During the GTC Fall 2022 keynote address this morning, NVIDIA Founder and CEO Jensen Huang automotive announcements include a new process DRIVE Thor, new DRIVE Sim features, neural digital twins and Concierge services for inside the vehicle.
NVIDIA DRIVE™ Thor, its next-generation centralized computer for safe and secure autonomous vehicles.
DRIVE Thor, achieves up to 2,000 teraflops of performance, unifies intelligent functions — including automated and assisted driving, parking, driver and occupant monitoring, digital instrument cluster, in-vehicle infotainment (IVI) and rear-seat entertainment — into a single architecture for greater efficiency and lower overall system cost.
The next-generation superchip comes packed with the cutting-edge AI capabilities first introduced in the NVIDIA Hopper™ Multi-Instance GPU architecture, along with the NVIDIA Grace™ CPU and NVIDIA Ada Lovelace GPU. DRIVE Thor with MIG support for graphics and compute uniquely enables IVI and advanced driver-assistance systems to run domain isolation, which allows concurrent time-critical processes to run without interruption. Available for automakers’ 2025 models, it will accelerate production roadmaps by bringing higher performance and advanced features to market in the same timeline.
DRIVE Thor supports multi-domain computing, isolating functions for automated driving and IVI. Typically, dozens of electric control units are distributed throughout a vehicle to power individual functions. With DRIVE Thor, manufacturers can efficiently consolidate many functions on a single system-on-a-chip (SoC), which eases supply constraints and simplifies vehicle-design development, resulting in significantly lower cost, less weight and fewer cables.
Neural Reconstruction Engine
Autonomous vehicle simulation poses two challenges: generating a world with enough detail and realism that the AI driver perceives the simulation as real, as well as creating simulations at a large enough scale to cover all the cases on which the AI driver needs to be fully trained and tested.
To address these challenges, NVIDIA researchers have created new AI-based tools to build simulations directly from real-world data.
The Neural Reconstruction Engine is a new AI toolset for the NVIDIA DRIVE Sim simulation platform that uses multiple AI networks to turn recorded video data into simulation.
The new pipeline uses AI to automatically extract the key components needed for simulation, including the environment, 3D assets and scenarios. These pieces are then reconstructed into simulation scenes that have the realism of data recordings, but are fully reactive and can be manipulated as needed. Achieving this level of detail and diversity by hand is costly, time consuming and not scalable.
A simulation needs an environment in which to operate. The AI pipeline converts 2D video data from a real-world drive to a dynamic, 3D digital twin environment that can be loaded into DRIVE Sim.
Concierge platform for Cockpit, Monitoring, Digital Assistants & Entertainment
The NVIDIA DRIVE Concierge platform spans traditional cockpit and cluster capabilities, as well as personalized, AI-powered safety, convenience and entertainment features for every occupant.
Drivers in the U.S. spend an average of nearly 450 hours in their car every year. With just a traditional cockpit and infotainment display, those hours can seem even longer.
DRIVE Concierge makes time in vehicles more enjoyable, convenient and safe, extending intelligent features to every passenger using the DRIVE AGX compute platform, DRIVE IX software stack and Omniverse Avatar Cloud Engine (ACE).
These capabilities include crystal-clear graphics and visualizations in the cockpit and cluster, intelligent digital assistants, driver and occupant monitoring, and streaming content such as games and movies.
By running on the cross-domain DRIVE platform, DRIVE Concierge can virtualize, as well as host, multiple virtual machines on a single chip — rather than distributed computers — for streamlined development.
With this centralized architecture, DRIVE Concierge seamlessly orchestrates driver information, cockpit and infotainment functions. It supports the Android Automotive operating system, so automakers can easily customize and scale their IVI offerings.
DRIVE Concierge is tightly integrated with the DRIVE Chauffeur platform to provide high-quality, 360-degree, 4D visualization with low latency. Drivers and passengers can always see what’s in the mind of the vehicle’s AI, with beautiful 3D graphics.
This visualization is critical to building trust between the autonomous vehicle and its passengers, so occupants can be confident in the AV system’s perception and planned path.
How May AI Help You?
In addition to revolutionizing driving, AI is creating a more intelligent vehicle interior with personalized digital assistants.
Omniverse ACE is a collection of cloud-based AI models and services for developers to easily build, customize and deploy interactive avatars.
With ACE, AV developers can create in-vehicle assistants that are easily customizable with speech AI, computer vision, natural language understanding, recommendation engines and simulation technologies.
These avatars can help make recommendations, book reservations, access vehicle controls and provide alerts for situations like if a valuable item is left behind.
With software-defined capabilities, cars are becoming living spaces, complete with the same entertainment available at home.
NVIDIA DRIVE Concierge lets passengers watch videos and experience high-performance gaming wherever they go. Users can choose from their favorite apps and stream videos and games on any vehicle screen.
By using the NVIDIA GeForce NOW cloud gaming service, passengers can access more than 1,400 titles without the need for downloads, benefitting from automatic updates and unlimited cloud storage.
Intelligent interiors provide an added layer of safety to vehicles, in addition to convenience and entertainment.
DRIVE Concierge uses interior sensors and dedicated deep neural networks for driver monitoring, which ensures attention is on the road in situations where the human is in control.
It can also perform passenger monitoring to make sure that occupants are safe and no precious cargo is left behind.
NVIDIA also announced:
- Geely-backed EV maker, ZEEKR, has selected DRIVE Thor as the brain of their future lineup of intelligent electric vehicles, with start of production early 2025.
- XPENG Motor’s flagship G9 smart SUV is powered by NVIDIA DRIVE Orin.
- QCraft’s L4 robotaxi fleet begins operations and is also built on NVIDIA Orin.
- Over ten ecosystem partners’ unveiling new tech on DRIVE Sim, DRIVE IX and DRIVE Hyperion.