Felix Ocker
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Felix Ocker has a total of 29 co-authors. Here are the top co-authors by number of shared publications:
- Birgit Vogel-Heuser
Technical University of Munich
8 shared publications Birgit Vogel-Heuser
Institute of Automation and Information Systems, Department of Mechanical Engineering, TUM School of Engineering and Design, Core Member of MDSI and Member of MIRMI , Technical University of Munich , Munich , Germany
2 shared publications- André Kraft
BMW AG , Lilienthalallee 25, 80788 München , Germany
1 shared publication - Antonello Ceravola
Honda Research Institute Europe
1 shared publication - Bernd Vojanec
WITTENSTEIN SE, Zentrale Forschung & Entwicklung , Igersheim , Germany
1 shared publication - Chao Wang
Honda Research Institute Europe, Offenbach/Main, Germany
1 shared publication
Latest Publications
- Top Cited PapersOpen Access
- 2 May 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-10
LaMI: Large Language Models for Multi-Modal Human-Robot Interaction
This paper presents an innovative large language model (LLM)-based robotic system for enhancing multi-modal human-robot interaction (HRI). Traditional HRI systems relied on complex designs for intent estimation, reasoning, and behavior generation, which were resource-intensive. In contrast, our system empowers researchers and practitioners to regulate robot behavior through three key aspects: providing high-level linguistic guidance, creating "atomic actions" and expressions the robot can use, and offering a set of examples. Implemented on a physical robot, it demonstrates proficiency in adapting to multi-modal inputs and determining the appropriate manner of action to assist humans with its arms, following researchers’ defined guidelines. Simultaneously, it coordinates the robot’s lid, neck, and ear movements with speech output to produce dynamic, multi-modal expressions. This showcases the system’s potential to revolutionize HRI by shifting from conventional, manual state-and-flow design methods to an intuitive, guidance-based, and example-driven approach. Supplementary material can be found at https://hri-eu.github.io/Lami/
- 2 May 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-10
Top Cited PapersOpen AccessLaMI: Large Language Models for Multi-Modal Human-Robot Interaction
This paper presents an innovative large language model (LLM)-based robotic system for enhancing multi-modal human-robot interaction (HRI). Traditional HRI systems relied on complex designs for intent estimation, reasoning, and behavior generation, which were resource-intensive. In contrast, our system empowers researchers and practitioners to regulate robot behavior through three key aspects: providing high-level linguistic guidance, creating "atomic actions" and expressions the robot can use, and offering a set of examples. Implemented on a physical robot, it demonstrates proficiency in adapting to multi-modal inputs and determining the appropriate manner of action to assist humans with its arms, following researchers’ defined guidelines. Simultaneously, it coordinates the robot’s lid, neck, and ear movements with speech output to produce dynamic, multi-modal expressions. This showcases the system’s potential to revolutionize HRI by shifting from conventional, manual state-and-flow design methods to an intuitive, guidance-based, and example-driven approach. Supplementary material can be found at https://hri-eu.github.io/Lami/
- Open Access
- 29 February 2024
- Published by Walter de Gruyter GmbH in at - Automatisierungstechnik
- Vol. 72 (3) , 214-231
Erstellung und Integration von Verwaltungsschalen aus Heterogenen Datenquellen
Zusammenfassung: Heterogene Datenquellen und inkonsistente Schnittstellen zwischen verschiedenen Ingenieursdisziplinen stellen eine enorme Herausforderung bei der Erstellung einer virtuellen Repräsentation eines realen Produkts, Anlage oder Prozesses dar. Zu dieser digitalen Darstellung wird die Verwaltungsschale (VWS) als ein standardisiertes Konzept vorgeschlagen. Jedoch erfordert die VWS-Erstellung oft erheblichen manuellen Aufwand, um Informationen aus technischen Engineering- und Betriebsdaten zu extrahieren und zu strukturieren. Der folgende Beitrag schlägt einen semi-automatisierten Ansatz zur Extraktion von Engineering-Informationen aus Dokumenten der Formate PDF, STP, XML, AML sowie URDF vor, um anhand dieser Informationen mehrere VWS zu erstellen, die zusammengeführt werden können. Anhand dreier Anwendungsfälle werden die Möglichkeiten und Grenzen des Ansatzes diskutiert.
