IN4PL 2025 Abstracts

Area 1 - Industry of the Future
Full Papers Short Papers
Area 2 - Logistics
Full Papers Short Papers

Area 1 - Industry of the Future

Full Papers
Paper Nr: 33
Title:

A Human Ontology with Cognition and Ability Models for Human and Cognitive Digital Twins
Authors:

Yannick Naudet, Eloïse Zehnder, Ben Gaffinet, Jana Al Haj Ali and Hervé Panetto
Abstract: In this paper, we present a comprehensive ontology of human cognition and abilities, designed as a formal framework for digital twins. This model enables digital twins of humans to replicate aspects of human cognition, while cognitive digital twins enhance cyber-physical systems with human-like reasoning and intelligence. The cognition meta-model results from the integration of multiple perspectives on cognition in Neuropsychology, Education Sciences, Engineering Sciences, Cognitive Informatics, and Cognitive Architectures, including indirectly also perspectives of Cognitive Sciences and Artificial Intelligence. Our Human Ontology (HUMO) is an extension of the SOMA (Socio-physical Model of Activities) ontology, which serves as a basis to design cases for cognitive robot - human collaboration. It aims at being exploited by digital twins in their representation of the world and the entity they twin.
Paper Nr: 34
Title:

Synergizing Systems Engineering and System Dynamics: A Model-Based Approach to Enhance Manufacturing Circularity
Authors:

Ali Asghar Bataleblu, Maryam Esmaeilian, Sergio Salimbeni and Erwin Rauch
Abstract: Enhancing the circular economy (CE) using digitalization and green strate-gies is increasingly considered a crucial way to mitigate the impact of indus-trial operations on climate change while making compromises between eco-nomic, social, and environmental priorities. While digital and sustainable so-lutions reinforce each other in theory, sometimes they clash in practice. Higher-level management of interactions in twin digital and green transition can create performance synergy in the implementation phase and mitigate the impacts of upcoming actions. This study proposes an approach to ad-vance CE decision-making in the presence of inevitable interconnectedness among involved systems in the manufacturing era, by incorporating system dynamics and model-based systems engineering to transition from traditional systems engineering to circular systems engineering. To this end, model-based systems engineering tools, by providing connectivity and traceability throughout the entire system life cycle, enable systems designers to not only consider the impact of interdisciplinary interactions in system dynamics modeling but also think beyond systems and include the external influential criteria. This paper presents an integrated framework for creating a holistic digital model to facilitate the optimization of the CE problem, spanning from system design to policy assessment. By connecting system dynamics, standards, and system functionalities across both operational and enterprise levels, the proposed framework enhances the ability to make resilient and purposeful decisions when encountering a complex network of systems in a CE problem.
Paper Nr: 36
Title:

From Semantic Interoperability to Cognitive Interoperability: Enabling Human–CPS Collaboration in Industry 5.0
Authors:

Jana Al Haj Ali, Ben Gaffinet, Hervé Panetto and Yannick Naudet
Abstract: In the context of Industry 5.0, where human-centred collaboration is paramount, effective interaction between humans and Cyber–Physical Systems (CPS) requires us to reconsider the traditional concept of interoperability. Although technical, syntactic and semantic interoperability facilitated system integration in Industry 4.0, they are insufficient when humans become active collaborators. In particular, semantic interoperability fails to capture the cognitive and contextual nuances of human reasoning, often resulting in gaps in mutual understanding. This article discusses and defines cognitive interoperability, which goes beyond semantic alignment by integrating shared perception, contextual modelling, and reasoning mechanisms to support seamless collaboration between humans and CPS. First, we provide a comprehensive analysis of how cognitive interoperability has been defined in various fields, offering a unified and clarified perspective. Next, we present a structured diagram detailing the cognitive functions necessary to achieve cognitive interoperability between humans and CPSs. Finally, we examine a real-world use case in the field of Human–Robot Collaboration (HRC) to illustrate the practical implications of this concept. Through this example, we demonstrate how cognitive interoperability can address the limitations of semantic interoperability in dynamic and cooperative contexts by enabling mutual understanding and adaptive interaction. Our work contributes to advancing human-centred intelligent systems and provides a foundation for designing next-generation collaborative manufacturing environments.
Paper Nr: 39
Title:

Shaping the Future of Aerospace Industrial Architecture with MBE-Driven Solutions: MOONRISE Project
Authors:

Fernando Mas, Manuel Oliva, Sophia Salas-Cordero and Tamara Borreguero
Abstract: The MOONRISE project represents a major advancement in applying Model-Based Engineering (MBE) to industrial architecture within Airbus Defense and Space. Grounded in systems engineering and digital transformation principles, it transitions from document-based to model-centric methodologies to address the complexity and customization of modern aerospace manufacturing. This paper describes the application of MOONRISE to Airbus Defense and Space operational activities, highlighting the effectiveness of MBE approaches to enable instant design decisions, enhance integration across the different disciplines, and maximize domain-specific expertise applications. This project advanced concepts such as model lifecycle management, simulation integration, and learning curve analysis through the creation of a sophisticated and reusable digital twin of a customized unmanned aerial system. The article outlines the methodology, tools, and organizational structure used to translate theoretical concepts into practical solutions, overcoming the challenges faced by the defense industry with low production volumes and deep customization. The MOONRISE project also provides substantial empirical evidence that substantiates the role of Model-Based Engineering in ensuring digital continuity, fostering organizational cultural change, and delivering incremental benefits to business processes. The insights gained from the project advance scientific understanding and inform future business practices, making it a seminal reference case for MBE in complex industrial environments.
Paper Nr: 44
Title:

Semantic Validation for AAS Submodels Using Semantic Dictionary and Generative AI
Authors:

Israt Nowshin, Dirk Schöttke, Ghada Mohamed, Stephan Schäfer and Aaron Zielstorff
Abstract: Asset Administration Shell (AAS) and its submodels are essential for achieving standardization and interoperability in Industry 4.0 environments. To ensure standardization in industrial settings, our previous research focused on automatically validating standardized submodels according to the Industrial Digital Twin Association (IDTA) standards and non-standardized submodels based on user-defined templates. Although earlier work focused on automatic submodel validation triggered via MQTT, the semantic correctness of the elements remains a critical, yet underexplored area. This paper extends the Test Orchestrator framework that leverages a semantic dictionary such as ECLASS and Generative AI for increased semantic validation capabilities. These enhancements enable validation of element naming, unit appropriateness, and compatibility of values with declared value types, thereby improving the contextual accuracy of submodels. Additionally, the system introduces feedback generation for incorrect or inconsistent elements, helping users better understand and resolve validation issues. A large-scale scalability evaluation demonstrates the framework's ability to efficiently handle a significant number of submodels while maintaining minimal per-submodel validation time. The proposed solution contributes to more robust, intelligent, and semantically aware digital twin systems that are more closely aligned with the objectives of Industry 4.0.
Paper Nr: 50
Title:

