LEARNING to ACT from OBSERVATION and PRACTICE

Darrin C. Bentivegna; Christopher G. Atkeson; Aleš Ude; Gordon Cheng

doi:10.1142/S0219843604000307

LEARNING to ACT from OBSERVATION and PRACTICE

Darrin C. Bentivegna, Christopher G. Atkeson, Aleš Ude, Gordon Cheng

Research output: Contribution to journal › Article › peer-review

39 Scopus citations

Abstract

We present a method for humanoid robots to quickly learn new dynamic tasks from observing others and from practice. Ways in which the robot can adapt to initial and also changing conditions are described. Agents are given domain knowledge in the form of task primitives. A key element of our approach is to break learning problems up into as many simple learning problems as possible. We present a case study of a humanoid robot learning to play air hockey.

Original language	English
Pages (from-to)	585-611
Number of pages	27
Journal	International Journal of Humanoid Robotics
Volume	1
Issue number	4
DOIs	https://doi.org/10.1142/S0219843604000307
State	Published - 1 Dec 2004
Externally published	Yes

Keywords

Air hockey
Humanoid robot
Imitation
Learning from observation
Locally weighted learning
Movement primitives

Access to Document

10.1142/S0219843604000307

Cite this

@article{8faf01131ccb4f8ea7d59c4468c2d4f1,

title = "LEARNING to ACT from OBSERVATION and PRACTICE",

abstract = "We present a method for humanoid robots to quickly learn new dynamic tasks from observing others and from practice. Ways in which the robot can adapt to initial and also changing conditions are described. Agents are given domain knowledge in the form of task primitives. A key element of our approach is to break learning problems up into as many simple learning problems as possible. We present a case study of a humanoid robot learning to play air hockey.",

keywords = "Air hockey, Humanoid robot, Imitation, Learning from observation, Locally weighted learning, Movement primitives",

author = "Bentivegna, {Darrin C.} and Atkeson, {Christopher G.} and Ale{\v s} Ude and Gordon Cheng",

note = "Publisher Copyright: {\textcopyright} 2004 World Scientific Publishing Company.",

year = "2004",

month = dec,

day = "1",

doi = "10.1142/S0219843604000307",

language = "English",

volume = "1",

pages = "585--611",

journal = "International Journal of Humanoid Robotics",

issn = "0219-8436",

publisher = "World Scientific Publishing Co. Pte Ltd",

number = "4",

}

TY - JOUR

T1 - LEARNING to ACT from OBSERVATION and PRACTICE

AU - Bentivegna, Darrin C.

AU - Atkeson, Christopher G.

AU - Ude, Aleš

AU - Cheng, Gordon

PY - 2004/12/1

Y1 - 2004/12/1

N2 - We present a method for humanoid robots to quickly learn new dynamic tasks from observing others and from practice. Ways in which the robot can adapt to initial and also changing conditions are described. Agents are given domain knowledge in the form of task primitives. A key element of our approach is to break learning problems up into as many simple learning problems as possible. We present a case study of a humanoid robot learning to play air hockey.

AB - We present a method for humanoid robots to quickly learn new dynamic tasks from observing others and from practice. Ways in which the robot can adapt to initial and also changing conditions are described. Agents are given domain knowledge in the form of task primitives. A key element of our approach is to break learning problems up into as many simple learning problems as possible. We present a case study of a humanoid robot learning to play air hockey.

KW - Air hockey

KW - Humanoid robot

KW - Imitation

KW - Learning from observation

KW - Locally weighted learning

KW - Movement primitives

UR - http://www.scopus.com/inward/record.url?scp=34250645111&partnerID=8YFLogxK

U2 - 10.1142/S0219843604000307

DO - 10.1142/S0219843604000307

M3 - Article

AN - SCOPUS:34250645111

SN - 0219-8436

VL - 1

SP - 585

EP - 611

JO - International Journal of Humanoid Robotics

JF - International Journal of Humanoid Robotics

IS - 4

ER -

LEARNING to ACT from OBSERVATION and PRACTICE

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this