Planning, Training and Learning in Supervision of Flexible Assembly Systems

Luís Manuel Camarinha-Matos; Luis Seabra Lopes

doi:10.1007/978-0-387-34910-7_7

Planning, Training and Learning in Supervision of Flexible Assembly Systems

Luís Manuel Camarinha-Matos, Luis Seabra Lopes

DEE - Departamento de Engenharia Electrotécnica e de Computadores

Research output: Chapter in Book/Report/Conference proceeding › Foreword/postscript › peer-review

Abstract

In the context of balanced automation systems, a generic architecture for evolutive supervision of robotized assembly tasks is presented. This architecture provides, at various abstraction levels, functions for dispatching actions, execution monitoring, and diagnosing and recovering from failures. A planning strategy and domain knowledge for nominal plan execution and error recovery is described. Through the use of machine learning techniques, the supervision architecture will be given capabilities to improve its performance over time. The participation of humans in the training and supervision activities is considered essential. The combination of human interactivity with automatic aspects (planning, learning,..) is discussed.

Original language	English
Title of host publication	Balanced Automation Systems
Publisher	Springer
Pages	63-74
Number of pages	12
ISBN (Print)	0-412-72200-3
DOIs	https://doi.org/10.1007/978-0-387-34910-7_7
Publication status	Published - Jan 1995
Event	BASYS'95 – IEEE/IFIP Int. Conf. On Balanced Automation Systems - Victoria, Brazil Duration: 23 Jul 1995 → 26 Jul 1995

Conference

Conference	BASYS'95 – IEEE/IFIP Int. Conf. On Balanced Automation Systems
Abbreviated title	BASYS'95
Country	Brazil
City	Victoria
Period	23/07/95 → 26/07/95

Keywords

Robotized assembly
action sequence planning
monitoring
failure diagnosis
machine learning

Access to Document

10.1007/978-0-387-34910-7_7

Cite this

@inbook{be439473db0a4a9aa0498acd6d9390e1,

title = "Planning, Training and Learning in Supervision of Flexible Assembly Systems",

abstract = "In the context of balanced automation systems, a generic architecture for evolutive supervision of robotized assembly tasks is presented. This architecture provides, at various abstraction levels, functions for dispatching actions, execution monitoring, and diagnosing and recovering from failures. A planning strategy and domain knowledge for nominal plan execution and error recovery is described. Through the use of machine learning techniques, the supervision architecture will be given capabilities to improve its performance over time. The participation of humans in the training and supervision activities is considered essential. The combination of human interactivity with automatic aspects (planning, learning,..) is discussed.",

keywords = "Robotized assembly, action sequence planning, monitoring, failure diagnosis, machine learning",

author = "Camarinha-Matos, {Lu{\'i}s Manuel} and Lopes, {Luis Seabra}",

year = "1995",

month = jan,

doi = "10.1007/978-0-387-34910-7_7",

language = "English",

isbn = "0-412-72200-3",

pages = "63--74",

booktitle = "Balanced Automation Systems",

publisher = "Springer",

note = "BASYS'95 – IEEE/IFIP Int. Conf. On Balanced Automation Systems, BASYS'95 ; Conference date: 23-07-1995 Through 26-07-1995",

}

TY - CHAP

T1 - Planning, Training and Learning in Supervision of Flexible Assembly Systems

AU - Camarinha-Matos, Luís Manuel

AU - Lopes, Luis Seabra

PY - 1995/1

Y1 - 1995/1

N2 - In the context of balanced automation systems, a generic architecture for evolutive supervision of robotized assembly tasks is presented. This architecture provides, at various abstraction levels, functions for dispatching actions, execution monitoring, and diagnosing and recovering from failures. A planning strategy and domain knowledge for nominal plan execution and error recovery is described. Through the use of machine learning techniques, the supervision architecture will be given capabilities to improve its performance over time. The participation of humans in the training and supervision activities is considered essential. The combination of human interactivity with automatic aspects (planning, learning,..) is discussed.

AB - In the context of balanced automation systems, a generic architecture for evolutive supervision of robotized assembly tasks is presented. This architecture provides, at various abstraction levels, functions for dispatching actions, execution monitoring, and diagnosing and recovering from failures. A planning strategy and domain knowledge for nominal plan execution and error recovery is described. Through the use of machine learning techniques, the supervision architecture will be given capabilities to improve its performance over time. The participation of humans in the training and supervision activities is considered essential. The combination of human interactivity with automatic aspects (planning, learning,..) is discussed.

KW - Robotized assembly

KW - action sequence planning

KW - monitoring

KW - failure diagnosis

KW - machine learning

U2 - 10.1007/978-0-387-34910-7_7

DO - 10.1007/978-0-387-34910-7_7

M3 - Foreword/postscript

SN - 0-412-72200-3

SP - 63

EP - 74

BT - Balanced Automation Systems

PB - Springer

T2 - BASYS'95 – IEEE/IFIP Int. Conf. On Balanced Automation Systems

Y2 - 23 July 1995 through 26 July 1995

ER -

Planning, Training and Learning in Supervision of Flexible Assembly Systems

Abstract

Conference

Keywords

Access to Document

Fingerprint

Cite this