File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Conference Paper: Teach robots understanding new object types and attributes through natural language instructions

TitleTeach robots understanding new object types and attributes through natural language instructions
Authors
Issue Date2016
PublisherIEEE. The Journal's web site is located at https://ieeexplore.ieee.org/xpl/conhome.jsp?punumber=1002593
Citation
2016 10th International Conference on Sensing Technology (ICST), Nanjing, China, 11-13 November 2016, p. 1-6 How to Cite?
AbstractRobots often have limited knowledge about the environment and need to continuously acquire new knowledge in order to collaborate with the humans. To address this issue, this paper presents a method which allows the human to teach a robot new object types and attributes through natural language (NL) instructions. A simple yet robust vision algorithm is proposed to segment objects and describe the relations between objects. The segmented objects as well as their relations are regarded as the basic knowledge of the robot. The NL instructions are processed to domain-specific representations for the robot to identify the target objects. The target objects as well as the object type or attribute labels referred in the NL instructions are collected as training samples for the robot to learn. Experimental results demonstrate the effectiveness and advantages of the proposed method.
Persistent Identifierhttp://hdl.handle.net/10722/261968

 

DC FieldValueLanguage
dc.contributor.authorBao, J-
dc.contributor.authorHong, Z-
dc.contributor.authorTang, H-
dc.contributor.authorCheng, Y-
dc.contributor.authorJia, Y-
dc.contributor.authorXi, N-
dc.date.accessioned2018-09-28T04:51:07Z-
dc.date.available2018-09-28T04:51:07Z-
dc.date.issued2016-
dc.identifier.citation2016 10th International Conference on Sensing Technology (ICST), Nanjing, China, 11-13 November 2016, p. 1-6-
dc.identifier.urihttp://hdl.handle.net/10722/261968-
dc.description.abstractRobots often have limited knowledge about the environment and need to continuously acquire new knowledge in order to collaborate with the humans. To address this issue, this paper presents a method which allows the human to teach a robot new object types and attributes through natural language (NL) instructions. A simple yet robust vision algorithm is proposed to segment objects and describe the relations between objects. The segmented objects as well as their relations are regarded as the basic knowledge of the robot. The NL instructions are processed to domain-specific representations for the robot to identify the target objects. The target objects as well as the object type or attribute labels referred in the NL instructions are collected as training samples for the robot to learn. Experimental results demonstrate the effectiveness and advantages of the proposed method.-
dc.languageeng-
dc.publisherIEEE. The Journal's web site is located at https://ieeexplore.ieee.org/xpl/conhome.jsp?punumber=1002593-
dc.relation.ispartofInternational Conference on Sensing Technology (ICST) Proceedings-
dc.rightsInternational Conference on Sensing Technology (ICST) Proceedings. Copyright © IEEE.-
dc.rights©2016 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.-
dc.titleTeach robots understanding new object types and attributes through natural language instructions-
dc.typeConference_Paper-
dc.identifier.emailXi, N: xining@hku.hk-
dc.identifier.authorityXi, N=rp02044-
dc.identifier.doi10.1109/ICSensT.2016.7796256-
dc.identifier.scopuseid_2-s2.0-85010041765-
dc.identifier.hkuros292808-
dc.identifier.spage1-
dc.identifier.epage6-
dc.publisher.placeUnited States-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats