Deep Inference for Covariance Estimation: Learning Gaussian Noise Models for State Estimation

We present a novel method of measurement covariance estimation that models measurement uncertainty as a function of the measurement itself. Existing work in predictive sensor modeling outperforms conventional fixed models, but requires domain knowledge of the sensors that heavily influences the accu...

Full description

Bibliographic Details
Main Authors: Liu, Katherine (Author), Ok, Kyel (Author), Vega-Brown, William R (Author), Roy, Nicholas (Author)
Other Authors: Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory (Contributor)
Format: Article
Language:English
Published: IEEE, 2020-01-24T15:21:14Z.
Subjects:
Online Access:Get fulltext