NVIDIA has unveiled details of its functional safety architecture for NVIDIA DRIVE, the company’s Artificial Intelligence (AI) autonomous vehicle platform at CES 2018. NVIDIA DRIVE uses redundant and diverse functions to enable OEMs to create self-driving vehicles to operate safely, even in the event of faults related to the operator, environment or systems. This 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, noted NVIDIA.
NVIDIA DRIVE provides a holistic safety platform that includes process, technologies and simulation systems, the company noted. In terms of process, it sets out the steps for establishing a pervasive safety methodology for the design, management and documentation of the self-driving system. The platform incorporates a diversity of processors to achieve fail operation capabilities, including NVIDIA-designed IP related to NVIDIA Xavier covering design and hardware functionality.
The NVIDIA DRIVE platform integrates safety technology from partners, like BlackBerry QNX’s 64-bit real-time operating system, along with TTTech’s MotionWise safety application framework. It also offers full support of Adaptive AUTOSAR, while the NVIDIA toolchain uses ISO 26262 tool classification levels to ensure a safe and robust development environment. The NVIDIA DRIVE AV autonomous vehicle software stack performs functions like ego-motion, perception, localisation and path planning, and to realise fail operation capability, each functionality includes a redundancy and diversity strategy. Additionally, the platform also offers virtual reality simulation, especially since road testing is not sufficiently controllable, repeatable, exhaustive or fast.
Jensen Huang, Founder and CEO, NVIDIA, said safety is the most important feature of a self-driving car. It is imperative that it operates safely, even when things go wrong, he added. Huang noted that NVIDIA’s investment into this functional safety platform is one of the most important ones it’s made, and provides a critical ingredient for automakers to bring self-driving cars to market.