Apple appears to be working on a new system to correct GPS coordinates of its maps service. The company is planning to use machine learning for the correction of Global Navigation Satellite System (GNSS) data by obtaining data from consumer location. If implemented, this method will help the company improve the accuracy of its mapping service.
If the machine learning (ML) model imagined by Apple works out, it will be able to generate location estimates based on the previous data gathered by the company. It will help reduce multipath errors or any other mapping problems which consumers face sometimes.
The Apple mapping patent application reads, “A device implementing a system for estimating device location includes at least one processor configured to receive an estimated position based on a positioning system comprising a Global Navigation Satellite System (GNSS) satellite, and receive a set of parameters associated with the estimated position.”
“The processor is further configured to apply the set of parameters and the estimated position to a machine learning model, the machine learning model having been trained based at least on a position of a receiving device relative to the GNSS satellite. The processor is further configured to provide the estimated position and an output of the machine learning model to a Kalman filter, and provide an estimated device location based on an output of the Kalman filter.”
Apple has largely improved its mapping system since its release in 2012. It was initially condemned for its poor navigation system and for its bugs. It was the same year that the company dumped Google Maps in favour of its in-house mapping application.
Scott Forstall, SVP of iOS Software was fired the same year for reasons related to the debacle of Apple Maps. Since then, Craig Federighi, now SVP of Software Engineering (Apple) has taken his place