US Patent Issued to NVIDIA on Aug. 26 for "Deep neural network for detecting obstacle instances using radar sensors in autonomous machine applications" (Washington, California Inventors)

ALEXANDRIA, Va., Aug. 26 -- United States Patent no. 12,399,253, issued on Aug. 26, was assigned to NVIDIA Corp. (Santa Clara, Calif.).

"Deep neural network for detecting obstacle instances using radar sensors in autonomous machine applications" was invented by Alexander Popov (Kirkland, Wash.), Nikolai Smolyanskiy (Seattle), Ryan Oldja (Redmond, Wash.), Shane Murray (San Jose, Calif.), Tilman Wekel (Sunnyvale, Calif.), David Nister (Bellevue, Wash.), Joachim Pehserl (Lynnwood, Wash.), Ruchi Bhargava (Redmond, Wash.) and Sangmin Oh (San Jose, Calif.).

According to the abstract* released by the U.S. Patent & Trademark Office: "In various examples, a deep neural network(s) (e.g., a convolutional neural network) may be trained to detect movi...