New York team developing AI to upgrade HD maps for autonomous vehicles


Researchers at New York University (NYU) are developing artificial intelligence (AI) technology that will allow self-driving vehicles to navigate with centimeter precision using Here’s cloud-based HD Live Map system.

For autonomous vehicles to deliver their expected societal and consumer benefits they will need onboard AI technology able to link them to highly detailed maps that reflect every change in the status of lanes, hazards, obstacles, and speed-limits in real time. Edward K Wong, an associate professor in the NYU Tandon Department of Computer Science and Engineering and Yi Fang, a research assistant professor at NYU Abu Dhabi, are developing a deep learning system that will allow self-driving cars to navigate, maneuver, and respond to changing road conditions by mating data from onboard sensors to information on Here’s cloud-based HD Live Map for automated driving. The NYU Multimedia and Visual Computing Lab directed by Professor Fang will house the collaborative project.

The NYU team recently received a gift fund from Here, making it one of the company’s first university research and development partners in its HD Live Map program. High-definition (HD) maps meant for machine-to-machine (M2M) communication must be accurate to within 4-8in (10-20cm), as self-driving vehicles need to continuously update, or register, their location on these maps with an equally high degree of accuracy. This precision is also important because automobiles connected to Here’s HD Live Map service will deliver data to the cloud on current road conditions, traffic, weather, obstacles, speed limits, and other variables, allowing the service to upgrade nearly in real time to reflect changing conditions.

According to Fang, the goal of the collaborative research is to enhance car-to-map precision to within 4in (10cm). “Essentially, we want to be able to precisely match what the car sees with what’s in the cloud database. An incredibly precise ruler isn’t of much use if your vision is blurry,” Fang explained.

Xin Chen, Here senior engineering manager and research scientist, noted, “3D computer vision and Deep Neural Networks are the technologies driving the development of high- definition live maps for self-driving cars. We’re excited to kick off a long-term research collaboration with Professors Wong and Fang individually based upon their expertise in this domain, as well as with NYU as a top institution for research and learning in the field.”

The Here mapping project joins a number of recent initiatives at NYU Tandon addressing safer and smarter transportation. The US Department of Transportation (USDOT) selected a research consortium led by NYU Tandon Department of Civil and Urban Engineering researchers to become the first Tier 1 University Transportation Center (UTC) in New York City, dedicated to using data to make every mode of surface transportation, from walking through mass transit, more efficient and safe. Another venture is developing the first free, open-source method for auto makers to secure software updates. ‘Uptane’ will protect vehicles from cyber criminals and cyber war, while providing the auto industry with an inexpensive and quick way to install safety fixes.

Share this story:

About Author


Tom has edited Traffic Technology International (TTi) magazine and its Traffic Technology Today website since May 2014. During his time at the title, he has interviewed some of the top transportation chiefs at public agencies around the world as well as CEOs of leading multinationals and ground-breaking start-ups. Tom's earlier career saw him working on some the UK's leading consumer magazine titles. He has a law degree from the London School of Economics (LSE).