RootSLAM boosts visual-inertial mapping speed twentyfold with high accuracy
RootSLAM: Square Root Bundle Adjustment for Visual-Inertial SLAM
RoboticsComputer Vision and Pattern Recognition
Summary
Many small devices like drones and augmented reality glasses need to know where they are and what’s around them, which requires complicated computer calculations called SLAM. The authors built RootSLAM, a system that uses cameras and motion sensors to map surroundings and track movement much faster than before without losing accuracy. They improved how the system processes data by using a new mathematical approach that lets it run quicker and more efficiently on limited hardware. This makes it easier to put smart perception technology into small, low-power devices.
What this means in practice
- •For drone developers: Create drone navigation systems that run visually based mapping and localization twenty times faster on resource-limited hardware.
- •For augmented reality device engineers: Implement fast multi-camera SLAM solutions that conserve power while maintaining accurate tracking and environmental mapping.
Authors
Tomás Santucci, Mateo de Mayo, Daniel Cremers, Taihú Pire
Abstract
Efficient perception is a prerequisite for the small, low-power devices targeted by robotics, mixed reality, autonomous driving, and drone applications, all of which rely on Simultaneous Localization and Mapping (SLAM) to estimate their motion within their surroundings. Learning-based SLAM systems achieve state-of-the-art accuracy but are demanding in compute, whereas classical geometry-based methods retain a strong efficiency advantage with little to no loss in accuracy. In this work we present RootSLAM, a fully-featured visual-inertial SLAM system for multi-camera setups built on Basalt. RootSLAM achieves accuracy competitive with the state of the art while running up to 20 times faster, facilitating the deployment of perception systems in resource constrained environments. We adapt the square-root bundle adjustment formulation from structure from motion into the multi-camera visual-inertial SLAM setting through a novel reformulation that leverages the system's pose-graph, letting the global optimizer run in single-precision floating point, thus doubling its performance. We provide a thorough benchmark against the state of the art together with an ablation study of our contributions. Our new implementation, including its map management and loop detection module, pose-graph optimizer, and global mapping components, will be open-sourced.