This is not the latest version of this item. The latest version can be found here.
Non-Gaussian belief space planning: Correctness and complexity
Name
ICRA12_1775_FI.pdf
Description
Accepted version
Size
245.24 KB
Format
Adobe PDF
Checksum (MD5)
530a3aab7617d7aa98ecc4ccc0dae092
Author(s)
Platt, Robert
Kaelbling, Leslie
Lozano-Perez, Tomas
Tedrake, Russ
Date Issued
May 2012
Publisher
IEEE
Citation
Platt, Robert, Kaelbling, Leslie, Lozano-Perez, Tomas and Tedrake, Russ. 2012. "Non-Gaussian belief space planning: Correctness and complexity."
Version
Author's final manuscript
Abstract
We consider the partially observable control problem where it is potentially necessary to perform complex information-gathering operations in order to localize state. One approach to solving these problems is to create plans in belief-space, the space of probability distributions over the underlying state of the system. The belief-space plan encodes a strategy for performing a task while gaining information as necessary. Unlike most approaches in the literature which rely upon representing belief state as a Gaussian distribution, we have recently proposed an approach to non-Gaussian belief space planning based on solving a non-linear optimization problem defined in terms of a set of state samples [1]. In this paper, we show that even though our approach makes optimistic assumptions about the content of future observations for planning purposes, all low-cost plans are guaranteed to gain information in a specific way under certain conditions. We show that eventually, the algorithm is guaranteed to localize the true state of the system and to reach a goal region with high probability. Although the computational complexity of the algorithm is dominated by the number of samples used to define the optimization problem, our convergence guarantee holds with as few as two samples. Moreover, we show empirically that it is unnecessary to use large numbers of samples in order to obtain good performance. © 2012 IEEE.
Terms of Use
Creative Commons Attribution-Noncommercial-Share Alike
Persistent DSpace Link
DOI of Published Version
10.1109/icra.2012.6225223
