US 12,449,512 B2
Radar point cloud multipath reflection compensation
Georg Kuschk, Garmisch-Partenkirchen (DE); Marc Unzueta Canals, Munich (DE); Michael Meyer, Munich (DE); and Sven Möller, Lübbecke (DE)
Assigned to GM Cruise Holdings LLC, San Francisco, CA (US)
Filed by GM Cruise Holdings LLC, San Francisco, CA (US)
Filed on Aug. 31, 2022, as Appl. No. 17/899,762.
Claims priority of application No. 22187788 (EP), filed on Jul. 29, 2022.
Prior Publication US 2024/0036168 A1, Feb. 1, 2024
Int. Cl. G01S 7/41 (2006.01); B60W 60/00 (2020.01); G01S 13/89 (2006.01); G01S 13/931 (2020.01)
CPC G01S 7/417 (2013.01) [G01S 13/89 (2013.01); G01S 13/931 (2013.01); B60W 60/001 (2020.02); B60W 2420/408 (2024.01)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method comprising:
generating, based on real-world autonomous vehicle (AV) scene data captured by sensors of an AV during a real-world scenario, a simulation of the real-world scenario;
adding a first object to the simulation of the real-world scenario;
determining, using polarimetry analysis of received signals, a number of signal reflections associated with data indirectly representing the first object;
transforming the data indirectly representing the first object based on the number of signal reflections;
generating synthetic AV scene data based on the transformed data and the simulation of the real-world scenario, including the first object; and
augmenting the real-world AV scene data with a portion of the synthetic AV scene data that describes the first object, resulting in augmented real-world AV scene data that describes the real-world scenario, including the first object.