The RACE Project: Robustness by Autonomous Competence Enhancement

Joachim Hertzberg; Jianwei Zhang; Liwei Zhang; Sebastian Rockel; Bernd Neumann; Jos Lehmann; Krishna S.R. Dubba; Anthony G. Cohn; Alessandro Saffiotti; Federico Pecora; Masoumeh Mansouri; Štefan Konečný; Martin Günther; Sebastian Stock; Luis Seabra Lopes; Miguel Oliveira; Gi Hyun Lim; Hamidreza Kasaei; Vahid Mokhtari; Lothar Hotz; Wilfried Bohlken

doi:10.1007/s13218-014-0327-y

The RACE Project: Robustness by Autonomous Competence Enhancement

Joachim Hertzberg^*, Jianwei Zhang, Liwei Zhang, Sebastian Rockel, Bernd Neumann, Jos Lehmann, Krishna S.R. Dubba, Anthony G. Cohn, Alessandro Saffiotti, Federico Pecora, Masoumeh Mansouri, Štefan Konečný, Martin Günther, Sebastian Stock, Luis Seabra Lopes, Miguel Oliveira, Gi Hyun Lim, Hamidreza Kasaei, Vahid Mokhtari, Lothar HotzWilfried Bohlken

^*Corresponding author for this work

Computer Science

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

18 Citations (Scopus)

Abstract

This paper reports on the aims, the approach, and the results of the European project RACE. The project aim was to enhance the behavior of an autonomous robot by having the robot learn from conceptualized experiences of previous performance, based on initial models of the domain and its own actions in it. This paper introduces the general system architecture; it then sketches some results in detail regarding hybrid reasoning and planning used in RACE, and instances of learning from the experiences of real robot task execution. Enhancement of robot competence is operationalized in terms of performance quality and description length of the robot instructions, and such enhancement is shown to result from the RACE system.

Original language	English
Pages (from-to)	297-304
Number of pages	8
Journal	KI - Kunstliche Intelligenz
Volume	28
Issue number	4
Early online date	21 Sept 2014
DOIs	https://doi.org/10.1007/s13218-014-0327-y
Publication status	Published - Nov 2014

Keywords

Control Architecture
Early Integration
Object Category
Perceptual Memory
Plan Execution

ASJC Scopus subject areas

Artificial Intelligence

Access to Document

10.1007/s13218-014-0327-yLicence: None: All rights reserved

https://doi.org/10.1007/s13218-014-0327-yLicence: None: All rights reserved

Cite this

Hertzberg, J., Zhang, J., Zhang, L., Rockel, S., Neumann, B., Lehmann, J., Dubba, K. S. R., Cohn, A. G., Saffiotti, A., Pecora, F., Mansouri, M., Konečný, Š., Günther, M., Stock, S., Lopes, L. S., Oliveira, M., Lim, G. H., Kasaei, H., Mokhtari, V., ... Bohlken, W. (2014). The RACE Project: Robustness by Autonomous Competence Enhancement. KI - Kunstliche Intelligenz, 28(4), 297-304. Advance online publication. https://doi.org/10.1007/s13218-014-0327-y

@article{8a9ccadaba534154baaf3c6d7a960486,

title = "The RACE Project: Robustness by Autonomous Competence Enhancement",

abstract = "This paper reports on the aims, the approach, and the results of the European project RACE. The project aim was to enhance the behavior of an autonomous robot by having the robot learn from conceptualized experiences of previous performance, based on initial models of the domain and its own actions in it. This paper introduces the general system architecture; it then sketches some results in detail regarding hybrid reasoning and planning used in RACE, and instances of learning from the experiences of real robot task execution. Enhancement of robot competence is operationalized in terms of performance quality and description length of the robot instructions, and such enhancement is shown to result from the RACE system.",

keywords = "Control Architecture, Early Integration, Object Category, Perceptual Memory, Plan Execution",

