A learn by demonstration approach for closed-Loop, robust, anthropomorphic grasp planning

Show simple item record

dc.contributor.author Liarokapis, Minas en
dc.contributor.author Bechlioulis, CP en
dc.contributor.author Boutselis, GI en
dc.contributor.author Kyriakopoulos, KJ en
dc.contributor.editor Bianchi, M en
dc.contributor.editor Moscatelli, A en
dc.date.accessioned 2018-10-09T23:02:34Z en
dc.date.issued 2016 en
dc.identifier.isbn 978-3-319-26706-7 en
dc.identifier.uri http://hdl.handle.net/2292/40136 en
dc.description.abstract This chapter presents a learn by demonstration approach, for closed-loop, robust, anthropomorphic grasp planning. In this respect, human demonstrations are used to perform skill transfer between the human and the robot artifacts, mapping human to robot motion with functional anthropomorphism [1]. In this work we extend the synergistic description adopted in Chaps. 2–6 for human grasping, in Chap. 8 for robotic hand design and, finally, in Chap. 15 for hand pose reconstruction systems, to define a low-dimensional manifold where the extracted anthropomorphic robot arm hand system kinematics are projected and appropriate Navigation Function (NF) models are trained. The training of the NF models is performed in a task-specific manner, for various: (1) subspaces, (2) objects and (3) tasks to be executed with the corresponding object. A vision system based on RGB-D cameras (Kinect, Microsoft) provides online feedback, performing object detection, object pose estimation and triggering the appropriate NF models. The NF models formulate a closed-loop velocity control scheme, that ensures humanlikeness of robot motion and guarantees convergence to the desired goals. The aforementioned scheme is also supplemented with a grasping control methodology, that derives task-specific, force closure grasps, utilizing tactile sensing. This methodology takes into consideration the mechanical and geometric limitations imposed by the robot hand design and enables stable grasps of a plethora of everyday life objects, under a wide range of uncertainties. The efficiency of the proposed methods is verified through extensive experimental paradigms, with the Mitsubishi PA10 – DLR/HIT II 22 DoF robot arm hand system. en
dc.publisher Springer International Publishing en
dc.relation.ispartof Human and robot hands: Sensorimotor synergies to bridge the gap between neuroscience and robotics en
dc.relation.ispartofseries Springer series on touch and haptic systems en
dc.rights Items in ResearchSpace are protected by copyright, with all rights reserved, unless otherwise indicated. Previously published items are made available in accordance with the copyright policy of the publisher. en
dc.rights.uri https://researchspace.auckland.ac.nz/docs/uoa-docs/rights.htm en
dc.title A learn by demonstration approach for closed-Loop, robust, anthropomorphic grasp planning en
dc.type Book Item en
dc.identifier.doi 10.1007/978-3-319-26706-7_9 en
pubs.begin-page 127 en
dc.rights.holder Copyright: The author en
pubs.end-page 149 en
pubs.place-of-publication Switzerland en
dc.rights.accessrights http://purl.org/eprint/accessRights/RestrictedAccess en
pubs.elements-id 606886 en
pubs.org-id Engineering en
pubs.org-id Mechanical Engineering en
pubs.number Part II en
pubs.record-created-at-source-date 2017-01-17 en


Files in this item

There are no files associated with this item.

Find Full text

This item appears in the following Collection(s)

Show simple item record

Share

Search ResearchSpace


Browse

Statistics