Towards the Application of Operational Design Domain Based Scene Generation for Artificial Intelligence Training in Railway Automation.
Mersmann, T.; Betz, F.; Eichenbaum, J.; Hampel, F.; Klamt, S.; Otten, Y.; Scholl, I.; and Schindler, C.
In
2024 IEEE 27th International Conference on Intelligent Transportation Systems (ITSC), pages 3181–3188, Sep. 2024.
doi
link
bibtex
abstract
@InProceedings{Mersmann-etAl_ITSC2024_Towards-Application-ODD,
author = {Mersmann, Till and Betz, Friedrich and Eichenbaum, Julian and Hampel, Fabian and Klamt, Simon and Otten, Yannick and Scholl, Ingrid and Schindler, Christian},
booktitle = {2024 IEEE 27th International Conference on Intelligent Transportation Systems (ITSC)},
title = {Towards the Application of Operational Design Domain Based Scene Generation for Artificial Intelligence Training in Railway Automation},
funding = {The project “Rail Automation with Artificial
Intelligence for Detection of Exceptional
Situations” (RailAIxs) received funding in the mFUND
conveyor line by the German Federal Ministry for
Digital and Transport under the funding code
19FS2031A-D.},
year = {2024},
month = {Sep.},
pages = {3181--3188},
abstract = {For automated, driverless rail transportation
applications in open environments, Artificial
Intelligence (AI)-based methods are gaining
importance, especially in computer vision and
perception tasks. The safe operation of complex
automated systems requires validation processes. For
this purpose, the concept of Operational Design
Domains (ODDs), driven by recent developments in the
automotive industry, is gaining momentum, allowing
to describe different aspects of operating
conditions as scenes and scenarios. With regard to
safety and authorization using AI-based vision
systems, data coverage is needed, which can be
enhanced by employing virtual reality in different
forms. The creation of virtual scenes and sensor
models allows the generation of synthetic sensor
data and metadata that can be used as a database for
the training of the vision system.},
keywords = {Training; Solid modeling; Automation;Machine vision;
Virtual reality; Rail transportation; Safety;
Artificial intelligence; Standards; Synthetic data;
RailAIxs},
doi = {10.1109/ITSC58415.2024.10919732},
ISSN = {2153-0017},
}
For automated, driverless rail transportation applications in open environments, Artificial Intelligence (AI)-based methods are gaining importance, especially in computer vision and perception tasks. The safe operation of complex automated systems requires validation processes. For this purpose, the concept of Operational Design Domains (ODDs), driven by recent developments in the automotive industry, is gaining momentum, allowing to describe different aspects of operating conditions as scenes and scenarios. With regard to safety and authorization using AI-based vision systems, data coverage is needed, which can be enhanced by employing virtual reality in different forms. The creation of virtual scenes and sensor models allows the generation of synthetic sensor data and metadata that can be used as a database for the training of the vision system.
A ROS 2-based Navigation and Simulation Stack for the Robotino.
Borse, S.; Viehmann, T.; Ferrein, A.; and Lakemeyer, G.
In
RoboCup Symposium 2024, 2024.
to appear
Paper
link
bibtex
@InProceedings{borse2024ros2basednavigationsimulationstack,
title = {{A ROS~2-based Navigation and Simulation Stack for the Robotino}},
author = {Saurabh Borse and Tarik Viehmann and Alexander Ferrein and Gerhard Lakemeyer},
booktitle = {RoboCup Symposium 2024},
year = {2024},
eprint = {2411.09441},
archivePrefix= {arXiv},
primaryClass = {cs.RO},
url = {https://arxiv.org/abs/2411.09441},
note = {to appear},
}
Look: AI at Work! - Analysing Key Aspects of AI-support at the Work Place.
Schiffer, S.; Rothermel, A. M.; Ferrein, A.; and Rosenthal-von der Pütten, A.
