Current ongoing work on dataset collection to apply to robot navigation in the wild based on strong semantic priors and rich examples from demonstration. paper.
How to perceive the environment and understand it? How to adapt to any label encountered in the real world?
paper
The Eigen-Factor (EF) method, which estimates a planar surface from a set of point clouds (PCs), with the peculiarity that these points have been observed from different poses, i.e. the trajectory described by a sensor. We propose to use multiple Eigen-Factors (EFs) or different planes’ estimations, that allow to solve the multi-frame alignment over a sequence of observed PCs. Moreover, the complexity of the EFs optimization is independent of the number of points, but depends on the number of planes and poses. To achieve this, a closed-form of the gradient is derived by differentiating over the minimum eigenvalue with respect to poses, hence the name Eigen-Factor.
Dealing with uncertainty is an essential element to deploy robots in real conditions. On this work, we set the initial research lines, and this research continues under different paradigms, an hybrid of optimization and data-driven neural algorithm. paper