TY - CHAP A1 - Bauer, Gregor A1 - Grossmann, Benjamin A1 - Schlegl, Thomas A1 - Kobayashi, Hiroshi T1 - Modeling, identification and control of an antagonistically actuated joint for telerobotic systems T2 - IECON 2015 - 41st Annual Conference of the IEEE Industrial Electronics Society, 9-12 Nov. 2015, Yokohama, Japan N2 - Within this paper a modeling, identification and control technique for an antagonistically actuated joint consisting of two pneumatically actuated muscles is presented. The antagonistically actuated joint acts as a test bench for control architectures which are going to be used to control an exoskeleton within a telerobotic system. A static and dynamic model of the muscle and the joint is derived and the parameters of the models are identified using a least-squares algorithm. The control architecture, consisting of a inner pressure and an outer position controller is presented. The pressure controller is evaluated using switching valves compared against proportional valves. KW - DYNAMICS KW - FORCE KW - Muscles KW - Telerobotics KW - Torque KW - Valves Y1 - 2015 U6 - https://doi.org/10.1109/IECON.2015.7392676 SP - 3696 EP - 3701 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 - Weiß, Roman A1 - Großmann, Benjamin A1 - Leibold, Marion A1 - Schlegl, Thomas A1 - Wollherr, Dirk A1 - Weiss, Roman A1 - Grossmann, Benjamin T1 - Modeling and nonlinear control of antagonistically actuating pneumatic artificial muscles T2 - 2017 IEEE International Conference on Advanced Intelligent Mechatronics (AIM), 3-7 July 2017, Munich, Germany N2 - This paper discusses modeling and nonlinear control of a joint antagonistically actuated by two pneumatic, artificial muscles. A single model of the whole system is obtained by a combined physical and phenomenological modeling approach. The combined model for the joint, the muscles and the proportional valves results in a nonlinear, affine-in-control system description. The model is used to derive control laws for an input/output linearization approach to linearize the plant. Modeling and parametrization errors are covered via an outer control loop consisting of a state-feedback which is extended by an additional feedback of error integral. Extensive experimental results show the quality of the model and the performance of the respective control laws. KW - FORCE KW - Muscles KW - Pulleys KW - Robot sensing systems KW - Transfer functions KW - Valves Y1 - 2017 U6 - https://doi.org/10.1109/AIM.2017.8014001 SP - 94 EP - 99 PB - IEEE ER - TY - CHAP A1 - Pohlt, Clemens A1 - Hell, Sebastian A1 - Schlegl, Thomas A1 - Wachsmuth, Sven ED - Wrede, Britta ED - Nagai, Yukie ED - Komatsu, Takanori ED - Hanheide, Marc ED - Natale, Lorenzo T1 - Impact of Spontaneous Human Inputs during Gesture based Interaction on a Real-World Manufacturing Scenario T2 - Proceedings of the 5th International Conference on Human Agent Interaction (HAI '17), Bielefeld Germany, 17.10.2017 -20.10.2017 N2 - Seamless human-robot collaboration depends on high non-verbal behaviour recognition rates. To realize that in real-world manufacturing scenarios with an ecological valid setup, a lot of effort has to be invested. In this paper, we evaluate the impact of spontaneous inputs on the robustness of human-robot collaboration during gesture-based interaction. A high share of these spontaneous inputs lead to a reduced capability to predict behaviour and subsequently to a loss of robustness. We observe body and hand behaviour during interactive manufacturing of a collaborative task within two experiments. First, we analyse the occurrence frequency, reason and manner of human inputs in specific situations during a human-human experiment. We show the high impact of spontaneous inputs, especially in situations that differ from the typical working procedure. Second, we concentrate on implicit inputs during a real-world Wizard of Oz experiment using our human-robot working cell. We show that hand positions can be used to anticipate user needs in a semi-structured environment by applying knowledge about the semi-structured human behaviour which is distributed over working space and time in a typical manner. Y1 - 2017 SN - 9781450351133 U6 - https://doi.org/10.1145/3125739.3132590 