Mobile robots, becoming increasingly autonomous, are capable of operating in diverse and unknown environments. This flexibility allows them to fulfill goals independently and adapting their actions dynamically without rigidly predefined control codes. However, their autonomous behavior complicates guaranteeing safety and reliability due to the limited influence of a human operator to accurately supervise and verify each robot’s actions. To ensure autonomous mobile robot’s safety and reliability, which are aspects of dependability, methods are needed both in the planning and execution of missions for autonomous mobile robots. In this article, a twofold approach is presented that ensures fault removal in the context of mission planning and fault prevention during mission execution for autonomous mobile robots. First, the approach consists of a concept based on formal verification applied during the planning phase of missions. Second, the approach consists of a rule-based concept applied during mission execution. A use case applying the approach is presented, discussing how the two concepts complement each other and what contribution they make to certain aspects of dependability.

Explicit modeling of capabilities and skills – whether based on ontologies, Asset Administration Shells, or other technologies – requires considerable manual effort and often results in representations that are not easily accessible to Large Language Models (LLMs). In this work-in-progress paper, we present an alternative approach based on the recently introduced Model Context Protocol (MCP). MCP allows systems to expose functionality through a standardized interface that is directly consumable by LLM-based agents. We conduct a prototypical evaluation on a laboratory-scale manufacturing system, where resource functions are made available via MCP. A general-purpose LLM is then tasked with planning and executing a multi-step process, including constraint handling and the invocation of resource functions via MCP. The results indicate that such an approach can enable flexible industrial automation without relying on explicit semantic models. This work lays the basis for further exploration of external tool integration in LLM-driven production systems.

Modern automation systems increasingly rely on modular architectures, with capabilities and skills as one solution approach. Capabilities define the functions of resources in a machine-readable form and skills provide the concrete implementations that realize those capabilities. However, the development of a skill implementation conforming to a corresponding capability remains a time-consuming and challenging task. In this paper, we present a method that treats capabilities as contracts for skill implementations and leverages large language models to generate executable code based on natural language user input. A key feature of our approach is the integration of existing software libraries and interface technologies, enabling the generation of skill implementations across different target languages. We introduce a framework that allows users to incorporate their own libraries and resource interfaces into the code generation process through a retrieval-augmented generation architecture. The proposed method is evaluated using an autonomous mobile robot controlled via Python and ROS 2, demonstrating the feasibility and flexibility of the approach.

Capability ontologies are increasingly used to model functionalities of systems or machines. The creation of such onto-logical models with all properties and constraints of capabilities is very complex and can only be done by ontology experts. However, Large Language Models (LLMs) have shown that they can generate machine-interpretable models from natural language text input and thus support engineers / ontology experts. Therefore, this paper investigates how LLMs can be used to create capability ontologies. We present a study with a series of experiments in which capabilities with varying complexities are generated using different prompting techniques and with different LLMs. Errors in the generated ontologies are recorded and compared. To analyze the quality of the generated ontologies, a semi-automated approach based on RDF syntax checking, OWL reasoning, and SHACL constraints is used. The results of this study are very promising because even for complex capabilities, the generated ontologies are almost free of errors.

To achieve a flexible and adaptable system, capabil-ity ontologies are increasingly leveraged to describe functions in a machine-interpretable way. However, modeling such complex ontological descriptions is still a manual and error-prone task that requires a significant amount of effort and ontology expertise. This contribution presents an innovative method to automate capability ontology modeling using Large Language Models (LLMs), which have proven to be well suited for such tasks. Our approach requires only a natural language description of a capability, which is then automatically inserted into a predefined prompt using a few-shot prompting technique. After prompting an LLM, the resulting capability ontology is automatically verified through various steps in a loop with the LLM to check the overall correctness of the capability ontology. First, a syntax check is performed, then a check for contradictions, and finally a check for hallucinations and missing ontology elements. Our method greatly reduces manual effort, as only the initial natural language description and a final human review and possible correction are necessary, thereby streamlining the capability ontology generation process.

