Now showing 1 - 10 of 178
  • Publication
    PowerGrasp: Development Aspects for Arm Support Systems
    ( 2022)
    Goppold, J.-P.
    ;
    Kuschan, J.
    ;
    Schmidt, H.
    ;
    Krüger, J.
    Exoskeletons can support workers on physically demanding tasks, but in industry they lack of acceptance. This contribution gives an insight into design aspects for upper body exoskeletons, especially how active exoskeletons for industrial applications differ from military and medical use-cases. To overcome typical rigid exoskeleton problems, we suggest the use of modular soft-exosuit support systems and therefore checked different types of soft actuation principles for their eligibility for the use on upper body joints. Most promising approach is using two-layered actuators sting of robust fabric with embedded rubber tubes as pressure chambers. By inflating the tubes, it is possible to vary the stiffness of the chambers, which can be effectively used to generate assisting forces and moments at human joints (shoulder, elbow, wrist, finger).
  • Publication
    Data driven automatic parameter inference for robotic assembly programs
    ( 2021)
    Stephan, P.
    ;
    Fisch, J.
    ;
    Can, A.
    ;
    Heimann, O.
    ;
    Thiele, G.
    ;
    Krüger, J.
    In a high-mix low volume production environment, time to market is a key factor. However, one bottleneck lies in the often times manual parametrization of machines for new or modified designs. A truly flexible manufacturing environment therefore requires a continuous data flow from the design stages to the shop floor. This paper presents a concept for the automated parameterization of machines at a large automotive plant. It describes the interface requirements of the stakeholders involved as well as the overall system architecture. Finally, the paper presents first results of a prototype tested in serial production, spanning more than 100 machines.
  • Publication
    How can the programming of impedance control be simplified?
    ( 2021)
    Cruz, A.B.
    ;
    Radke, M.
    ;
    Haninger, K.
    ;
    Krüger, J.
    Impedance control uses force/torque measurements to adapt a robot's motion, broadening a robot's capabilities in contact tasks. However, potential benefits of impedance control are largely not realized in industry, partly due to complexity: it requires a large number of parameters (compliance frame, impedance parameters, reference position/force) and expertise to set these parameters for a specific application. Pre-defined action templates can be used to hide and preset parameters as required for a specific action, potentially reducing the expertise and time required for an integration. However, objectives and methods to design such primitives are not well-established. This paper considers application requirements common in impedance control, and how actions can be designed to support such requirements. Parameter sensitivity and independence are considered, supported experimentally with a 'hole-in-peg' assembly task, where the impact of compliance frame and environmental uncertainty are analyzed.
  • Publication
    Universal identification and control of industrial manufacturing equipment as a service
    ( 2021)
    Tessaro, V.
    ;
    Vick, A.
    ;
    Krüger, J.
    This paper presents a universal approach of identification and closed-loop control of manufacturing equipment, de- livered through web services using Open Platform Communications United Architecture (OPC UA). Rapid prototyping as well as retrofitting and digitization of legacy systems often need design and application of closed-loop controllers. The analysis and modelling for systems such as energy-conversion or material transport devices is labour-intensive and needs process understanding. Current identification and control toolboxes require systematic preparation of input/output data, modification and tuning of the derived models, also proper design of classic PID controllers. An on-demand service paradigm is applied to allow identification and control with direct access to the controlled system over a network connection. The identified parameters are used to adapt a model predictive controller (MPC), which stabilizes the system and drives trajectories to different operating points. To evaluate the performance of the controllers in terms of stability, accuracy, and time response, several target trajectories and disturbances (signal noise, external physical disturbances, latency in communication) were investigated. The identification service was used to model the linear dynamics of a 6-DOF industrial robot and a laboratory-scale waterworks containing two separately controllable pumps. The robot's axes and the waterworks' pumps were successfully controlled with current set-points by using their respective identified state-space models. Simulation and laboratory experiments show promising results for the control of diverse systems with varying time-constants, and imply broad applicability. As a major achievement, this approach enables to efficiently implement system identification and model predictive control in manufacturing.
  • Publication
    Fatigue recognition in overhead assembly based on a soft robotic exosuit for worker assistance
    ( 2021)
    Kuschan, J.
    ;
    Krüger, J.
    Physical stress and overuse during assembly tasks is one of the main causes of musculoskeletal disorders of workers. Innovative body-worn robotic assist systems aim to reduce the physical stress in manual assembly and handling operations. A novel approach for automatic fatigue detection using machine learning techniques, combined with body-borne sensors, enables early detection and classification of fatigue. This article introduces the new method for an innovative soft robotic exosuit for physical worker assistance. The feasibility of the method is demonstrated in a case study for overhead car assembly.
  • Publication
    Inertial measurement unit based human action recognition for soft-robotic exoskeletons
    ( 2021)
    Kuschan, J.
    ;
    Burgdorff, M.
    ;
    Filaretov, H.
    ;
    Krüger, J.
