000205639 001__ 205639
000205639 005__ 20190317000121.0
000205639 022__ $$a1939-1412
000205639 02470 $$2ISI$$a000346319500009
000205639 0247_ $$2doi$$a10.1109/Toh.2013.54
000205639 037__ $$aARTICLE
000205639 245__ $$aLearning Compliant Manipulation through Kinesthetic and Tactile Human-Robot Interaction
000205639 269__ $$a2014
000205639 260__ $$bIeee Computer Soc$$c2014$$aLos Alamitos
000205639 300__ $$a14
000205639 336__ $$aJournal Articles
000205639 520__ $$aRobot Learning from Demonstration (RLfD) has been identified as a key element for making robots useful in daily lives. A wide range of techniques has been proposed for deriving a task model from a set of demonstrations of the task. Most previous works use learning to model the kinematics of the task, and for autonomous execution the robot then relies on a stiff position controller. While many tasks can and have been learned this way, there are tasks in which controlling the position alone is insufficient to achieve the goals of the task. These are typically tasks that involve contact or require a specific response to physical perturbations. The question of how to adjust the compliance to suit the need of the task has not yet been fully treated in Robot Learning from Demonstration. In this paper, we address this issue and present interfaces that allow a human teacher to indicate compliance variations by physically interacting with the robot during task execution. We validate our approach in two different experiments on the 7 DoF Barrett WAM and KUKA LWR robot manipulators. Furthermore, we conduct a user study to evaluate the usability of our approach from a non-roboticists perspective.
000205639 6531_ $$aRobot learning from demonstration
000205639 6531_ $$aPhysical Human-Robot Interaction
000205639 6531_ $$acompliant control
000205639 6531_ $$aphysical human-robot interaction
000205639 6531_ $$ahaptic feedback
000205639 6531_ $$atactile interfaces
000205639 700__ $$0245199$$g203745$$aKronander, Klas
000205639 700__ $$aBillard, Aude$$g115671$$0240594
000205639 773__ $$j7$$tIeee Transactions On Haptics$$k3$$q367-380
000205639 8564_ $$uhttps://infoscience.epfl.ch/record/205639/files/StiffnessJournal.pdf$$zPostprint$$s3328196$$yPostprint
000205639 909C0 $$xU10660$$0252119$$pLASA
000205639 909C0 $$pNCCR-ROBOTICS$$xU12367$$0252409
000205639 909CO $$qGLOBAL_SET$$pSTI$$particle$$ooai:infoscience.tind.io:205639
000205639 917Z8 $$x115671
000205639 917Z8 $$x203745
000205639 937__ $$aEPFL-ARTICLE-205639
000205639 973__ $$rREVIEWED$$sPUBLISHED$$aEPFL
000205639 980__ $$aARTICLE