Large-scale terrain modeling from multiple sensors with dependent Gaussian processes
Lists
Only you see this
Abstract
Terrain modeling remains a challenging yet key component for the deployment of ground robots to the field. The difficulty arrives from the variability of terrain shapes, sparseness of the data, and high degree uncertainty often encountered in large, unstructured environments. This paper presents significant advances to data fusion for stochastic processes modeling spatial data, demonstrated in large-scale terrain modeling tasks. We explore dependent Gaussian processes to provide a multi-resolution representation of space and associated uncertainties, while integrating sensors from different modalities. Experiments performed on multiple multi-modal datasets (3D laser scans and GPS) demonstrate the approach for terrains of about 5 km <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> .
BibTeX
@inproceedings{vasudevan2010large,
author = {Shrihari Vasudevan and Fabio T. Ramos and Eric Nettleton and Hugh F. Durrant-Whyte},
title = {{Large-scale terrain modeling from multiple sensors with dependent Gaussian processes}},
booktitle = {IEEE/RSJ International Conference on Intelligent Robots and Systems},
year = {2010},
url = {https://openreview.net/forum?id=v3u_PvNfP7D},
}Loading related content...