Unsupervised learning of action primitives
(2010) 2010 10th IEEE-RAS International Conference on Humanoid Robots, Humanoids 2010 p.554-559- Abstract
Action representation is a key issue in imitation learning for humanoids. With the recent finding of mirror neurons there has been a growing interest in expressing actions as a combination meaningful subparts called primitives. Primitives could be thought of as an alphabet for the human actions. In this paper we observe that human actions and objects can be seen as being intertwined: we can interpret actions from the way the body parts are moving, but as well from how their effect on the involved object. While human movements can look vastly different even under minor changes in location, orientation and scale, the use of the object can provide a strong invariant for the detection of motion primitives. In this paper we propose an... (More)
Action representation is a key issue in imitation learning for humanoids. With the recent finding of mirror neurons there has been a growing interest in expressing actions as a combination meaningful subparts called primitives. Primitives could be thought of as an alphabet for the human actions. In this paper we observe that human actions and objects can be seen as being intertwined: we can interpret actions from the way the body parts are moving, but as well from how their effect on the involved object. While human movements can look vastly different even under minor changes in location, orientation and scale, the use of the object can provide a strong invariant for the detection of motion primitives. In this paper we propose an unsupervised learning approach for action primitives that makes use of the human movements as well as the object state changes. We group actions according to the changes they make to the object state space. Movements that produce the same state change in the object state space are classified to be instances of the same action primitive. This allows us to define action primitives as sets of movements where the movements of each primitive are connected through the object state change they induce.
(Less)
- author
- Sanmohan
; Krüger, Volker
LU
and Kragic, Danica
- publishing date
- 2010-12-01
- type
- Chapter in Book/Report/Conference proceeding
- publication status
- published
- subject
- host publication
- 2010 10th IEEE-RAS International Conference on Humanoid Robots, Humanoids 2010
- article number
- 5686309
- pages
- 6 pages
- publisher
- IEEE - Institute of Electrical and Electronics Engineers Inc.
- conference name
- 2010 10th IEEE-RAS International Conference on Humanoid Robots, Humanoids 2010
- conference location
- Nashville, TN, United States
- conference dates
- 2010-12-06 - 2010-12-08
- external identifiers
-
- scopus:79851504957
- ISBN
- 9781424486908
- 9781424486885
- DOI
- 10.1109/ICHR.2010.5686309
- language
- English
- LU publication?
- no
- id
- 060e3765-64b2-4ea6-8d23-b626c00e50f5
- date added to LUP
- 2019-06-28 09:23:14
- date last changed
- 2024-06-25 21:36:46
@inproceedings{060e3765-64b2-4ea6-8d23-b626c00e50f5, abstract = {{<p>Action representation is a key issue in imitation learning for humanoids. With the recent finding of mirror neurons there has been a growing interest in expressing actions as a combination meaningful subparts called primitives. Primitives could be thought of as an alphabet for the human actions. In this paper we observe that human actions and objects can be seen as being intertwined: we can interpret actions from the way the body parts are moving, but as well from how their effect on the involved object. While human movements can look vastly different even under minor changes in location, orientation and scale, the use of the object can provide a strong invariant for the detection of motion primitives. In this paper we propose an unsupervised learning approach for action primitives that makes use of the human movements as well as the object state changes. We group actions according to the changes they make to the object state space. Movements that produce the same state change in the object state space are classified to be instances of the same action primitive. This allows us to define action primitives as sets of movements where the movements of each primitive are connected through the object state change they induce.</p>}}, author = {{Sanmohan and Krüger, Volker and Kragic, Danica}}, booktitle = {{2010 10th IEEE-RAS International Conference on Humanoid Robots, Humanoids 2010}}, isbn = {{9781424486908}}, language = {{eng}}, month = {{12}}, pages = {{554--559}}, publisher = {{IEEE - Institute of Electrical and Electronics Engineers Inc.}}, title = {{Unsupervised learning of action primitives}}, url = {{http://dx.doi.org/10.1109/ICHR.2010.5686309}}, doi = {{10.1109/ICHR.2010.5686309}}, year = {{2010}}, }