Magnetic Position Sensor System Using Recurrent Neural Network

ChangeBridge: Patent Grants - AI & Computing (G06N)

Published April 7th, 2026

Detected April 7th, 2026

Summary

USPTO issued Patent US12596017B2 to MELEXIS TECHNOLOGIES SA covering a magnetic position sensor system that uses a recurrent neural network trained with at most 300 trainable parameters per degree of freedom. The patent includes 20 claims and has CPC classifications in neural networks (G06N 3/044, G06N 3/08, G06N 3/04) and magnetic sensors (G01D 5/145). This is a routine patent grant notification with no compliance obligations.

View original document View source feed page

What changed

USPTO granted Patent US12596017B2 to MELEXIS TECHNOLOGIES SA for a magnetic position sensor system, device, and method using a recurrent neural network. The patent covers determining the position of a sensor device relative to a magnetic source using magnetic sensor signals processed through a neural network with at most 300 trainable parameters per degree of freedom. The application (18350262) was filed on July 11, 2023, and the patent includes 20 claims covering both the method and the position sensor system/device.

This patent grant creates no compliance obligations for any regulated entities. It is an informational notice establishing intellectual property rights for MELEXIS TECHNOLOGIES SA. Competitors developing similar magnetic position sensors with neural networks should review this patent for potential licensing considerations or to assess whether their products may fall outside the patent's scope.

Source document (simplified)

← USPTO Patent Grants

Magnetic position sensor system, device and method

Grant US12596017B2 Kind: B2 Apr 07, 2026

Assignee

MELEXIS TECHNOLOGIES SA

Inventors

Leon Denis, Adrian Munteanu, Illia Khvastunov, Kristof Coddens

Abstract

Method of determining a position (f a sensor device movable relative to a magnetic source, or vice versa; the sensor device comprising at least two magnetic sensors; the method comprising the steps of: a) obtaining a plurality of magnetic sensor signals from said magnetic sensors; b) determining or estimating the position of the sensor device based on said plurality of sensor signals or signals derived therefrom; wherein step b) comprises: determining said position (sing an artificial neural network; the artificial neural network being a recurrent neural network trained for determining said position using at most three hundred trainable parameters per degree of freedom. A position sensor system. A position sensor device.