ZF and NVIDIA Announce Artificial Intelligence System for Autonomous Cars, Trucks and Industrial Applications
- ZF ProAI for automated driving built on high-performance NVIDIA DRIVE PX 2 AI computing platform
- Vehicles will be able to see, think, act
Friedrichshafen/Las Vegas. ZF, one of the world’s largest automotive suppliers and a global leader in active and passive safety technology, today announced it is working with NVIDIA to develop artificial intelligence (AI) systems for the transportation industry, including automated and autonomous driving systems for passenger cars, commercial trucks, and industrial applications. Unveiled at the CES 2017 in Las Vegas, the ZF ProAI for highway automated driving is ZF’s first system developed using NVIDIA AI technology. It will enable vehicles to better understand their environment by using deep learning to process sensor and camera data. In addition, the companies are developing solutions for more advanced highly automated driving—in which systems have the capability to control the vehicle with greater levels of autonomy.
Current electronic control units in cars consist of numerous processors, each of which controls a system or a specific function. However, their computing power is not currently sufficient for autonomous driving.
“With NVIDIA, we are bringing the supercomputing power required for artificial intelligence into cars and commercial vehicles,” explains ZF CEO Dr. Stefan Sommer. “ZF is enabling vehicles to see, think and act. NVIDIA’s AI platform lets us take a giant leap forward when it comes to enabling vehicles – whether cars, trucks or forklifts -- to think.”
ZF ProAI will use the scalable NVIDIA DRIVE PX 2 AI computing platform to process inputs from multiple cameras, plus lidar, radar and ultrasonic sensors. ZF ProAI will have the capability to understand in real time what is happening around a vehicle, precisely locate itself on an HD map and plan a safe path forward. The solution will meet automotive-grade standards to function when exposed to extreme temperatures, moisture and dust. Series production is planned for 2018 onwards.
“Transportation is a massive industry that AI can transform,” said Rob Csongor, vice-president and general manager of Automotive at NVIDIA. “With NVIDIA’s autonomous driving technology and ZF’s powerful position in transportation, AI self-driving can now be enabled in any vehicle from passenger cars to commercial vehicles worldwide.”
AI opens up massive possibilities
Supercomputing and deep learning capabilities are dramatically accelerating the development of autonomous cars. The NVIDIA DRIVE PX 2 AI platform provides the enormous computing power necessary to comprehend a 360-degree view around a vehicle and plan appropriate action.
ZF is delivering ZF ProAI as an in-vehicle system capable of over-the-air updates to add new features and capabilities throughout the life of the vehicle. It is also configured for V2X applications, so it can communicate with other vehicles and with the surrounding infrastructure. In addition, the learning and networking capacity of ZF ProAI can help make an entire vehicle fleet safer and more efficient by means of “swarm intelligence.”
“We see NVIDIA’s deep learning platform as the basis for our future AI-capable software, plus we will make it available to third parties,” explains Torsten Gollewski, head of Advanced Engineering at ZF. “In addition to autonomous cars, we see many opportunities to bring this technology to commercial vehicles and other industrial applications. AI-capable software and deep learning will become more prevalent in many AI industries in the coming years.”