Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

Motion imitation and recognition using parametric hidden Markov models

Herzog, Dennis ; Ude, Aleš and Krüger, Volker LU orcid (2008) 2008 8th IEEE-RAS International Conference on Humanoid Robots, Humanoids 2008 p.339-346
Abstract

The recognition and synthesis of parametric movements play an important role in human-robot interaction. To understand the whole purpose of an arm movement of a human agent, both its recognition (e.g., pointing or reaching) as well as its parameterization (i.e., where the agent is pointing at) are important. Only together they convey the whole meaning of an action. Similarly, to imitate a movement, the robot needs to select the proper action and parameterize it, e. g., by the relative position of the object that needs to be grasped. We propose to utilize parametric hidden Markov models (PH-MMs), which extend the classical HMMs by introducing a joint parameterization of the observation densities, to simultaneously solve the problems of... (More)

The recognition and synthesis of parametric movements play an important role in human-robot interaction. To understand the whole purpose of an arm movement of a human agent, both its recognition (e.g., pointing or reaching) as well as its parameterization (i.e., where the agent is pointing at) are important. Only together they convey the whole meaning of an action. Similarly, to imitate a movement, the robot needs to select the proper action and parameterize it, e. g., by the relative position of the object that needs to be grasped. We propose to utilize parametric hidden Markov models (PH-MMs), which extend the classical HMMs by introducing a joint parameterization of the observation densities, to simultaneously solve the problems of action recognition, parameterization of the observed actions, and action synthesis. The proposed approach was fully implemented on a humanoid robot HOAP-3. To evaluate the approach, we focused on reaching and pointing actions. Even though the movements are very similar in appearance, our approach is able to distinguish the two movement types and discover the parameterization, and is thus enabling both, action recognition and action synthesis. Through parameterization we ensure that the synthesized movements can be applied to different configurations of the external world and are thus suitable for actions that involve the manipulation of objects.

(Less)
Please use this url to cite or link to this publication:
author
; and
publishing date
type
Chapter in Book/Report/Conference proceeding
publication status
published
subject
host publication
2008 8th IEEE-RAS International Conference on Humanoid Robots, Humanoids 2008
article number
4756002
pages
8 pages
publisher
IEEE - Institute of Electrical and Electronics Engineers Inc.
conference name
2008 8th IEEE-RAS International Conference on Humanoid Robots, Humanoids 2008
conference location
Daejeon, Korea, Republic of
conference dates
2008-12-01 - 2008-12-03
external identifiers
  • scopus:63549139567
ISBN
978-1-4244-2821-2
DOI
10.1109/ICHR.2008.4756002
language
English
LU publication?
no
id
090fdae2-3e98-4d6f-bee8-a80e2bec17db
date added to LUP
2019-06-28 09:25:36
date last changed
2022-01-31 22:50:20
@inproceedings{090fdae2-3e98-4d6f-bee8-a80e2bec17db,
  abstract     = {{<p>The recognition and synthesis of parametric movements play an important role in human-robot interaction. To understand the whole purpose of an arm movement of a human agent, both its recognition (e.g., pointing or reaching) as well as its parameterization (i.e., where the agent is pointing at) are important. Only together they convey the whole meaning of an action. Similarly, to imitate a movement, the robot needs to select the proper action and parameterize it, e. g., by the relative position of the object that needs to be grasped. We propose to utilize parametric hidden Markov models (PH-MMs), which extend the classical HMMs by introducing a joint parameterization of the observation densities, to simultaneously solve the problems of action recognition, parameterization of the observed actions, and action synthesis. The proposed approach was fully implemented on a humanoid robot HOAP-3. To evaluate the approach, we focused on reaching and pointing actions. Even though the movements are very similar in appearance, our approach is able to distinguish the two movement types and discover the parameterization, and is thus enabling both, action recognition and action synthesis. Through parameterization we ensure that the synthesized movements can be applied to different configurations of the external world and are thus suitable for actions that involve the manipulation of objects.</p>}},
  author       = {{Herzog, Dennis and Ude, Aleš and Krüger, Volker}},
  booktitle    = {{2008 8th IEEE-RAS International Conference on Humanoid Robots, Humanoids 2008}},
  isbn         = {{978-1-4244-2821-2}},
  language     = {{eng}},
  month        = {{12}},
  pages        = {{339--346}},
  publisher    = {{IEEE - Institute of Electrical and Electronics Engineers Inc.}},
  title        = {{Motion imitation and recognition using parametric hidden Markov models}},
  url          = {{http://dx.doi.org/10.1109/ICHR.2008.4756002}},
  doi          = {{10.1109/ICHR.2008.4756002}},
  year         = {{2008}},
}