Advanced

Connecting natural language to task demonstrations and low-level control of industrial robots

Stenmark, Maj LU and Malec, Jacek LU (2015) In CEUR Workshop Proceedings 1540. p.25-29
Abstract

Industrial robotics is a complex domain, not easily amenable to formalization using semantic technologies. It involves such disparate aspects of the real world as geometry, dynamics, constraint-satisfaction, planning and scheduling, real-time control, robot-robot and human-robot communication and, finally, intentions of the robot user. To represent so different kinds of knowledge is a challenge and the research on combining those topics is only in its infancy. This paper describes our attempts to combine descriptions of robot tasks using natural language together with their realizations using robot hardware involving force sensing, ultimately leading to a potential of learning new robot skills employing force-based assembly. We believe... (More)

Industrial robotics is a complex domain, not easily amenable to formalization using semantic technologies. It involves such disparate aspects of the real world as geometry, dynamics, constraint-satisfaction, planning and scheduling, real-time control, robot-robot and human-robot communication and, finally, intentions of the robot user. To represent so different kinds of knowledge is a challenge and the research on combining those topics is only in its infancy. This paper describes our attempts to combine descriptions of robot tasks using natural language together with their realizations using robot hardware involving force sensing, ultimately leading to a potential of learning new robot skills employing force-based assembly. We believe it is a novel approach opening possibilities of semantic anchoring for learning from demonstration.

(Less)
Please use this url to cite or link to this publication:
author
organization
publishing date
type
Contribution to journal
publication status
published
subject
in
CEUR Workshop Proceedings
volume
1540
pages
5 pages
external identifiers
  • Scopus:84964053756
ISSN
1613-0073
language
English
LU publication?
yes
id
1173e008-13f8-4fae-a420-e9304bd26a5d
date added to LUP
2016-09-23 13:19:18
date last changed
2017-01-01 08:35:07
@article{1173e008-13f8-4fae-a420-e9304bd26a5d,
  abstract     = {<p>Industrial robotics is a complex domain, not easily amenable to formalization using semantic technologies. It involves such disparate aspects of the real world as geometry, dynamics, constraint-satisfaction, planning and scheduling, real-time control, robot-robot and human-robot communication and, finally, intentions of the robot user. To represent so different kinds of knowledge is a challenge and the research on combining those topics is only in its infancy. This paper describes our attempts to combine descriptions of robot tasks using natural language together with their realizations using robot hardware involving force sensing, ultimately leading to a potential of learning new robot skills employing force-based assembly. We believe it is a novel approach opening possibilities of semantic anchoring for learning from demonstration.</p>},
  author       = {Stenmark, Maj and Malec, Jacek},
  issn         = {1613-0073},
  language     = {eng},
  pages        = {25--29},
  series       = {CEUR Workshop Proceedings},
  title        = {Connecting natural language to task demonstrations and low-level control of industrial robots},
  volume       = {1540},
  year         = {2015},
}