Item


Learning by demonstration applied to underwater intervention

Comunicació de congrés presentada a: 17th International Conference of the Catalan Association for Artificial Intelligence, Barcelona, Catalonia, Spain, October 22-24, 2014

Performing subsea intervention tasks is a challenge due to the complexities of the underwater domain. We propose to use a learning by demonstraition algorithm to intuitively teach an intervention autonomous underwater vehicle (IAUV) how to perform a given task. Taking as an input few operator demonstrations, the algorithm generalizes the task into a model and simultaneously controls the vehicle and the manipulator (using 8 degrees of freedom) to reproduce the task. A complete framework has been implemented in order to integrate the LbD algorithm with the different onboard sensors and actuators. A valve turning intervention task is used to validate the full framework through real experiments conducted in a water tank

This research was sponsored by the Spanish government (COMAROB Project, DPI2011-27977-C03-02) and the PANDORA EU FP7-Project under the Grant agreement FP7-ICT-2011-7-288273

info:eu-repo/grantAgreement/EC/FP7/288273/EU/Persistent Autonomy through Learning, Adaptation, Observation and Re-planning/PANDORA

IOS Press

Manager: Ministerio de Ciencia e Innovación (Espanya)
Author: Carrera Viñas, Arnau
Palomeras Rovira, Narcís
Hurtós Vilarnau, Natàlia
Kormushev, Petar
Carreras Pérez, Marc
Date: 2014
Abstract: Comunicació de congrés presentada a: 17th International Conference of the Catalan Association for Artificial Intelligence, Barcelona, Catalonia, Spain, October 22-24, 2014
Performing subsea intervention tasks is a challenge due to the complexities of the underwater domain. We propose to use a learning by demonstraition algorithm to intuitively teach an intervention autonomous underwater vehicle (IAUV) how to perform a given task. Taking as an input few operator demonstrations, the algorithm generalizes the task into a model and simultaneously controls the vehicle and the manipulator (using 8 degrees of freedom) to reproduce the task. A complete framework has been implemented in order to integrate the LbD algorithm with the different onboard sensors and actuators. A valve turning intervention task is used to validate the full framework through real experiments conducted in a water tank
This research was sponsored by the Spanish government (COMAROB Project, DPI2011-27977-C03-02) and the PANDORA EU FP7-Project under the Grant agreement FP7-ICT-2011-7-288273
Format: application/pdf
Document access: http://hdl.handle.net/10256/17356
Language: eng
Publisher: IOS Press
Collection: info:eu-repo/semantics/altIdentifier/doi/10.3233/978-1-61499-452-7-95
info:eu-repo/semantics/altIdentifier/isbn/978-1-61499-451-0
info:eu-repo/grantAgreement/MICINN//DPI2011-27977-C03-02/ES/COMAROB: ROBOTICA COOPERATIVA MARINA PARA EL MAPEO ACUSTICO Y LA INTERVENCION/
Is part of: info:eu-repo/grantAgreement/EC/FP7/288273/EU/Persistent Autonomy through Learning, Adaptation, Observation and Re-planning/PANDORA
Rights: Tots els drets reservats
Subject: Robots mòbils -- Sistemes de control
Mobile robots -- Control systems
Intel·ligència artificial
Artificial intelligence
Vehicles submergibles
Submersibles
Aprenentatge automàtic
Machine learning
Robots -- Programació
Robots -- Programming
Title: Learning by demonstration applied to underwater intervention
Type: info:eu-repo/semantics/conferenceObject
Repository: DUGiDocs

Subjects

Authors