- 29 February 2024
- Published by Walter de Gruyter GmbH in at - Automatisierungstechnik
- Vol. 72 (3) , 214-231
Open AccessErstellung und Integration von Verwaltungsschalen aus Heterogenen Datenquellen
Zusammenfassung: Heterogene Datenquellen und inkonsistente Schnittstellen zwischen verschiedenen Ingenieursdisziplinen stellen eine enorme Herausforderung bei der Erstellung einer virtuellen Repräsentation eines realen Produkts, Anlage oder Prozesses dar. Zu dieser digitalen Darstellung wird die Verwaltungsschale (VWS) als ein standardisiertes Konzept vorgeschlagen. Jedoch erfordert die VWS-Erstellung oft erheblichen manuellen Aufwand, um Informationen aus technischen Engineering- und Betriebsdaten zu extrahieren und zu strukturieren. Der folgende Beitrag schlägt einen semi-automatisierten Ansatz zur Extraktion von Engineering-Informationen aus Dokumenten der Formate PDF, STP, XML, AML sowie URDF vor, um anhand dieser Informationen mehrere VWS zu erstellen, die zusammengeführt werden können. Anhand dreier Anwendungsfälle werden die Möglichkeiten und Grenzen des Ansatzes diskutiert.
- Open Access
- 27 November 2021
- Published by Walter de Gruyter GmbH in at - Automatisierungstechnik
- Vol. 69 (12) , 1026-1039
An approach for leveraging Digital Twins in agent-based production systems
To cope with individualization and the high costs of downtimes, modern production systems should be flexible, adaptable, and resilient. Multi-Agent Systems are suitable to address these requirements by decentralizing production systems. However, the agent paradigm is still not widely applied. One of the key reasons is that the agents’ knowledge bases had to be created manually, which is cumbersome, error-prone, and insufficiently standardized. Digital Twins have the potential to solve this issue, as they describe relevant information in a standardized way. This paper presents an approach to leveraging Digital Twins, i. e., the Asset Administration Shell, to realize Multi-Agent Systems in the production context. For this, a parser automatically extracts relevant information from the Digital Twins and initializes the individual agents in a Multi-Agent System, i. e., PADE.
- 27 November 2021
- Published by Walter de Gruyter GmbH in at - Automatisierungstechnik
- Vol. 69 (12) , 1026-1039
Open AccessAn approach for leveraging Digital Twins in agent-based production systems
To cope with individualization and the high costs of downtimes, modern production systems should be flexible, adaptable, and resilient. Multi-Agent Systems are suitable to address these requirements by decentralizing production systems. However, the agent paradigm is still not widely applied. One of the key reasons is that the agents’ knowledge bases had to be created manually, which is cumbersome, error-prone, and insufficiently standardized. Digital Twins have the potential to solve this issue, as they describe relevant information in a standardized way. This paper presents an approach to leveraging Digital Twins, i. e., the Asset Administration Shell, to realize Multi-Agent Systems in the production context. For this, a parser automatically extracts relevant information from the Digital Twins and initializes the individual agents in a Multi-Agent System, i. e., PADE.
- Open Access
- 16 August 2021
- Published by The Royal Society in Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences
- Vol. 379 (2207) , 20200368
Potential for combining semantics and data analysis in the context of digital twins
Modern production systems can benefit greatly from integrated and up-to-date digital representations. Their applications range from consistency checks during the design phase to smart manufacturing to maintenance support. Such digital twins not only require data, information and knowledge as inputs but can also be considered integrated models themselves. This paper provides an overview of data, information and knowledge typically available throughout the lifecycle of production systems and the variety of applications driven by data analysis, expert knowledge and knowledge-based systems. On this basis, we describe the potential for combining data analysis and knowledge-based systems in the context of production systems and describe two feasibility studies that demonstrate how knowledge-based systems can be created using data analysis. This article is part of the theme issue ‘Towards symbiotic autonomous systems’.
