Publications
All project outputs are openly available on our Zenodo community page . We publish publications, deliverables, and other materials there as they are completed. Feel free to explore the collection, it’s the most comprehensive overview of our research results in one place.
Digital Twins and World Models: A Systematic Taxonomic Disambiguation
Although often conflated, Digital Twins and World Models represent distinct paradigms of system reasoning. A Digital Twin is defined by a persistent, bidirectional data coupling with a specific physical asset. Conversely, a World Model captures environmental dynamics to support prediction and planning, without necessitating a direct link to a singular physical counterpart. This paper establishes a rigorous disambiguation for researchers and practitioners in the Physical AI realm. We define minimal criteria for each paradigm, compare them via a multidimensional taxonomy, and validate the framework using concrete real–world systems. Our analysis demonstrates that neither paradigm subsumes the other. Rather, they intersect within a bounded convergence zone where specific architectures integrate both. While this taxonomy is descriptive and integrative, we note that formal ontological grounding remains an avenue for future work.
Towards an LLM-powered expert system for AAS-based product digital twin development
Manufacturing-as-a-Service (MaaS) is emerging as a cornerstone of Industry 4.0 and 5.0, enabling production requesters and providers to orchestrate manufacturing and supply chain processes as interoperable digital services. At the core of this paradigm are Product Digital Twins (PDTs), which extend beyond virtual representations of physical assets to encompass the entire product lifecycle—from design and configuration to maintenance, recycling, and sustainability compliance. This paper presents an initial conceptual approach to a Large Language Model (LLM)-powered expert system engineered to support Asset Administration Shell (AAS)-based PDT development within a MaaS ecosystem, supporting domain experts in creating and deploying PDTs and enhancing manufacturing resilience.
The RAASCEMAN Approach: Resilient and Adaptive Supply Chains for Capability-based Manufacturing as a Service Networks
The Manufacturing-as-a-Service (MaaS) model has been proposed by the research community and has been given significant attention by the industry as it holds the promise for agility and resilience of production networks. This work aims to enable companies to mitigate both short- and medium-term unforeseen events and support participation in dynamic MaaS networks. Five research objectives are discussed: 1) actionable propositions for adapting supply chains or internal production; 2) dynamic supply chain generation; 3) building trust in MaaS networks; 4) dynamic planning and scheduling of production processes; 5) dynamic assembly and disassembly. Moreover, a novel digital platform for implementing and integrating these objectives is presented, with empirical validation ongoing in two industrial pilots.
Isaac Sim Integrated Digital Twin For Feasibility Checks In Skill-based Engineering
Skill-based engineering is an approach to encapsulating the complexity of control software into reusable and parametrisable components. Digital Twin (DT) technologies can be applied to predict the future behavior of the skills, enabling feasibility checks for specific action requests. In this work, we introduce a methodology for combining NVIDIA’s Isaac Sim framework for high-quality DT-based simulations with an interoperable control component integration based on ROS and OPC UA. Furthermore, we demonstrate skill-based robot feasibility checks, which apply physical control (Hardware-in-the-Loop), virtual control (Software-in-the-Loop) as well as combinations of both.
Towards engineering product digital twins for industry 5.0: definition and modeling approach
The vision of Industry 5.0 builds upon the advanced technologies of Industry 4.0, aligning its emerging concepts with three key pillars: human-centricity, sustainability, and resilience. In this context, the idea of the Product Digital Twin (PDT), first introduced in 2002, which has further matured (and refined) by the Asset Administration Shell (AAS) standard, must continue evolving to integrate the vision of Digital Product Passport (DPP) as promoted via several initiatives from the European Commission. Moreover, positioning PDT correctly within this broader context of Industry 5.0 is crucial, as it involves the modeling and implementation of PDT instances, which then significantly influence manufacturing applications. To address this need, this paper first harmonizes different PDT definitions and then proposes a modeling and deployment approach appropriate to the new concept of PDT information models
The Role of Technical Documentation in Enabling Automated Generation of Machine Capabilities
To meet the dynamic demands of Industry 4.0, manufacturing systems require enhanced adaptability and interoperability, particularly in light of the transition from Machinery Directive 2006/42/EC to Machinery Regulation 2023/1230/EU. This transition emphasizes the need for machine-readable and digital documentation standards. However, integrating these standards with capability modeling frameworks such as the Capability-Skill-Service model (CSS model), the Open Platform Communications Unified Architecture (OPC UA) and the Asset Administration Shell (AAS) remains challenging, which limits seamless interoperability and dynamic reconfiguration. This paper addresses these issues by presenting a methodology to automate capability generation using large language models. This approach standardizes technical documentation and bridges gaps through automation. Aligning the CSS model with the OPC UA and AAS frameworks enables integration into Manufacturing-as-a-Service platforms, driving innovation and efficiency in modern manufacturing ecosystems.
Capability Determination in Manufacturing Using Historical Data
The increasing dynamics and complexity of today’s manufacturing environments require greater flexibility and resilience to meet the demands of producing multi-variant products, including batch size one, with minimal additional effort. The Capability, Service and Skill Model provides an answer to this problem by decoupling processes and the resources used. However, especially small and medium-sized enterprises face the challenge of systematically modeling their machines and systems in terms of capabilities and skills, as the required knowledge is often not available in a structured form and is often tied to individual key personnel. To ensure a consistent and practical description of capabilities, a method based on historical data is proposed to help companies integrate their manufacturing resources into a networked system of manufacturing service providers. On this basis, historical manufacturing features are systematically examined to evaluate the potential to use them to determine capabilities.
Composing Relative Spatial Location Models in Skill-based Robotic Reconfigurable Cyber-Physical Production Modules
Skill-based robotic reconfigurable cyber-physical production modules (RCPPMs) have an aggregated structure, and their functionality depends on the submodules and components that define their current topology. This application-oriented paper proposes a method for integrating the OPC UA Relative Spatial Location (RSL) Companion Specification models and the ROS2 tf2-library functionality to automatically update the SRL models of the RCPPMs when their structure changes. This enables the proper composition and sharing of the necessary information regarding the kinematic structure of each RCPPM’s submodule. On an example, we illustrate how this approach can be employed to enhance the coupling functionality of the skill-based robotic RCPPMs.
Towards OPC UA over Shared Memory as an Open Intra-Host Middleware for Automation Software
The increasing virtualization of automation software and its decoupling from hardware introduces a significant change in industrial automation. This transition allows classical operational technology software instances, such as programmable logic controllers, to coexist on the same host system alongside applications from various domains. Such coexistence offers substantial potential for a more efficient interconnection between applications from different areas, overcoming typical limitations associated with conventional interfaces. However, current middleware solutions for automation applications are often proprietary and not standardized. In this paper, we present an initial concept for an intra-host middleware based on the OPC Unified Architecture, employing a centralized data directory combined with a shared memory-based transport mechanism. The proposed concept aims to enable efficient, low-latency, and scalable communication, thereby facilitating seamless interaction between diverse automation applications and promoting the use of microservice architectures.