Automotive

End-to-End HD Mapping for Self-Driving Cars
End-to-end HD Mapping for Self-Driving Cars

Welcome to the
future of Mapping

 

NVIDIA offers an end-to-end mapping system for self-driving cars, designed to help automakers, map companies and startups to rapidly create HD maps and keep them updated. This process that used to take weeks can now happen in near real-time. For automotive developers, the same architecture used to create maps and keep them up-to-date can also enable self-driving cars.

This state-of-the-art technology uses an NVIDIA DRIVE™ PX 2 AI supercomputer, coupled with NVIDIA Tesla® GPUs in the data centre, to accelerate the creation and updating of highly detailed maps for autonomous vehicles. Traditional mapping techniques have required numerous expensive sensors in the car to collect massive volumes of data that were recorded and then processed offline. Conversely, this HD mapping system is highly-efficient, moving data processing data into the vehicle, and minimizing communication with the cloud. The process that used to take weeks can now happen in near real-time.

NVIDIA's open mapping platform is built on the NVIDIA DriveWorks software toolkit for autonomous driving, and designed for carmakers, map companies and startups to accelerate development. When just using cameras, the system incorporates deep learning algorithms to detect lanes, signs and other landmarks, and can be used to both create maps and determine when the environment has changed.

From Cloud to Car

For localisation, structure-from-motion algorithms enable data from multiple cameras to be converted into detailed 3D mapping information. Combining data from various inertial sensors in the car, along with GPS data and cameras, enables precise positioning of key landmarks. If desired, lidar information can be utilised to create even richer maps with greater detail. A combination of artificial intelligence and VSLAM (Visual Simultaneous Localisation and Mapping) handle all stages of map creation.

The end-to-end system is highly customisable, incorporating both an in-vehicle AI supercomputer, and a cloud component based on Tesla GPUs. For automotive developers, this same architecture used to create maps and keep them up-to-date can also enable self-driving cars.

 

For more information

Contact Us