- 16 August 2021
- Published by The Royal Society in Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences
- Vol. 379 (2207) , 20200368
Open AccessPotential for combining semantics and data analysis in the context of digital twins
Modern production systems can benefit greatly from integrated and up-to-date digital representations. Their applications range from consistency checks during the design phase to smart manufacturing to maintenance support. Such digital twins not only require data, information and knowledge as inputs but can also be considered integrated models themselves. This paper provides an overview of data, information and knowledge typically available throughout the lifecycle of production systems and the variety of applications driven by data analysis, expert knowledge and knowledge-based systems. On this basis, we describe the potential for combining data analysis and knowledge-based systems in the context of production systems and describe two feasibility studies that demonstrate how knowledge-based systems can be created using data analysis. This article is part of the theme issue ‘Towards symbiotic autonomous systems’.
- 1 January 2020
- Published by Elsevier in IFAC-PapersOnLine
- Vol. 53 (2) , 8217-8224
A concept for fault diagnosis combining Case-Based Reasoning with topological system models
- 1 January 2020
- Published by Elsevier in IFAC-PapersOnLine
- Vol. 53 (2) , 8217-8224
A concept for fault diagnosis combining Case-Based Reasoning with topological system models
- Open Access
- 29 July 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 4 (4) , 4330-4337
A Framework for Automatic Initialization of Multi-Agent Production Systems Using Semantic Web Technologies
Mass customization and global competition require Cyber-Physical Systems of Systems (CPSoS) to become increasingly flexible. Modern CPSoS have to be able to create a wide and versatile variety of products, which takes centralized approaches to their limits. In addition, they have to produce these products as quickly as possible. Hence, they must be able to react promptly if problems arise, such as the failure of a single machine. Modern agent-based production systems provide the flexibility required to cope with these challenges. While resource agents (RAs) represent the available resources, i.e., machines, such as robots, individual customer orders can be represented by so-called product agents (PAs). However, a challenge in the design of agent-based production systems is still the amount of communication and computation that is necessary online. The PAs have to communicate their requests and the RAs their capabilities and capacities. On this basis, PAs must compute the appropriate production sequence. We propose to automatically initialize every agent with a knowledge base (KB) created a priori using semantic web technologies (SWT). On the one hand, the KBs of RAs describe the RAs’ capabilities in terms of product features and production processes. Every KB of a PA, on the other hand, expresses all possible production sequences based on the customer specification and the CPSoS in question. This allows consistency checks regarding the specification as well as more purposeful communication that focuses on aspects that actually need to be determined at runtime, such as the resources’ current capacities or failures. The framework presented aims to reduce both the communication and computational load necessary at runtime for agent-based CPSoS.
- 29 July 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 4 (4) , 4330-4337
Open AccessA Framework for Automatic Initialization of Multi-Agent Production Systems Using Semantic Web Technologies
Mass customization and global competition require Cyber-Physical Systems of Systems (CPSoS) to become increasingly flexible. Modern CPSoS have to be able to create a wide and versatile variety of products, which takes centralized approaches to their limits. In addition, they have to produce these products as quickly as possible. Hence, they must be able to react promptly if problems arise, such as the failure of a single machine. Modern agent-based production systems provide the flexibility required to cope with these challenges. While resource agents (RAs) represent the available resources, i.e., machines, such as robots, individual customer orders can be represented by so-called product agents (PAs). However, a challenge in the design of agent-based production systems is still the amount of communication and computation that is necessary online. The PAs have to communicate their requests and the RAs their capabilities and capacities. On this basis, PAs must compute the appropriate production sequence. We propose to automatically initialize every agent with a knowledge base (KB) created a priori using semantic web technologies (SWT). On the one hand, the KBs of RAs describe the RAs’ capabilities in terms of product features and production processes. Every KB of a PA, on the other hand, expresses all possible production sequences based on the customer specification and the CPSoS in question. This allows consistency checks regarding the specification as well as more purposeful communication that focuses on aspects that actually need to be determined at runtime, such as the resources’ current capacities or failures. The framework presented aims to reduce both the communication and computational load necessary at runtime for agent-based CPSoS.
