US Patent Application 17804809. POSITION-GRID BASED MACHINE LEARNING FOR GNSS WARM-START POSITION ACCURACY IMPROVEMENT simplified abstract

POSITION-GRID BASED MACHINE LEARNING FOR GNSS WARM-START POSITION ACCURACY IMPROVEMENT

Organization Name

QUALCOMM Incorporated==Inventor(s)==

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

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

POSITION-GRID BASED MACHINE LEARNING FOR GNSS WARM-START POSITION ACCURACY IMPROVEMENT - A simplified explanation of the abstract

This abstract first appeared for US patent application 17804809 titled 'POSITION-GRID BASED MACHINE LEARNING FOR GNSS WARM-START POSITION ACCURACY IMPROVEMENT

Simplified Explanation

- The patent application aims to improve the performance and accuracy of GNSS-based positioning. - A position-grid based machine learning (ML) system is proposed to enhance the identification of a warm-start position of a user equipment (UE). - The UE or a location server calculates a set of PR residuals for each grid point within a certain range of the UE's initial position. - PR residuals are determined based on the pseudoranges (PRs) obtained from a set of satellite vehicles (SVs). - Using the sets of determined PR residuals, the UE or the location server estimates the position of the UE. - The innovation focuses on utilizing a position-grid based ML approach to enhance the accuracy of determining the UE's warm-start position.

Original Abstract Submitted

Aspects presented herein may improve the performance and accuracy of GNSS-based positioning, where a position-grid based ML may be implemented by a UE or a location server to improve the accuracy of identifying a warm-start position of the UE. In one aspect, a UE or a location server determines, for each grid point within a range of an initial position of a UE, a set of PR residuals based on PRs for each SV of a set of SVs. The UE or the location server determines an estimated position of the UE based on the sets of determined PR residuals.