Conventional robot programming methods are not suited for non-experts to intuitively teach robots new tasks. For this reason, the potential of collaborative robots for production cannot yet be fully exploited. In this work, we propose an active learning framework, in which the robot and the user collaborate to incrementally program a complex task. Starting with a basic model, the robot's task knowledge can be extended over time if new situations require additional skills. An on-line anomaly detection algorithm therefore automatically identifies new situations during task execution by monitoring the deviation between measured- and commanded sensor values. The robot then triggers a teaching phase, in which the user decides to either refine an existing skill or demonstrate a new skill. The different skills of a task are encoded in separate probabilistic models and structured in a high-level graph, guaranteeing robust execution and successful transition between skills. In the experiments, our approach is compared to two state-of-the-art Programming by Demonstration frameworks on a real system. Increased intuitiveness and task performance of the method can be shown, allowing shop-floor workers to program industrial tasks with our framework.


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Collaborative Programming of Conditional Robot Tasks


    Beteiligte:

    Kongress:

    2020 ; Las Vegas, NV, USA (Virtual)



    Erscheinungsdatum :

    2020


    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch




    Intuitive Programming of Conditional Tasks by Demonstration of Multiple Solutions

    Eiband, Thomas / Saveriano, Matteo / Lee, Dongheui | Deutsches Zentrum für Luft- und Raumfahrt (DLR) | 2019

    Freier Zugriff


    Ux in ar-supported industrial human–robot collaborative tasks: A systematic review

    Khamaisi R. K. / Prati E. / Peruzzini M. et al. | BASE | 2021

    Freier Zugriff

    Investigating Collaborative Robot Gripper Configurations for Simple Fabric Pick and Place Tasks

    Djuric, Ana / Wang, Bowen / Kalami, Hamed et al. | SAE Technical Papers | 2019


    Ux in ar-supported industrial human–robot collaborative tasks: A systematic review

    Khamaisi R. K. / Prati E. / Peruzzini M. et al. | BASE | 2021

    Freier Zugriff