- Open Access
- 26 July 2019
- Published by Cambridge University Press (CUP) in Proceedings of the Design Society: International Conference on Engineering Design
- Vol. 1 (1) , 1045-1054
A Pragmatic Approach Towards Leveraging Employee Competences by Use of Semantic Web Technologies
Global competition in combination with the increasing specialization of labor requires organizations to leverage their employees' competences. The approach presented in this paper empowers organizations to do so in two ways. First, we give employers a lean tool to allocate their employees to current and upcoming projects and make informed decisions whether they should take on new projects. Secondly, we provide the means to identify potential areas for innovation by identifying blind spots of technology transfer. The approach presented relies on semantic web technologies, i.e. an ontology built in OWL and SPARQL queries. To increase usability, we realized a user interface based on a semi-formalized spreadsheet and a python script for the transformation.
- 26 July 2019
- Published by Cambridge University Press (CUP) in Proceedings of the Design Society: International Conference on Engineering Design
- Vol. 1 (1) , 1045-1054
Open AccessA Pragmatic Approach Towards Leveraging Employee Competences by Use of Semantic Web Technologies
Global competition in combination with the increasing specialization of labor requires organizations to leverage their employees' competences. The approach presented in this paper empowers organizations to do so in two ways. First, we give employers a lean tool to allocate their employees to current and upcoming projects and make informed decisions whether they should take on new projects. Secondly, we provide the means to identify potential areas for innovation by identifying blind spots of technology transfer. The approach presented relies on semantic web technologies, i.e. an ontology built in OWL and SPARQL queries. To increase usability, we realized a user interface based on a semi-formalized spreadsheet and a python script for the transformation.
- 18 July 2019
- Published by Wiley in Journal of Computing and Information Science in Engineering
- Vol. 19 (4) , 1-15
Applying Semantic Web Technologies to Provide Feasibility Feedback in Early Design Phases
In the product development process, as it is currently practiced, production is still often neglected in the early design phases, leading to late and costly changes. Using the knowledge of product designers concerning production process design, this paper introduces an ontological framework that enables early feasibility analyses. In this way, the number of iterations between product and process design can almost certainly be reduced, which would accelerate the product development process. Additionally, the approach provides process engineers with possible production sequences that can be used for process planning. To provide feasibility feedback, the approach presented relies on semantic web technologies. An ontology was developed that supports designers to model the relations among products, processes, and resources in a way that allows the use of generic Sparql Protocol And RDF Query Language (SPARQL) queries. Future applicability of this approach is ensured by aligning it with the top-level ontology Descriptive Ontology for Linguistic and Cognitive Engineering (DOLCE). We also compare the ontology’s universals to fundamental classes of existing knowledge bases from the manufacturing and the batch processing domains. This comparison demonstrates the approach’s domain-independent applicability. Two proofs of concept are described, one in the manufacturing domain and one in the batch processing domain.
- 18 July 2019
- Published by Wiley in Journal of Computing and Information Science in Engineering
- Vol. 19 (4) , 1-15
Applying Semantic Web Technologies to Provide Feasibility Feedback in Early Design Phases
In the product development process, as it is currently practiced, production is still often neglected in the early design phases, leading to late and costly changes. Using the knowledge of product designers concerning production process design, this paper introduces an ontological framework that enables early feasibility analyses. In this way, the number of iterations between product and process design can almost certainly be reduced, which would accelerate the product development process. Additionally, the approach provides process engineers with possible production sequences that can be used for process planning. To provide feasibility feedback, the approach presented relies on semantic web technologies. An ontology was developed that supports designers to model the relations among products, processes, and resources in a way that allows the use of generic Sparql Protocol And RDF Query Language (SPARQL) queries. Future applicability of this approach is ensured by aligning it with the top-level ontology Descriptive Ontology for Linguistic and Cognitive Engineering (DOLCE). We also compare the ontology’s universals to fundamental classes of existing knowledge bases from the manufacturing and the batch processing domains. This comparison demonstrates the approach’s domain-independent applicability. Two proofs of concept are described, one in the manufacturing domain and one in the batch processing domain.
