Continuous State POMDPs for Object Manipulation Tasks

Emma Brunskill

My research focus is on using continuous state partially observable Markov decision processes (POMDPs) to perform object manipulation tasks using a robotic arm. During object manipulation, object dynamics can be extremely complex, non-linear and challenging to specify. To avoid modeling the full complexity of possible dynamics, I instead use a model which switches between a discrete number of simple dynamics models. By learning these models and extending Porta’s continuous state POMDP framework (Porta et al. 2006) to incorporate this switching dynamics model, we hope to handle tasks that involve absolute and relative dynamics within a single framework. This dynamics model may be applicable not only to object manipulation tasks, but also to a number of other problems, such as robot navigation. By using an explicit model of uncertainty, I hope to create solutions to object manipulation tasks that more robustly handle the noisy sensory information received by physical robots.

Subjects: 1.11 Planning; 3.4 Probabilistic Reasoning

Submitted: Apr 24, 2007

This page is copyrighted by AAAI. All rights reserved. Your use of this site constitutes acceptance of all of AAAI's terms and conditions and privacy policy.