Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

Towards Consistent State and Covariance Initialization for Monocular SLAM Filters

Towards Consistent State and Covariance Initialization for Monocular SLAM Filters In this paper we perform a consistency investigation for the initialization of Monocular Simultaneous Localization and Mapping filters by utilizing an existing closed-form solution for metric velocity, landmark distance and attitude determination. This closed-form solution offers a consistent initial estimate for the state as well as the covariance of the considered system. The resulting initialization equations solely rely on monocular images and measurements of an inertial measurement unit (IMU) with 9 degrees of freedom. Furthermore they do not require any prior knowledge or assumptions about the estimates or the surrounding static environment. Based on these analytical expressions, we will derive conditions which are required in order to gain consistent initial estimates. The actual consistency, the accuracy of the initial state and the properties of the initial covariance will then be discussed thoroughly on the basis of simulated experiments. http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png Journal of Intelligent & Robotic Systems Springer Journals

Towards Consistent State and Covariance Initialization for Monocular SLAM Filters

Loading next page...
 
/lp/springer-journals/towards-consistent-state-and-covariance-initialization-for-monocular-rK2RfadRqM

References (17)

Publisher
Springer Journals
Copyright
Copyright © 2015 by Springer Science+Business Media Dordrecht
Subject
Engineering; Control, Robotics, Mechatronics; Electrical Engineering; Artificial Intelligence (incl. Robotics); Mechanical Engineering
ISSN
0921-0296
eISSN
1573-0409
DOI
10.1007/s10846-015-0185-3
Publisher site
See Article on Publisher Site

Abstract

In this paper we perform a consistency investigation for the initialization of Monocular Simultaneous Localization and Mapping filters by utilizing an existing closed-form solution for metric velocity, landmark distance and attitude determination. This closed-form solution offers a consistent initial estimate for the state as well as the covariance of the considered system. The resulting initialization equations solely rely on monocular images and measurements of an inertial measurement unit (IMU) with 9 degrees of freedom. Furthermore they do not require any prior knowledge or assumptions about the estimates or the surrounding static environment. Based on these analytical expressions, we will derive conditions which are required in order to gain consistent initial estimates. The actual consistency, the accuracy of the initial state and the properties of the initial covariance will then be discussed thoroughly on the basis of simulated experiments.

Journal

Journal of Intelligent & Robotic SystemsSpringer Journals

Published: Jan 31, 2015

There are no references for this article.