Autonomous driving has evolved from science fiction to technology that is actively deployed on roads today.
Sarah Tariq, VP of autonomous driving software at NVIDIA, is a key player in this transition. She worked on the ground floor of autonomous vehicle development at both NVIDIA and robotaxi company Zoox, and is now developing solutions for the coming generation of software-defined vehicles.
Tariq is working to redefine how the world views personal transportation, transforming it into an experience that surprises and delights. She spoke with NVIDIA AI Podcast host Katie Washabaugh about her decade in AV development, the many ways in which software can improve mobility and what’s on the road ahead for intelligent transportation.
Key Points From This Episode
- The same factors that led to early breakthroughs in AI are accelerating autonomous vehicle development: increased amounts of training data, GPU compute and a scalable AI infrastructure.
- NVIDIA is developing an entire platform that enables autonomous driving capabilities on consumer vehicles, with continuously upgraded software for constantly improving functionality.
- Digital assistants and in-cabin services are the next frontier in intelligent transportation. Software-defined vehicles make it possible for every passenger to easily access convenience and safety features inside the car.
“We’ve gotten to the place where we look at the false positives these networks are generating, it turns out, there was actually something there, and I as a human, I’m wrong in thinking there’s no object.” – Sarah Tariq [6:44]
“You’re constantly improving the models and shipping software that is providing better functionality. For a consumer, you get a car and it’s forever getting better and better rather than depreciating.” – Sarah Tariq [11:22]
You Might Also Like
Robots aren’t limited to the assembly line. Liila Torabi, senior product manager for Isaac Sim, a robotics and AI simulation platform powered by NVIDIA Omniverse, talks about where the field’s headed.
Humans playing games against machines is nothing new, but now computers can develop their own games for people to play. Programming enthusiast and social media influencer Harrison Kinsley created GANTheftAuto, an AI-based neural network that generates a playable chunk of the classic video game Grand Theft Auto V.
The neural networks powering autonomous vehicles require petabytes of driving data to learn how to operate. Nikita Jaipuria and Rohan Bhasin from Ford Motor Company explain how they use generative adversarial networks (GAN) to fill in the gaps of real world data used in AV training.
Subscribe to the AI Podcast: Now Available on Amazon Music
You can now listen to the AI Podcast through Amazon Music.
You can also get the AI Podcast through iTunes, Google Podcasts, Google Play, Castbox, DoggCatcher, Overcast, PlayerFM, Pocket Casts, Podbay, PodBean, PodCruncher, PodKicker, Soundcloud, Spotify, Stitcher and TuneIn.
Make the AI Podcast Better: Have a few minutes to spare? Fill out our listener survey.
Go to Publisher: – Archives Page 1 – The Official NVIDIA Blog
Author: Brian Caulfield