Nvidia's new Pegasus AI computer is created to drive autonomous taxis

NVIDIA Unveils Drive PX Pegasus: Made To Power Fully Autonomous Vehicles

NVIDIA Unveils Drive PX Pegasus: Made To Power Fully Autonomous Vehicles

On Tuesday, Nvidia announced a new version of its automotive-grade compute platforms, Drive PX Pegasus.

Nvidia has learned from 225 partners, including Yandex NV, Zoox and NuTonomy, that are using its computing systems to bring autonomous capabilities to vehicles.

DRIVE PX Pegasus will enable the "Holy Grail" for driverless vehicles: Level 5 autonomy.

Looking to power "Level 5" standard robotic vehicles, particularly self-driving taxis, the Drive PX Pegasus offers major steps forward in terms of computing power, able to carry out over 320 trillion operations per second. Even Tesla's Autopilot system, which on some roads can operate the steering, accelerator and brake, and switch lanes when asked to by the driver, is only regarded as Level Three, as the driver is always ultimately responsible for the car's actions. The new chip is aimed at "Level 5" autonomous driving, the highest level of autonomy.

Nvidia is aiming the system at the ever-growing ride-haling economy and hopes that Pegasus will help to create a new class of robot taxis, or robotaxis, that are capable of safely transporting passengers to their destination. New types of cars will be invented, resembling offices, living rooms or hotel rooms on wheels. "The future of society will be reshaped", he says.

Huang said: "Basic neural networks that we've already trained, combined with the perception of what the auto sees is going to allow our customers to write applications that are magic".

Pegasus will be retailed to the hundreds of automakers and tech companies that are now developing autonomous vehicles starting the second half of 2018, according to the company. DPDHL will equip its electric light trucks with the ZF ProAI self-driving system in a move that Nvidia claims could pave the way for 24/7 automated deliveries.

"The development of autonomous delivery vehicles demonstrates how AI and deep learning are also reshaping the commercial transportation industry", said Jensen Huang.
Trials will begin next year, and eventually driverless trucks may follow human-controlled vehicles drivers around as they drop off parcels. The event will also feature disruptive innovations as early-stage companies and startups present their work. Graphics processors are good at small manipulations of visual data in parallel, and Nvidia argues that's ideal for the kind computing needed to make cars see the world around them.

Recommended News

We are pleased to provide this opportunity to share information, experiences and observations about what's in the news.
Some of the comments may be reprinted elsewhere in the site or in the newspaper.
Thank you for taking the time to offer your thoughts.