Reading group on Gradslam. Gradslam is an open-source framework providing
differentiable building blocks for simultaneous localization and mapping (SLAM)
systems. It enable the usage of dense SLAM subsystems from the comfort of
PyTorch.

Jatavallabhula, Krishna Murthy, Ganesh Iyer, and Liam Paull. "∇ SLAM: Dense
SLAM meets Automatic Differentiation." 2020 IEEE International Conference on
Robotics and Automation (ICRA). IEEE, 2020

Paper URL: https://gradslam.github.io/

Abstract:
The question of “representation” is central in the context of dense
simultaneous localization and mapping (SLAM). Newer learning-based approaches
have the potential to leverage data or task performance to directly inform the
choice of representation. However, learning representations for SLAM has been
an
open question, because traditional SLAM systems are not end-to-end
differentiable. In this work, we present gradSLAM, a differentiable
computational graph take on SLAM. Leveraging the automatic differentiation
capabilities of computational graphs, gradSLAM enables the design of SLAM
systems that allow for gradient-based learning across each of their components,
or the system as a whole. This is achieved by creating differentiable
alternatives for each non-differentiable component in a typical dense SLAM
system. Specifically, we demonstrate how to design differentiable trust-region
optimizers, surface measurement and fusion schemes, as well as differentiate
over rays, without sacrificing performance. This amalgamation of dense SLAM
with
computational graphs enables us to backprop all the way from 3D maps to 2D
pixels, opening up new possibilities in gradient-based learning for SLAM.