A Modular Multi-Agent Architecture for Order Fulfillment in Industry 5.0
Abstract
This article presents the design and validation of an automated packaging agent built on a modular multi-agent architecture that integrates generative AI, computer vision, robotics, and simulation. In response to spoken user commands, specialized agents (planning, production, packaging, inventory, and quality control) collaboratively identify target items, plan order fulfillment, execute packaging actions, and verify outcomes. The system is validated in a simulated industrial environment implemented in CoppeliaSim, with a web-based control layer for service integration and orchestration. A large language model (LLM) converts verbal instructions into structured task plans, while OpenCV-based perception is complemented by a custom YOLOv11 detector trained on automatically labeled data generated with the Segment Anything Model (SAM). Experimental results in simulation demonstrate reliable end-to-end autonomy, including conveyor control, box selection, pick-and-place execution, and vision-based quality checks. The agent completes a full packaging cycle in ~6 minutes and achieves near-perfect object identification accuracy in the evaluated simulated scenarios. Remaining challenges include improving grasp reliability for physical deployment and reducing inter-platform latency. Overall, the proposed approach illustrates the potential of combining AI, robotics, and simulation to build resilient, adaptable industrial agents aligned with Industry 5.0 requirements.
Keywords: artificial intelligence; Industry 5.0; intelligent agents; pick-and-place; computer vision; robotic packaging.
Full Text:
PDFReferences
A. K. MEHER, D. MISHRA, G. NANDINI, T. SINGH, and A. K. SAHOO. Role of AI in Shaping Industry 5.0: A Transformative Journey, in 2025 International Conference on Advancements in Smart, Secure and Intelligent Computing (ASSIC), Bhubaneswar, India, 2025, 1-6, https://doi.org/10.1109/ASSIC64892.2025.11158454
L. B. PESSOA DA SILVA, J. PONTES, E. MOSCONI, F. TAVARES TREINTA, R. TADASHI YOSHINO, and L. M. MARTINS DE RESENDE. The future of HRM for intelligent manufacturing systems in the context of industry 5.0. Computers & Industrial Engineering, 2026, 211: 111587, https://doi.org/10.1016/j.cie.2025.111587
Z. LUO, J. PENG, X. ZHANG, H. JIANG, R. YIN, Y. TAN, and M. LV. Optimal scheduling of smart home energy systems: A user-friendly and adaptive home intelligent agent with self-learning capability. Advances in Applied Energy, 2024, 15: 100182, https://doi.org/10.1016/j.adapen.2024.100182
L. PENG, D. LI, Z. ZHANG, T. ZHANG, A. HUANG, S. YANG, and Y. HU. Human-AI collaboration: Unraveling the effects of user proficiency and AI agent capability in intelligent decision support systems. International Journal of Industrial Ergonomics, 2024, 103: 103629, https://doi.org/10.1016/j.ergon.2024.103629
P. LI, M. YANG, Y. LIU, J. ZHANG, S. HE, C. YANG, W. YANG, X. CAI, L. ZHU, S. YE, H. SUN, C. HOU, N. ZHOU, M. ZHU, and G. TAO. The rise of intelligent fabric agent from mass-produced advanced fiber materials. Science Bulletin, 2024, 69(23): 3644-3647, https://doi.org/10.1016/j.scib.2024.09.034
P. WANG, Q. HU, Q. MEI, S. WANG, Y. YANG, D. GUO, X. LIU, W. HU, and J. CHEN. Intelligent port logistics: A spatiotemporal knowledge graph and AI-agent framework for berth allocation. Advanced Engineering Informatics, 2025, 68(Part B): 103633, https://doi.org/10.1016/j.aei.2025.103633
M. M. ASLAM, W. SHAFIK, A. F. HIDAYATULLAH, K. KALINAKI, H. GUL, R. Y. ZAKARI, and A. TUFAIL. Intelligent Transportation Systems: A Critical Review of Integration of Cyber-physical Systems (CPS) and Industry 4.0. Digital Communications and Networks, 2025, https://doi.org/10.1016/j.dcan.2025.06.014
X. YU, Z. WANG, Z. GAO, H. LANG, X. SHAO, and Z. LIU. Applications, challenges, and prospects of AI-driven intelligent packaging technologies in the food supply chain under Industry 4.0. Trends in Food Science & Technology, 2025, 165: 105367, https://doi.org/10.1016/j.tifs.2025.105367
P. GHADIMI, C. WANG, M. K. LIM, and C. HEAVEY. Intelligent sustainable supplier selection using multi-agent technology: Theory and application for Industry 4.0 supply chains. Computers & Industrial Engineering, 2019, 127: 588-600, https://doi.org/10.1016/j.cie.2018.10.050
