Self-Driving Car Maps Will Be Provided By Mapbox

San Francisco: US-based mapping start-up Mapbox has partnered with Microsoft, Intel, and Softbank Group to provide maps for self-driving cars.

Mapbox provides the underlying maps in other apps like Snapchat and Instacart rather than the app itself.

"Our newly announced Vision SDK integrates with the Microsoft Azure IoT platform. This partnership improves the driving experience inside the vehicle and generates road data on the backend to power analytic solutions for smart cities, insurance companies, and more," Eric Gundersen, CEO, Mapbox, said in a statement late Wednesday.

The future of location will be building live maps in real time from distributed sensor networks embedded in vehicles and mobile devices at scale.

The Vision SDK runs neural networks directly on a user's mobile device or embedded hardware within a vehicle to segment the environment and detect discrete features like other vehicles, pedestrians, speed limits, construction signs, crosswalks, vegetation and more.

On the hardware side, Mapbox collaborated with Softbank Group Corp's ARM Holdings chip unit.

"We're collaborating with Arm on low power optimisation that will bring the Vision SDK to tens of millions of devices and machines," Gundersen said.

Mapbox also joined Intel's Mobileye self-driving unit.

Also Read: Alibaba Mulls Self Driving Cars

Mapbox's "RoadBook" provides lane level maps for semi- and fully-autonomous vehicles.

"Through the cooperation with Mapbox, we enabled a large-scale, low data-rate, cloud-to-car distribution of the RoadBook," said Erez Dagan, SVP Advanced Development and Strategy at Mobileye.

Mobileye cameras crowdsource live data to the Cloud through wireless communication networks, updating the map in real time.

As the data is ingested, it's fed directly into Mobileye's private vector maps and then distributed to the vehicles. (IANS)