Adaptive Learning Paths for Industry~4.0 Competencies: Didactic Framework with Role- and Maturity-Based Differentiation Using the Asset Administration Shell
Authors:

Daniel Büttner, Dirk Schöttke, Stephan Schäfer, Sönke Konch, Daniel Porta, Tim Schwartz, Claudette Ocando-Röhrich, Aaron Zielstorff and Andreas Bayha
Abstract: The AAS is recognized as a key enabler for the digital transformation of industrial production. However, its implementation creates heterogeneous learning demands across technical, operational, and strategic roles—challenges that conventional training formats rarely address in a differentiated manner. This paper presents a pedagogically grounded framework for adaptive learning paths that integrates three design axes: (1) organizational maturity level, (2) role-specific competence requirements, and (3) established instructional models such as Kolb’s experiential learning cycle and scaffolding. The framework is validated through a role-differentiated survey on AAS-related digital maturity in SMEs, revealing a pronounced need for low-threshold entry points and staged progression logic. Building on these findings, the paper demonstrates practical operationalization in three use cases: a hybrid demonstrator for immersive AAS training, a higher education implementation combining simulation and real-world integration, and a proof of concept for DPP integration in switchgear manufacturing. A prototype implementation in Moodle illustrates how maturity and role mapping can be translated into conditional learning path access. Results confirm the framework’s scalability and transferability, enabling targeted competence development aligned with real-world product lifecycle and digitalization processes. The approach addresses both researchers and practitioners, offering a replicable model for structuring complex Industry 4.0 competencies in industrial and educational contexts.
Paper Nr: 53
Title:

LLM Trained Bandit Algorithms For Improving Q-Commerce Grocery Swaps
Authors:

Ioan Webber, Maharshi Dhada, Madalina Lupu, Matteo Giaretti and Duncan McFarlane
Abstract: In the modern competitive marketplace, providing consumers with convenience, low costs, and a positive customer experience is essential. Online shopping at supermarkets via quick commerce (Q-commerce) has become increasingly common, presenting new challenges due to product catalogue sizes ranging from hundreds to tens of thousands. This makes stockouts or outdated product listings very common, requiring significant attention to maintain customer satisfaction by creating robust and scalable product swap systems. Product similarity is often used to suggest alternative product swaps, but large catalogues and limited customer feedback data make it difficult to monitor and change swap suggestions if they are not satisfactory. This paper explores methods for incorporating customer feedback to change product swap recommendations over time, by using Thompson sampling multi-armed bandits and upper confidence bound (UCB) contextual bandits with network-based experience sharing. A multimodal LLM is used to provide feedback for the process, enabling the generation of synthetic responses via human-like automation, in the absence of real-world data.
Paper Nr: 58
Title:

Towards Farmers 5.0 by Collaborative Networks Support
Authors:

Sanaz Nikghadam-Hojjati, Sepideh Kalateh, Sara Oleiro Araújo, Ricardo Silva Peres and José Barata
Abstract: Technological innovations are reshaping every facet of our lives, empowering us to be more innovative, efficient, precise, agile, connected, and sustainable. These advancements also foster greater intelligence by harnessing collective wisdom through collaborative networks. Among the industries undergoing rapid transformation, agriculture stands out, with its 27% share of the global workforce. To meet the daunting task of feeding an estimated 9.3 billion people by 2050, the agricultural sector must embrace technological innovation wholeheartedly. Any alteration in processes, technologies, or skill requirements within agriculture directly impacts job definitions and skillsets. This dynamic landscape prompts an urgent exploration of Agriculture 5.0—a vision of farming that integrates cutting-edge technologies and practices to meet future demands sustainably. In this exploratory paper, we embark on the journey towards Agriculture 5.0, delving into the essential characteristics and skill requirements of the modern farmer, often referred to as Farmer 5.0. Moreover, we highlight the indispensable role of collaborative networks in cultivating these skills, fostering adaptability within the realm of interconnected smart agriculture. With presented research, we aim to equip farmers and stakeholders with the insights necessary to navigate the complexities of this evolving landscape effectively.
Short Papers
Paper Nr: 29
Title:

Enhancing Advanced Planning of Manufacturing Operations Using Discrete Event Simulation
Authors:

Gaston Batchoudi, Mohammed-Amine Abdous, Roland De Guio, Eric Ramat and Patrick Sondi Obwang
Abstract: In recent decades, manufacturing system, particularly small and medium-sized enterprises (SMEs) have faced rising challenges due to increased demand for customization and shorter delivery times. To adapt, many firms rely on temporary workforce teams, yet determining optimal staffing remains complex due to budget limits, contractual constraints, and forecast uncertainties. Although Advanced Planning and Scheduling (APS) systems have long been proposed to address such issues, they often focus on complex mathematical models with limited practical implementation guidance. This work introduces a practical APS framework built around three modules. The first handles data structuring, analysis, and demand forecasting. The second focuses on production planning, combining a multi-objective lot-sizing optimization sub-module for aggregated planning and a discrete-event simulation sub-module for operational scheduling. A regulation heuristic corrects forecast deviations in real time. The third module offers decision support, assessing the impact of strategies on KPIs such as service level, inventory, and workforce use. The results from the case study demonstrate that the proposed system consistently achieves a 100% service level, while the customer satisfaction rate remains close to 100% as well.
Paper Nr: 35
Title:

Integrating Product Lifecycle Management, Business Innovation, and Sustainability in the Era of Industry 5.0: A Synergistic Framework
Authors:

