Research in learning from demonstration has focused on transferring movements from humans to robots. However, a need is arising for robots that do not just replicate the task on their own, but that also interact with humans in a safe and natural way to accomplish tasks cooperatively. Robots with variable impedance capabilities opens the door to new challenging applications, where the learning algorithms must be extended by encapsulating force and vision information. In this paper we propose a framework to transfer impedance-based behaviors to a torque-controlled robot by kinesthetic teaching. The proposed model encodes the exam- ples as a task-parameterized statistical dynamical system, where the robot impedance is shaped by estimating virtual stiffness matrices from the set of demonstrations. A collaborative assembly task is used as testbed. The results show that the model can be used to modify the robot impedance along task execution to facilitate the collaboration, by triggering stiff and compliant behaviors in an on-line manner to adapt to the user's actions. ; Peer Reviewed ; Postprint (author’s final draft)


    Access

    Download


    Export, share and cite



    Learning collaborative impedance-based robot behaviors

    Rozo, Leonel / Calinon, Sylvain / Caldwell, Darwin et al. | BASE | 2013

    Free access

    Learning physical collaborative robot behaviors from human demonstrations

    Rozo Castañeda, Leonel / Calinon, Sylvain / Caldwell, Darwin et al. | BASE | 2016

    Free access

    Learning physical collaborative robot behaviors from human demonstrations

    Rozo, Leonel / Calinon, Sylvain / Caldwell, Darwin et al. | BASE | 2016

    Free access

    Learning outdoor mobile robot behaviors by example

    Roberts, R. / Pippin, C. / Balch, T. | British Library Online Contents | 2009


    A Cognitive Robot Collaborative Reinforcement Learning Algorithm

    Amit Gil / Helman Stern / Yael Edan | BASE | 2009

    Free access