SP - 347 EP - 351 PB - ACM CY - New York, NY ER - TY - CHAP A1 - Pohlt, Clemens A1 - Schlegl, Thomas A1 - Wachsmuth, Sven T1 - Weakly-Supervised Learning for Multimodal Human Activity Recognition in Human-Robot Collaboration Scenarios T2 - 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS): October 25-29, 2020, Las Vegas, NV, USA (virtual) N2 - The ability to synchronize expectations among human-robot teams and understand discrepancies between expectations and reality is essential for human-robot collaboration scenarios. To ensure this, human activities and intentions must be interpreted quickly and reliably by the robot using various modalities. In this paper we propose a multimodal recognition system designed to detect physical interactions as well as nonverbal gestures. Existing approaches feature high post-transfer recognition rates which, however, can only be achieved based on well-prepared and large datasets. Unfortunately, the acquisition and preparation of domain-specific samples especially in industrial context is time consuming and expensive. To reduce this effort we introduce a weakly-supervised classification approach. Therefore, we learn a latent representation of the human activities with a variational autoencoder network. Additional modalities and unlabeled samples are incorporated by a scalable product-of-expert sampling approach. The applicability in industrial context is evaluated by two domain-specific collaborative robot datasets. Our results demonstrate, that we can keep the number of labeled samples constant while increasing the network performance by providing additional unprocessed information. KW - Activity recognition KW - Collaboration KW - Intelligent robots KW - reliability KW - Service robots KW - Synchronization Y1 - 2020 U6 - https://doi.org/10.1109/IROS45743.2020.9340788 SP - 8381 EP - 8386 PB - IEEE ER - TY - JOUR A1 - Niedersteiner, Sascha A1 - Lang, Jonas A1 - Pohlt, Clemens A1 - Schlegl, Thomas T1 - Klassifikation des Arbeitsfortschritts BT - Support-Vector-Machine-Ansatz für intelligente Arbeitsplätze JF - atp magazin N2 - Steigende Anforderungen an die Qualität von zum Teil manuell gefertigten Produkten führen dazu, dass Handarbeitsplätze mit Assistenzsystemen für die Unterstützung der am Arbeitsplatz arbeitenden Mitarbeiterinnen und Mitarbeiter ausgestattet werden. Der Beitrag beschreibt einen neuen Ansatz, um mittels Verfahren des maschinellen Lernens die Objekterkennung sowie die Transitionen eines, den Arbeitsprozess repräsentierenden Zustandsautomaten eines solchen Systems einzulernen. Hierfür werden nach einer Vorverarbeitung Daten aus einer Tiefenkamera in drei Stufen durch Support Vector Machines (SVM) klassifiziert und das Ergebnis mit dem Zustandsautomaten verknüpft. Das Konzept wird an einem industriellen Montageprozess überschaubarer Komplexität evaluiert; es zeigt gute Ergebnisse hinsichtlich der Robustheit gegenüber Fehlern bei der Objektklassifikation. KW - assistierender Arbeitsplatz KW - Maschinelles Lernen KW - Mensch-Maschine-Interaktion KW - robuste Erkennung des Arbeitsfortschritts KW - Tiefenkamera Y1 - 2017 U6 - https://doi.org/10.17560/atp.v59i11.1911 VL - 59 IS - 11 SP - 58 EP - 66 PB - Vulkan-Verlag ER - TY - JOUR A1 - Niedersteiner, Sascha A1 - Lang, Jonas A1 - Pohlt, Clemens A1 - Schlegl, Thomas T1 - Tracking work task completion - A support vector machine approach for assisting workbenches JF - atp edition N2 - Tightening quality requirements of industrial products involving manual assembly lead to the development of assisting workbenches with integrated functions to support workers performing these manual tasks. This contribution discusses a new approach to learning transitions of a finite state automaton representing the sequence of work tasks based on the video stream of a 3D depth camera. Preprocessed video data is fed into a three-stage classification scheme based on support vector machines. The results of the classification are then related to the state automation to trigger state transitions indicating the completion of a specific work task and the start of the next one. The proposed approach has been evaluated at an industrial assembly process of moderate complexity