Marcelo Calixto, Anderson Szejka and Eduardo Rocha Loures
Abstract: This paper presents a human‑centric Product Lifecycle Management (PLM) framework aligned with Industry 5.0 that brings together Digital Twins (DTs), Smart Manufacturing, and Generative AI (GenAI) under a PLM backbone. The framework is designed around three pillars—human‑centricity, sustainability, and resilience—and incorporates explainable AI (XAI) and lifecycle assessment to support transparent, accountable decisions. A focused systematic literature review motivates the architecture and identifies gaps in explainability, interoperability, and end‑to‑end lifecycle coverage. The study demonstrates feasibility with a NASA milling case study, integrating sensor data, DT‑based emulation, and a predictive model within PLM workflows to achieve traceability and operator‑in‑the‑loop validation. Results show modest predictive performance, highlighting the need for feature engineering and model generalization; the paper outlines concrete improvement paths and discuss industrial adoption barriers (skills, integration, and governance). Contributions are: (i) a precise definition of PLM 5.0 and its dependencies, (ii) a modular framework integrating DT/GenAI/XAI with PLM and sustainability assessment, and (iii) a reproducible case configuration that maps each operational step to the framework. The paper concludes with open challenges in interoperability, security, and ethical governance and proposes evaluation and benchmarking directions.
Paper Nr: 42
Title:

Feature Fusion with Online Principal Component Analysis for Embedded Unsupervised Machine Monitoring
Authors:

Guillaume Prevost, Jérôme Boutet, Esteban Cabanillas and Cornel Ioana
Abstract: This paper presents a novel unsupervised incremental approach for real-time bearing health monitoring using online Principal Component Analysis (PCA) for feature fusion. The method addresses the need for memory-efficient, embedded monitoring systems that can operate without prior training data or full historical records. Time-domain features are extracted from streaming vibration signals and fused using an adaptive online PCA algorithm with exponential weighted moving averages (EWMA) and continuity corrections to ensure temporal consistency. A health index is constructed from the first principal component using a standardized CUSUM ap-proach, enabling robust detection of gradual degradation patterns. The methodology is validated on the XJTU-SY bearing dataset comprising 15 run-to-failure experi-ments under varying operating conditions. The algorithm has been successfully im-plemented on an STM32 microcontroller, demonstrating its practical viability for embedded prognostic applications in resource-constrained environments.
Paper Nr: 43
Title:

Remote Industry Supervision on Mobile Application Based on OPC UA Protocol
Authors:

Hadjer Bouzebiba, Oussama Hadj Abdelkader and Fernando Fontes
Abstract: This study introduces a lightweight, efficient, and secure architecture designed for the remote monitoring and control of Programmable Logic Controllers (PLCs). The proposed system uses the Open Platform Communications Unified Architecture (OPC UA) protocol to establish a standardized communication with a Raspberry Pi serving as an edge client able to interface industrial PLCs with other systems, facilitating both remote data acquisition and control operations. The collected data is synchronized with a real-time database, facilitating remote access through a mobile application as a human machine interface. This setup supports bidirectional communication, allowing for both monitoring and command issuance through the cloud. The proposed architecture offers a cost-effective alternative to traditional SCADA systems by emphasizing modularity, adaptability, low power consumption, real-time visualization, and cloud accessibility. Experimental evaluations demonstrate the system's responsiveness, reliability, and applicability in both industrial and educational environments.
Paper Nr: 45
Title:

Next-Gen Contextual Anomaly Detection for Sustainable and Efficient Production in Industry 4.0
Authors:

Kiavash Fathi, Marcin Sadurski, Stefan Waskow, Tobias Kleinert and Hans Wernher van de Venn
Abstract: Increasing market competitiveness is driving manufacturers to continuously adapt and optimize their production processes. Under these conditions, even marginal improvements in production asset settings can yield substantial financial benefits. However, the continuously evolving market requirements shorten the lifecycle of AI-enhanced digital assets, leading developers to primarily rely on anomaly detection-based solutions. The currently available anomaly detection models are designed to detect drastic changes in the system, such as failure and leakage, ignoring the subtle differences between ideal and suboptimal production settings. This paper proposes a novel contextual anomaly detection framework that utilizes the decision scores of a classification model trained on the reconstruction errors of an autoencoder. Contextual information from the signal reading batches of the physical asset is integrated into the classification model to improve the interpretability of the reconstruction errors. Experimental results from a production line at ABB Schweiz AG Production Plant chaffhausen demonstrate that the proposed method achieves zero false positives and false negatives, outperforming state-of-the-art solutions.
Paper Nr: 46
Title:

Toward Dynamic Flexible Job-Shop Scheduling Combining Graph Neural Networks and Deep Reinforcement Learning on Heterogeneous Graph Representations
Authors:

Marco Wölfel and Bernhard Bauer
Abstract: This position paper describes a novel approach for dynamic flexible job-shop scheduling. The proposed approach enables batched and continuous scheduling, taking into account setup times, transportation times, new job arrivals and machine breakdowns. This is achieved by using a heterogeneous graph with a graph neural network and deep reinforcement learning. The heterogeneous graph represents the relationships between operations, machines and vehicles. Reinforcement learning and the graph neural network are used to learn the embedding and ranking of nodes and sets of nodes and therefore enable the scheduling of operations. The graph representation considers that one operation can possibly be completed in different ways, and that machines and vehicles have different capabilities that can be mapped to the required capabilities of the operation and transportation requirements. The jobs are represented in a way that enables parallel execution and partially ordered operations on top of the usual sequential and totally ordered execution. The training uses multi-objective optimization to adapt the policy to the improvement of the makespan of the entire batch, the duration of a single workpiece and the cost.
Paper Nr: 52
Title:

Industrial Metaverse Architecture in the Automotive Sector
Authors:

Alexandre Parant and Yuhan Chen
Abstract: The transition from Industry 4.0 to Industry 5.0 aims to develop production systems that are more people-centered, sustainable, and resilient. An emerging concept that supports this evolution is the Industrial Metaverse, which integrates technologies such as the Industrial Internet of Things (IIoT), Big Data, and virtual environments to bridge physical and digital worlds. As this is a recent concept, few articles describe the actual application of the Industrial Metaverse. To overcome this problem, this paper presents Renault’s implementation of the Industrial Metaverse in the automotive sector, structured around a layered reference architecture. This article highlights the main challenges in implementing Industrial Metaverse, including data standardization, real-time monitoring, integrating heterogeneous systems, and exploiting augmented and virtual reality (AR/VR) technologies. Research directions are suggested to bridge the gap between the theoretical architectures of the Industrial Metaverse and the needs of manufacturers in the automotive industry.
Paper Nr: 56
Title:

