Gm Cruise Holdings LLC

Georg Kuschk

Michael Meyer

Marc Unzueta Canals

Sven Möller

A method and apparatus for implementing a method are disclosed. The method includes providing point cloud data to a machine learning algorithm, the point cloud data detected in the vicinity of an autonomous vehicle. The method further includes differentiating, via the machine learning algorithm, in the point cloud, data directly representing a location of a first object and data indirectly representing a location of a second object. The method includes transforming the data indirectly representing the location of the second object into data directly representing the location of the second object and generating corrected point cloud data based on the data directly representing the location of the first object and the data directly representing the location of the second object. The method includes outputting the corrected point cloud data to the autonomous vehicle.

Radar point cloud multipath reflection compensation

Technologies described herein relate to learning parameter values of a preprocessing algorithm that is executed in a radar system. The preprocessing algorithm is configured to receive raw radar data as input and is further configured to generate three-dimensional point clouds as output, where the preprocessing algorithm generates the three-dimensional point clouds based upon the raw radar data and the parameter values that are assigned to the preprocessing algorithm. To learn the parameter values, the preprocessing algorithm is converted to auto-differentiated form and is added as an input network layer to a deep neural network (DNN) that is configured to identify objects represented in three-dimensional point clouds. The parameter values are learned jointly with weight matrices of the DNN.

Setting radar parameters for generating point clouds based upon raw radar data

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.

Radar beamforming by way of latent space encoding

The technologies described herein relate to a computing architecture in an autonomous vehicle (AV). The AV includes a radar system that includes a local data processing device. The AV also includes a centralized data processing device. The local data processing device is configured to perform processing on raw sensor data generated by the radar system to form a feature vector. The local data processing device transmits the feature vector to the centralized data processing device, which performs further processing to identify an object in an environment of the AV.

Growing community of inventors

Garmisch-Partenkirchen, Germany

Georg Kuschk