mekhoukh
author_facet Ibrahim Kadri
Sid Ahmed Selouani
Mohsen Ghribi
Rayen Ghali
Sabrina Mekhoukh
author_sort Ibrahim Kadri
collection DOAJ
description This study investigates the integration of large language models (LLMs) into a voice- and vision-based robotic control system in autonomous industrial applications. The main objective is to demonstrate that an LLM-based agent can interpret natural instructions, dynamically plan movements, and execute robotic actions without domain-specific supervised learning, thereby enabling autonomous robotic planning. The proposed system relies on a voice interface, an LLM agent, and tools for real-time robot control. A dedicated communication module was developed to ensure the full control of a KUKA industrial robot using WebSocket, without resorting to proprietary solutions. To validate the approach, a case study was conducted using a robotic cell, which was applied to snow-crab sorting, where computer vision provides real-time perception. The experimental evaluation covered a wide range of commands, including movement instructions, complex planning tasks (e.g., trajectory generation), and visual queries based on crab quality, size, and anatomy. The results showed that the model exhibited robust interpretation capabilities with an overall success rate of 98.46%. These performances highlight the potential of LLMs to facilitate human-robot interaction in real industrial environments, while reducing programming complexity and increasing system autonomy.
format Article
id doaj-art-a3e9480c1a3a4809859d38deec7d79e1
institution Kabale University
issn 2590-1230
language English
publishDate 2025-09-01
publisher Elsevier
record_format Article
series Results in Engineering
spelling doaj-art-a3e9480c1a3a4809859d38deec7d79e12025-08-20T03:46:54ZengElsevierResults in Engineering2590-12302025-09-012710666010.1016/j.rineng.2025.106660LLM-driven agent for speech-enabled control of industrial robots: A case study in snow-crab quality inspectionIbrahim Kadri0Sid Ahmed Selouani1Mohsen Ghribi2Rayen Ghali3Sabrina Mekhoukh4Université de Moncton, Campus of Shippagan, 218 Bd J. D. Gauthier, Shippagan, E8S 1P6, NB, Canada; Corresponding author.Université de Moncton, Campus of Shippagan, 218 Bd J. D. Gauthier, Shippagan, E8S 1P6, NB, CanadaUniversité de Moncton, Campus of Moncton, 18 Av Antonine-Maillet, Moncton, E1A 3E9, NB, CanadaUniversité de Moncton, Campus of Shippagan, 218 Bd J. D. Gauthier, Shippagan, E8S 1P6, NB, CanadaUniversité de Moncton, Campus of Shippagan, 218 Bd J. D. Gauthier, Shippagan, E8S 1P6, NB, CanadaThis study investigates the integration of large language models (LLMs) into a voice- and vision-based robotic control system in autonomous industrial applications. The main objective is to demonstrate that an LLM-based agent can interpret natural instructions, dynamically plan movements, and execute robotic actions without domain-specific supervised learning, thereby enabling autonomous robotic planning. The proposed system relies on a voice interface, an LLM agent, and tools for real-time robot control. A dedicated communication module was developed to ensure the full control of a KUKA industrial robot using WebSocket, without resorting to proprietary solutions. To validate the approach, a case study was conducted using a robotic cell, which was applied to snow-crab sorting, where computer vision provides real-time perception. The experimental evaluation covered a wide range of commands, including movement instructions, complex planning tasks (e.g., trajectory generation), and visual queries based on crab quality, size, and anatomy. The results showed that the model exhibited robust interpretation capabilities with an overall success rate of 98.46%. These performances highlight the potential of LLMs to facilitate human-robot interaction in real industrial environments, while reducing programming complexity and increasing system autonomy.http://www.sciencedirect.com/science/article/pii/S2590123025027276Large language models (LLMs)Voice interfaceKUKA industrial robotHuman-robot interactionAutonomous robotic planningSnow crab sorting
spellingShingle Ibrahim Kadri
Sid Ahmed Selouani
Mohsen Ghribi
Rayen Ghali
Sabrina Mekhoukh
LLM-driven agent for speech-enabled control of industrial robots: A case study in snow-crab quality inspection
Results in Engineering
Large language models (LLMs)
Voice interface
KUKA industrial robot
Human-robot interaction
Autonomous robotic planning
Snow crab sorting
title LLM-driven agent for speech-enabled control of industrial robots: A case study in snow-crab quality inspection
title_full LLM-driven agent for speech-enabled control of industrial robots: A case study in snow-crab quality inspection
title_fullStr LLM-driven agent for speech-enabled control of industrial robots: A case study in snow-crab quality inspection
title_full_unstemmed LLM-driven agent for speech-enabled control of industrial robots: A case study in snow-crab quality inspection
title_short LLM-driven agent for speech-enabled control of industrial robots: A case study in snow-crab quality inspection
title_sort llm driven agent for speech enabled control of industrial robots a case study in snow crab quality inspection
topic Large language models (LLMs)
Voice interface
KUKA industrial robot
Human-robot interaction
Autonomous robotic planning
Snow crab sorting
url http://www.sciencedirect.com/science/article/pii/S2590123025027276
work_keys_str_mv AT ibrahimkadri llmdrivenagentforspeechenabledcontrolofindustrialrobotsacasestudyinsnowcrabqualityinspection
AT sidahmedselouani llmdrivenagentforspeechenabledcontrolofindustrialrobotsacasestudyinsnowcrabqualityinspection
AT mohsenghribi llmdrivenagentforspeechenabledcontrolofindustrialrobotsacasestudyinsnowcrabqualityinspection
AT rayenghali llmdrivenagentforspeechenabledcontrolofindustrialrobotsacasestudyinsnowcrabqualityinspection
AT sabrinamekhoukh llmdrivenagentforspeechenabledcontrolofindustrialrobotsacasestudyinsnowcrabqualityinspection