View source for US Patent Application 17804849. SPACE VEHICLE GEOMETRY BASED MACHINE LEARNING FOR MEASUREMENT ERROR DETECTION AND CLASSIFICATION simplified abstract

=SPACE VEHICLE GEOMETRY BASED MACHINE LEARNING FOR MEASUREMENT ERROR DETECTION AND CLASSIFICATION=


==Organization Name==

[[:Category:QUALCOMM Incorporated|QUALCOMM Incorporated]]


[[Category:QUALCOMM Incorporated]]==Inventor(s)==

[[Category:[[:Category:Songwon Jee of San Jose CA (US)|Songwon Jee of San Jose CA (US)]]]]

[[Category:[[:Category:Yunxiang Liu of Kirkland WA (US)|Yunxiang Liu of Kirkland WA (US)]]]]

[[Category:[[:Category:William Morrison of San Francisco CA (US)|William Morrison of San Francisco CA (US)]]]]

==SPACE VEHICLE GEOMETRY BASED MACHINE LEARNING FOR MEASUREMENT ERROR DETECTION AND CLASSIFICATION - A simplified explanation of the abstract==


This abstract first appeared for US patent application 17804849 titled 'SPACE VEHICLE GEOMETRY BASED MACHINE LEARNING FOR MEASUREMENT ERROR DETECTION AND CLASSIFICATION

==Simplified Explanation==

This patent application describes a method for detecting and classifying measurement errors in positioning devices using machine learning. 

* The method involves determining the geometric orientation of each satellite in a set of satellites with respect to the positioning device.
* A machine learning classifier is used to determine a relative weight for each satellite based on its geometric orientation.
* The positioning device then estimates its own position using the measurements from each satellite, taking into account the relative weights determined by the classifier.


==Original Abstract Submitted==

Aspects presented herein may enable a positioning device or entity to perform PR measurement error detection and classification based on SV geometry via ML. In one aspect, a UE or a location server determines for each SV of a set of SVs at least a geometric orientation with respect to the UE. The UE or the location server determines, based on an ML classifier and the determined geometric orientation with respect to the UE for each SV of at least a subset of the set of SVs, a relative PR weight for each SV of the set of SVs. The UE or the location server estimates a position of the UE based on PR measurements of each SV of the set of SVs and the relative PR weight for each SV of the set of SVs.



[[Category:B64G1/28]]
[[Category:B64G1/24]]