C. Gentil

Scalix achieves state-of-the-art scale consistency in monocular SLAM by treating scale predictions as independent measurements, revolutionizing how robots perceive their environments.

Radar SLAM can now achieve state-of-the-art performance via direct scan registration, eliminating the need for hand-engineered feature extraction and enabling robust localization in adverse weather.

LiDAR odometry can be made significantly more robust in challenging, feature-poor environments by representing surfaces as compact voxel-wise oriented height images and focusing registration on geometrically informative regions.

Robots can now adapt demonstrated skills to significantly different starting conditions thanks to a Gaussian Process representation that preserves kinematic profiles.