Ali Kani, vice president and general manager of automotive at NVIDIA, says: “DeepMap is expected to extend our mapping products, help us scale worldwide map operations and expand our full self-driving expertise.”
In a blog post, NVIDIA's senior director of automotive Danny Shapiro says maps that are accurate to within a few metres are good enough when providing turn by turn directions for humans, but AVs require much greater precision.
“They must operate with centimetre-level precision for accurate localisation, the ability of an AV to locate itself in the world,” he adds.
Shapiro emphasises that “proper localisation” requires constantly updated maps, which must also reflect current road conditions, such as a workzone or a lane closure.
“These maps need to efficiently scale across AV fleets, with fast processing and minimal data storage,” he continues.
“Finally, they must be able to function worldwide.”
According to Shapiro, DeepMap’s technology will bolster the mapping and localisation capabilities available on NVIDIA Drive, ensuring AVs always know precisely where they are and where they’re going.
“NVIDIA Drive is a software-defined, end-to-end platform — from deep neural network training and validation in the data centre to high-performance compute in the vehicle — that enables continuous improvement and deployment via over the air updates,” he explains.
As part of the deal, NVIDIA is to continue working with DeepMap's ecosystem, investing in new capabilities and services for new and existing partners.
The deal is expected to close in the third quarter of 2021.