Nissan showcases on-road autonomous vehicle testing in Europe
Renault-Nissan Alliance and Transdev to develop driverless vehicle fleet system for future public and on-demand transportation

Qualcomm and TomTom partner on crowdsourcing high-definition mapping data for autonomous driving

Qualcomm Technologies is working with TomTom on using the Qualcomm Drive Data Platform for high-definition (HD) map crowdsourcing, to accelerate the future of autonomous driving. Qualcomm Drive Data Platform intelligently collects and analyzes data from different vehicle sensors, supporting smarter vehicles to determine their location, monitor and learn driving patterns, perceive their surroundings and share this perception with the rest of the world reliably and accurately.

TomTom’s HD Map, including RoadDNA, is a highly accurate, digital map-based product, which assists automated vehicles to precisely locate themselves on the road and help determine which way to maneuver, even when traveling at high speeds.

Traditional development of maps requires deploying dedicated fleets of vehicles that are equipped with professional-grade sensors to collect location, raw imagery, LiDAR and other data, which is then transferred, stored and processed in data centers. Now that cars are increasingly connected and equipped with a range of sensors, new and complimentary approaches become possible.

Using the precise positioning, on-device machine learning, heterogeneous compute and connectivity capabilities of the Qualcomm Drive Data Platform—which features the Qualcomm Snapdragon 820Am automotive processor—TomTom and Qualcomm Technologies aim to facilitate adding an improved, scalable and cost-efficient crowdsourcing approach to the mix of sources for HD map making. The concept is designed to allow massive numbers of connected cars to see and to understand their environment, traffic and road conditions, and support real-time input for map and road condition updates.

Machine learning algorithms, running on the Snapdragon 820Am processor, are optimized using the Qualcomm Snapdragon Neural Processing Engine toolkit, and are intended to identify features such as traffic signs and lane markers, and fuse this information with the precise positioning to generate feature-rich, highly accurate and lightweight map updates. This facilitates cars on the road to become live sensors that automatically update navigation services about real-time road conditions using the integrated X12 LTE modem of the Snapdragon 820Am.

The Snapdragon Neural Processing Engine SDK is powered by the Qualcomm Zeroth Machine Intelligence Platform and is optimized to utilize Snapdragon’s heterogeneous compute capabilities to provide OEMs a powerful, energy efficient platform for delivering intuitive and engaging deep learning-driven experiences on device. The Zeroth Machine Intelligence Platform is a Snapdragon-optimized software platform designed for mobile machine learning.

Object identification and classification processing runs on the heterogeneous cores of the Snapdragon processor, avoiding the need and cost of sending raw video over the network. The process is designed to further optimize over multiple iterations, running locally on the Snapdragon 820Am-powered platform, and then upload to the cloud for crowdsourcing. The result is a real-time HD map, constantly improving and with highly accurate location, for safer and advanced driving experiences.

Comments

The comments to this entry are closed.