Research and development

Advancing AI through collaborative fundamental and applied research

About the Naska.AI R&D team

In Naska.AI, our research philosophy centers around new product innovation, product enhancement through fundamental breakthroughs, operational efficiency through technical innovation. With a strong product focus, we work on exciting research problems to deliver direct impact to our customers through customer facing product solutions powered by deep technical advances.

Naska.AI research areas

Machine learning

Geometric Deep Learning allows us to build models that operate on data structures that can encode geometry, texture and semantics. We utilize representation learning methods to build abstractions of our domain specific data that can be utilized for various downstream learning tasks. Finally, we also focus on Active and Few shot learning methods to adapt the insights to new downstream inference tasks.

Computer vision

Advanced computer vision and computer graphics algorithms allow us to deal with the noise inherent to construction reality capture data. Photogrammetry techniques like SLAM and Structure from motion help us to build accurate representations of the built environment. This combined with inverse rendering algorithms allows us to accurately distinguish between the various artifacts observed on site.

Robotics

Meet Noether, Naska.AI’s research and development robot (named after the famous mathematician Emmy Noether). This UGV is equipped with multimodal sensing, allowing Naska.AI’s R&D Team to validate new groundbreaking ideas and experimental workflows that have the potential to impact the construction industry—built with intelligent autonomy to test new ideas with minimal human supervision. Noether is involved in several Horizon Europe projects to push the boundaries of construction automation.