Nvidia has launched a new mapping platform that will provide the self-driving car industry with ground truth mapping coverage for more than 300,000 miles of roads in North America, Europe and Asia by 2024, founder and CEO Jensen Huang said Tuesday. Said at the company’s GTC event.
This platform, called DriveMap, aims to enable a high level of autonomous driving. Drivemap not only exposes to existing Nvidia customers, but also enhances the company’s existing solutions for the AV industry.
At the same event, the company announced the next generation of Drive Hyperion. This is Nvidia’s sensor and computing autonomous driving toolkit used by Mercedes, Volvo, JiDu, BYD as of Tuesday, Lucid Motors and others to provide a variety of services. Of smart driving and advanced driving support functions.
AV companies such as TuSimple, WeRide, Zoox and DeepRoute.ai are also Hyperion’s customers.
Drivemap represents the result of Nvidia’s acquisition of high-resolution mapping startup DeepMap last year. This tool provides centimeter-level accuracy by combining DeepMap’s accurate survey mapping with anonymous mapping data crowdsourced from all vehicles using Nvidia’s Hyperion architecture. The mapping tool has three localization layers: camera, lidar, and radar to provide the redundancy required for autonomy.
All data obtained from Nvidia customers is constantly uploaded to the cloud while driving the vehicle. Then aggregate it and load it into Nvidia’s Omniverse. It is the company’s open platform built for virtual collaboration and real-time physically accurate simulations and is used to update maps to enable vehicles to achieve proper localization. In the process, Nvidia can scale its mapping footprint more quickly.
In addition, Omniverse uses automated content generation tools to create detailed maps and transform them into a drivable simulation environment that can be used with Nvidia DriveSim, an end-to-end simulation platform for self-driving cars.