The transition from Industry 4.0 to Industry 5.0 introduces a structural reconfiguration of the distributed manufacturing systems, shifting the emphasis from automation-centric efficiency toward human-centricity, sustainability, and systemic resilience. Although robotic swarm intelligence has demonstrated its effectiveness in decentralized task allocation and adaptive optimization, the existing architectures remain predominantly performance-driven, treating human workload and stability as secondary indicators. This study proposes a human-centric swarm intelligence control architecture in which sustainability and the supervisory workload are internalized within the distributed functional objective. This framework integrates Particle Swarm Optimization-based coordination, reinforcement learning adaptation, and predictive conditional variance modelling into a unified multi-agent structure. A multi-objective optimization problem is formulated in order to jointly minimize the task completion time, energy consumption, operational volatility, and human workload, while the autonomy is formalized as a dynamically regulated control variable. The simulation experiments conducted across multiple stochastic realizations demonstrate a statistically significant reduction in the value of energy consumption, variance amplification, and supervisory overload, together with an accelerated post-disturbance recovery for the proposed architecture in comparison with the conventional Industry 4.0 swarm configurations. The findings confirm that embedding human-centric and sustainability-aware constraints enhances a system’s stability and resilience without compromising its efficiency, thereby validating a mathematically grounded and simulation-based framework aligned with the Industry 5.0 manufacturing principles.
Industry 5.0, Human-in-the-loop control, Swarm intelligence, Multi-objective optimization, Reinforcement learning , Distributed manufacturing systems, Resilient distributed control.
Cezar BRAICU, Cătălina Loredana ROGOZEANU, Marius PETRESCU, Rareș-Vladimir NIȚU, Ionuț-Adrian GHIBANU, "Human-Centric Swarm Intelligence for Sustainable Distributed Manufacturing in Industry 5.0", Studies in Informatics and Control, ISSN 1220-1766, vol. 35(3), pp. 47-59, 2026. https://doi.org/10.24846/v35i3y202605
All articles published by Studies in Informatics and Control (SIC) are published in accordance with the terms and conditions of the Creative Commons Attribution License (CC BY-NC-SA 4.0).