@inproceedings{WittigRuettersBragard2024, author = {Wittig, M. and R{\"u}tters, Ren{\´e} and Bragard, Michael}, title = {Application of RL in control systems using the example of a rotatory inverted pendulum}, series = {Tagungsband AALE 2024 : Fit f{\"u}r die Zukunft: praktische L{\"o}sungen f{\"u}r die industrielle Automation}, booktitle = {Tagungsband AALE 2024 : Fit f{\"u}r die Zukunft: praktische L{\"o}sungen f{\"u}r die industrielle Automation}, editor = {Reiff-Stephan, J{\"o}rg and J{\"a}kel, Jens and Schwarz, Andr{\´e}}, publisher = {le-tex publishing services GmbH}, address = {Leipzig}, isbn = {978-3-910103-02-3}, doi = {10.33968/2024.53}, pages = {241 -- 248}, year = {2024}, abstract = {In this paper, the use of reinforcement learning (RL) in control systems is investigated using a rotatory inverted pendulum as an example. The control behavior of an RL controller is compared to that of traditional LQR and MPC controllers. This is done by evaluating their behavior under optimal conditions, their disturbance behavior, their robustness and their development process. All the investigated controllers are developed using MATLAB and the Simulink simulation environment and later deployed to a real pendulum model powered by a Raspberry Pi. The RL algorithm used is Proximal Policy Optimization (PPO). The LQR controller exhibits an easy development process, an average to good control behavior and average to good robustness. A linear MPC controller could show excellent results under optimal operating conditions. However, when subjected to disturbances or deviations from the equilibrium point, it showed poor performance and sometimes instable behavior. Employing a nonlinear MPC Controller in real time was not possible due to the high computational effort involved. The RL controller exhibits by far the most versatile and robust control behavior. When operated in the simulation environment, it achieved a high control accuracy. When employed in the real system, however, it only shows average accuracy and a significantly greater performance loss compared to the simulation than the traditional controllers. With MATLAB, it is not yet possible to directly post-train the RL controller on the Raspberry Pi, which is an obstacle to the practical application of RL in a prototyping or teaching setting. Nevertheless, RL in general proves to be a flexible and powerful control method, which is well suited for complex or nonlinear systems where traditional controllers struggle.}, language = {en} } @inproceedings{AltherrDoeringFrauenrathetal.2024, author = {Altherr, Lena and D{\"o}ring, Bernd and Frauenrath, Tobias and Groß, Rolf and Mohan, Nijanthan and Oyen, Marc and Schnittcher, Lukas and Voß, Norbert}, title = {DiggiTwin: ein interdisziplin{\"a}res Projekt zur Nutzung digitaler Zwillinge auf dem Weg zu einem klimaneutralen Geb{\"a}udebestand}, series = {Tagungsband AALE 2024 : Fit f{\"u}r die Zukunft: praktische L{\"o}sungen f{\"u}r die industrielle Automation}, booktitle = {Tagungsband AALE 2024 : Fit f{\"u}r die Zukunft: praktische L{\"o}sungen f{\"u}r die industrielle Automation}, editor = {Reiff-Stephan, J{\"o}rg and J{\"a}kel, Jens and Schwarz, Andr{\´e}}, publisher = {le-tex publishing services GmbH}, address = {Leipzig}, isbn = {978-3-910103-02-3}, doi = {10.33968/2024.67}, pages = {341 -- 346}, year = {2024}, abstract = {Im Hinblick auf die Klimaziele der Bundesrepublik Deutschland konzentriert sich das Projekt Diggi Twin auf die nachhaltige Geb{\"a}udeoptimierung. Grundlage f{\"u}r eine ganzheitliche Geb{\"a}ude{\"u}berwachung und -optimierung bildet dabei die Digitalisierung und Automation im Sinne eines Smart Buildings. Das interdisziplin{\"a}re Projekt der FH Aachen hat das Ziel, ein bestehendes Hochschulgeb{\"a}ude und einen Neubau an klimaneutrale Standards anzupassen. Im Rahmen des Projekts werden bekannte Verfahren, wie das Building Information Modeling (BIM), so erweitert, dass ein digitaler Geb{\"a}udezwilling entsteht. Dieser kann zur