Learning Nullspace Policies

Christopher Towell; Matthew Howard; Sethu Vijayakumar

Learning Nullspace Policies

Christopher Towell, Matthew Howard, Sethu Vijayakumar

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract / Description of output

Many everyday tasks performed by people, such as reaching, pointing or drawing, resolve redundant degrees of freedom in the arm in a similar way. In this paper we present a novel method for learning the strategy used to resolve redundancy by exploiting the variability in multiple observations of different tasks. We demonstrate the effectiveness of this method on three simulated plants: a toy example, a three link planar arm, and the KUKA lightweight arm.

Original language	English
Title of host publication	IEEE/RSJ 2010 INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS 2010)
Place of Publication	NEW YORK
Publisher	Institute of Electrical and Electronics Engineers (IEEE)
Pages	-
Number of pages	8
ISBN (Print)	978-1-4244-6675-7
Publication status	Published - 2010
Event	IEEE/RSJ International Conference on Intelligent Robots and Systems - Taipei Duration: 18 Oct 2010 → 22 Oct 2010

Conference

Conference	IEEE/RSJ International Conference on Intelligent Robots and Systems
City	Taipei
Period	18/10/10 → 22/10/10

Cite this

@inproceedings{9c6e1eb19f784d6ea0892cdc1d6dcab9,

title = "Learning Nullspace Policies",

abstract = "Many everyday tasks performed by people, such as reaching, pointing or drawing, resolve redundant degrees of freedom in the arm in a similar way. In this paper we present a novel method for learning the strategy used to resolve redundancy by exploiting the variability in multiple observations of different tasks. We demonstrate the effectiveness of this method on three simulated plants: a toy example, a three link planar arm, and the KUKA lightweight arm.",

author = "Christopher Towell and Matthew Howard and Sethu Vijayakumar",

year = "2010",

language = "English",

isbn = "978-1-4244-6675-7",

pages = "--",

booktitle = "IEEE/RSJ 2010 INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS 2010)",

publisher = "Institute of Electrical and Electronics Engineers (IEEE)",

address = "United States",

note = "IEEE/RSJ International Conference on Intelligent Robots and Systems ; Conference date: 18-10-2010 Through 22-10-2010",

}

TY - GEN

T1 - Learning Nullspace Policies

AU - Towell, Christopher

AU - Howard, Matthew

AU - Vijayakumar, Sethu

PY - 2010

Y1 - 2010

N2 - Many everyday tasks performed by people, such as reaching, pointing or drawing, resolve redundant degrees of freedom in the arm in a similar way. In this paper we present a novel method for learning the strategy used to resolve redundancy by exploiting the variability in multiple observations of different tasks. We demonstrate the effectiveness of this method on three simulated plants: a toy example, a three link planar arm, and the KUKA lightweight arm.

AB - Many everyday tasks performed by people, such as reaching, pointing or drawing, resolve redundant degrees of freedom in the arm in a similar way. In this paper we present a novel method for learning the strategy used to resolve redundancy by exploiting the variability in multiple observations of different tasks. We demonstrate the effectiveness of this method on three simulated plants: a toy example, a three link planar arm, and the KUKA lightweight arm.

M3 - Conference contribution

SN - 978-1-4244-6675-7

SP - -

BT - IEEE/RSJ 2010 INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS 2010)

PB - Institute of Electrical and Electronics Engineers (IEEE)

CY - NEW YORK

T2 - IEEE/RSJ International Conference on Intelligent Robots and Systems

Y2 - 18 October 2010 through 22 October 2010

ER -

Learning Nullspace Policies

Abstract / Description of output

Conference

Fingerprint

Cite this