Tightly-Coupled Aided Inertial Navigation with Point and Plane Features
And a plane having a feature point closely coupled secondary inertial navigation
Yulin Yang *, Patrick Geneva ††, Xingxing Zuo †, Kevin Eckenhoff *, Yong Liu †, and Guoquan Huang *
This paper presents a tightly-coupled aided inertial navigation system (INS) with point and plane features, a general sensor fusion framework applicable to any visual and depth sensor (e.g., RGBD, LiDAR) configuration, in which the camera is used for point feature tracking and depth sensor for plane extraction. The proposed system exploits geometrical structures (planes) of the environments and adopts the closest point (CP) for plane parameterization. Moreover, we distinguish planar point features from non-planar point features in order to enforce point-on-plane constraints which are used in our state estimator, thus further exploiting structural information from the environment. We also introduce a simple but effective plane feature initialization algorithm for feature-based simultaneous localization and mapping (SLAM). In addition, we perform online spatial calibration between the IMU and the depth sensor as it is difficult to obtain this critical calibration parameter in high precision. Both Monte-Carlo simulations and real-world experiments are performed to validate the proposed approach.
In this paper, the close coupling secondary inertial navigation system (INS) and having a planar feature point, a generic framework in any visual sensor fusion and the depth sensor (e.g. RGBD, LiDAR) suitable configuration, wherein the characteristic points for the camera tracking and the depth sensor for plane extraction. The proposed system environment using the geometry (a plane), and using the closest point (CP) for plane parameterization. In addition, we point to a plane non-planar feature point feature distinguished, to the point of use in our state estimator constraint enforcement plane, so that further use of the structural information in the environment. We also feature-based simultaneous localization and map building (SLAM) introduced a simple and effective feature plane initialization algorithm. Further, since it is difficult to accurately obtain this key calibration parameters, we perform an online calibration in the space between the IMU and the depth sensor. Monte Carlo simulations and real-world experiments are proposed method can be verified.