ICRA 2011 Paper Abstract


Paper TuA210.2

Huang, Joseph (Stanford University), Millman, David (Stanford University), Quigley, Morgan (Stanford University), Stavens, David Michael (Stanford University), Thrun, Sebastian (Stanford University), Aggarwal, Alok (Qualcomm)

Efficient, Generalized Indoor WiFi GraphSLAM

Scheduled for presentation during the Regular Sessions "Localization and Mapping II" (TuA210), Tuesday, May 10, 2011, 10:20−10:35, Room 5E

2011 IEEE International Conference on Robotics and Automation, May 9-13, 2011, Shanghai International Conference Center, Shanghai, China

This information is tentative and subject to change. Compiled on April 2, 2020

Keywords SLAM, Mapping, Localization


The widespread deployment of wireless networks presents an opportunity for localization and mapping using only signal-strength measurements. The current state of the art is to use Gaussian process latent variable models (GP-LVM). This method works well, but relies on a signature uniqueness assumption which limits its applicability to only signal-rich environments. Moreover, it does not scale computationally to large sets of data, requiring O(N^3) operations per iteration. We present a GraphSLAM-like algorithm for signal strength SLAM. Our algorithm shares many of the bene?ts of Gaussian processes, yet is viable for a broader range of environments since it makes no signature uniqueness assumptions. It is also more tractable to larger map sizes, requiring O(N^2) operations per iteration. We apply our algorithm in a number of applications, showing it produces excellent results in practise.



Technical Content © IEEE Robotics & Automation Society

This site is protected by copyright and trademark laws under US and International law.
All rights reserved. © 2002-2020 PaperCept, Inc.
Page generated 2020-04-02  11:02:10 PST  Terms of use