NVIDIA Announces World's First Functionally Safe AI Self-Driving Platform at CES
【Summary】Today at CES, NVIDIA unveiled details of its functional safety architecture for NVIDIA DRIVE, its fail-safe AI autonomous vehicle platform which uses redundant and diverse functions to enable vehicles to operate safely, even in the event of faults related to the operator, environment or systems.
LAS VEGAS — Today at CES, NVIDIA unveiled details of its functional safety architecture for NVIDIA DRIVE, its fail-safe AI autonomous vehicle platform, which uses redundant and diverse functions to enable vehicles to operate safely, even in the event of faults related to the operator, environment or systems.
The NVIDIA DRIVE architecture enables automakers to build and deploy self-driving cars and trucks that are functionally safe and can be certified to international safety standards, such as ISO 26262.
"Safety is the most important feature of a self-driving car," said Jensen Huang, founder and chief executive officer of NVIDIA. "It is imperative that it operate safely, even when things go wrong. NVIDIA's investment into this functional safety platform is one of the most important ones we've ever made, and it provides a critical ingredient for automakers to bring self-driving cars to market."
NVIDIA DRIVE provides an intergrated safety platform, that includes processing technologies and a simulation enviorment as described below:
Processor Design and Hardware Functionality: Incorporates a diversity of processors to achieve fail operation capabilities. These include NVIDIA-designed IP related to NVIDIA Xavier covering CPU and GPU processors, deep learning accelerator, image processing ISP, computer vision PVA, and video processors – all at the highest quality and safety standards.
Also included are lockstep processing and error-correcting code on memory and buses, with built-in testing capabilities. The ASIL-C NVIDIA DRIVE Xavier processor and ASIL-D rated safety microcontroller can achieve the highest system ASIL-D rating.
NVIDIA Integrates world-leading safety technology from key partners. NVIDIA DRIVE OS system software integrates BlackBerry QNX's 64-bit real-time operating system, which is ASIL-D safety certified, along with TTTech's MotionWise safety application framework, which encapsulates each application and isolates them from each other, while providing real-time computing capability. NVIDIA DRIVE OS offers full support of Adaptive AUTOSAR, the open-standard automotive system architecture and application framework. The NVIDIA toolchain, including the CUDA compiler and TensorRT, uses ISO 26262 Tool Classification Levels to ensure a safe and robust development environment.
Deep Learning Algorithms
The NVIDIA DRIVE AV autonomous vehicle software stack performs functions like ego-motion, perception, localization and path planning, all necessary for autonomous driving.
To prevent failures, each functionality includes a redundancy and diversity strategy. For example, perception redundancy is achieved by fusing lidar, camera and radar. Deep learning and computer vision algorithms running on CPU, CUDA GPU, DLA and PVA enhance redundancy and diversity.
The NVIDIA DRIVE AV stack is a full backup system to the self-driving stack developed by the automaker, enabling Level 5 autonomous vehicles to achieve the highest level of functional safety.
Virtual Reality Simulation Using NVIDIA AutoSIM
A self-driving car is an extremely complex system with state-of-the-art technologies. Proving that the system does what it is designed to do —captured by the term SoTIF, ( safety of the intended functionality) is a great challenge.
Additionally, these self-driving systems must work in a wide range of situations and weather conditions. Road testing is not always sufficiently controllable or repeatable, so a realistic simulation environment is essential.
To address this need, NVIDIA has created a virtual reality simulator, called NVIDIA AutoSIM, to test the DRIVE platform and simulate against rare conditions within the safe confines of the simulator. Running on NVIDIA DGX supercomputers, NVIDIA AutoSIM is repeatable for regression testing and will eventually simulate billions of miles.
Industry Partner Support
"The deep learning capabilities that NVIDIA provides combined with BlackBerry QNX's safety-critical real-time operating system are exactly what automakers want and need," said John Chen, executive chairman and CEO, BlackBerry. "Our partnership with NVIDIA will provide the automotive industry with a functionally safe AI self-driving platform that is secured to the highest standards."
"We are excited to team up with NVIDIA, the leader in automotive AI technologies, and to contribute our series-proven safety software framework MotionWise for autonomous systems in close partnership with our joint customers," said Georg Kopetz, CEO of TTTech. "This strategic world-class partnership will jointly bring a complete solution fast to market, ready for the high safety and security requirements for Level 2 to Level 5 fully fail-operational autonomous systems."
Originally from New Jersey, Eric is an automotive and technology reporter specializing in the high-tech industry in Silicon Valley. Eric has over fifteen years of automotive experience and a B.A. in computer science. These skills, combined with technical writing and news reporting, allows him to fully understand and identify new and innovative technologies in the automotive industry and beyond. He has worked on self-driving cars and as a technical writer, helping people to understand and work with technology. Outside of work, Eric likes to travel to new places, play guitar, and explore the outdoors.
January 19, 2018 News of the Day: BMW’s iNext EV Will Have Double the Range of Tesla’s Model 3, PSA Group to Built North American Headquarters Near Atlanta
Lithium Producers for Tesla’s Batteries to Get a Dedicated Hedge Fund
January 18, 2018 News of the Day: Honda Clarity Honored as the Most Innovative Car in the 2018 Edmunds CES Tech Driven Awards, GAC Motor May Use Fiat for Foothold into the U.S. Market
Uber Plans to Have Autonomous Trips With No Human Backup in 2019
AdaSky Demonstrates its Thermal Vision Solution for Autonomous Cars at CES
January 17, 2018 News of the Day: Nissan's Infiniti to Electrify its Models, China’s GAC Plans to Sell Cars in the U.S. in 2019
Autonomous Driving Startup Pony.ai Raises $112 Million in Funding
Hyundai's 2019 NEXO Fuel Cell EV Named Digital Trends Top Tech of CES 2018
- Hyundai & Aurora Partner to Bring Level 4 Autonomous Vehicles by 2021
- Tesla Sets Up a R&D Center in Beijing
- Waymo CEO John Krafcik Talks Autonomous Cars at Automobility LA
- Charging at Home is a Big Drawback to Electric Vehicles
- Highway Chargers Are Holding EVs Back From Becoming Mainstream
- BYTON Opens North American Headquarters in Silicon Valley
- CEO of Aptiv States Autonomous Taxis Will Arrive in 2018
- Optimus Ride Looks to Ferry Passengers in Autonomous Vehicles in Massachusetts
- Foxconn Wants a Highway Lane for Autonomous Vehicles in Wisconsin
- BYTON Debuts its Intelligent Connected SUV Concept at CES