Autonomous and user controlled vehicle summon to a target

E Musk, K Park, N Uzunovic, CC Moore… - US Patent …, 2023 - Google Patents
(57) ABSTRACT A processor coupled to memory is configured to receive an identification of
a geographical location associated with a target specified by a user remote from a vehicle. A …

Enhanced object detection for autonomous vehicles based on field view

A Shen, R Phadte, G Joshi - US Patent 11,537,811, 2022 - Google Patents
Systems and methods for enhanced object detection for autonomous vehicles based on field
of view. An example method includes obtaining an image from an image sensor of one or …

Optimizing neural network structures for embedded systems

HS Sidhu, PJ Jain, DP Tomasello… - US Patent 11,636,333, 2023 - Google Patents
(57) ABSTRACT A model training and implementation pipeline trains models for individual
embedded systems. The pipeline iterates through multiple models and estimates the …

Machine learning models operating at different frequencies for autonomous vehicles

A Shen - US Patent 11,816,585, 2023 - Google Patents
US11816585B2 - Machine learning models operating at different frequencies for
autonomous vehicles - Google Patents US11816585B2 - Machine learning models …

Vector computational unit receiving data elements in parallel from a last row of a computational array

DD Sarma, E Talpes, PJ Bannon - US Patent 11,561,791, 2023 - Google Patents
Machine learning and artificial intelligence operations often rely on the repeated application
of a set of specific machine learning processor operations over very large datasets …

Data synthesis for autonomous control systems

FN Iandola, DB MacMillen, A Shen, HS Sidhu… - US Patent …, 2022 - Google Patents
An autonomous control system generates synthetic data that reflect simulated environments.
Specifically, the synthetic data is a representation of sensor data of the simulated …

System and method for adapting a neural network model on a hardware platform

M Driscoll - US Patent 11,610,117, 2023 - Google Patents
different neural networks with differing hyperparameters are trained. These different neural
networks are then used to analyze the same validation training set and a particular neural …

Metal loss determinations based on thermography machine learning approach for insulated structures

A Amer, A Al Shehri, V Cunningham - US Patent 11,112,349, 2021 - Google Patents
(57) ABSTRACT A method for identifying metal wall loss in an insulated metal structure is
provided. The method includes receiving thermograms of the outer surface of the structure …

Accelerated mathematical engine

PJ Bannon, KA Hurd, E Talpes - US Patent 11,403,069, 2022 - Google Patents
Various embodiments of the disclosure relate to an acceler ated mathematical engine. In
certain embodiments, the accelerated mathematical engine is applied to image pro cessing …

Vector computational unit

DD Sarma, E Talpes, PJ Bannon - US Patent 11,409,692, 2022 - Google Patents
5,311,459 A 5,333,296 A 5,471,627 A 5,519,864 A 5,600,843 A 5,717,947 A 5,742,782 A
5,850,530 A 5,887,183 A 6,122,722 A 6,195,674 B1 6,446,190 B1 6,882,755 B2 7,209,031 …