A Strategic Roadmap for the Adoption and Operational Integration of Robot-Assisted Surgery in Modern Healthcare System
Authors:

Abdullah Riad, Majed Hadid, Regina Padmanabhan, Adel Elomri, Abdelfatteh El Omri, OmarM. Aboumarzouk and Abdulla Al-Ansari
Abstract: Robot-assisted surgery (RAS) has witnessed a rapid expansion in recent years, further accelerated by the emergence of Healthcare 5.0 and its enabling technolo-gies, particularly artificial intelligence. These advancements have significantly im-proved critical areas such as surgical training, image segmentation, and classifica-tion. Despite this growing adoption, healthcare institutions still lack a structured and comprehensive roadmap (RM) to guide the implementation and operational management of RAS. This study aims to develop a robust RM to support healthcare facilities in effectively integrating RAS into clinical practice. Two main research questions are addressed: (1) What are the essential requirements for suc-cessful RAS implementation? and (2) What defines a practical and reliable framework for managing RAS operations? Our analysis identified seven core pil-lars that underpin the proposed RM, grouped into four key domains: technology and infrastructure, implementation strategies and legal framework, telesurgery and emerging innovations, and training and human resources—all interdependent and critical to sustainable RAS deployment.
Paper Nr: 70
Title:

Creative Attention: Detecting Creativity Stages Through Human Attention Dynamics
Authors:

Sepideh Kalateh, Nastaran Farhadighalati, Luis A. Estrada-Jimenez, Sanaz Nikghadam-Hojjati and José Barata
Abstract: As automation accelerates and generative AI reshapes the digital landscape, creativity is emerging as one of the most valuable and uniquely human skills. A recent report identified creativity as the 1 soft skill in global demand across industries. Yet creativity does not occur in a vacuum—it is intimately shaped by our patterns of attention, emotions, characteristics, way of thinking, cultural backgrounds, etc, which govern how we explore, combine, and evaluate ideas. Recent studies in cognitive neuroscience reveal that flexible attention control—the ability to shift between focused and diffuse thinking—is a key predictor of creative insight, linking attention dynamics directly to the stages of the creative process. As a result, modelling attention has become a critical frontier in affective computing and cognitive AI, offering new pathways to understand and augment human creativity. In this work, we propose a computational framework to detect creativity stages by analyzing indicators of attention. We first examine the interplay between cognitive attention types (Focused, Defocused, Flexible, and Sustained) and creative ideation. Then, we explore computational models that infer attentional cues. Building upon this foundation, we propose a multimodal approach that combines AI with user-level interaction signals (e.g., voice cues or behavioral metadata) to predict creativity stages. We conclude with a discussion on the applicability of our method in real-world scenarios and its integration in intelligent systems.
Paper Nr: 72
Title:

Toward Cybersecure-by-Design Manufacturing Systems: A Taxonomy of Hardware-Based Approaches for Software Cybersecurity Violation Detection
Authors:

Eda Marchetti, Anikó Costa, Sanaz Nikghadam-Hojjati, José Barata and Antonello Calabrò
Abstract: The shift from Industry 4.0 to 5.0 has created highly interconnected manufacturing systems, but this expansion increases cybersecurity risks. Existing software- and hardware-based solutions are mostly reactive, which is insufficient for real-time, safety-critical environments that demand proactive and resilient protection. This paper addresses this critical gap by proposing a taxonomy of hardware-based approaches for detecting and mitigating software cybersecurity violations, grounded in cybersecure-by-design principles. The taxonomy is developed through a conceptual synthesis and comparative analysis of state-ofthe- art literature, structured across dimensions such as execution layer, security function, and design paradigm. It extends current detection-focused models by classifying approaches that embed security at the hardware level to prevent or contain threats autonomously. In doing so, it introduces a novel perspective by highlighting hardware not only as a trusted anchor but as an active defender of software integrity, thereby contributing a systematic foundation for cross-layer resilience in smart manufacturing systems. The taxonomy’s relevance is demonstrated through its application to smart manufacturing systems, highlighting its value for system designers, cybersecurity engineers, and policymakers. This contribution offers a structured foundation for developing next-generation industrial systems that are secure not only by detection, but by architecture.
Paper Nr: 30
Title:

Digital Twins in Warehousing Logistics: Trends and Insights from a Systematic Mapping Study
Authors:

Miljana Lukovic, Biljana Cvetic, Dragan Vasiljevic and Milos Danilovic
Abstract: A new era of technological advancement has led to the increasing use of Digital Twins technology across various industries and fields. The aim of this study is to examine how Digital Twin technology is used in a very specific and important field of warehousing logistics. The chosen methodology is the Systematic Mapping Study for filtering academic papers, as well as the use of non-academic sources for an industrial view. The paper scope is limited to the Google Scholar research base and free publicly available non-academic sources. The findings show academic and industrial proof of utilization of Digital Twins in ware-house logistics as well as available relevant Digital Twins software solutions. Digital Twins are being used for simulations, monitoring, testing and control of warehouse logistics operations and tasks and they can be integrated with other warehouse logistics technologies. The outcomes of this study can be valuable to logistics and supply chain professionals and to other interested parties.
Paper Nr: 32
Title:

Kubernetes-Driven Digital Twin Framework Using Asset Administration Shell for Smart Industry
Authors:

Mirco Antona, Corrado Caia, Salvatore Cavalieri, Raffaele Di Natale, Salvatore Gambadoro, Salvatore Quattropani and Simona Rossitto
Abstract: Industry 4.0 is transforming the manufacturing sector by integrating technologies like IoT, cloud computing, AI, and cyber-physical systems. Virtualization is par-ticularly strategic in this context as it allows flexibility, scalability and optimiza-tion of resources, by separating the control processes from the hardware. Digital Twins, being real-time digital representations of physical systems, are key ele-ments in Industry 4.0, supporting predictive maintenance, performance optimiza-tion and decision-making processes. Development of modular, scalable and agile industrial applications, enabling the use of advanced Digital Twins better allows to meet the challenges of Industry 4.0. Microservices architecture has become a preferred solution for the development of industrial applications. The adoption of microservices architectures, combined with virtualization and orchestration tech-nologies, represents a crucial step in the development of advanced Digital Twins, capable of evolving and adapting to the changing needs of the industrial sector. The aim of this paper is the presentation of a microservices architecture, com-bined with virtualization and orchestration technologies, used for the development of advanced Digital Twins. The paper will consider the Asset Administration Shell standard for the Digital Twin.
Paper Nr: 37
Title:

