Radar beamforming by way of latent space encoding

US12092759B2 · kind B2 · utility

Assignee

• GM Cruise Holdings LLC · US

Inventors

• Michael Meyer · Indianapolis, US
• Georg Kuschk · Garmisch-Partenkirchen, DE

Key dates

• Filing date: Dec 30, 2021
• Grant date: Sep 17, 2024
• Expiry date: Sep 14, 2042

Classification

• Technology area (CPC G): Physics
• CPC primary: G01S2013/93185
• WIPO field: Measurement
• WIPO sector: Instruments

Abstract

A radar sensor system receives or generates radar data indicative of radar returns received at an antenna array. An encoder neural network encodes the radar data into first embeddings defined in a first latent space. A transformer neural network receives the first embeddings and transforms the first embeddings to second embeddings defined in a second latent space. A decoder neural network receives the second embeddings and decodes the second embeddings to generate beamformed radar data.