Inductive generation of diagnostic knowledge for autonomous assembly

L. Seabra Lopes, L. M. Camarinha-Matos

Research output: Contribution to conferencePaper

3 Citations (Scopus)

Abstract

A generic architecture for evolutive supervision of robotized assembly tasks is presented. This architecture provides, at different levels of abstraction, functions for dispatching actions, monitoring their execution, and diagnosing and recovering from failures. Modeling execution failures through taxonomies and causal networks plays a central role in diagnosis and recovery. Through the use of machine learning techniques, the supervision architecture will be given capabilities for improving its performance over time. Particular attention is given to the inductive generation of structured classification knowledge for diagnosis. The applied methodologies, performed experiments and obtained results are described in detail.

Original languageEnglish
Pages2545-2552
Number of pages8
Publication statusPublished - 1995
EventIEEE International Conference on Robotics and Automation - Nagoya, Japan
Duration: 21 May 1995 → …

Conference

ConferenceIEEE International Conference on Robotics and Automation
CountryJapan
CityNagoya
Period21/05/95 → …

Fingerprint

Taxonomies
Learning systems
Recovery
Monitoring
Experiments

Keywords

  • Robot learning
  • SCADA systems
  • Computer simulation
  • Concurrent engineering
  • Failure analysis
  • Flexible manufacturing systems
  • Hierarchical systems
  • Knowledge engineering
  • Monitoring
  • Performance
  • Planning

Cite this

Lopes, L. S., & Camarinha-Matos, L. M. (1995). Inductive generation of diagnostic knowledge for autonomous assembly. 2545-2552. Paper presented at IEEE International Conference on Robotics and Automation, Nagoya, Japan.
Lopes, L. Seabra ; Camarinha-Matos, L. M. / Inductive generation of diagnostic knowledge for autonomous assembly. Paper presented at IEEE International Conference on Robotics and Automation, Nagoya, Japan.8 p.
@conference{b6f1da4c341b41059729ffa42c06a5ad,
title = "Inductive generation of diagnostic knowledge for autonomous assembly",
abstract = "A generic architecture for evolutive supervision of robotized assembly tasks is presented. This architecture provides, at different levels of abstraction, functions for dispatching actions, monitoring their execution, and diagnosing and recovering from failures. Modeling execution failures through taxonomies and causal networks plays a central role in diagnosis and recovery. Through the use of machine learning techniques, the supervision architecture will be given capabilities for improving its performance over time. Particular attention is given to the inductive generation of structured classification knowledge for diagnosis. The applied methodologies, performed experiments and obtained results are described in detail.",
keywords = "Robot learning, SCADA systems, Computer simulation, Concurrent engineering, Failure analysis, Flexible manufacturing systems, Hierarchical systems, Knowledge engineering, Monitoring, Performance, Planning",
author = "Lopes, {L. Seabra} and Camarinha-Matos, {L. M.}",
year = "1995",
language = "English",
pages = "2545--2552",
note = "IEEE International Conference on Robotics and Automation ; Conference date: 21-05-1995",

}

Lopes, LS & Camarinha-Matos, LM 1995, 'Inductive generation of diagnostic knowledge for autonomous assembly' Paper presented at IEEE International Conference on Robotics and Automation, Nagoya, Japan, 21/05/95, pp. 2545-2552.

Inductive generation of diagnostic knowledge for autonomous assembly. / Lopes, L. Seabra; Camarinha-Matos, L. M.

1995. 2545-2552 Paper presented at IEEE International Conference on Robotics and Automation, Nagoya, Japan.

Research output: Contribution to conferencePaper

TY - CONF

T1 - Inductive generation of diagnostic knowledge for autonomous assembly

AU - Lopes, L. Seabra

AU - Camarinha-Matos, L. M.

PY - 1995

Y1 - 1995

N2 - A generic architecture for evolutive supervision of robotized assembly tasks is presented. This architecture provides, at different levels of abstraction, functions for dispatching actions, monitoring their execution, and diagnosing and recovering from failures. Modeling execution failures through taxonomies and causal networks plays a central role in diagnosis and recovery. Through the use of machine learning techniques, the supervision architecture will be given capabilities for improving its performance over time. Particular attention is given to the inductive generation of structured classification knowledge for diagnosis. The applied methodologies, performed experiments and obtained results are described in detail.

AB - A generic architecture for evolutive supervision of robotized assembly tasks is presented. This architecture provides, at different levels of abstraction, functions for dispatching actions, monitoring their execution, and diagnosing and recovering from failures. Modeling execution failures through taxonomies and causal networks plays a central role in diagnosis and recovery. Through the use of machine learning techniques, the supervision architecture will be given capabilities for improving its performance over time. Particular attention is given to the inductive generation of structured classification knowledge for diagnosis. The applied methodologies, performed experiments and obtained results are described in detail.

KW - Robot learning

KW - SCADA systems

KW - Computer simulation

KW - Concurrent engineering

KW - Failure analysis

KW - Flexible manufacturing systems

KW - Hierarchical systems

KW - Knowledge engineering

KW - Monitoring

KW - Performance

KW - Planning

UR - http://www.scopus.com/inward/record.url?scp=0029200661&partnerID=8YFLogxK

M3 - Paper

SP - 2545

EP - 2552

ER -

Lopes LS, Camarinha-Matos LM. Inductive generation of diagnostic knowledge for autonomous assembly. 1995. Paper presented at IEEE International Conference on Robotics and Automation, Nagoya, Japan.