File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Conference Paper: Collaborative Human-Robot Motion Generation Using LSTM-RNN

TitleCollaborative Human-Robot Motion Generation Using LSTM-RNN
Authors
Zhao, XuanChumkamon, SakmongkonDuan, ShuandaRojas, JuanPan, Jia
Issue Date6-Nov-2018
PublisherIEEE
Abstract

We propose a deep learning based method for fast and responsive human-robot handovers that generate robot motion according to human motion observations. Our method learns an offline human-robot interaction model through a Recurrent Neural Network with Long Short-Term Memory units (LSTM-RNN). The robot uses the learned network to respond appropriately to novel online human motions. Our method is tested both on pre-recorded data and real-world human-robot handover experiments. Our method achieves robot motion accuracies that outperform the baseline. In addition, our method demonstrates a strong ability to adapt to changes in velocity of human motions.


Persistent Identifierhttp://hdl.handle.net/10722/369711

 

DC FieldValueLanguage
dc.contributor.authorZhao, Xuan-
dc.contributor.authorChumkamon, Sakmongkon-
dc.contributor.authorDuan, Shuanda-
dc.contributor.authorRojas, Juan-
dc.contributor.authorPan, Jia-
dc.date.accessioned2026-01-30T00:36:04Z-
dc.date.available2026-01-30T00:36:04Z-
dc.date.issued2018-11-06-
dc.identifier.urihttp://hdl.handle.net/10722/369711-
dc.description.abstract<p>We propose a deep learning based method for fast and responsive human-robot handovers that generate robot motion according to human motion observations. Our method learns an offline human-robot interaction model through a Recurrent Neural Network with Long Short-Term Memory units (LSTM-RNN). The robot uses the learned network to respond appropriately to novel online human motions. Our method is tested both on pre-recorded data and real-world human-robot handover experiments. Our method achieves robot motion accuracies that outperform the baseline. In addition, our method demonstrates a strong ability to adapt to changes in velocity of human motions.</p>-
dc.languageeng-
dc.publisherIEEE-
dc.relation.ispartofIEEE-RAS 18th International Conference on Humanoid Robots (Humanoids 2018) (06/11/2018-09/11/2018, Beijing)-
dc.titleCollaborative Human-Robot Motion Generation Using LSTM-RNN-
dc.typeConference_Paper-
dc.identifier.doi10.1109/HUMANOIDS.2018.8625068-

Export via OAI-PMH Interface in XML Formats

OR

Export to Other Non-XML Formats