In Yamshchikov, I.; Meißner, P.; and Rezagholi, S., editor(s),
Workshop on Human-Machine Interaction (HuMaIn) held at KI 2024, 2024.
to appear
link
bibtex
abstract
@InProceedings{ Schiffer-etAl_KI2024HuMaIn_Look-AI-at-Work,
author = {Stefan Schiffer and Anna Milena Rothermel and Alexander Ferrein and Astrid {Rosenthal-von der P{\"u}tten}},
title = {Look: AI at Work! - Analysing Key Aspects of AI-support at the Work Place},
booktitle = {Workshop on Human-Machine Interaction (HuMaIn) held at KI 2024},
location = {W{\"u}rzburg, Germany},
OPTpages = {--},
year = {2024},
editor = {Ivan Yamshchikov and Pascal Mei{\ss}ner and Sharwin Rezagholi},
keywords = {WIRKsam, artificial intelligence, AI, Work, Social Psychology},
abstract = {In this paper we present an analysis of
technological and psychological factors of applying
artificial intelligence (AI) at the work place. We
do so for a number of twelve application cases in
the context of a project where AI is integrated at
work places and in work systems of the future. From
a technological point of view we mainly look at the
areas of AI that the applications are concerned
with. This allows to formulate recommendations in
terms of what to look at in developing an AI
application and what to pay attention to with
regards to building AI literacy with different
stakeholders using the system. This includes the
importance of high-quality data for training
learning-based systems as well as the integration of
human expertise, especially with knowledge- based
systems. In terms of the psychological factors we
derive research questions to investigate in the
development of AI supported work systems and to
consider in future work, mainly concerned with
topics such as acceptance, openness, and trust in an
AI system.},
note = {to appear},
}
In this paper we present an analysis of technological and psychological factors of applying artificial intelligence (AI) at the work place. We do so for a number of twelve application cases in the context of a project where AI is integrated at work places and in work systems of the future. From a technological point of view we mainly look at the areas of AI that the applications are concerned with. This allows to formulate recommendations in terms of what to look at in developing an AI application and what to pay attention to with regards to building AI literacy with different stakeholders using the system. This includes the importance of high-quality data for training learning-based systems as well as the integration of human expertise, especially with knowledge- based systems. In terms of the psychological factors we derive research questions to investigate in the development of AI supported work systems and to consider in future work, mainly concerned with topics such as acceptance, openness, and trust in an AI system.
Towards Conceptually Elevating Modern Concepts of Operational Design Domains and Implications for Operating in Unstructured Environments.
Eichenbaum, J.; Bracht, L.; Schulte-Tigges, J.; Reke, M.; Ferrein, A.; and Scholl, I.
In Yilmaz, M.; Clarke, P.; Riel, A.; Messnarz, R.; Greiner, C.; and Peisl, T., editor(s),
Systems, Software and Services Process Improvement (EuroSPI), pages 172–185, Cham, 2024. Springer Nature Switzerland
springer
doi
link
bibtex
abstract
@InProceedings{ Eichenbaum-etAl_EuroSPI2024_Towards-Conceptually-Elevating-ODDs,
author = {Eichenbaum, Julian and Bracht, Leonard and Schulte-Tigges, Joschua and
Reke, Michael and Ferrein, Alexander and Scholl, Ingrid},
editor = "Yilmaz, Murat and Clarke, Paul and Riel, Andreas and
Messnarz, Richard and Greiner, Christian and Peisl, Thomas",
title = {{Towards Conceptually Elevating Modern Concepts of {O}perational {D}esign {D}omains
and Implications for Operating in Unstructured Environments}},
booktitle = "Systems, Software and Services Process Improvement (EuroSPI)",
year = "2024",
publisher = "Springer Nature Switzerland",
address = "Cham",
pages = "172--185",
doi = {10.1007/978-3-031-71142-8_13},
url_springer = {https://link.springer.com/chapter/10.1007/978-3-031-71142-8_13},
abstract = "This paper explores the basic concepts of
Operational Design Domains (ODDs) in the field of
autonomous driving. We address the intricacies of
different scenario descriptions and promote the
communication of system requirements and operational
constraints in the context of Automated Driving
Systems (ADSs).
