Keyframe-based Visual-Inertial SLAM using Nonlinear Optimization

TLDR

Fusion of visual and inertial cues is popular in robotics, and recent work has shifted from filtering to nonlinear optimization for SLAM because it improves performance and computational complexity. The paper proposes a novel tightly coupled visual–inertial SLAM method. An IMU error term is integrated with landmark reprojection error in a fully probabilistic manner, forming a joint nonlinear cost function, and keyframes are used to partially marginalize old states to keep the optimization window bounded for real‑time operation. Experiments comparing against vision‑only and loosely coupled visual‑inertial algorithms confirm that tight fusion improves accuracy and robustness.

Abstract

The fusion of visual and inertial cues has become popular in robotics due to the complementary nature of the two sensing modalities. While most fusion strategies to date rely on filtering schemes, the visual robotics community has recently turned to non-linear optimization approaches for tasks such as visual Simultaneous Localization And Mapping (SLAM), following the discovery that this comes with significant advantages in quality of performance and computational complexity. Following this trend, we present a novel approach to tightly integrate visual measurements with readings from an Inertial Measurement Unit (IMU) in SLAM. An IMU error term is integrated with the landmark reprojection error in a fully probabilistic manner, resulting to a joint non-linear cost function to be optimized. Employing the powerful concept of ‘keyframes’ we partially marginalize old states to maintain a bounded-sized optimization window, ensuring real-time operation. Comparing against both vision-only and loosely-coupled visual-inertial algorithms, our experiments confirm the benefits of tight fusion in terms of accuracy and robustness.