Session: 03-15-03: Smart Manufacturing and Robotics for the Future III

Paper Number: 165682

Smart Packaging Optimization Using Digital Twins and Industrial 5.0 With Human Robot Interaction 

Industry 5.0 is transforming manufacturing by emphasizing human-robot interaction (HRI) alongside automation. Despite their efficiency, traditional robotic packaging lines struggle with adaptability, resource optimization, and human safety. A major challenge in industry is the lack of seamless human-robot collaboration in digital manufacturing systems, leading to inefficiencies in cycle times, unoptimized resource utilization, and limited system adaptability. Existing digital twin (DT) frameworks lack full integration of real-time adjustments and human involvement, particularly in packaging applications. To address this gap, this study integrates Industry 4.0 and 5.0 technologies—including the Industrial Internet of Things (IIoT), machine learning, and real-time data analytics—to develop an advanced DT framework within Siemens Tecnomatix Process Simulate. This approach aims to enhance manufacturing efficiency while ensuring that automation enhances rather than replaces human expertise.

This study develops a digital twin of a physical packaging line, specifically for packaging delivery products into boxes. Three distinct configurations are evaluated: a human-only packaging line, a fully automated robotic line, and a hybrid human-robot collaborative system. In each scenario, human workers or robots are responsible for picking, scanning, and placing products into appropriately sized boxes, sealing them, and labeling them for shipment. The research utilizes Siemens Tecnomatix Process Simulate for DT development, MATLAB for data analysis, and Python for machine learning implementation. Hardware tools include Elephant Robotics' myCobot 280 6-axis collaborative robotic arms, industrial conveyor belts, automated box sealers, and IoT-enabled devices. To enable accurate monitoring and optimization, the system integrates industrial sensors, including photoelectric sensors for object detection, capacitive touch sensors for safe human-robot interaction, piezoelectric sensors for force sensing, and RFID scanners for inventory tracking.

Preliminary results from Tecnomatix simulations indicate that the human-robot collaborative approach significantly outperforms human-only and fully automated configurations. The DT mirrors physical workflows with a cycle-time prediction discrepancy of less than 5%. IIoT-driven predictive maintenance reduced downtime by 15%, while collaborative work cells improved task efficiency by 30% compared to traditional setups. The hybrid system improved by 20% compared to manual processes and enhanced efficiency by 5% over fully automated setups. By integrating real-time data with adaptive robotics, this study highlights the potential of Industry 5.0 principles to create more responsive and scalable packaging lines. The primary focus is on improving packaging line efficiency through intelligent human-robot cooperation and predictive maintenance.

This research advances digital manufacturing by demonstrating how DTs and IIoT enhance robotic process optimization while maintaining human oversight. The findings support Industry 5.0’s vision of automation complementing human skills rather than replacing them. Future work will expand the framework to multi-task robotic operations and incorporate augmented reality (AR) interfaces for improved operator control. Additionally, extending machine learning applications to multi-robot, multi-operator environments will further enhance predictive analytics and system adaptability. By addressing key challenges in robotic packaging lines, this study establishes a foundation for future advancements in intelligent manufacturing, paving the way for seamless human-robot integration in industrial environments.

Presenting Author: Kay Morgan Kennesaw State University

Presenting Author Biography: Kay Morgan
Graduate Student. MS-Intelligent Robotics Systems. Kennesaw State University. Second M.S. Expected 2026 Dec.
Ph.D. Technology Management (Quality Systems) Industrial Engineering Technology. Indiana State University (2019 May)
Assistant Professor of Engineering Technologies, Monroe Community College - State University of New York (Present)

Authors:

Kay Morgan Kennesaw State University
David Guerra-Zubiaga Kennesaw State University
Gershom Richards Kennesaw State University