Voice-Based Collaborative Robot Interaction: A Modular, Speech-Based Interface Using LLMs

Authors:

Anna Syberfeldt and Eric Svensson
Abstract: As the boundaries between human and machine interaction continue to blur, the need for intuitive and efficient interfaces becomes increasingly pressing. In industrial settings, collaborative robots (cobots) have emerged as pivotal tools in facilitating human-machine synergy. This paper presents a comprehensive design, implementation, and evaluation of a voice-controlled cobot interface using open-source software, speech recognition technologies, and large language models (LLMs). The system enables users to issue verbal commands, obtain audio feedback, inquire about process status, and even engage in casual conversation with the robot. By leveraging modular software architecture and locally deployed LLMs, the prototype offers a scalable and user-friendly solution. The study delves into the technical underpinnings, practical limitations, and future possibilities of hands-free robotic control, offering a contribution to the evolving field of human-robot interaction.
Paper Nr: 55
Title:

Intelligent Monitoring System Integrating IoT and Machine Learning for Air Quality Detection and Control
Authors:

Edgar Onofre Ruiz, Rodrigo Carcausto and Alejandrina Huarcaya Junes
Abstract: Air pollution can originate from both natural sources, such as wildfires and volcanic eruptions, and human activities, including vehicular traffic and industrial processes. These activities release particulate matter (PM2.5, PM10) and gases like CO₂ and volatile organic compounds (VOCs) into the environment, negatively impacting health and productivity in workplace settings. In response to this issue, an intelligent system is proposed that utilizes IoT sensors and machine learning algorithms to monitor, predict, and control air quality in real time within automotive workshops. A data storage and processing architecture was implemented using Amazon Web Services (AWS), and the predictive model was trained using the Random Forest algorithm. The system also incorporates automated air filters that are activated when critical pollutant concentrations are detected. Preliminary results show high accuracy in pollutant prediction, highlighting the system’s potential to effectively monitor environmental conditions in industrial environments.
Paper Nr: 60
Title:

Cloud Technologies Driving Scalable Innovation with Strategic Governance
Authors:

Dmytro Smirnov and J. Cecil
Abstract: Cloud computing has evolved from an emerging technology to a critical business infrastructure, fundamentally transforming how organizations develop, deploy, and scale technological solutions. This comprehensive study examines the intersection of cloud adoption strategies, governance frameworks, and innovation enablement across multiple industry sectors. Through analysis of industry data, case studies from healthcare, finance, and retail sectors, and evaluation of cloud management platforms, this research demonstrates that strategic cloud governance is essential for realizing the full potential of cloud technologies. Key findings reveal that 94% of enterprises have adopted cloud computing, with 89% utilizing multi-cloud strategies to optimize performance and mitigate vendor lock-in risks [1]. Organizations implementing comprehensive governance frameworks achieve 40% faster innovation cycles while maintaining regulatory compliance and reducing operational costs by 15-30% [2]. The study also examines emerging trends including Green Cloud computing initiatives, which demonstrate potential for 30% energy cost reductions while supporting sustainability objectives [3]. This research contributes to the understanding of how strategic governance enables cloud technologies to drive scalable innovation while addressing critical challenges in security, cost management, and environmental sustainability.
Paper Nr: 61
Title:

Ontology-Driven Adaptive Manufacturing System for Real-Time CNC Turning Optimisation
Authors:

Murillo Skrzek, Anderson Szejka and Fernando Mas
Abstract: Industries must remain agile to respond to evolving market behaviours driven by fluctuating consumer demands, technological advances, and global economic uncertainties. A key challenge is integrating real-time data for agile decision-making that balances customisation, efficiency, cost, and sustainability. This paper proposes an intelligent and integrated manufacturing system that leverages sensors, artificial intelligence, and ontological knowledge layers to enable real-time reconfiguration of production parameters, specifically in CNC turning operations. The framework is based on a revised ISA-95 standard and was validated through a case study involving the turning of ABNT 8640 steel. Sensor data, including vibration and temperature, were integrated into an ontological model that interfaced with the ERP system. This integration enabled the automatic adjustment of cutting parameters in response to production contexts, including delayed orders and machine load, through an XML-based connection between the ontology and the machines’ PLCs. The model demonstrates the potential of combining heterogeneous data and computational intelligence to enhance industrial adaptability and efficiency. The revised ISA-95 standard supports system scalability and interoperability. Nonetheless, critical challenges remain, such as ensuring data reliability, achieving full system integration, and capturing tacit knowledge from experienced operators to fully realise the system’s capabilities.

Area 2 - Logistics

Full Papers
Paper Nr: 16
Title:

An Artificial General Intelligence Enabled Supply Chain Framework for CO2 Emission Reduction
Authors:

Mohammad Reza Rezaei, Sridhar Iyer, Sripathy Kathiresan Tamilselvan and Omid Fatahi Valilai
Abstract: This study explores the development of an Artificial General Intelligence (AGI) enabled framework aimed at reducing CO2 emissions globally over the supply chain. While traditional Artificial Intelligence (AI) has been instrumental in addressing inefficiencies and optimizing supply chain processes, its dependency on predefined parameters and static environments limits its adaptability. The AGI framework provides a transformative solution by autonomously learning, reasoning, and generalizing strategies across diverse supply chain scenarios, enabling dynamic decision-making and real-time optimization without human intervention. The proposed framework integrates AGI into supply chain management to enhance operational efficiency and align with sustainability goals. By leveraging AGI for clustering, dynamic routing, the study demonstrates how carbon footprints can be significantly reduced across supply chain nodes. Illustrative examples highlight AGI’s ability to identify inefficiencies, adapt to changing conditions, and foster sustainable practices, creating a flexible and scalable framework adaptable to various industries.
Paper Nr: 17
Title:

Developing an AI Enabled Operations Research Model for Adaptive, Resilience and Sustainable Dynamic Supply Chain
Authors:

