Publication
Distance-based kernels for dynamical movement primitives
Conference Article
Conference
Catalan Conference on Artificial Intelligence (CCIA)
Edition
18th
Pages
133-142
Doc link
http://dx.doi.org/10.3233/978-1-61499-578-4-133
File
Abstract
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 using the shape-attractor instead of weights is feasible for both formulations. In addition, we propose to use distance-based kernels, as RBF and TrE, to classify DMPs in some predefined actions. Our experiments based on an existing dataset and using 1-NN and SVM techniques confirm that shape-attractor function is a better choice for movement recognition with DMPs.
Categories
generalisation (artificial intelligence), learning (artificial intelligence), pattern recognition.
Author keywords
trajectories, DMP, learning, kernel, classification, 1-NN, SVM, actions
Scientific reference
D. Escudero and R. Alquézar Mancho. Distance-based kernels for dynamical movement primitives, 18th Catalan Conference on Artificial Intelligence, 2015, Valencia, in Artificial Intelligence Research and Development, Vol 277 of Frontiers in Artificial Intelligence and Applications, pp. 133-142, 2015, IOS Press.
Follow us!