Optimierung des Geb{\"a}udebetriebs herangezogen werden, sowie als Basis f{\"u}r eine Erweiterung des Bewertungssystems Nachhaltiges Bauen (BNB) dienen. Mithilfe von Sensortechnologie und k{\"u}nstlicher Intelligenz kann so ein pr{\"a}zises Monitoring wichtiger Geb{\"a}udedaten erfolgen, um ungenutzte Energieeinsparpotenziale zu erkennen und zu nutzen. Das Projekt erforscht und setzt methodische Erkenntnisse zu BIM und digitalen Geb{\"a}udezwillingen praxisnah um, indem es spezifische Fragen zur Energie- und Ressourceneffizienz von Geb{\"a}uden untersucht und konkrete L{\"o}sungen f{\"u}r die Geb{\"a}udeoptimierung entwickelt.}, language = {de} } @inproceedings{HofmannLimpertMatareetal.2019, author = {Hofmann, Till and Limpert, Nicolas and Matar{\´e}, Viktor and Ferrein, Alexander and Lakemeyer, Gerhard}, title = {Winning the RoboCup Logistics League with Fast Navigation, Precise Manipulation, and Robust Goal Reasoning}, series = {RoboCup 2019: Robot World Cup XXIII. RoboCup}, booktitle = {RoboCup 2019: Robot World Cup XXIII. RoboCup}, publisher = {Springer}, address = {Cham}, isbn = {978-3-030-35699-6}, doi = {10.1007/978-3-030-35699-6_41}, pages = {504 -- 516}, year = {2019}, language = {en} } @inproceedings{HoegenDonckerRuetters2020, author = {Hoegen, Anne von and Doncker, Rik W. De and R{\"u}tters, Ren{\´e}}, title = {Teaching Digital Control of Operational Amplifier Processes with a LabVIEW Interface and Embedded Hardware}, series = {The 23rd International Conference on Electrical Machines and Systems (ICEMS), Hamamatsu, Japan}, booktitle = {The 23rd International Conference on Electrical Machines and Systems (ICEMS), Hamamatsu, Japan}, doi = {10.23919/ICEMS50442.2020.9290928}, pages = {1117 -- 1122}, year = {2020}, language = {en} } @inproceedings{HoegenDonckerBragardetal.2021, author = {Hoegen, Anne von and Doncker, Rik W. De and Bragard, Michael and Hoegen, Svenja von}, title = {Problem-Based Learning in Automation Engineering: Performing a Remote Laboratory Session Serving Various Educational Attainments}, series = {2021 IEEE Global Engineering Education Conference (EDUCON)}, booktitle = {2021 IEEE Global Engineering Education Conference (EDUCON)}, doi = {10.1109/EDUCON46332.2021.9453925}, pages = {1605 -- 1614}, year = {2021}, language = {en} } @inproceedings{HueningStuettgen2021, author = {H{\"u}ning, Felix and St{\"u}ttgen, Marcel}, title = {Work in Progress: Interdisciplinary projects in times of COVID-19 crisis - challenges, risks and chances}, series = {2021 IEEE Global Engineering Education Conference (EDUCON)}, booktitle = {2021 IEEE Global Engineering Education Conference (EDUCON)}, doi = {10.1109/EDUCON46332.2021.9454006}, pages = {1175 -- 1179}, year = {2021}, language = {en} } @inproceedings{AltherrEdererSchaenzleetal.2017, author = {Altherr, Lena and Ederer, Thorsten and Sch{\"a}nzle, Christian and Lorenz, Ulf and Pelz, Peter F.}, title = {Algorithmic system design using scaling and affinity laws}, series = {Operations Research Proceedings 2015}, booktitle = {Operations Research Proceedings 2015}, publisher = {Springer}, address = {Cham}, isbn = {978-3-319-42901-4}, doi = {10.1007/978-3-319-42902-1}, pages = {605 -- 611}, year = {2017}, abstract = {Energy-efficient components do not automatically lead to energy-efficient systems. Technical Operations Research (TOR) shifts the focus from the single component to the system as a whole and finds its optimal topology and operating strategy simultaneously. In previous works, we provided a preselected construction kit of suitable components for the algorithm. This approach may give rise to a combinatorial explosion if the preselection cannot be cut down to a reasonable number by human intuition. To reduce the number of discrete decisions, we integrate laws derived from similarity theory into the optimization model. Since the physical characteristics of a production series are similar, it can be described by affinity and scaling laws. Making use of these laws, our construction kit can be modeled more efficiently: Instead of a preselection of components, it now encompasses whole model ranges. This allows us to significantly increase the number of possible set-ups in our model. In this paper, we present how to embed this new formulation into a mixed-integer program and assess the run time via benchmarks. We present our approach on the example of a ventilation system design problem.