Ongoing standardization efforts highlight
the recognition of the importance of ODDs
as a tool to manage the complexity of an ADS in
accurately defining operational boundaries and
conditions, particularly in structured
environments. In line with this, our work explores
the conceptual integration of multiple ODDs within
an ADS to enable operation across different
domains. Drawing on the existing literature on ODD
extension concepts and leveraging insights from our
research efforts, we strive for exemplary adaptation
of operations in unstructured environments such as
hybrid mines. A key focus is the translation of a
solution that has been successfully tested in the
context of hybrid mines and structured terrain into
modern ODD frameworks. In particular, we focus on
taxonomy as a fundamental element of an ODD
framework. Through comparative analysis and
evaluation of existing taxonomies, we aim to provide
insights into the configuration of ODDs for both
structured and unstructured environments, thereby
contributing to their broader implementation in the
dynamic landscape of autonomous driving
technologies.",
isbn = "978-3-031-71142-8",
}
This paper explores the basic concepts of Operational Design Domains (ODDs) in the field of autonomous driving. We address the intricacies of different scenario descriptions and promote the communication of system requirements and operational constraints in the context of Automated Driving Systems (ADSs). Ongoing standardization efforts highlight the recognition of the importance of ODDs as a tool to manage the complexity of an ADS in accurately defining operational boundaries and conditions, particularly in structured environments. In line with this, our work explores the conceptual integration of multiple ODDs within an ADS to enable operation across different domains. Drawing on the existing literature on ODD extension concepts and leveraging insights from our research efforts, we strive for exemplary adaptation of operations in unstructured environments such as hybrid mines. A key focus is the translation of a solution that has been successfully tested in the context of hybrid mines and structured terrain into modern ODD frameworks. In particular, we focus on taxonomy as a fundamental element of an ODD framework. Through comparative analysis and evaluation of existing taxonomies, we aim to provide insights into the configuration of ODDs for both structured and unstructured environments, thereby contributing to their broader implementation in the dynamic landscape of autonomous driving technologies.
Conceptualization of Demonstrators for Human-Technology Interaction with a Three-Layer Model.
Altepost, A.; Elaroussi, F.; Hirsch, L.; Merx, W.; Oppermann, L.; Rosenthal-von der Pütten, A.; Rothermel, A. M.; and Schiffer, S.
In
Proceedings of the 22nd Triennial Congress of the International Ergonomics Association (IEA 2024), of
Springer Series in Design and Innovation, 2024. Springer Cham
to appear
link
bibtex
abstract
@inproceedings{Altepost-etAl_IEA2024_Conceptualization-of-Demonstrators,
author = {Andrea Altepost and Farah Elaroussi and Linda Hirsch and Wolfgang Merx and Leif Oppermann and Astrid {Rosenthal-von der P{\"u}tten} and Anna Milena Rothermel and Stefan Schiffer},
title = {Conceptualization of Demonstrators for Human-Technology Interaction with a Three-Layer Model},
booktitle = {Proceedings of the 22nd Triennial Congress of the International Ergonomics Association (IEA 2024)},
OPTpages = {},
series = {Springer Series in Design and Innovation},
publisher = {Springer Cham},
OPTaddress = {},
year = 2024,
keywords = {WIRKsam, Stakeholder Involvement, Demonstrators, Human-Technology Interaction, Artificial Intelligence, AI},
abstract = {We present a three-layer model of stakeholder
involvement, developed as part of the ongoing
WIRKsam project. WIRKsam creates or modifies
socio-technical work systems by integrating
artificial intelligence (AI) in a participatory
fashion and in such a way that all stakeholders
benefit from better conditions of labor. While the
technological elements of these changes are easy to
highlight to others, it is difficult to convey the
human-related and organizational changes and their
benefits. Therefore, we aim to develop demonstrators
in the field of human factors which should showcase
the transformation of work and not just technology,
using extended reality (XR) in a transdisciplinary
setting.},
note = {to appear},
}
We present a three-layer model of stakeholder involvement, developed as part of the ongoing WIRKsam project. WIRKsam creates or modifies socio-technical work systems by integrating artificial intelligence (AI) in a participatory fashion and in such a way that all stakeholders benefit from better conditions of labor. While the technological elements of these changes are easy to highlight to others, it is difficult to convey the human-related and organizational changes and their benefits. Therefore, we aim to develop demonstrators in the field of human factors which should showcase the transformation of work and not just technology, using extended reality (XR) in a transdisciplinary setting.
