Toward Consistent Drift-free Visual Inertial Localization on Keyframe Based Map
This work addresses global localization for robots, which is incremental as it builds on existing MSCKF methods with specific enhancements.
The paper tackles the problem of global localization for robots by proposing a filter-based visual-inertial odometry framework that maintains consistency and reduces computation by using keyframe poses and Schmidt-EKF, with a re-linearization mechanism to improve precision in large scenes.
Global localization is essential for robots to perform further tasks like navigation. In this paper, we propose a new framework to perform global localization based on a filter-based visual-inertial odometry framework MSCKF. To reduce the computation and memory consumption, we only maintain the keyframe poses of the map and employ Schmidt-EKF to update the state. This global localization framework is shown to be able to maintain the consistency of the state estimator. Furthermore, we introduce a re-linearization mechanism during the updating phase. This mechanism could ease the linearization error of observation function to make the state estimation more precise. The experiments show that this mechanism is crucial for large and challenging scenes. Simulations and experiments demonstrate the effectiveness and consistency of our global localization framework.