PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Active sequential learning with tactile feedback
Hannes Saal, Jo-Anne Ting and Sethu Vijayakumar
International Conference on Artificial Intelligence and Statistics 2010.

Abstract

We consider the problem of tactile discrimination, with the goal of estimating an underlying state parameter in a sequential setting. If the data is continuous and high dimensional, collecting enough representative data samples becomes difficult. We present a framework that uses active learning to help with the sequential gathering of data samples, using information-theoretic criteria to find optimal actions at each time step. We consider two approaches to recursively update the state parameter belief: an analytical Gaussian approximation and a Monte Carlo sampling method. We show how both active frameworks improve convergence, demonstrating results are on a real robotic hand-arm system that estimates the viscosity of liquids from tactile feedback data.

EPrint Type:Article
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Learning/Statistics & Optimisation
ID Code:5992
Deposited By:Jo-Anne Ting
Deposited On:08 March 2010