分散ブロック座標移動ホライズン推定による2D視覚慣性オドメトリSLAM
Distributed Block Coordinate Moving Horizon Estimation for 2D Visual-Inertial-Odometry SLAM
ランドマークごとに並列化可能なバンドル調整に基づく分散ブロック座標非線形移動ホライズン推定を用いた視覚慣性SLAMを提案し、シミュレーションで軌道形状による推定性能の違いを検証した。
著者: Emilien Flayac, Iman Shames
分類: cs.RO, math.OC
原文アブストラクト
This paper presents a Visual Inertial Odometry Landmark-based Simultaneous Localisation and Mapping algorithm based on a distributed block coordinate nonlinear Moving Horizon Estimation scheme. The main advantage of the proposed method is that the updates on the position of the landmarks are based on a Bundle Adjustment technique that can be parallelised over the landmarks. The performance of the method is demonstrated in simulations in different environments and with different types of robot trajectory. Circular and wiggling patterns in the trajectory lead to better estimation performance than straight ones, confirming what is expected from recent nonlinear observability theory.
