deep learning

Advances in Inference and Representation for Simultaneous Localization and Mapping

Simultaneous localization and mapping (SLAM) is the process of constructing a global model of an environment from local observations of it; this is a foundational capability for mobile robots, supporting such core functions as planning, navigation, …

A Smooth Representation of Belief over SO(3) for Deep Rotation Learning with Uncertainty

A novel parameterization for deep Bayesian rotation estimation Best Student Paper Award (RSS 2020)