and shows very robust results with respect to disturbances caused by inaccurate object classification. N2 - Steigende Anforderungen an die Qualität von zum Teil manuell gefertigten Produkten führen dazu, dass Handarbeitsplätze mit Assistenzsystemen für die Unterstützung der am Arbeitsplatz arbeitenden Mitarbeiterinnen und Mitarbeiter ausgestattet werden. Der Beitrag beschreibt einen neuen Ansatz, um mittels Verfahren des maschinellen Lernens die Objekterkennung sowie die Transitionen eines, den Arbeitsprozess repräsentierenden Zustandsautomaten eines solchen Systems einzulernen. Hierfür werden nach einer Vorverarbeitung Daten aus einer Tiefenkamera in drei Stufen durch Support Vector Machines (SVM) klassifiziert und das Ergebnis mit dem Zustandsautomaten verknüpft. Das Konzept wird an einem industriellen Montageprozess überschaubarer Komplexität evaluiert; es zeigt gute Ergebnisse hinsichtlich der Robustheit gegenüber Fehlern bei der Objektklassifikation. T2 - Klassifikation des Arbeitsfortschritts - Support-Vector-Machine-Ansatz für intelligente Arbeitsplätze KW - 3D depth camera KW - assisting workbench KW - human-machine interaction KW - Machine learning KW - robust tracking of task completion KW - SYSTEM Y1 - 2017 U6 - https://doi.org/10.17560/atp.v59i11.1911 IS - 11 SP - 58 EP - 66 PB - DIV Deutscher Industrieverl. ER - TY - CHAP A1 - Niedersteiner, Sascha A1 - Pohlt, Clemens A1 - Schlegl, Thomas T1 - Smart Workbench: A Multimodal and Bidirectional Assistance System for Industrial Application T2 - IECON 2015 - 41st Annual Conference of the IEEE Industrial Electronics Society, 09.-12.11.2015, Yokohama, Japan N2 - Manual tasks in industrial production are often monotonous, leading to a decrease in concentration and motivation of the worker and thus to deficiencies in the products. With quality as well as performance requirements getting more and more stringent, workers need additional support by their work environment. We developed a novel approach providing worker assistance and inline quality assurance for manual workplaces. The prototypical system Smart Workbench (SWoB) uses a multimodal sensor interface consisting of a 3D depth sensor in combination with a 2D camera to control quality aspects of the product and track the work progress. The bidirectional flow of information is handled via an image processing driven gestural interface and the displaying of advice directly on the work surface. In this paper the developed system is introduced and the current state of evaluating its industrial usage with a manual quality control and packaging task reported. Y1 - 2015 SN - 978-1-4799-1762-4 SN - 978-1-4799-1761-7 U6 - https://doi.org/10.1109/iecon.2015.7392549 PB - IEEE CY - Piscataway, N.J. ER - TY - JOUR A1 - Großmann, Benjamin A1 - Schlegl, Thomas T1 - Development of a Hybrid Path/Force Control Architecture for an Assisting Robot JF - International journal of mechanics and control : JoMaC N2 - For human machine interaction a control ar chitecture for the force controlled guidance mode of a five axis robot is developed. This enables a human operator to move the robot easily by applying forces at th e end-effector. The position and th e path can then be tracked and stored for a later reuse. The control archit ecture is also used in a hybrid mode where it is possible to control chosen workspace coordinates with a path controller and others with a force controller. The hybrid mode is especially used to cut tissue material with a scalpel which is mounted at the robots effector. KW - robotics KW - force control KW - hybrid control KW - assisting robot Y1 - 2014 UR - http://www.jomac.it/data/uploads/freeissue/jomac14a.pdf SN - 1590-8844 VL - 15 IS - 1 SP - 27 EP - 34 PB - Levrotto&Bella CY - Torino ER - TY - JOUR A1 - Schlegl, Peter A1 - Robatzek, Patrick A1 - Kucera, Markus A1 - Volbert, Klaus A1 - Waas, Thomas T1 - Performance analysis of mobile radio for automatic control in smart grids JF - International Journal of Advancements in Electronics and Electrical Engineering N2 - In the context of a "Smart Grid" research project, together with industrial partners, the OTH-Regensburg realized an intelligent medium-voltage grid in the local area. Goal was to improve