US Patent Application 17661399. MEASUREMENT ERROR FEEDBACK TO ENABLE MACHINE LEARNING-BASED POSITIONING simplified abstract

From WikiPatents
Jump to navigation Jump to search

MEASUREMENT ERROR FEEDBACK TO ENABLE MACHINE LEARNING-BASED POSITIONING

Organization Name

QUALCOMM Incorporated


Inventor(s)

Jay Kumar Sundararajan of San Diego CA (US)


Alexandros Manolakos of Escondido CA (US)


Taesang Yoo of San Diego CA (US)


Sooryanarayanan Gopalakrishnan of San Diego CA (US)


Naga Bhushan of San Diego CA (US)


Krishna Kiran Mukkavilli of San Diego CA (US)


Tingfang Ji of San Diego CA (US)


MEASUREMENT ERROR FEEDBACK TO ENABLE MACHINE LEARNING-BASED POSITIONING - A simplified explanation of the abstract

  • This abstract for appeared for US patent application number 17661399 Titled 'MEASUREMENT ERROR FEEDBACK TO ENABLE MACHINE LEARNING-BASED POSITIONING'

Simplified Explanation

The abstract describes a method for wireless communication. It explains that a first network node determines the position of a second network node by analyzing a signal transmitted by the second node. The first node then receives feedback on the accuracy of the position measurement. This feedback is based on an expected position calculated using the locations of both nodes.


Original Abstract Submitted

Disclosed are techniques for wireless communication. In an aspect, a first network node determines at least one positioning measurement based on a channel estimate of a positioning reference signal (PRS) transmitted by a second network node, and obtains measurement error feedback for at least the at least one positioning measurement, wherein the measurement error feedback is based on an expected positioning measurement corresponding to the at least one positioning measurement, and wherein the expected positioning measurement is based on a location of the first network node and a location of the second network node.