- Open Access
- 1 June 2019
- Published by Walter de Gruyter GmbH in at - Automatisierungstechnik
- Vol. 67 (6) , 504-517
Applying knowledge bases to make factories smarter
Knowledge Bases (KBs) enable engineers to capture knowledge in a formalized way. This formalization allows us to combine knowledge, thus creating the basis for smart factories while also supporting product and production system design. Building comprehensive and reusable KBs is still a challenge, though, especially for knowledge-intensive domains like engineering and production. To cope with the sheer amount of knowledge, engineers should reuse existing KBs. This paper presents a comprehensive overview of domain-specific KBs for production and engineering, as well as generic top-level ontologies. The application of such top-level ontologies offers new insights by integrating knowledge from various domains, stakeholders, and companies. To bridge the gap between top-level ontologies and existing domain KBs, we introduce an Intermediate Engineering Ontology (IEO).
- 1 June 2019
- Published by Walter de Gruyter GmbH in at - Automatisierungstechnik
- Vol. 67 (6) , 504-517
Open AccessApplying knowledge bases to make factories smarter
Knowledge Bases (KBs) enable engineers to capture knowledge in a formalized way. This formalization allows us to combine knowledge, thus creating the basis for smart factories while also supporting product and production system design. Building comprehensive and reusable KBs is still a challenge, though, especially for knowledge-intensive domains like engineering and production. To cope with the sheer amount of knowledge, engineers should reuse existing KBs. This paper presents a comprehensive overview of domain-specific KBs for production and engineering, as well as generic top-level ontologies. The application of such top-level ontologies offers new insights by integrating knowledge from various domains, stakeholders, and companies. To bridge the gap between top-level ontologies and existing domain KBs, we introduce an Intermediate Engineering Ontology (IEO).
- 1 June 2019
- Published by Walter de Gruyter GmbH in at - Automatisierungstechnik
- Vol. 67 (6) , 477-489
Effiziente Initialisierung von Steuerungsparametern für Cyber-Physische Produktionssysteme via Multi-Ebenen-Optimierung
Zusammenfassung: An moderne Cyber-Physische Produktionssysteme werden hohe Anforderungen hinsichtlich Flexibilität und Effizienz gestellt. Flexibilität wird zum Teil bereits durch moderne Steuerungssoftware unterstützt, wobei die initialen Steuerungsparameter bisher typischerweise ad-hoc festgelegt werden. Dieser Beitrag stellt einen Ansatz zur Optimierung der initialen Steuerungsparameter vor, der mehrere Simulationsmodelle verschiedener Genauigkeit mittels ordinaler Transformation kombiniert. Die Anwendbarkeit des Ansatzes wird anhand eines Labordemonstrators für Produktionssysteme gezeigt.
- 1 June 2019
- Published by Walter de Gruyter GmbH in at - Automatisierungstechnik
- Vol. 67 (6) , 477-489
Effiziente Initialisierung von Steuerungsparametern für Cyber-Physische Produktionssysteme via Multi-Ebenen-Optimierung
Zusammenfassung: An moderne Cyber-Physische Produktionssysteme werden hohe Anforderungen hinsichtlich Flexibilität und Effizienz gestellt. Flexibilität wird zum Teil bereits durch moderne Steuerungssoftware unterstützt, wobei die initialen Steuerungsparameter bisher typischerweise ad-hoc festgelegt werden. Dieser Beitrag stellt einen Ansatz zur Optimierung der initialen Steuerungsparameter vor, der mehrere Simulationsmodelle verschiedener Genauigkeit mittels ordinaler Transformation kombiniert. Die Anwendbarkeit des Ansatzes wird anhand eines Labordemonstrators für Produktionssysteme gezeigt.