Download
gradslam is an open-source framework providing differentiable building blocks for simultaneous localization and mapping (SLAM) systems. We enable the usage of dense SLAM subsystems from the comfort of PyTorch. 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.
Features
- Each approache sparked a new line-of-research in dense SLAM
- The approaches themselves are fairly simple from an algorithmic standpoint
- We aim to provide differentiable SLAM solutions for a wide variety of 3D representations (voxels, surfels, points)
- The differentiable SLAM systems perform quite similarly to the non-differentiable counterparts
- Further, we have evaluated gradslam on the TUM RGB-D benchmark
- Attractively poised to be used in gradient-based learning systems
Project Samples