Mohammad Reza Rezaei, Pranjal Nagaraj Patil, Omkar Vishwas Patil and Omid Fatahi Valilai
Abstract: In the rapidly growing global markets, supply chains are facing issues like fluctuating demand, disruptions, and sustainability pressures, making the supply chains volatile and complex. Traditional supply chain management methods fail to address the dynamics behind these issues. This paper introduces a framework designed to enable traditional OR models with dynamic adaptability, resilience, and sustainability capabilities. This framework combines existing Enterprise Resource Planning (ERP) and Robotic Process Automation (RPA) systems with AI. By leveraging AI-enabled OR models and declarative modeling, the study introduces a framework for complex decision-making. The proposed framework will dynamically identify disruptions and inefficiencies based on various parameters, and with the help of Answer Set Programming (ASP), the model will be able to make decisions based on different scenarios and provide an optimized solution. This framework will overcome the lack of real-time responsiveness in supply chains. The proposed framework will enhance operational efficiency and make supply chains adaptive, resilient, and sustainable.
Paper Nr: 18
Title:

A Surrogate Model-Based Combustion Optimization for Pellet Stoves
Authors:

Eliott Gauthey-Franet, Yinling Liu, Hind Bril El-Haouzi, Yann Rogaume and Jérémy Hugues dit Ciles
Abstract: The increasing consumption of pellets has recently driven stove manufacturers to design more efficient combustion devices. However, due to the inherent variability of biomass, the expected performance is often unmet. Therefore, we propose a surrogate model-based approach to optimize combustion for pellet stoves. To do so, we first analysed the data via Analysis of Variance (ANOVA, feature selection) and t-distributed Stochastic Neighbor Embedding (t-SNE, data visualization). Subsequently, a Gaussian Process Regression (GPR) was implemented to predict Carbon Monoxide (CO) emissions across different stove settings, leveraging its strong predictive capabilities with small datasets. Finally, performance metrics were employed to analyze the predictive accuracy of the model. Several experimental scenarios were tested. It was observed that the model is not yet able to generalize the results due to a lack of quantity and quality in the data used. However, the first results show great potential and will serve as a basis for optimizing the combustion of the pellet stove.
Paper Nr: 31
Title:

Enhancing Sustainability in Construction Management: Optimization of Workforce Planning Considering Economic, Social, and Environmental Aspects
Authors:

Ayman R. Mohammed, Majed Hadid and Roberto Baldacci
Abstract: This paper introduces a novel Mixed-Integer Linear Programming (MILP) framework for optimizing workforce allocation in multiproject construction management by integrating comprehensive Environmental, Social, and Governance (ESG) considerations and addressing temporal hiring constraints. Traditional workforce optimization approaches typically neglect dynamic workforce availability patterns and environmental impacts, limiting their applicability in contemporary regulatory contexts. To bridge this gap, the proposed ESG-enhanced model simultaneously minimizes operational costs, reduces carbon emissions from workforce mobility, ensures compliance with social constraints (including vacation scheduling and transfer limitations), and manages realistic workforce availability based on diverse hiring schedules. Computational experiments utilizing real-world data demonstrate that the developed model achieves significant cost reductions (7.9% compared to baseline). This research contributes a scalable and practical framework enabling construction firms to meet stringent ESG regulatory requirements while effectively managing temporal workforce constraints.
Paper Nr: 38
Title:

A Unified Ontology Framework for Human-Centered Digital Twins
Authors:

Kolitha Kottagaha W. M., Pantelis Karapanagiotis, Jos A. C. Bokhorst and Christos Emmanouilidis
Abstract: This paper presents a top-level ontology framework for Human-Centered Digital Twins designed to enhance semantic interoperability and reasoning in socio-technical systems. Existing ontologies are typically domain-specific, which eases coverage of a specific domain but limits cross-domain reuse and adaptability. Addressing this gap, the proposed ontology is structured around three foundational concepts: Digital Twins, Human-Centricity, and Sociotechnical System Actors within the system. The ontology was developed following established ontology engineering practices, with emphasis on modularity, reusability, and formal representation of key concepts. It supports the integration of sensor observations, interaction modalities, and representation of human-centricity factors. Its applicability is demonstrated through a logistics use case, which involves cognitive decision support for yard operators and forklift drivers engaged in short-term scheduling of yard operations. The ontology offers a reusable semantic foundation that supports integration, context representation, and human-centric system modelling and can be extended to diverse domains.
Paper Nr: 40
Title:

Mathematical Modeling of Supply Chain Resilience: Structure, Dynamics, and Indicator-Based Evaluation
Authors:

N. Rahiel, S. Addouche, A. El Mhamedi and K. Hachemi
Abstract: In an increasingly turbulent global environment, supply chains face multifaceted disruptions ranging from pandemics to geopolitical crises and climate shocks. While the concept of supply chain resilience (SCR) has gained prominence, most existing models fail to accurately capture the nonlinear, dynamic behavior of organizations facing disruption. Building on this gap, this study proposes a mathematically robust and behaviorally coherent model of resilience based on hyperbolic tangent functions. The model accounts for the complete disruption cycle (degradation, latency, recovery) and is characterized by seven interpretable parameters that enable smooth, bounded, and asymmetric performance trajectories over time. A set of six resilience indicators is derived to evaluate critical system dimensions such as cumulative loss, recovery speed, and adaptive robustness. Applied to four organizational scenarios (healthcare, manufacturing, retail, and tech startup), the model reveals distinct resilience archetypes, demonstrating its ability to differentiate strategic response profiles. A web-based interface further enables real-time evaluation and scenario planning. The proposed framework contributes a unified, customizable, and operational tool for quantitative resilience analysis, bridging the gap between conceptual models and actionable decision support in crisis management.
Paper Nr: 57
Title:

Analyzing Freight Truck Arrival Scheduling and Operations for an International Beverage Company's Warehouse
Authors:

Andres Munoz Villamizar, Jairo Montoya-Torres, Christopher Mejía-Argueta, Julian Queirolo and Daniel Hernandez
Abstract: This study examines delays in processing returned shipments at a beverage distribution center in Bogotá, Colombia. Returned trucks undergo reception, inspection, and reloading processes, which can result in congestion at the processing docks. We develop a discrete-event simulation model based on historical operational data and a focused time-and-motion study to represent the current system. Two improvement scenarios are evaluated: (1) increased verification staffing, and (2) regulated truck arrivals (i.e., arrival scheduling). Performance is assessed in terms of average turnaround time, average waiting time, processing time, queue length, resource utilization, and number of external waiting vehicles (i.e., congestion caused around the distribution center to citizens). Simulation results indicate that the addition of staff reduces truck turnaround by approximately 30%, decreases the average queue length by over 60%, and lowers peak dock utilization. Meanwhile, managed arrivals yield more consistent throughput, with a 20% reduction in waiting times and decreased variability in resource use. Both interventions enhance driver worklife balance, improve service levels, and mitigate community impacts caused by external queuing. The proposed framework offers a replicable, data-driven approach for distribution centers to mitigate dock-level bottlenecks, enabling informed decision-making on resource allocation and scheduling strategies.
Paper Nr: 62
Title:

