Atlas Lab: using AI for developing HD maps for self-driving vehicles
13 november 2019
In collaboration with TomTom, the UvA is embarking on research on the use of AI for creating HD maps suitable for all levels of autonomous driving. Theo Gevers, one of the Scientific Directors at Atlas Lab, comments: 'At the UvA we are already doing research on automated recognition of items in images and videos. Yet the recognition of items and creation of HD maps in highly complex situations like a moving car, is still a huge challenge. This collaboration with TomTom provides an extra dimension to new and challenging AI-research.'
For the next five years, five PhD students will work in the Atlas lab on projects contributing to automated recognition of items like traffic signs, 3D-localization of vehicles and combining LIDAR (light detection and ranging) laser and camera images. For retrieving data, mobile mapping vans equipped with sensors, like LIDAR-systems and cameras, are being used.
'TomTom is pushing the boundaries of the use of AI for making HD maps for self-driving cars,' said Harold Goddijn, TomTom’s CEO. 'We need groundbreaking research into AI technology, which is why we’re collaborating with UvA’s world-leading AI department on this initiative. This will move us a step closer to an autonomous future with safer roads, free of congestion and emissions.'
The Atlas Lab is the eleventh lab that is part of ICAI. In the past year ICAI already launched AIRlab Amsterdam (a joint industry-lab with Ahold Delhaize), the National Police lab (collaboration between UvA, Utrecht University and the Dutch National Police), Elsevier AI Lab (collaboration between UvA, Free University of Amsterdam and Elsevier) and AIM Lab (collaboration between UvA and Inception Institute of Artificial Intelligence Ltd.).