}, language = {en} } @inproceedings{NikolovskiRekeElsenetal.2021, author = {Nikolovski, Gjorgji and Reke, Michael and Elsen, Ingo and Schiffer, Stefan}, title = {Machine learning based 3D object detection for navigation in unstructured environments}, series = {2021 IEEE Intelligent Vehicles Symposium Workshops (IV Workshops)}, booktitle = {2021 IEEE Intelligent Vehicles Symposium Workshops (IV Workshops)}, publisher = {IEEE}, isbn = {978-1-6654-7921-9}, doi = {10.1109/IVWorkshops54471.2021.9669218}, pages = {236 -- 242}, year = {2021}, abstract = {In this paper we investigate the use of deep neural networks for 3D object detection in uncommon, unstructured environments such as in an open-pit mine. While neural nets are frequently used for object detection in regular autonomous driving applications, more unusual driving scenarios aside street traffic pose additional challenges. For one, the collection of appropriate data sets to train the networks is an issue. For another, testing the performance of trained networks often requires tailored integration with the particular domain as well. While there exist different solutions for these problems in regular autonomous driving, there are only very few approaches that work for special domains just as well. We address both the challenges above in this work. First, we discuss two possible ways of acquiring data for training and evaluation. That is, we evaluate a semi-automated annotation of recorded LIDAR data and we examine synthetic data generation. Using these datasets we train and test different deep neural network for the task of object detection. Second, we propose a possible integration of a ROS2 detector module for an autonomous driving platform. Finally, we present the performance of three state-of-the-art deep neural networks in the domain of 3D object detection on a synthetic dataset and a smaller one containing a characteristic object from an open-pit mine.}, language = {en} } @inproceedings{AltherrEdererVergeetal.2015, author = {Altherr, Lena and Ederer, Thorsten and Verg{\´e}, Angela and Pelz, Peter F.}, title = {Algorithmische Struktursynthese eines hydrostatischen Getriebes}, series = {Antriebssysteme 2015 : Elektrik, Mechanik, Fluidtechnik in der Anwendung}, booktitle = {Antriebssysteme 2015 : Elektrik, Mechanik, Fluidtechnik in der Anwendung}, publisher = {VDI-Verlag}, address = {D{\"u}sseldorf}, isbn = {978-3-18-092268-3}, pages = {145 -- 155}, year = {2015}, language = {de} } @inproceedings{SchaenzleAltherrEdereretal.2015, author = {Sch{\"a}nzle, Christian and Altherr, Lena and Ederer, Thorsten and Lorenz, Ulf and Pelz, Peter F.}, title = {As good as it can be: Ventilation system design by a combined scaling and discrete optimization method}, series = {Proceedings of FAN 2015}, booktitle = {Proceedings of FAN 2015}, pages = {1 -- 11}, year = {2015}, abstract = {The understanding that optimized components do not automatically lead to energy-efficient systems sets the attention from the single component on the entire technical system. At TU Darmstadt, a new field of research named Technical Operations Research (TOR) has its origin. It combines mathematical and technical know-how for the optimal design of technical systems. We illustrate our optimization approach in a case study for the design of a ventilation system with the ambition to minimize the energy consumption for a temporal distribution of diverse load demands. By combining scaling laws with our optimization methods we find the optimal combination of fans and show the advantage of the use of multiple fans.}, language = {en} }