In order to react efficiently to changes in production, resources and their functions must be integrated into plants in accordance with the plug and produce principle. In this context, research on so-called capabilities and skills has shown promise. However, there are currently two incompatible approaches to modeling capabilities and skills. On the one hand, formal descriptions using ontologies have been developed. On the other hand, there are efforts to standardize submodels of the Asset Administration Shell (AAS) for this purpose. In this paper, we present ongoing research to connect these two incompatible modeling approaches. Both models are analyzed to identify comparable as well as dissimilar model elements. Subsequently, we present a concept for a bidirectional mapping between AAS submodels and a capability and skill ontology. For this purpose, two unidirectional, declarative mappings are applied that implement transformations from one modeling approach to the other - and vice versa.

Heterogeneous teams of autonomous robots offer a number of benefits for a variety of applications. But deploying such robots is a complex task that requires machine-interpretable descriptions in order to be flexible and adaptable. Formal descriptions in the form of ontologies are increasingly used to describe the functions of such autonomous robots in the form of capabilities and skills. However, these ontological descriptions and a corresponding invocation interface for skills need to be created, causing additional efforts for developers which are complex, time-consuming and error-prone. This contribution presents a Python framework that automates all these additional efforts. It supports a developer in implementing functionalities as skills by having them program only the skill behavior. The framework automatically takes care of generating a standardized state machine, an invocation interface and an ontological description. The presented framework can be used to implement arbitrary functionalities as skills using Python. This is demonstrated using two different evaluation case studies: a simplified behavior of a mobile robot as well as a machine learning algorithm used as an analytical skill for quality control. Both are integrated into an existing skill execution system and can interact with other skills based on their ontological description.

Current challenges of the manufacturing industry require modular and changeable manufacturing systems that can be adapted to variable conditions with little effort. At the same time, production recipes typically represent important company know-how that should not be directly tied to changing plant configurations. Thus, there is a need to model general production recipes independent of specific plant layouts. For execution of such a recipe however, a binding to then available production resources needs to be made. In this contribution, we select a suitable modeling language to model and execute such recipes. Furthermore, we present an approach to solve the issue of recipe modeling and execution in modular plants using semantically modeled capabilities and skills as well as BPMN. We make use of BPMN to model production recipes using capability processes, i.e. production processes referencing abstract descriptions of resource functions. These capability processes are not bound to a certain plant layout, as there can be multiple resources fulfilling the same capability. For execution, every capability in a capability process is replaced by a skill realizing it, effectively creating a skill process consisting of various skill invocations. The presented solution is capable of orchestrating and executing complex processes that integrate production steps with typical IT functionalities such as error handling, user interactions and notifications. Benefits of the approach are demonstrated using a flexible manufacturing system.

Semantic technologies such as ontologies are increasingly used to describe the functions of machines in the form of so-called capabilities or skills. Ontologies provide powerful mechanisms to infer new knowledge, but there are no builtin mechanisms to test the presence of information which is needed by other systems, e.g. for skill execution. In this contribution, we show how the Shapes Constraint Language (SHACL) can be used in order to formulate constraints against skills. Such constraints contain all mandatory information and can be used to check the validity of new skills when they are added into an existing production system. This ensures interoperability of skills from different manufacturers as wrongfully modelled skills that lack certain information can be discarded and marked for revision.

Manufacturing companies face an environment that is dominated by influences which affect the usage of their manufacturing equipment. Trends like shortening life cycles of products, increasing numbers of product variants and the resulting decrease in lot sizes put pressure on companies' operations. Existing machines have to be adaptable to provide a high degree of flexibility and new machines have to be easily integrated into an existing plant in a plug and produce fashion. Research contributions that focus on a higher level description of machine functionalities are seen as a promising approach to cope with the aforementioned challenges. While there exists quite a large amount of contributions on this topic, these contributions focus either on formal models or on executable functions. The developed models mostly represent project specific contents and are rarely based on industry standards. In this contribution, we present an approach to a formal model of machine capabilities that directly includes a description of executable skills. The presented capability and skill model is based on a variety of separate so-called ontology design patterns that contain the vocabulary of industry standards and therefore provide a profound knowledge which is agreed upon by a large community. In addition to the description of our model, this contribution shows how these models can be used in order to achieve simple and rapid integration of new manufacturing modules and their capabilities.