Bitzer, Sebastian

Havoutis, Ioannis

Vijayakumar, Sethu

Asada, Minoru

Hallam, John

Meyer, Jean-Arcady

Tani, Jun

2010-08-24T08:34:06Z

2010-08-24T08:34:06Z

2008

2010-08-24T08:34:06Z

We propose a novel methodology for learning and synthesising whole classes of high dimensional movements from a limited set of demonstrated examples that satisfy some underlying ’latent’ low dimensional task constraints. We employ non-linear dimensionality reduction to extract a canonical latent space that captures some of the essential topology of the unobserved task space. In this latent space, we identify suitable parametrisation of movements with control policies such that they are easily modulated to generate novel movements from the same class and are robust to perturbations. We evaluate our method on controlled simulation experiments with simple robots (reaching and periodic movement tasks) as well as on a data set of very high-dimensional human (punching) movements.We verify that we can generate a continuum of new movements from the demonstrated class from only a few examples in both robotic and human data.

10

10.1007/978-3-540-69134-1_20

978-3-540-69133-4

http://www.springerlink.com/content/r4kq04513317w230/

http://hdl.handle.net/1842/3667

en

Springer-Verlag

Informatics Report Series

EDI-INF-RR-1299

Informatics

Computer Science

Synthesising Novel Movements through Latent Space Modulation of Scalable Control Policies

Book Chapter

From Animals to Animats 10