Abstract
According to news reporting originatin g from Washington, D.C., by NewsRx journalists, a patent application by the inve ntors Anwar, Malik Aqeel (Atlanta, GA, US); Choe, Tae Eun (Belmont, CA, US); Fid ler, Sanja (Toronto, CA); Park, Minwoo (Santa Clara, CA, US); Wang, Zian (Toront o, CA), filed on February 29, 2024, was made available online on September 19, 2 024. The assignee for this patent application is NVIDIA Corporation (Santa Clara, Cal ifornia, United States). Reporters obtained the following quote from the background information supplied by the inventors: "Many partial (SAE L2), conditional (L3), and high (L4) drivin g automation systems include perception systems (sometimes referred to as percep tion modules) that are trained using datasets containing thousands to millions o f images. For example, to develop a vision-based perception system, individual i mages are collected while a vehicle is driven in various environments and under various conditions. These images are then inspected by humans and annotated with tags representing objects or agents found in the image. The resulting images an d corresponding tags are then used to update parameters of trained machine learn ing models implemented by the perception systems to classify later-encountered o bjects or agents.
NETL
NSTL