The Atlas Lab centers its research on developing advanced, highly accurate, and safe high-definition (HD) maps for self-driving vehicles.
To drive these advancements, the lab leverages key technical AI components, focusing primarily on:
With a commitment to socially aware, reliable, and privacy-preserving AI systems.
The Atlas Lab is dedicated to bridging the gap between cutting-edge AI research and the future of safe, autonomous mobility.
The lab’s mission and vision are to build the fundamental knowledge base, technological tools, and human capacities necessary to transition to a new generation of smart, automated transportation supported and enhanced by high-definition (HD) mapping systems.
The impact of the lab lies in accelerating a comprehensive sociotechnical transition, moving closer to safer roads free of congestion and emissions, achieved by validating breakthroughs directly alongside industrial partners like TomTom, fostering top scientific talent, and embedding socially aware, privacy-preserving, and reliable AI frameworks to build trust across the autonomous technology ecosystem
3D point cloud object detection – Focuses on detecting and localizing key objects in 3D space using point cloud data captured by vehicle sensors.
Sparse data representation for point cloud segmentation – Focuses on compressing and efficiently processing large, sparse LiDAR datasets to speed up spatial mapping.
Structured semantic segmentation – Focuses on classifying road environments into hierarchical semantic layers, such as lane markers, traffic signs, and drivable areas.
Few-shot tiny object detection – Focuses on recognizing small or rare road objects accurately, even when very few training examples are available.
Cross-sensor transfer learning – Focuses on seamlessly fusing and transferring knowledge across different sensor types, including camera imagery and LiDAR data.
Automated recognition & 3D vehicle localization – Focuses on pinpointing precise vehicle positions and tracking traffic elements dynamically within complex urban driving settings.
Collaborative mapping & life-long learning – Focuses on continuously updating high-definition maps online via crowd-sourced data while preserving user privacy.
TomTom is a leading independent location technology specialist, shaping mobility with highly accurate maps, navigation software, real-time traffic information and services.
University of Amsterdam (UvA) is the Netherlands’ largest university, offering the widest range of academic programmes.
