TY - JOUR A1 - Maier, Robert A1 - Grabinger, Lisa A1 - Urlhart, David A1 - Mottok, Jürgen T1 - Causal Models to Support Scenario-Based Testing of ADAS JF - IEEE Transactions on Intelligent Transportation Systems N2 - In modern vehicles, system complexity and technical capabilities are constantly growing. As a result, manufacturers and regulators are both increasingly challenged to ensure the reliability, safety, and intended behavior of these systems. With current methodologies, it is difficult to address the various interactions between vehicle components and environmental factors. However, model-based engineering offers a solution by allowing to abstract reality and enhancing communication among engineers and stakeholders. Applying this method requires a model format that is machine-processable, human-understandable, and mathematically sound. In addition, the model format needs to support probabilistic reasoning to account for incomplete data and knowledge about a problem domain. We propose structural causal models as a suitable framework for addressing these demands. In this article, we show how to combine data from different sources into an inferable causal model for an advanced driver-assistance system. We then consider the developed causal model for scenario-based testing to illustrate how a model-based approach can improve industrial system development processes. We conclude this paper by discussing the ongoing challenges to our approach and provide pointers for future work. KW - automated driving systems KW - Automation KW - Bayesian networks KW - Causal inference KW - Data models KW - ISO Standards KW - model-based testing KW - Safety KW - Task analysis KW - Testing KW - Vehicles Y1 - 2023 U6 - https://doi.org/10.1109/TITS.2023.3317475 SN - 1524-9050 SP - 1 EP - 17 PB - IEEE ER - TY - CHAP A1 - Fuhrmann, Thomas T1 - Semi-Structured Lab Projects in Communication Engineering Education T2 - 2023 IEEE Global Engineering Education Conference (EDUCON), 01-04 May 2023, Kuwait N2 - It is generally known that project-based learning is a very important part of engineering education to connect theoretical knowledge with practical work. Students learn to apply their knowledge to real-world challenges as it is the case in their later professional life. If students are not used to project work or the scientific topic is new and relatively complex, they may be overwhelmed. The consequence is that students achieve poor results, are frustrated, and therefore learning success is low. Semi-structured projects are introduced that combine the advantages of structured experiments with projects. The project work is structured into several parts with detailed descriptions of the tasks. In the end, students get similar results to doing a free project, but the success rate is higher due to higher guidance. Therefore, these semi-structured projects are seen to be an appropriate method to guide students to learn how to do project work. The feedback from most students is very positive. Some students with no previous lab experience complained about the project work and wished for more guidance to become familiar with lab work. In sum, the student feedback is encouraging to develop semi-structured projects further. KW - Knowledge engineering KW - Task analysis KW - Communication engineering education Y1 - 2023 U6 - https://doi.org/10.1109/EDUCON54358.2023.10125244 SP - 1 EP - 5 PB - IEEE ER - TY - CHAP A1 - Störl, Uta A1 - Müller, Daniel A1 - Tekleab, Alexander A1 - Tolale, Stephane A1 - Stenzel, Julian A1 - Klettke, Meike A1 - Scherzinger, Stefanie A1 - Storl, Uta A1 - Muller, Daniel T1 - Curating Variational Data in Application Development T2 - 2018 IEEE 34th International Conference on Data Engineering, 16-19 April 2018, Paris, France N2 - Building applications for processing data lakes is a software engineering challenge. We present Darwin, a middleware for applications that operate on variational data. This concerns data with heterogeneous structure, usually stored within a schema-flexible NoSQL database. Darwin assists application developers in essential data and schema curation tasks: Upon request, Darwin extracts a schema description, discovers the history of schema versions, and proposes mappings between these versions. Users of Darwin may interactively choose which mappings are most realistic. Darwin is further capable of rewriting queries at runtime, to ensure that queries also comply with legacy data. Alternatively, Darwin can migrate legacy data to reduce the structural heterogeneity. Using Darwin, developers may thus evolve their data in sync with their code. In our hands-on demo, we curate synthetic as well as real-life datasets. KW - data migration KW - Data mining KW - Evolution (biology) KW - history KW - NoSQL databases KW - query rewriting KW - schema evolution KW - schema management KW - Software KW - Task analysis KW - variational data Y1 - 2018 U6 - https://doi.org/10.1109/ICDE.2018.00187 SP - 1605 EP - 1608 PB - IEEE ER - TY - CHAP A1 - Rösel, Birgit A1 - Köhler, Thomas T1 - First results of a new digitalized concept for teaching control theory as minor subject at a university of applied science T2 - 2018 IEEE Global Engineering Education Conference (EDUCON), 17-20 April 2018, Santa Cruz de Tenerife, Spain N2 - This paper presents a digitalized concept for teaching control theory as minor subject with an integrated approach for lectures, exercises and practical sessions and first results of the implementation at the department of electrical engineering at the OTH Regensburg. The concept uses activating methods like blended learning and possibilities of digitalization of teaching implementing Just in Time Teaching and Peer Instruction. The base of the new concept is the idea of constructive alignment. Furthermore this paper presents the feedback of the students along with an accompanying scientific research over several semesters. The data