Visually Navigating the RMS Titanic with SLAM Information Filters
نویسندگان
چکیده
This paper describes a vision-based, large-area, simultaneous localization and mapping (SLAM) algorithm that respects the low-overlap imagery constraints typical of underwater vehicles while exploiting the inertial sensor information that is routinely available on such platforms. We present a novel strategy for efficiently accessing and maintaining consistent covariance bounds within a SLAM information filter, thereby greatly increasing the reliability of data association. The technique is based upon solving a sparse system of linear equations coupled with the application of constant-time Kalman updates. The method is shown to produce consistent covariance estimates suitable for robot planning and data association. Real-world results are presented for a vision-based 6-DOF SLAM implementation using data from a recent ROV survey of the wreck of the RMS Titanic.
منابع مشابه
Large-Area Visually Augmented Navigation for Autonomous Underwater Vehicles
This thesis describes a vision-based, large-area, simultaneous localization and mapping (SLAM) algorithm that respects the low-overlap imagery constraints typical of autonomous underwater vehicles (AUVs) while exploiting the inertial sensor information that is routinely available on such platforms. We adopt a systems-level approach exploiting the complementary aspects of inertial sensing and vi...
متن کاملTradeoffs in SLAM with Sparse Information Filters
Designing filters exploiting the sparse information matrix for efficiently solving the simultaneous localization and mapping (SLAM) problem has attracted significant attention during the recent past. The main contribution of this paper is a review of the various sparse information filters proposed in the literature to date, in particular, the compromises used to achieve sparseness. Two of the m...
متن کاملAdvances in High Resolution Imaging from Underwater Vehicles
Large area mapping at high resolution underwater continues to be constrained by the mismatch between available navigation as compared to sensor accuracy. In this paper we present advances that exploit consistency and redundancy within local sensor measurements to build high resolution optical and acoustic maps that are a consistent representation of the environment. We present our work in the c...
متن کاملEfficient Large Scale SLAM Including Data Association using the Combined Filter
In this paper we describe the Combined Filter, a judicious combination of Extended Kalman (EKF) and Extended Information filters (EIF) that can be used to execute highly efficient SLAM in large environments. With the CF, filter updates can be executed in as low as O(logn) as compared with other EKF and EIF based algorithms: O(n2) for Map Joining SLAM, O(n) for Divide and Conquer (D&C) SLAM, and...
متن کاملPlanar Features and 6D-SLAM based on Linear Regression Kalman Filters with n-Dimensional Approximated Gaussians
In this paper, a six-dimensional (6D) Simultaneous Localization and Mapping (SLAM) based on novel Linear Regression Kalman Filter (LRKF), called Smart Sampling Kalman Filter (S2KF), is proposed. While the conventional feature based SLAM methods use point features as landmarks, only a few take the advantage of geometric information like corners, edges, and planes. A feature based SLAM method usi...
متن کامل