Cost-Aware Soft-Constrained Optimization for Scenario-Driven Urban Logistics Resilience
Authors:

Pranesh Kannan M K, Snazal Singh, Anish Kirupakaran, Balasubramaniam Natarajan and Babji Srinivasan
Abstract: Urban logistics systems often face disruptions such as warehouse shutdowns, vehicle shortages, and sudden demand spikes, making it difficult to meet all customer needs. This paper presents a scenario-based optimization framework that supports resilient fulfillment planning when resources are limited. We combine two solver approaches—Linear Programming (LP) and Unbalanced Optimal Transport (UOT)—to allow partial demand fulfillment, with penalties for unmet demand. LP focuses on minimizing total cost, while UOT offers more flexible, fairness-aware delivery by relaxing strict fulfillment constraints. The framework uses a detailed cost model that includes distance, fuel usage, emissions, delays, and zone-based charges to reflect real operational conditions. Using case studies from Chennai, we compare solver performance under different disruption scenarios. Results show that LP provides low-cost solutions but may neglect high-cost zones, while UOT ensures broader coverage with more balanced allocations. The scientific novelty of this work lies in integrating soft-constrained optimization with UOT to explicitly capture trade-offs between cost efficiency and service equity under disruption—an aspect often overlooked in existing logistics models. This unified framework contributes not only a practical decision-support tool for urban planners but also a generalizable methodological advance for resilienceoriented logistics optimization. This approach helps logistics planners explore trade-offs between cost and service equity and design more robust delivery strategies under uncertain conditions.
Paper Nr: 65
Title:

Flexible CO2 Aware Routing with Real Time Smart Locker Adjustments
Authors:

Mohammed Ali Ejjanfi and Jamal Benhra
Abstract: This paper formulates a smart-locker vehicle routing problem for urban logistics in Casablanca, Marrakech, and Tangier. The study frames last-mile parcel delivery as a carbon-capped routing problem that lets vans hand parcels either to customers or to a shared locker network in Casablanca, Marrakech, and Tangier. The model combines locker choice, tour construction, and real-time customer relocation triggered after dispatch. We build a modular simulator that feeds identical city graphs, locker sets, and carbon caps to both solvers under matched time budgets, enabling a transparent comparison. Across Tangier, Marrakech, and Casablanca, PPO reduced baseline fleet emissions by 2.6–4.3% relative to ACO and, after a late locker unavailability, contained the added carbon to ~2.0% on average (2.3% in Tangier, 1.9% in Marrakech, 1.6% in Casablanca) versus ~5% for ACO (9.5%, 0.0%, and 1.5%, respectively). We disclose hyperparameters and add a runtime/hardware profile to support reproducibility and deployment.
Short Papers
Paper Nr: 12
Title:

Simulating Safety Measures, and Protocols, in Air Cargo Handling and Optimize Air Cargo Unit Load Device
Authors:

Saeedeh Khalilpour, Roaa Al Shidi, Mehdi A. Kamran and Sana Nabati
Abstract: This study aims to improve safety and efficiency in air cargo handling by comparing manual and automated processes and optimizing the use of unit load devices (ULDs). Air cargo plays a major role in global trade, but handling cargo safely and efficiently presents many challenges. Safety protocols and efficient use of ULDs are important to avoid risks, protect goods and people, and reduce transportation costs. Using Arena simulation software, this study tests the effects of different safety measures and handling methods. It also uses an Excel-based Cargo Loading Problem (CLP) solver to optimize how cargo is packed in containers, helping to maximize space and balance weight. The results show that automated handling processes are faster and safer than manual ones, reducing the chance of accidents and delays. This study fills a gap in the literature by combining simulation and optimization to provide a complete approach to enhancing safety and efficiency in air cargo operations.
Paper Nr: 25
Title:

Fair Profit Allocation Methods in Horizontal Logistics Cooperation: A Systematic Review
Authors:

Rebecca Kißner, Stefan Senftleben, Liselotte Burger and Rainer Lasch
Abstract: Cooperation is a common practice in logistics, as it optimizes routes and reduces costs through joint freight transportation. Nevertheless, incentives such as the fair distribution of profits between companies are essential to maintaining such cooperation. This study provides an overview of relevant profit allocation mechanisms for sustaining long-term cooperation in logistics by reviewing recently published studies on horizontal cooperation in transport logistics. Thus, the paper describes relevant profit distribution methods and their application in transport logistics and examines the role of optimized transport planning as a prerequisite for profitable cooperation.
Paper Nr: 28
Title:

When Machines Fail: Online Scheduling Under Bounded Failures
Authors:

Christine Markarian and Alavikunhu Panthakkan
Abstract: Smart manufacturing systems operate in increasingly dynamic environments, where machines may experience unexpected failures and recoveries during operation. These disruptions pose a fundamental challenge to real-time scheduling, which must proceed without foreknowledge of future jobs or machine outages. In this paper, we introduce a new online scheduling model that incorporates bounded-delay machine failures—unlike classical online scheduling, which assumes static machine availability. Jobs arrive over time and must be assigned immediately to currently available machines. Our objective is to minimize makespan while ensuring resilience to temporary unavailability. We design failure-aware online algorithms and prove competitive bounds relative to an optimal offline scheduler. Our results establish a theoretical foundation for robust, real-time scheduling in failure-prone Industry 4.0 systems.
Paper Nr: 63
Title:

Truck-UAV Joint Distribution Route Optimization Model with Dynamic Recycling in New Retail Scenarios

Authors:

