gradSLAM: Automagically differentiable SLAM
This work addresses the challenge of integrating representation learning with SLAM for robotics and AI applications, offering a novel approach to enhance task performance through differentiable components.
The authors tackled the problem of making dense simultaneous localization and mapping (SLAM) systems differentiable to enable gradient-based learning for task optimization, resulting in gradSLAM, a methodology that unifies gradient-based learning with SLAM without sacrificing accuracy.
Blending representation learning approaches with simultaneous localization and mapping (SLAM) systems is an open question, because of their highly modular and complex nature. Functionally, SLAM is an operation that transforms raw sensor inputs into a distribution over the state(s) of the robot and the environment. If this transformation (SLAM) were expressible as a differentiable function, we could leverage task-based error signals to learn representations that optimize task performance. However, several components of a typical dense SLAM system are non-differentiable. In this work, we propose gradSLAM, a methodology for posing SLAM systems as differentiable computational graphs, which unifies gradient-based learning and SLAM. We propose differentiable trust-region optimizers, surface measurement and fusion schemes, and raycasting, without sacrificing accuracy. 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. TL;DR: We leverage the power of automatic differentiation frameworks to make dense SLAM differentiable.