BROOKLYN, N.Y. — Self-driving cars
need onboard artificial intelligence technology able to link them to highly detailed maps that reflect in real time every
change in the status of lanes, hazards,
obstacles and speed limits.
Researchers at the New York Univer-
sity (NYU) Tandon School of Engineering
are working hard to make this machine-
to-machine interaction possible. Yi Fang,
a research assistant professor in the de-
partment of electrical and computer en-
gineering and a faculty member at NYU
Abu Dhabi, and Edward Wong, an as-
sociate professor in the NYU Tandon
department of computer science and en-
gineering, are developing a deep learn-
ing system that will allow self-driving
cars to navigate, maneuver and respond
to changing road conditions. To do this,
they are combining data from onboard
sensors to information on the HERE HD
Live Map — a cloud-based service for
“Three-dimensional computer vision
and deep neural network are the technologies driving the development of
high-definition live maps for self-driving cars,” said Xin Chen, HERE senior
engineering manager and research scientist.
Wong said their work involves using
computer vision techniques to refine
the vehicle’s ability to locate itself with
respect to HERE’s cloud-based service.
“That requires real-time images of the
street and surrounding objects derived
from cameras, lidar and other on-board
sensors,” he said.
High-definition maps meant for
must be accurate to within 10 to 20 cm.
Self-driving vehicles need to continuously update and register their location
on these maps with an equally high degree of accuracy. Fang said the goal of
the research is to enhance car-to-map
precision to within 10 cm.
“Essentially, we want to be able to
precisely match what the car sees with
what’s in the cloud database,” said Fang.
“An incredibly precise ruler isn’t of
much use if your vision is blurry.”
Automobiles connected to HERE’s
HD Live Map service will deliver data
to the cloud on road conditions, traf-
fic, weather, obstacles, speed limits and
other variables, allowing the service
to upgrade nearly in real time to reflect
The HERE mapping project joins a
number of recent initiatives at NYU
Tandon addressing safer and smarter
3D computer vision helps autonomous vehicles locate themselves on maps
NYU Tandon researchers are developing an artificial intelligence system for
autonomous vehicles that links them to HERE Live Map cloud-based mapping system.
3D printers that produce scaffolds up to
100 nm in size by direct laser writing.
“The ink with defined breaking points
can be used for a variety of applications,”
said doctoral student Markus Zieger.
Structures written with erasable ink
can be integrated into structures made
of nonerasable ink. Support construc-
tions can be produced by 3D printing
and removed later on. According to the
scientists, it is also possible to produce
reversible wire bonds from erasable con-
ducting structures in the future. A per-
manent ink can be mixed with a nonper-
manent ink to influence the properties of
the printed material and make it more or
less porous, for instance.
“3D printing already is indispensable
in many fabrication areas. Its importance
is increasing,” said Barner-Kowollik.
“According to estimations, some 10 per-
cent of all goods will be produced by 3D
printing in 2030.”
The new process is presented in the
journal Angewandte Chemie under the
heading “Cleaving Direct Laser Writ-
ten Microstructures on Demand” (doi:
Using a laser, 3D microstructures can be written, erased, and rewritten.