Por favor, use este identificador para citar o enlazar a este item:
http://hdl.handle.net/10261/127300
COMPARTIR / EXPORTAR:
SHARE CORE BASE | |
Visualizar otros formatos: MARC | Dublin Core | RDF | ORE | MODS | METS | DIDL | DATACITE | |
Título: | Active learning of manipulation sequences |
Autor: | Martínez, David CSIC; Alenyà, Guillem CSIC ORCID ; Jiménez Schlegl, Pablo ; Torras, Carme CSIC ORCID ; Rossmann, Jürgen; Wantia, Nils; Aksoy, Eren Erdal; Haller, Simon; Piater, Justus | Fecha de publicación: | 2014 | Editor: | Institute of Electrical and Electronics Engineers | Citación: | IEEE International Conference on Robotics and Automation: 5671-5678 (2014) | Resumen: | We describe a system allowing a robot to learn goal-directed manipulation sequences such as steps of an assembly task. Learning is based on a free mix of exploration and instruction by an external teacher, and may be active in the sense that the system tests actions to maximize learning progress and asks the teacher if needed. The main component is a symbolic planning engine that operates on learned rules, defined by actions and their pre- and postconditions. Learned by model-based reinforcement learning, rules are immediately available for planning. Thus, there are no distinct learning and application phases. We show how dynamic plans, replanned after every action if necessary, can be used for automatic execution of manipulation sequences, for monitoring of observed manipulation sequences, or a mix of the two, all while extending and refining the rule base on the fly. Quantitative results indicate fast convergence using few training examples, and highly effective teacher intervention at early stages of learning. | Descripción: | Trabajo presentado al ICRA 2014 celebrado en Hong Kong del 31 de mayo al 7 de junio. | Versión del editor: | http://dx.doi.org/10.1109/ICRA.2014.6907693 | URI: | http://hdl.handle.net/10261/127300 | DOI: | 10.1109/ICRA.2014.6907693 | Identificadores: | issn: 1050-4729 |
Aparece en las colecciones: | (IRII) Artículos |
Ficheros en este ítem:
Fichero | Descripción | Tamaño | Formato | |
---|---|---|---|---|
manipulation-sequences.pdf | 1,79 MB | Adobe PDF | Visualizar/Abrir |
CORE Recommender
SCOPUSTM
Citations
17
checked on 16-mar-2024
Page view(s)
264
checked on 19-abr-2024
Download(s)
230
checked on 19-abr-2024
Google ScholarTM
Check
Altmetric
Altmetric
NOTA: Los ítems de Digital.CSIC están protegidos por copyright, con todos los derechos reservados, a menos que se indique lo contrario.