File Download
Supplementary

Conference Paper: Multi-contour initial pose estimation for 3D registration

TitleMulti-contour initial pose estimation for 3D registration
Authors
Issue Date2015
PublisherIEEE/RSJ.
Citation
The 2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2015), Hamburg, Germany, 28 September-2 October 2015. How to Cite?
AbstractReliable manipulation of everyday household objects is essential to the success of service robots. In order to accurately manipulate these objects, robots need to know objects’ full 6-DOF pose, which is challenging due to sensor noise, clutters and occlusions. In this paper, we present a new approach for effectively guessing the object pose given an observation of just a small patch of the object, by leveraging the fact that many household objects can only keep stable on a planar surface under a small set of poses. In particular, for each stable pose of an object, we slice the object with horizontal planes and extract multiple cross-section contours. The pose estimation is then reduced to find a stable pose whose contour matches best with that of the sensor data, and this can be solved efficiently by convolution. Experiments on the manipulation tasks in the DARPA Robotics Challenge validate our approach. In addition, we also investigate our method’s performance on object recognition tasks raising in the challenge.
Persistent Identifierhttp://hdl.handle.net/10722/211508

 

DC FieldValueLanguage
dc.contributor.authorCheung, CHE-
dc.contributor.authorCao, C-
dc.contributor.authorPan, J-
dc.date.accessioned2015-07-16T02:01:09Z-
dc.date.available2015-07-16T02:01:09Z-
dc.date.issued2015-
dc.identifier.citationThe 2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2015), Hamburg, Germany, 28 September-2 October 2015.-
dc.identifier.urihttp://hdl.handle.net/10722/211508-
dc.description.abstractReliable manipulation of everyday household objects is essential to the success of service robots. In order to accurately manipulate these objects, robots need to know objects’ full 6-DOF pose, which is challenging due to sensor noise, clutters and occlusions. In this paper, we present a new approach for effectively guessing the object pose given an observation of just a small patch of the object, by leveraging the fact that many household objects can only keep stable on a planar surface under a small set of poses. In particular, for each stable pose of an object, we slice the object with horizontal planes and extract multiple cross-section contours. The pose estimation is then reduced to find a stable pose whose contour matches best with that of the sensor data, and this can be solved efficiently by convolution. Experiments on the manipulation tasks in the DARPA Robotics Challenge validate our approach. In addition, we also investigate our method’s performance on object recognition tasks raising in the challenge.-
dc.languageeng-
dc.publisherIEEE/RSJ.-
dc.relation.ispartofIEEE/RSJ International Conference on Intelligent Robots and Systems-
dc.rightsCreative Commons: Attribution 3.0 Hong Kong License-
dc.titleMulti-contour initial pose estimation for 3D registration-
dc.typeConference_Paper-
dc.identifier.emailCheung, CHE: ernest1@hku.hk-
dc.identifier.emailPan, J: jpan@cs.hku.hk-
dc.identifier.authorityPan, J=rp01984-
dc.description.naturepostprint-
dc.identifier.hkuros244990-
dc.publisher.placeHamburg, Germany-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats