Gm Cruise Holdings LLC

Anton Mario Bongio Karrman

Daniel Flores Tapia

Yun Jiang

Brian Pierce

Shaogang Wang

Kotung Lin

Xiaowei Li

Weizhe Zhang

A current set of radar data may be combined with previous sets of radar data to create a combined set of radar data. Each of these sets of radar data and the combined set of radar data may include various data points and each of these data points may be associated with certain specific features or classifications. The set of combined data may then be pre-processed to identify distances to associate with certain data points, locations to associate with those data points, and velocities associated with the data points such that each of the respective data points may be mapped and tagged with data that identifies identify positions, velocities, and other physical details of the respective data points. This pre-processed data may then be processed by a machine learning process to identify kinematic information that may then be provided to a tracking system of an AV.

Object detection and state estimation from deep learned per-point radar representations

The present disclosure is directed to combining the strengths of different methods of analyzing collected sensor data to updating a driving pattern of an automated vehicle (AV). This may include combining data from sets of data that track movement of objects over time with instantaneously received sensor data based on a series of steps that include accessing data that tracks the motion of objects in the field of view of a sensing apparatus, receiving current sensor data that includes a component of current or instantaneous object motion, and identifying whether controls of AV should be maintained or changed. When controls of the AV are maintained, an AV may be controlled to stay in driving in a same lane of a roadway at a same velocity. When controls of an AV are changed, changes may include applying, increasing a velocity, or altering the course of the AV.

Unified radar perception architecture

Multi-frequency microDoppler fusion is described. An example of a method includes performing a 2D Fourier transform of raw Radar sensor data and raw LiDAR sensor data to generate Radar range-Doppler map data and LiDAR range-Doppler map data; performing a Stationary Wavelet Transform (SWT) calculation of the Radar and LiDAR sensor range-Doppler map data to generate a Radar SWT product and a LiDAR SWT product; performing an SWT product thresholding operation to extract signatures that are common to the Radar SWT product and the LiDAR SWT product; and performing a microDoppler calculation on the extracted common signatures to generate Radar-LIDAR joint fused micro-Doppler signatures.

Multi-frequency micro-doppler processing and fusion

The present disclosure is directed to a plurality of different software models allowing a processor to perform calculations associated with different sets of criteria using data associated with variables that have a strong correlation with one or more of the different criteria sets. Methods consistent with the present disclosure may use several different sets of software that include instructions associated with the collection and evaluation of data associated with a vehicle and with an automated driving system. Different criteria sets may be associated with a range of operating modes, spectral content of received signals, phases of radar signals, and an angular coverage/field of view of the radar apparatus. Results generated by each of the software models may allow a processor to assign weights to the results generated by the different models to generate a combined result that in turn is used to update an operational mode of the radar apparatus.

Growing community of inventors

Los Angeles, CA, United States of America

Anton Mario Bongio Karrman