Carregant...
Carregant...

Vés al contingut (premeu Retorn)

Distance-based kernels for dynamical movement primitives

Autor
Escudero, D.; Alquezar, R.
Tipus d'activitat
Presentació treball a congrés
Nom de l'edició
18th International Conference of the Catalan Association for Artificial Intelligence
Any de l'edició
2015
Data de presentació
2015
Llibre d'actes
Artificial Intelligence Research and Development: Proceedings of the 18th International Conference of the Catalan Association for Artificial Intelligence (CCIA 2015) held in Valencia, Spain, in October 2015
Pàgina inicial
133
Pàgina final
142
Editor
IOS Press
DOI
10.3233/978-1-61499-578-4-133
Repositori
http://hdl.handle.net/2117/83964 Obrir en finestra nova
URL
http://ebooks.iospress.nl/publication/40927 Obrir en finestra nova
Resum
In the Anchoring Problem actions and objects must be anchored to symbols; and movement primitives as DMPs seems a good option to describe actions. In the bottom-up approach to anchoring, the recognition of an action is done applying learning techniques as clustering. Although most work done about movement recognition with DMPs is focus on weights, we propose to use the shape-attractor function as feature vector. As several DMPs formulations exist, we have analyzed the two most known to check if ...
Citació
Escudero, D., Alquézar, R. Distance-based kernels for dynamical movement primitives. A: International Conference of the Catalan Association for Artificial Intelligence. "Artificial intelligence research and development: proceedings of the 18th international conference of the Catalan Association for Artificial Intelligence". València: IOS Press, 2015, p. 133-142.
Paraules clau
Generalisation (artificial Intelligence), Learning (artificial Intelligence), Pattern Recognition, Trajectories, Dmp, Learning, Kernel, Classification, 1-nn, Svm, Actions
Grup de recerca
VIS - Visió Artificial i Sistemes Intel.ligents

Participants