Document Type
Article
Publication Date
February 2020
Patent Number
10572802
CPC
G06N 3/02, G06N 3/0454, G06N 3/08, G06N 7/005
Abstract
A noise and bias can be determined for a sensor. An input vector can be received. A parameter vector can be generated based at least in part on a feed-forward neural network. Components can be determined using the parameter vector based at least in part on a mixture model. A conditional probability density function can be generated based at least in part on the conditional probability density function.
Application Number
16/236715
Recommended Citation
Sun, Yu and Williams, Troi, "Learning state-dependent sensor measurement models for localization" (2020). USF Patents. 1128.
https://digitalcommons.usf.edu/usf_patents/1128
Assignees
University of South Florida
Filing Date
12/31/2018