Nvidia Corporation

Mediatek Singapore Pte. Ltd.

Kevin Flory

David Nister

Gary D Hicok

Karl Friedrich Greb

Jonathan Sweedler

Ram Ganapathi

John George Mathieson

Ashok Srinivasan

Yasu Noguchi

Clement Farabet

Mohammed Abdulla Yousuf

Michael Truog

Michael Alan Ditty

Daniel Stewart Perrin

Mike Truog

Hung Do

William Stemper

Steven D Loi

Tai-Yuen Chan

Dan Hettena

TY Chan

Autonomous driving is one of the world's most challenging computational problems. Very large amounts of data from cameras, RADARs, LIDARs, and HD-Maps must be processed to generate commands to control the car safely and comfortably in real-time. This challenging task requires a dedicated supercomputer that is energy-efficient and low-power, complex high-performance software, and breakthroughs in deep learning AI algorithms. To meet this task, the present technology provides advanced systems and methods that facilitate autonomous driving functionality, including a platform for autonomous driving Levels 3, 4, and/or 5. In preferred embodiments, the technology provides an end-to-end platform with a flexible architecture, including an architecture for autonomous vehicles that leverages computer vision and known ADAS techniques, providing diversity and redundancy, and meeting functional safety standards. The technology provides for a faster, more reliable, safer, energy-efficient and space-efficient System-on-a-Chip, which may be integrated into a flexible, expandable platform that enables a wide-range of autonomous vehicles, including cars, taxis, trucks, and buses, as well as watercraft and aircraft.

Systems and methods for safe and reliable autonomous vehicles

A camera has a continuous full-resolution burst mode wherein a sequence of full-resolution images is captured, is image processed by a pipeline of dedicated hardware image processing engines, is zoomed by a zoom engine, is compressed by a compression engine, and is stored into nonvolatile storage as a sequence of discrete files. The capturing of images and the storing of files continues at a rate of at least three frames per second until the user indicates burst mode operation is to stop or until nonvolatile storage becomes filled. Although the camera has a buffer memory into which raw sensor data is placed before image processing, the number of images that can be captured in a single burst is not limited by the size of the buffer memory. The cost of a consumer market camera having continuous burst mode capability is therefore reduced by reducing the required amount of buffer memory.

Continuous burst mode digital camera

Growing community of inventors

Livermore, CA, United States of America

Kevin Flory