Title:
Place Recognition-Based Fixed-Lag Smoothing for Environments with Unreliable GPS
Place Recognition-Based Fixed-Lag Smoothing for Environments with Unreliable GPS
Author(s)
Mottaghi, Roozbeh
Kaess, Michael
Ranganathan, Ananth
Roberts, Richard
Dellaert, Frank
Kaess, Michael
Ranganathan, Ananth
Roberts, Richard
Dellaert, Frank
Advisor(s)
Editor(s)
Collections
Supplementary to
Permanent Link
Abstract
Pose estimation of outdoor robots presents some
distinct challenges due to the various uncertainties in the robot
sensing and action. In particular, global positioning sensors of
outdoor robots do not always work perfectly, causing large drift
in the location estimate of the robot. To overcome this common
problem, we propose a new approach for global localization
using place recognition. First, we learn the location of some
arbitrary key places using odometry measurements and GPS
measurements only at the start and the end of the robot
trajectory. In subsequent runs, when the robot perceives a key
place, our fixed-lag smoother fuses odometry measurements
with the relative location to the key place to improve its pose
estimate. Outdoor mobile robot experiments show that place
recognition measurements significantly improve the estimate of
the smoother in the absence of GPS measurements.
Sponsor
Date Issued
2008-05
Extent
Resource Type
Text
Resource Subtype
Post-print
Proceedings
Proceedings