Transformation of Work in the Textile Industry: Perspectives of Sustainable Innovation Processes.
Altepost, A.; Hansen-Ampah, A.; Merx, W.; Schiffer, S.; Schmenk, B.; and Gries, T.
In Letmathe, P.; Roll, C.; Balleer, A.; Böschen, S.; Breuer, W.; Förster, A.; Gramelsberger, G.; Greiff, K.; Häußling, R.; Lemme, M.; Leuchner, M.; Paegert, M.; Piller, F. T.; Seefried, E.; and Wahlbrink, T., editor(s),
Transformation Towards Sustainability: A Novel Interdisciplinary Framework from RWTH Aachen University, pages 331–362. Springer International Publishing, Cham, 2024.
Paper
doi
link
bibtex
abstract
@Incollection{ Altepost-etAl_2024_Transformation-of-Work,
author = "Altepost, Andrea and Hansen-Ampah, Adjan and
Merx, Wolfgang and Schiffer, Stefan and
Schmenk, Bernhard and Gries, Thomas",
editor = "Letmathe, Peter and Roll, Christine and Balleer, Almut
and B{\"o}schen, Stefan and Breuer, Wolfgang and
F{\"o}rster, Agnes and Gramelsberger, Gabriele and
Greiff, Kathrin and H{\"a}u{\ss}ling, Roger and
Lemme, Max and Leuchner, Michael and Paegert, Maren and
Piller, Frank T. and Seefried, Elke and Wahlbrink, Thorsten",
title = "Transformation of Work in the Textile Industry: Perspectives of Sustainable Innovation Processes",
bookTitle = "Transformation Towards Sustainability: A Novel Interdisciplinary Framework from RWTH Aachen University",
year = "2024",
publisher = "Springer International Publishing",
address = "Cham",
pages = "331--362",
isbn = "978-3-031-54700-3",
doi = "10.1007/978-3-031-54700-3_12",
url = "https://doi.org/10.1007/978-3-031-54700-3_12",
abstract = "What makes innovation processes in industry succeed? The
basic assumption of this paper is that not only
technological, but also social---especially
work-related---factors have a decisive impact. While
processes of sociotechnical system design are
established interdisciplinarily and have arrived at
least in many large companies, to the best of our
knowledge it still is a novelty in industrial
contexts to also add the concept of sustainability
to this perspective. Energy and circular economy as
well as a shortage of skilled workers dominate the
concerns of companies. At the same time,
technologies such as artificial intelligence (AI)
are traded as a beacon of hope to strengthen
competitiveness and contribute to more efficient,
resource-conserving economic activity (e.g., Lukic
et al., BCG 10.01.2023, 2023).). With the design of
AI-supported work systems in the textile and related
industries, the WIRKsam Competence Center for Work
Research wants to show how the use of artificial
intelligence, with appropriate work design, can
promote both innovative, human-centered work and
economic competitiveness, so that the two benefit
from each other. The project aims to strengthen the
industrial backbone of the Rhenish mining area and
to create attractive conditions and opportunities
for skilled workers. In this way, a sustainable
result of the various transformation levels in the
area of structural change, digitalization and the
future of work can be achieved, which lays the
foundation for shaping further future transformation
processes in an innovative way. In this paper, we
develop central questions originating from this
claim that need to be considered in the
aforementioned transformation processes in the areas
of people, technology and organization, because they
can be decisive for success.",
}
% %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
% 2023
% %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
What makes innovation processes in industry succeed? The basic assumption of this paper is that not only technological, but also social—especially work-related—factors have a decisive impact. While processes of sociotechnical system design are established interdisciplinarily and have arrived at least in many large companies, to the best of our knowledge it still is a novelty in industrial contexts to also add the concept of sustainability to this perspective. Energy and circular economy as well as a shortage of skilled workers dominate the concerns of companies. At the same time, technologies such as artificial intelligence (AI) are traded as a beacon of hope to strengthen competitiveness and contribute to more efficient, resource-conserving economic activity (e.g., Lukic et al., BCG 10.01.2023, 2023).). With the design of AI-supported work systems in the textile and related industries, the WIRKsam Competence Center for Work Research wants to show how the use of artificial intelligence, with appropriate work design, can promote both innovative, human-centered work and economic competitiveness, so that the two benefit from each other. The project aims to strengthen the industrial backbone of the Rhenish mining area and to create attractive conditions and opportunities for skilled workers. In this way, a sustainable result of the various transformation levels in the area of structural change, digitalization and the future of work can be achieved, which lays the foundation for shaping further future transformation processes in an innovative way. In this paper, we develop central questions originating from this claim that need to be considered in the aforementioned transformation processes in the areas of people, technology and organization, because they can be decisive for success.