author = "Joachim Hertzberg and Jianwei Zhang and Liwei Zhang and Sebastian Rockel and Bernd Neumann and Jos Lehmann and Dubba, {Krishna S.R.} and Cohn, {Anthony G.} and Alessandro Saffiotti and Federico Pecora and Masoumeh Mansouri and {\v S}tefan Kone{\v c}n{\'y} and Martin G{\"u}nther and Sebastian Stock and Lopes, {Luis Seabra} and Miguel Oliveira and Lim, {Gi Hyun} and Hamidreza Kasaei and Vahid Mokhtari and Lothar Hotz and Wilfried Bohlken",

year = "2014",

month = nov,

doi = "10.1007/s13218-014-0327-y",

language = "English",

volume = "28",

pages = "297--304",

journal = "KI - Kunstliche Intelligenz",

issn = "0933-1875",

publisher = "Springer",

number = "4",

}

Hertzberg, J, Zhang, J, Zhang, L, Rockel, S, Neumann, B, Lehmann, J, Dubba, KSR, Cohn, AG, Saffiotti, A, Pecora, F, Mansouri, M, Konečný, Š, Günther, M, Stock, S, Lopes, LS, Oliveira, M, Lim, GH, Kasaei, H, Mokhtari, V, Hotz, L & Bohlken, W 2014, 'The RACE Project: Robustness by Autonomous Competence Enhancement', KI - Kunstliche Intelligenz, vol. 28, no. 4, pp. 297-304. https://doi.org/10.1007/s13218-014-0327-y

TY - JOUR

T1 - The RACE Project

T2 - Robustness by Autonomous Competence Enhancement

AU - Hertzberg, Joachim

AU - Zhang, Jianwei

AU - Zhang, Liwei

AU - Rockel, Sebastian

AU - Neumann, Bernd

AU - Lehmann, Jos

AU - Dubba, Krishna S.R.

AU - Cohn, Anthony G.

AU - Saffiotti, Alessandro

AU - Pecora, Federico

AU - Mansouri, Masoumeh

AU - Konečný, Štefan

AU - Günther, Martin

AU - Stock, Sebastian

AU - Lopes, Luis Seabra

AU - Oliveira, Miguel

AU - Lim, Gi Hyun

AU - Kasaei, Hamidreza

AU - Mokhtari, Vahid

AU - Hotz, Lothar

AU - Bohlken, Wilfried

PY - 2014/11

Y1 - 2014/11

N2 - This paper reports on the aims, the approach, and the results of the European project RACE. The project aim was to enhance the behavior of an autonomous robot by having the robot learn from conceptualized experiences of previous performance, based on initial models of the domain and its own actions in it. This paper introduces the general system architecture; it then sketches some results in detail regarding hybrid reasoning and planning used in RACE, and instances of learning from the experiences of real robot task execution. Enhancement of robot competence is operationalized in terms of performance quality and description length of the robot instructions, and such enhancement is shown to result from the RACE system.

AB - This paper reports on the aims, the approach, and the results of the European project RACE. The project aim was to enhance the behavior of an autonomous robot by having the robot learn from conceptualized experiences of previous performance, based on initial models of the domain and its own actions in it. This paper introduces the general system architecture; it then sketches some results in detail regarding hybrid reasoning and planning used in RACE, and instances of learning from the experiences of real robot task execution. Enhancement of robot competence is operationalized in terms of performance quality and description length of the robot instructions, and such enhancement is shown to result from the RACE system.

KW - Control Architecture

KW - Early Integration

KW - Object Category

KW - Perceptual Memory

KW - Plan Execution

UR - http://www.scopus.com/inward/record.url?scp=84933054481&partnerID=8YFLogxK

U2 - 10.1007/s13218-014-0327-y

DO - 10.1007/s13218-014-0327-y

M3 - Article

AN - SCOPUS:84933054481

SN - 0933-1875

VL - 28

SP - 297

EP - 304

JO - KI - Kunstliche Intelligenz

JF - KI - Kunstliche Intelligenz

IS - 4

ER -

The RACE Project: Robustness by Autonomous Competence Enhancement

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Fingerprint

Cite this