A. M. AL-BAYATI, A. ALARABEYYAT, A. ALHROOB, A. ALIYU, N. A. MOSTAFA, and I. M. ALBAYATI. Intelligent Multi-Agent English Auction Interaction Protocol for Logistics Service Provider Selection. Transportation Research Procedia, 2025, 84: 185-192. https://doi.org/10.1016/j.trpro.2025.03.062
M. MAHMOODJANLOO, S. JALILVAND, A. BABOLI, and M. RUHLA. Augmented multi-agent algorithm utilizing intelligent search range detection heuristic to solve assembly line sequencing problem: A case study in the truck industry. Engineering Applications of Artificial Intelligence, 2024, 137(Part A): 109111. https://doi.org/10.1016/j.engappai.2024.109111
S. XU. Application of Multi-agent Cooperative Decision-making Model Based on LSTM and Attention Mechanism in Entrepreneurship Simulation, in 2nd International Conference on Intelligent Computing and Robotics (ICICR), Dalian, China, 2025, 135-140, https://doi.org/10.1109/ICICR65456.2025.00031
S. NIMMALA, P. V. SENA, S. INTURI, S. JANBHASHA, P. NARSIMHULU and J. MANORANJINI. Multi-Agent Deep Reinforcement Learning for Intelligent Industrial IoT Networks, in 9th International Conference on Inventive Systems and Control (ICISC), Coimbatore, India, 2025, 455-459, https://doi.org/10.1109/ICISC65841.2025.11187915
X. ZHANG, F. HE, Z. LIN and C. JIANG. Coordinated Motion Planning of Heterogeneous Multi-Agent Systems, in 44th Chinese Control Conference (CCC), Chongqing, China, 2025, 5664-5670, https://doi.org/10.23919/CCC64809.2025.11179105
Y. HILLALI, M. ZEGRARI, S. CHAFIK and N. ALFATHI. An Intelligent Framework for Multi-Agent System Based on Dynamic Balancing of Production 4.0. IEEE Access, 2025, 13: 165695-165717, https://doi.org/10.1109/ACCESS.2025.3611631
Z. ZHAO, D. TANG, C. LIU, L. WANG, Z. ZHANG, H. ZHU, K. CHEN, Q. NIE, and Y. JI. A Large language model-based multi-agent manufacturing system for intelligent shopfloors. Advanced Engineering Informatics, 2026, 69(Part A): 103888, https://doi.org/10.1016/j.aei.2025.103888
G. JAIN, A. JAIN, V. PRADHAN, and A. JAISWAL, Chapter 27 - Revolutionizing healthcare: intelligent machines and enhanced language support for diversified doctor–patient communication in Industry 4.0, Editor(s): A. K. TYAGI, and S. TIWARI, Human-Centric Integration of Next-Generation Data Science and Blockchain Technology, Academic Press, 2025, 441-464, https://doi.org/10.1016/B978-0-443-33498-6.00006-6
Y. MA, S. ZHENG, Z. YANG, P. ZHENG, J. LENG, and J. HONG. Leveraging large language models in next generation intelligent manufacturing: Retrospect and prospect. Journal of Manufacturing Systems, 2025, 82: 809-840, https://doi.org/10.1016/j.jmsy.2025.07.019
J. WEN, D. LIU, Y. XIE, Y. REN, J. WANG, Y. XIA, and P. ZHU. AcuGPT-Agent: An LLM-powered intelligent system for acupuncture-based infertility treatment. Neurocomputing, 2025, 652: 131116, https://doi.org/10.1016/j.neucom.2025.131116
Z. XIAO, and J. MA. LLM agent framework for intelligent change analysis in urban environment using remote sensing imagery. Automation in Construction, 2025, 177: 106341, https://doi.org/10.1016/j.autcon.2025.106341
S. OJURI, T. A. HAN, R. CHIONG, and A. DI STEFANO. Optimizing text-to-SQL conversion techniques through the integration of intelligent agents and large language models. Information Processing & Management, 2025, 62(5): 104136, https://doi.org/10.1016/j.ipm.2025.104136
S. DANG, Y. SON, B. KIM, K. JEONG, J. PARK and H. CHO. Converging High-Performance Computing, Artificial Intelligence, and Intelligent Workflows for Next-Generation Innovation, in 2025 International Conference on Artificial Intelligence, Computer, Data Sciences and Applications (ACDSA), Antalya, Turkiye, 2025, 1-6, https://doi.org/10.1109/ACDSA65407.2025.11166486
L. CUNHA. Modelagem de um ecossistema contábil inteligente utilizando agentes automatizados com N8N. Lumen et virtus (LEV), 2024, 2177-2789, https://doi.org/10.56238/levv15n41-115
S. BURATTINI, S. MARIANI, S. MONTAGNA, M. PICONE, and A. RICCI. Distributing intelligent functionalities in the Internet of Things with agents and Digital Twins. Internet of Things, 2025, 31: 101560, https://doi.org/10.1016/j.iot.2025.101560
S. YOON, J. SONG, and J. LI. Ontology-enabled AI agent-driven intelligent digital twins for building operations and maintenance. Journal of Building Engineering, 2025, 108: 112802, https://doi.org/10.1016/j.jobe.2025.112802
Refbacks
- There are currently no refbacks.