obtained from the presented module are compared with the data from other blended learning approaches in Germany. KW - Blended Learning KW - constructive alignment KW - Control theory KW - Electrical engineering KW - Electronic learning KW - Just in Time Teaching KW - Task analysis KW - taxonomy KW - teaching text Y1 - 2018 U6 - https://doi.org/10.1109/EDUCON.2018.8363217 SP - 118 EP - 125 PB - IEEE ER - TY - CHAP A1 - Pohlt, Clemens A1 - Haubner, Franz A1 - Lang, Jonas A1 - Rochholz, Sandra A1 - Schlegl, Thomas A1 - Wachsmuth, Sven T1 - Effects on User Experience During Human-Robot Collaboration in Industrial Scenarios T2 - 2018 IEEE International Conference on Systems, Man, and Cybernetics (SMC), 7-10 Oct. 2018, Miyazaki, Japan N2 - In smart manufacturing environments robots collaborate with human operators as peers. They even share the same working space and time. An intuitive interaction with different input modalities is decisive to reduce workload and training periods for collaboration. We introduce our interaction system that is able to recognize gestures, actions and objects in a typical smart working scenario. As key aspect, this article considers an empirical investigation of input modalities (touch, gesture), individual differences (performance, recognition rate, previous knowledge) and boundary conditions (level of automation) on user experience. Therefore, answers from 31 participants within two experiments are collected. We show that the arrangement of the human-robot collaboration (input modalities, boundary conditions) has a significant effect on user experience in real-world environments. This effect and the individual differences between participants can be measured utilizing recognition rates and standardized usability questionnaires. KW - Collaboration KW - Gesture recognition KW - Robots KW - Task analysis KW - Three-dimensional displays KW - Training KW - Tutorials Y1 - 2018 U6 - https://doi.org/10.1109/SMC.2018.00150 SP - 837 EP - 842 PB - IEEE ER - TY - CHAP A1 - Fuhrmann, Thomas T1 - Motivation Centered Learning T2 - 2018 IEEE Frontiers in Education Conference (FIE), 3-6 Oct. 2018, San Jose, CA, USA N2 - This Research Work in Progress Paper evaluates students’ motivation sources and shows the high impact that work of professors has on students’ motivation. Common goal of most professors is to help students acquiring knowledge and competencies that are relevant for their further life. From the beginning of Universities’ history, lectures are usually chosen to reach this goal but it is seen in recent years that they are in many cases not the optimal choice. In the last years, many efforts were made to increase students knowledge gain. From learning and motivation psychology research, many details are known how humans remember and transfer knowledge. These research results are used to create new lecture formats to activate students. Research based learning, project based lab courses, problem based learning, feedback systems, flipped classroom, blended learning and gamification in lectures are only some examples for new formats. Common goal of all these new types of learning formats is to increasing students’ motivation and to enhance learning success. In this paper, evaluations using a questionnaire with open questions were done among first year students, bachelor students before graduation and alumni, about their sources of motivation and demotivation. Interesting curricula and lectures with application related topics and possibilities for own work are the main sources of motivation. Enthusiastic professors with high competences and good lecture didactics also contribute to students’ motivation. On the other side, demotivated professors with boring lectures play a much higher role for demotivating students. Therefore, it is necessary to integrate aspects of student motivation into curriculum and lecture design and professors should become aware that they are important role-models for motivating or demotivating students. KW - Computational modeling KW - Electrical engineering KW - Information technology KW - Psychology KW - Social networking (online) KW - Task analysis KW - Urban areas Y1 - 2018 U6 - https://doi.org/10.1109/FIE.2018.8658436 SP - 1 EP - 5 PB - IEEE ER - TY - CHAP A1 - Pohlt, Clemens A1 - Schlegl, Thomas A1 - Wachsmuth, Sven T1 - Human Work Activity Recognition for Working Cells in Industrial Production Contexts T2 - 2019 IEEE International Conference on Systems, Man and Cybernetics (SMC), 6-9 Oct. 2019, Bari, Italy N2 - Collaboration between robots and humans requires communicative skills on both sides. The robot has to understand the conscious and unconscious activities of human workers. Many state-of-the-art activity recognition algorithms with high performance rates on existing benchmark datasets are available for this task. This paper re-evaluates appropriate architectures in light of human work activity recognition for working cells in industrial production contexts. The specific constraints of such a domain is elaborated and used as prior knowledge. We utilize state-of-the-art algorithms as spatiotemporal feature encoders and search for appropriate classification and fusion strategies. Furthermore, we combine keypoint-based with appearance-based approaches to a multi-stream recognition system. Due to data protection rules and the high effort of data annotation within industrial domains only small datasets are available that reflect production aspects. Therefore, we use transfer learning approaches to reduce the dependency on data volume and variance in the target domain. The resulting recognition system achieves high performance for both singular person action and human-object interaction. KW - Activity recognition KW - Pose estimation KW - Robots KW - Task analysis KW - Three-dimensional displays KW - Two dimensional displays Y1 - 2019 U6 - https://doi.org/10.1109/SMC.2019.8913873 SP - 4225 EP - 4230 ER -