Approach for the Identification of Requirements on the Design of AI-supported Work Systems (in Problem-based Projects).
Harlacher, M.; Altepost, A.; Ferrein, A.; Hansen-Ampah, A.; Merx, W.; Niehues, S.; Schiffer, S.; and Shahinfar, F. N.
In Lausberg, I.; and Vogelsang, M., editor(s),
AI in Business and Economics, 7, pages 87–100. De Gruyter, Berlin, Boston, 2024.
doi
pdf
doi
link
bibtex
abstract
@incollection{ Harlacher-etAl_EPAI2023_Identification-of-Requirements,
chapter = {7},
title = {Approach for the Identification of Requirements on the Design of AI-supported Work Systems (in Problem-based Projects)},
author = {Markus Harlacher and Andrea Altepost and Alexander Ferrein and Adjan Hansen-Ampah and Wolfgang Merx and Sina Niehues and Stefan Schiffer and Fatemeh Nasim Shahinfar},
booktitle = {AI in Business and Economics},
editor = {Isabel Lausberg and Michael Vogelsang},
publisher = {De Gruyter},
address = {Berlin, Boston},
pages = {87--100},
doi = {10.1515/9783110790320-007},
url_doi = {https://doi.org/10.1515/9783110790320-007},
url_pdf = {https://www.degruyter.com/document/doi/10.1515/9783110790320-007/pdf?licenseType=open-access},
isbn = {9783110790320},
year = {2024},
keywords = {WIRKsam, business understanding, requirements, process model, participation, implementation of AI-systems, Artificial Intelligence, AI},
abstract = {To successfully develop and introduce concrete
artificial intelligence (AI) solutions in
operational practice, a comprehensive process model
is being tested in the WIRKsam joint project. It is
based on a methodical approach that integrates
human, technical and organisational aspects and
involves employees in the process. The chapter
focuses on the procedure for identifying
requirements for a work system that is implementing
AI in problem-driven projects and for selecting
appropriate AI methods. This means that the use case
has already been narrowed down at the beginning of
the project and must be completely defined in the
following. Initially, the existing preliminary work
is presented. Based on this, an overview of all
procedural steps and methods is given. All methods
are presented in detail and good practice approaches
are shown. Finally, a reflection of the developed
procedure based on the application in nine companies
is given.},
}
To successfully develop and introduce concrete artificial intelligence (AI) solutions in operational practice, a comprehensive process model is being tested in the WIRKsam joint project. It is based on a methodical approach that integrates human, technical and organisational aspects and involves employees in the process. The chapter focuses on the procedure for identifying requirements for a work system that is implementing AI in problem-driven projects and for selecting appropriate AI methods. This means that the use case has already been narrowed down at the beginning of the project and must be completely defined in the following. Initially, the existing preliminary work is presented. Based on this, an overview of all procedural steps and methods is given. All methods are presented in detail and good practice approaches are shown. Finally, a reflection of the developed procedure based on the application in nine companies is given.