Ralf G. Herrtwich

Senior Director Automotive Software, NVIDIA

Artificial Intelligence for Self-Driving Cars

Behind the mere hardware and software that goes into a self-driving car stands the technology to develop the vehicle’s intelligence. That technique is a far cry from traditional programming, it involves continuous training and re-training of deep neural networks that allow the vehicle to cope better and better with the various traffic situations it encounters. Efficiency in this development can only be accomplished with the right tools and infrastructure which together yield a highly-performant system design – from flexible open modular software to hardware that is capable to interpret a multitude of high-volume sensor data streams in real-time. In this presentation, we illustrate how NVIDIA masters these challenges.


Ralf G. Herrtwich runs automotive software development for NVIDIA in Germany where he can draw upon his long R&D experience in vehicle automation as well as in infotainment and telematics technology. His past assignments include managing the automotive business of HERE Technologies, with a special focus on high-definition maps and crowd-sourced location services, and developing self-driving vehicles for Mercedes-Benz. In 2013, his team made an S-Class re-enact the world’s first overland drive, covering the historic 65-miles Bertha Benz Route autonomously in regular traffic. A computer scientist by education, Dr. Herrtwich started his career in academia at TU Berlin and UC Berkeley. He then held management positions with IBM and several telecommunication start-ups before joining Daimler in 1998 to manage its advanced engineering on telematics, infotainment and, later, driver assistance and chassis systems. Since 2009, he also is honorary professor for vehicle information technology at the Technical University of Berlin.