The Stack Archive

Self-driving startup to build new ‘language’ for cars using deep learning

Tue 30 Aug 2016


Self-driving car startup Drive.ai has today introduced its new technology, outlining plans to build unique driverless software powered by deep learning.

Founded last year by a team of experts from Stanford’s Artificial Intelligence Lab, Drive.ai also announced that it had appointed former General Motors executive Steve Girsky to its board of directors.

Drive.ai revealed that its strategy would take a completely different approach to self-driving, employing a full stack deep learning model. It explained that an integrated software and hardware system would allow vehicles to navigate safely in any driving setting – urban, suburban, and freeway. The system would continually communicate with users, other drivers, as well as people outside of the vehicle.

‘Deep learning is the most effective form of artificial intelligence, and the best one capable of responding intelligently to the infinite situations cars face on the roads,’ noted Drive.ai CEO and co-founder, Sameep Tandon in today’s release.

‘Our founding team has been working on deep learning’s applications to self-driving vehicles since its early stages. This is truly the enabling technology for the future of autonomous transportation, and we’re leveraging it for navigation and interaction both inside and outside vehicles,’ he continued.

Co-founder and President of Drive.ai Carol Reiley also commented that the company aims to build a brand new language for human-robot interaction. ‘It’s a once in a generation opportunity to reimagine the relationship between people, cars, and the world around them… Vehicles of the future will communicate transparently with us, they’ll have personality, and they’ll make us feel welcome and safe, even without a human driver,’ she said.

Drive.ai is initially proposing a retrofit self-driving kit for application in existing route-based fleets, such as vehicles involved in freight delivery, ride-sharing, or public transport. The product also includes sensors, a roof-mounted exterior communication system, and an in-car interface, all powered by deep learning algorithms.

The startup has already established relationships with major OEMs and automotive suppliers and is planning to expand these partnerships in the future.

On the Drive.ai announcement Girsky commented: ‘We all know that the automotive industry is in the midst of a foundational shift… The emergence of self-driving technology, and deep learning in particular, brings an incredible opportunity to save countless lives, transform the transportation landscape, and shift the way we think about cars and technology. The team at Drive.ai has the vision and expertise to lead this new era.’


news self-driving cars startup transport
Send us a correction about this article Send us a news tip