Automatic stimulation of experiments and learning based on prediction failure recognition

A.G. Juarez Cordova; B. Kahl; T. Henne; E. Prassler

doi:10.1109/ROBOT.2009.5152285

Automatic stimulation of experiments and learning based on prediction failure recognition

A.G. Juarez Cordova
, B. Kahl
, T. Henne
, E. Prassler

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

223 Downloads (Pure)

Abstract

In this paper we focus on the task of automatically and autonomously initiating experimentation and learning based on the recognition of prediction failure. We present a mechanism that utilizes conceptual knowledge to predict the outcome of robot actions, observes their execution and indicates when discrepancies occur. We show how this mechanism was applied to a robot that learns using the paradigm of learning by experimentation, and present first results obtained from this implementation.

Original language	English
Title of host publication	Proceedings of 2009 IEEE International Conference on Robotics and Automation, Kobe, Japan
Publisher	Institute of Electrical and Electronics Engineers
Pages	3607-3612
ISBN (Print)	978-1-4244-2789-5
DOIs	https://doi.org/10.1109/ROBOT.2009.5152285
Publication status	Published - 2009
Event	conference; 2009 IEEE International Conference on Robotics and Automation, Kobe, Japan; 2009-05-12; 2009-05-17 - Duration: 12 May 2009 → 17 May 2009

Conference

Conference	conference; 2009 IEEE International Conference on Robotics and Automation, Kobe, Japan; 2009-05-12; 2009-05-17
Period	12/05/09 → 17/05/09
Other	2009 IEEE International Conference on Robotics and Automation, Kobe, Japan

Access to Document

10.1109/ROBOT.2009.5152285

Metis234624Final published version, 837 KB

Cite this

@inproceedings{899726afb13c412297e109880b0b612f,

title = "Automatic stimulation of experiments and learning based on prediction failure recognition",

abstract = "In this paper we focus on the task of automatically and autonomously initiating experimentation and learning based on the recognition of prediction failure. We present a mechanism that utilizes conceptual knowledge to predict the outcome of robot actions, observes their execution and indicates when discrepancies occur. We show how this mechanism was applied to a robot that learns using the paradigm of learning by experimentation, and present first results obtained from this implementation.",

author = "\{Juarez Cordova\}, A.G. and B. Kahl and T. Henne and E. Prassler",

year = "2009",

doi = "10.1109/ROBOT.2009.5152285",

language = "English",

isbn = "978-1-4244-2789-5",

pages = "3607--3612",

booktitle = "Proceedings of 2009 IEEE International Conference on Robotics and Automation, Kobe, Japan",

publisher = "Institute of Electrical and Electronics Engineers",

address = "United States",

note = "conference; 2009 IEEE International Conference on Robotics and Automation, Kobe, Japan; 2009-05-12; 2009-05-17 ; Conference date: 12-05-2009 Through 17-05-2009",

}

Juarez Cordova, AG, Kahl, B, Henne, T & Prassler, E 2009, Automatic stimulation of experiments and learning based on prediction failure recognition. in Proceedings of 2009 IEEE International Conference on Robotics and Automation, Kobe, Japan. Institute of Electrical and Electronics Engineers, pp. 3607-3612, conference; 2009 IEEE International Conference on Robotics and Automation, Kobe, Japan; 2009-05-12; 2009-05-17, 12/05/09. https://doi.org/10.1109/ROBOT.2009.5152285

Automatic stimulation of experiments and learning based on prediction failure recognition. / Juarez Cordova, A.G.; Kahl, B.; Henne, T. et al.
Proceedings of 2009 IEEE International Conference on Robotics and Automation, Kobe, Japan. Institute of Electrical and Electronics Engineers, 2009. p. 3607-3612.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

TY - GEN

T1 - Automatic stimulation of experiments and learning based on prediction failure recognition

AU - Juarez Cordova, A.G.

AU - Kahl, B.

AU - Henne, T.

AU - Prassler, E.

PY - 2009

Y1 - 2009

N2 - In this paper we focus on the task of automatically and autonomously initiating experimentation and learning based on the recognition of prediction failure. We present a mechanism that utilizes conceptual knowledge to predict the outcome of robot actions, observes their execution and indicates when discrepancies occur. We show how this mechanism was applied to a robot that learns using the paradigm of learning by experimentation, and present first results obtained from this implementation.

AB - In this paper we focus on the task of automatically and autonomously initiating experimentation and learning based on the recognition of prediction failure. We present a mechanism that utilizes conceptual knowledge to predict the outcome of robot actions, observes their execution and indicates when discrepancies occur. We show how this mechanism was applied to a robot that learns using the paradigm of learning by experimentation, and present first results obtained from this implementation.

U2 - 10.1109/ROBOT.2009.5152285

DO - 10.1109/ROBOT.2009.5152285

M3 - Conference contribution

SN - 978-1-4244-2789-5

SP - 3607

EP - 3612

BT - Proceedings of 2009 IEEE International Conference on Robotics and Automation, Kobe, Japan

PB - Institute of Electrical and Electronics Engineers

T2 - conference; 2009 IEEE International Conference on Robotics and Automation, Kobe, Japan; 2009-05-12; 2009-05-17

Y2 - 12 May 2009 through 17 May 2009

ER -

Automatic stimulation of experiments and learning based on prediction failure recognition

Abstract

Conference

Access to Document

Fingerprint

Cite this