Radarsystem zur Unterscheidung von Objekten mittels eines Trainierten Neuronalen Netzes

Details

Veröffentlichungs-Nr.

EP4733799

Anmeldetag

23. Oktober 2025

Veröffentlichung

29. April 2026

Rechtsraum

EP

IPC

(UNIV XIDIAN et al.)

Abstract

Disclosed is Radar system (5) for differentiating objects (61, 62) in an environment (140) of a vehicle (40), the radar system (5) comprising an evaluation unit (4) with a trained first neural network (1), wherein the evaluation unit (4) is configured to:- generate power spectra (10) dependent on receiving signals (110), the receiving signals (110) being generated by means of receiving antennas (11),- select a pair of frequencies for each power spectrum, wherein each power spectrum comprises a phase information of the selected pair of frequencies of the respective power spectrum,- perform an angle estimation of the objects (61, 62) with respect to the receiving antennas (11) dependent on the selected pairs of frequencies, a result of the angle estimation (800) indicating a differentiation between the objects (61, 62),- generate an output (111) by means of the first neural network (1) dependent on the result of the angle estimation (800) and the phase information of the selected pairs of frequencies , the output (111) comprising a correction of the angle estimation of the objects (61, 62).

Anmelder

Firma

Valeo Schalter und Sensoren GmbH

Land

🇩🇪 Deutschland