    Absence from work caused by overloading the musculoskeletal system lowers the life quality of the worker and entails unnecessary costs for both the employer and the health system. Soft-robotic exoskeletons offer a possibility to overcome these problems by increasing the system flexibility, not limiting the supported Degrees of Freedom and being simultaneously an actuator and a joint. Since such exoskeletons can only be designed for using power when supporting the wearer, battery lifetime can be increased by covering only those actions for which support is needed. As regards controls, a major difficulty lies in finding a compromise between saving energy and supporting the wearer. However, an action-depending control can reduce the supported actions to only relevant ones and increase battery lifetime. The system conditions include detection of user actions in real time and distinguishing between actions requiring and not requiring support. We contributed an analysis and modification of human action recognition (HAR) benchmark algorithms from activities of daily living, transferred them onto industrial use cases and made the models compatible with embedded computers for real-time recognition on soft exoskeletons. We identified the most common challenges for inertial measurement unit based HAR and compared the best-performing algorithms using a newly recorded dataset of overhead car assembly for industrial relevance. By introducing orientation estimation, F1-scores could be increased by up to 0.04. With an overall F1-score without a Null class of up to 0.883, we were able to lay the foundation for using HAR for action dependent force support.
  • Publication
    DRL-basierte Navigationsansätze in der industriellen Robotik
    ( 2021)
    Kästner, L.
    ;
    Lambrecht, J.
    ;
    Vick, A.
    ;
    Krüger, J.
    Mobile Roboter sind in verschiedenen Bereichen der Industrie zu wichtigen Werkzeugen geworden, insbesondere in der Logistik. Die sichere Navigation in hochdynamischen Umgebungen stellt jedoch weiterhin eine große Herausforderung für klassische Pfadplanungsansätze dar. Deep Reinforcement Learning (DRL) hat sich als alternative Planungsmethode herauskristallisiert, um allzu konservative Ansätze zu ersetzen und verspricht eine effizientere und flexiblere Navigation. Diese Ansätze sind jedoch aufgrund ihrer Anfälligkeit für lokale Minima und das Mangeln eines Langzeitgedächtnisses nicht für die Langstreckennavigation geeignet, was eine breite Integration in industrielle Anwendungen der mobilen Robotik behindert. Dieser Beitrag stellt einen Ansatz für die Integration von DRL-basierter Navigation in existierende Navigationsansätze von industrieller mobiler Robotik vor.
  • Publication
    AI-enhanced Identification, Inspection and Sorting for Reverse Logistics in Remanufacturing
    ( 2021)
    Schlüter, M.
    ;
    Lickert, H.
    ;
    Schweitzer, K.
    ;
    Bilge, P.
    ;
    Briese, C.
    ;
    Dietrich, F.
    ;
    Krüger, J.
    In a circular economy for remanufacturing, after each life cycle used products are returned to a remanufacturer for identification, inspection, sorting and reprocessing. Shortcomings and requirements of the remanufacturing market are identified through expert interviews and process analysis. A concept is proposed to enable an improved identification and a more objective inspection by enhancing the working environment and processes of sorting stations. Digitization and machine learning are applied on business data, using machine vision as well as sensor and actor skills of the worker. With an experimental case study on visual object recognition a positive impact on identification and thus sorting could be demonstrated.
  • Publication
    Resilienz durch Redundanz. Cloud-und Edge-basierte Echtzeitsteuerung von autonomen mobilen Robotern
    ( 2021)
    Nouruzi-Pur, J.
    ;
    Lambrecht, J.
    ;
    Nguyen, T.D.
    ;
    Vick, A.
    ;
    Krüger, J.
    Die Auslagerung von Algorithmen auf Edge- und Cloud- umgebungen nach dem Software-as-a-Service-Paradigma bringt viele Vorteile für autonome mobile Roboter mit sich. Es kann jedoch nicht immer garantiert werden, dass die QoS-Anforderungen der ausgelagerten echtzeitkritischen Funktionen erfüllt sind. Das Bereitstellen von redundanten Kommunikationsmöglichkeiten und Berechnungsknoten sowie robotergesteuertes Umschalten ermöglichen Echtzeitfähigkeit innerhalb dieser unsicheren Infrastrukturen.
  • Publication
    Towards Deep Learning in Industrial Applications Taking Advantage of Service-Oriented Architectures
    ( 2020)
    Briese, C.
    ;
    Schlüter, M.
    ;
    Lehr, J.
    ;
    Maurer, K.
    ;
    Krüger, J.
    In reverse logistics, identification of products is necessary but due to uninterpretable markers information flow is not always consistent. Recent image-based recognition developments using Convolutional Neural Networks are promising but collecting required labeled data is time- and cost-intensive. To allow a quick deployment and usage of such systems, we present a conceptual service-oriented architecture that enables Deep Learning recognition systems to be used with initially small but growing data sets, as with every usage training data expands on run-time. An identification problem is reduced to digitization and labeling of data and as a side effect digital knowledge retention can be established in companies.