the current voltage regulation and to counter the problems with inconsistent energy feed-in of decentralized renewable energy producers. In this paper we discuss the possibilities of using 3rd generation (3G) cellular networks (UMTS) as basic technology to communicate the voltage-levels within a medium-voltage grid. We build an experimental hardware setup to generate data-traffic as specified for the smart grid. By analyzing the performance of 3G cellular networks in terms of transmission latency and rate of failure, we tried to evaluate the usability of this technology for such critical data exchange. Though mobile communication in its structure is not specified for the use of transmitting such infrastructure critical data, the results show a promising high reliability with low transmission latency. The experiments served just to test a fragment of the conditions of use in a real scenario. An expanded test scope is needed to further analyze the performance of mobile radio for automatic control in smart grids. In the end the results discussed in this paper led to a successful prototype of an intelligent medium-voltage grid with mobile radio as communication technology KW - mobile radio KW - cellular data transmission KW - 3G KW - 4G KW - Smart Grid KW - communication Y1 - 2014 UR - http://journals.theired.org/journals/paper/details/5456.html SN - 2319-7498 VL - 4 IS - 1 SP - 69 EP - 75 ER - TY - JOUR A1 - Broll, Alexander A1 - Rosentritt, Martin A1 - Schlegl, Thomas A1 - Goldhacker, Markus T1 - A data-driven approach for the partial reconstruction of individual human molar teeth using generative deep learning JF - Frontiers in Artificial Intelligence N2 - Background and objectiveDue to the high prevalence of dental caries, fixed dental restorations are regularly required to restore compromised teeth or replace missing teeth while retaining function and aesthetic appearance. The fabrication of dental restorations, however, remains challenging due to the complexity of the human masticatory system as well as the unique morphology of each individual dentition. Adaptation and reworking are frequently required during the insertion of fixed dental prostheses (FDPs), which increase cost and treatment time. This article proposes a data-driven approach for the partial reconstruction of occlusal surfaces based on a data set that comprises 92 3D mesh files of full dental crown restorations.MethodsA Generative Adversarial Network (GAN) is considered for the given task in view of its ability to represent extensive data sets in an unsupervised manner with a wide variety of applications. Having demonstrated good capabilities in terms of image quality and training stability, StyleGAN-2 has been chosen as the main network for generating the occlusal surfaces. A 2D projection method is proposed in order to generate 2D representations of the provided 3D tooth data set for integration with the StyleGAN architecture. The reconstruction capabilities of the trained network are demonstrated by means of 4 common inlay types using a Bayesian Image Reconstruction method. This involves pre-processing the data in order to extract the necessary information of the tooth preparations required for the used method as well as the modification of the initial reconstruction loss.ResultsThe reconstruction process yields satisfactory visual and quantitative results for all preparations with a root mean square error (RMSE) ranging from 0.02 mm to 0.18 mm. When compared against a clinical procedure for CAD inlay fabrication, the group of dentists preferred the GAN-based restorations for 3 of the total 4 inlay geometries.ConclusionsThis article shows the effectiveness of the StyleGAN architecture with a downstream optimization process for the reconstruction of 4 different inlay geometries. The independence of the reconstruction process and the initial training of the GAN enables the application of the method for arbitrary inlay geometries without time-consuming retraining of the GAN. KW - inlay restoration KW - dental prosthesis design KW - StyleGAN KW - machine learning KW - digital dentistry Y1 - 2024 U6 - https://doi.org/10.3389/frai.2024.1339193 SN - 2624-8212 VL - 7 PB - Frontiers Media SA ER -