Yiting Wang, Xinran Wang, Haixiao Guo, Jiaxin Bian, Xiaohui Ma and Xinmeng Wang
Abstract: In big data-driven new retail, the reconstruction of "people, goods, marketplaces" has fostered online-offline integration and intelligent services, spurring a surge in consumers' demand for "instant delivery". However, traditional logistics faces three core bottlenecks: static capacity scheduling fails to adapt to urban traffic's spatiotemporal dynamics, such as peak-hour UAV takeoff/ landing congestion and redundant truck stays; short-distance delivery relies on the "UAV-truck-UAV" transfer link, causing poor timeliness; and no unified framework quantifies transportation, time, and carbon emission costs, hindering multi-objective optimization balance. To address these, this paper proposes a truck-UAV joint distribution route optimization model with dynamic recycling. Methodologically, it builds a "time-phased & zone-divided" dynamic recycling framework where UAVs operate at dedicated points during peak hours and return to original trucks during off-peak periods; develops a UAV short-distance direct delivery mode that eliminates truck transfers for merchant-customer short-distance orders; introduces dynamic battery consumption functions and time-sensitive coefficients to quantify the three costs; and designs a hybrid heuristic algorithm integrated with machine learning for screening high-quality solutions and deep learning for optimizing initial populations to solve the "task-route" combinatorial explosion in dynamic scenarios. The main contributions include overcoming traditional static recycling limits to adapt to new retail's temporal variability; simplifying short-distance links to meet instantaneity demands; establishing a unified multi-cost quantification model that transforms multi-objective optimization into weighted total costs minimization.
Paper Nr: 64
Title:

A New Improved Algorithm for a Rich Production and Routing Problem
Authors:

Mário Leite, Telmo Pinto and Cláudio Alves
Abstract: This paper addresses a rich integrated combinatorial optimization problem designated by Production Routing Problem (PRP) inspired by the real-world case study. The PRP involves coordinating production and distribution decisions over a finite planning horizon, divided into periods, for multiple products characterized by heterogeneous attributes, such as weight, size, and number of components. This PRP incorporates several constraints, including sequence-dependent setups, safety stocks and limited production capacity, multi-period routing, and customers with multiple time windows and deadlines. The objective is to minimize the total cost, which comprises setup costs, inventory holding, and transportation expenses. This integration of production and distribution decisions introduces temporal and spatial interdependencies which make the problem NPhard. To tackle this problem, we propose a hybrid approach that combines a Variable Neighborhood Search metaheuristic with an embedded Integer Programming model. The proposed approach is evaluated through extensive computational experiments on benchmark instances, demonstrating its effectiveness in solving the PRP and handling its inherent combinatorial complexity.
Paper Nr: 67
Title:

Circular Business Models for Logistic Service Providers
Authors:

Francesco Cafforio, Roberto Cerchione, Ilaria Giannoccaro, Giovanni Massari, Mariarosaria Morelli and Viviana Sicardi
Abstract: Logistic Service Providers (LSPs) are central actors in advancing the Circular Economy (CE) due to their pivotal role in managing material, information, and service flows across supply chains. Yet, how LSPs are integrating CE principles into their business models remains underexplored. This study addresses this gap by identifying and analyzing Circular Business Model (CBM) archetypes adopted by LSPs. Drawing on a multiple-case study approach involving 27 global LSPs, we conduct a qualitative content analysis of GRIaligned sustainability reports and complementary firm documents. Our findings reveal four distinct CBM archetypes: (1) \emph{efficiency optimization business models}, focused on minimizing emissions and resource use through digital innovation, representing evolutionary business model innovation (BMI); (2) \emph{reverse logistics business models}, enabling post-use material recovery and reintegration, aligned with adaptive BMI; (3) \emph{asset life-extending business models}, combining adaptive and focused BMIs to preserve infrastructure and vehicle lifespan via predictive maintenance; and (4) \emph{service-based logistics business models}, involving complex BMI that reconfigures logistics through sharing platforms and access-based services. The novelty of this study lies in developing the first typology of CBMs tailored to the logistics sector, clarifying how circularity is operationalized in a domain often overlooked by CBM research. The study contributes to CE and business model literature by clarifying how LSPs operationalize circularity and provides actionable guidance for logistics managers navigating sustainability transitions.
Paper Nr: 15
Title:

Innovation in Logistics Management: Systems Adapted to SMEs
Authors:

Emanuel Jankovic and Dumitru Tucu
Abstract: The paper investigates innovations in logistics management being tailored to small and medium-sized enterprises (SMEs), given their critical importance in the global economy. SMEs in the Romanian market represent a significant share of job creation and economic output, but face unique challenges in implementing efficient logistics systems. In this paper I propose a way in which management software programs can be adapted for SMEs, this research aims to develop a clear methodology to help SMEs improve their logistics performance by addressing specific needs and capitalizing on innovative practices. The proposed methodology includes an assessment of SME needs and establishes customized solutions resulting from the identification of an acute lack of centralized management system, that allow different departments to access data and the necessary steps for the actual implementation of a management system created from scratch and the milestones required for a successful implementation. Also the increased needs of the consumers put pressures for fast deliveries, stock accuracy and customized services require streamlined logistics processes, all of these factors are producing large quantity of waste and a reduced efficiency. The results and conclusions are presented through quantitative and qualitative data, highlighting the positive impact these solutions can have on SME competitiveness. Therefore, the future of logistics is shaped by technology integration, sustainability, market dynamics and efficient risk management, which are essential elements for the development of flexible, high-performance and customer-oriented logistics systems.
Paper Nr: 71
Title:

A Systems Approach to Evaluating AI Agent Risks in AI-Based Planning and Collaborative Supply Chains
Authors:

Javad Jassbi, Roozbeh Aliabadi and José Barata
Abstract: Artificial Intelligence (AI) agents are increasingly embedded in collaborative supply chains, introducing not only opportunities for efficiency but also systemic risks. This paper develops a systems-based framework for evaluating AI-agent risks by integrating DEMATEL and System Dynamics. The study identifies eight interdependent risk categories, including autonomy overreach, trust erosion, ethical misalignment, and governance gaps. Through expert input and simulation modeling, we demonstrate how certain risks function as causal drivers, while others act as amplifiers in cascading effects. Results show that autonomy overreach and ethical misalignment are the most influential risks, while proactive governance mechanisms significantly mitigate their impact. Contributions of this paper are threefold: (i) mapping AI-agent risks within collaborative supply chains, (ii) developing a hybrid DEMATEL–System Dynamics framework for systemic risk evaluation, and (iii) simulating governance strategies to inform resilient policy and decision-making.