Nvidia is teaming up with TomTom to create a cloud-to-car mapping system for self-driving cars.
The NVIDIA DriveWorks software development kit now integrates support for TomTom’s HD mapping environment (credit: TomTom)
On Thursday, the companies announced the partnership to develop artificial intelligence to create a solution that will speed up support for real-time in-vehicle localization and mapping.
The project will connect TomTom’s extensive HD map coverage, which already spans more than 120,000 km of highways and freeways, with the Nvidia Drive PX 2 computing platform.
“Self-driving cars require a highly accurate HD mapping system that can generate an always up-to-date HD map in the cloud,” said Rob Csongor, vice president and general manager of Automotive at Nvidia.
He was speaking at the company’s inaugural GTC Europe, a conference dedicated to GPU-accelerated computing.
Rob notes that Nvidia’s Px 2 provides TomTom with a real-time, in-vehicle source for HD map updates. It can support sensor fusion, deep learning, and advanced computer vision (CV) libraries and primitives.
The computing giant already has made public the developer tools for self-driving cars. Nvidia’s DriveWorks software development kit (SDK) gives developers a real platform to build applications, using the intensive algorithms for object detection, map localization, and path planning.
The open solution is available for automakers and tier 1 suppliers developing systems that enable cars to drive themselves. The DriveWorks now also integrates support for TomTom’s HD mapping environment.
“This collaboration is an important step for TomTom,” said Willem Strijbosch, head of Autonomous Driving at TomTom. He observed that combining the company’s HD maps with Nvidia’s self-driving car platform will bring new features to automakers faster and make autonomous driving a commercial reality.
COMMENTS