Publication

A structured prediction approach for robot imitation learning

Related publications (59)

Graph Chatbot

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.

An Approach for Imitation Learning on Riemannian Manifolds

Sylvain Calinon

In imitation learning, multivariate Gaussians are widely used to encode robot behaviors. Such approaches do not provide the ability to properly represent end-effector orientation, as the distance metric in the space of orientations is not Euclidean. In thi ...

2017

Dynamics of particles with anisotropic mass depending on time and position

Tudor Ratiu

Representations of solutions of equations describing the diffusion and quantum dynamics of particles in a Riemannian manifold are discussed under the assumption that the mass of particles is anisotropic and depends on both time and position. These equation ...

Springer Verlag2015

Codimension one stability of the catenoid under the vanishing mean curvature flow in Minkowski space

Joachim Krieger, Roland Donninger, Willie Wai Yeung Wong

We study time-like hypersurfaces with vanishing mean curvature in the (3+1) dimensional Minkowski space, which are the hyperbolic counterparts to minimal embeddings of Riemannian manifolds. The catenoid is a stationary solution of the associated Cauchy pro ...

Duke Univ Press2015

ShapeNet: Convolutional Neural Networks on Non-Euclidean Manifolds

Pierre Vandergheynst, Michael Bronstein

Feature descriptors play a crucial role in a wide range of geometry analysis and processing applications, including shape correspondence, retrieval, and segmentation. In this paper, we propose ShapeNet, a generalization of the popular convolutional neural ...

2015

Unraveling the Salvinia Paradox: Design Principles for Submerged Superhydrophobicity

Simone Meloni

The complex structure of the Salvinia molesta is investigated via rare event molecular dynamics simulations. Results show that a hydrophilic/hydrophobic patterning together with a re-entrant geometry control the free energy barriers for bubble nucleation a ...

Wiley-Blackwell2015

Principal Flows

Victor Panaretos, Tung Huy Pham, Zhigang Yao

We revisit the problem of extending the notion of principal component analysis (PCA) to multivariate datasets that satisfy nonlinear constraints, therefore lying on Riemannian manifolds. Our aim is to determine curves on the manifold that retain their cano ...

American Statistical Association2014

Principal Polynomial Analysis

Devis Tuia

This paper presents a new framework for manifold learning based on a sequence of principal polynomials that capture the possibly nonlinear nature of the data. The proposed Principal Polynomial Analysis (PPA) generalizes PCA by modeling the directions of ma ...

World Scientific Publ Co Pte Ltd2014

Semi-supervised and unsupervised kernel-based novelty detection with application to remote sensing images

Frank Grégoire Jean de Morsier

The main challenge of new information technologies is to retrieve intelligible information from the large volume of digital data gathered every day. Among the variety of existing data sources, the satellites continuously observing the surface of the Earth ...

EPFL2014

Deformation of complex structures and the coupled Kahler-Yang-Mills equations

Mario Garcia Fernandez

In this work, we define a deformation theory for the coupled Kahler-Yang-Mills equations, generalizing work of Sz,kelyhidi on constant scalar curvature Kahler metrics. We use the theory to find new solutions of the equations via deformation of the complex ...

Oxford University Press2014

Weakly Supervised Alignment Of Image Manifolds With Semantic Ties

Devis Tuia

Aligning data distributions that underwent spectral distortions related to acquisition conditions is a key issue to improve the performance of classifiers applied to multi-temporal and multi-angular images. In this paper, we propose a feature extraction me ...

Ieee2014