Robotic agent control combining reactive and learning capabilities

Witold Jacak; Stephan Dreiseitl

Robotic agent control combining reactive and learning capabilities

Publikation: Konferenzbeitrag › Papier › Begutachtung

Abstract

This paper presents the concept of an autonomous robotic agent combining reactive and machine learning-based algorithms. The focus is on the machine learning-based part that we implement by neural networks. A method for reducing the environment state space to a smaller conceptual world space is given. We then show how the concept of 'lifelong learning' can be implemented by neural networks in a robotic action planner.

Originalsprache	Englisch
Seiten	1682-1686
Seitenumfang	5
Publikationsstatus	Veröffentlicht - 1996
Extern publiziert	Ja
Veranstaltung	Proceedings of the 1996 IEEE International Conference on Neural Networks, ICNN. Part 1 (of 4) - Washington, DC, USA Dauer: 3 Juni 1996 → 6 Juni 1996

Konferenz

Konferenz	Proceedings of the 1996 IEEE International Conference on Neural Networks, ICNN. Part 1 (of 4)
Ort	Washington, DC, USA
Zeitraum	03.06.1996 → 06.06.1996

Andere Dateien und Links

Link to publication in Scopus

Zitieren

@conference{2d68451b4cef4ce3ab6ca2e669a79a92,

title = "Robotic agent control combining reactive and learning capabilities",

abstract = "This paper presents the concept of an autonomous robotic agent combining reactive and machine learning-based algorithms. The focus is on the machine learning-based part that we implement by neural networks. A method for reducing the environment state space to a smaller conceptual world space is given. We then show how the concept of 'lifelong learning' can be implemented by neural networks in a robotic action planner.",

author = "Witold Jacak and Stephan Dreiseitl",

year = "1996",

language = "English",

pages = "1682--1686",

note = "Proceedings of the 1996 IEEE International Conference on Neural Networks, ICNN. Part 1 (of 4) ; Conference date: 03-06-1996 Through 06-06-1996",

}

TY - CONF

T1 - Robotic agent control combining reactive and learning capabilities

AU - Jacak, Witold

AU - Dreiseitl, Stephan

PY - 1996

Y1 - 1996

N2 - This paper presents the concept of an autonomous robotic agent combining reactive and machine learning-based algorithms. The focus is on the machine learning-based part that we implement by neural networks. A method for reducing the environment state space to a smaller conceptual world space is given. We then show how the concept of 'lifelong learning' can be implemented by neural networks in a robotic action planner.

AB - This paper presents the concept of an autonomous robotic agent combining reactive and machine learning-based algorithms. The focus is on the machine learning-based part that we implement by neural networks. A method for reducing the environment state space to a smaller conceptual world space is given. We then show how the concept of 'lifelong learning' can be implemented by neural networks in a robotic action planner.

UR - http://www.scopus.com/inward/record.url?scp=0029770317&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:0029770317

SP - 1682

EP - 1686

T2 - Proceedings of the 1996 IEEE International Conference on Neural Networks, ICNN. Part 1 (of 4)

Y2 - 3 June 1996 through 6 June 1996

ER -

Robotic agent control combining reactive and learning capabilities

Abstract

Konferenz

Andere Dateien und Links

Fingerprint

Zitieren