6-DOF Multi-session Visual SLAM using Anchor Nodes

Robotics and Autonomous Systems, 2012

This paper describes a system for performing real-time multi-session visual mapping in large-scale environments. Multi-session mapping considers the problem of combining the results of multiple simultaneous localisation and mapping (SLAM) missions performed repeatedly over time in the same environment. The goal is to robustly combine multiple maps in a common metrical coordinate system, with consistent estimates of uncertainty. Our work employs incremental smoothing and mapping (iSAM) as the ...

International Conference on Robotics and Automation, 2008

The main contribution of this paper arises from the development of a new framework, which has its inspiration in the mechanics of human navigation, for solving the problem of Simultaneous Localization and Mapping (SLAM). The proposed framework has specific relevance to vision based SLAM, in particular, small baseline stereo vision based SLAM and addresses several key issues relevant to the particular sensor domain. Firstly, as observed in the authors' earlier work, the particular sensing device has a highly nonlinear observation model resulting in inconsistent state estimations when standard recursive estimators such as the Extended Kalman Filter (EKF) or the Unscented variants are used.

Springer Tracts in Advanced Robotics, 2003

This paper addresses the problem of Simultaneous Localization and Mapping (SLAM) when working in very large environments. A Hybrid architecture is presented that makes use of the Extended Kalman Filter to perform SLAM in a very efficient form and a Monte Carlo type filter to resolve the data association problem potentially present when returning to a known location after a large exploration task. The proposed algorithm incorporates significant integrity to the standard SLAM algorithms by providing the ability to handle multimodal distributions in real time. Experimental results in outdoor environments are presented to demonstrate the performance of the algorithm proposed.

2009

SLAM algorithms do not perform consistent maps for large areas mainly due to the uncertainties that become prohibitive when the scenario becomes larger and to the increase of computational cost. The use of local maps has been demonstrated to be well suited for mapping large environments, reducing computational cost and improving map consistency. This paper proposes a technique based on using independent local maps. Every time a loop is detected, these local maps are corrected using the information from local maps that overlap with them. Meanwhile a global stochastic map is kept through loop detection and minimization as it is done in the classical Hierarchical SLAM approach. This global level contains the relative transformations between local maps, which are updated once a new loop is detected. In addition, the information within the local maps is also corrected, maintaining always each local map separately. This approach requires robust data association algorithms, for instance, an adapted version of the JCBB algorithm. Experimental results show that our approach is able to obtain large maps areas with high accuracy.

PloS one, 2018

This paper presents the concept of Simultaneous Localization and Multi-Mapping (SLAMM). It is a system that ensures continuous mapping and information preservation despite failures in tracking due to corrupted frames or sensor's malfunction; making it suitable for real-world applications. It works with single or multiple robots. In a single robot scenario the algorithm generates a new map at the time of tracking failure, and later it merges maps at the event of loop closure. Similarly, maps generated from multiple robots are merged without prior knowledge of their relative poses; which makes this algorithm flexible. The system works in real time at frame-rate speed. The proposed approach was tested on the KITTI and TUM RGB-D public datasets and it showed superior results compared to the state-of-the-arts in calibrated visual monocular keyframe-based SLAM. The mean tracking time is around 22 milliseconds. The initialization is twice as fast as it is in ORB-SLAM, and the retrieved...

Twitter @CulturalRoc Facebook. @rocchabas ACLARIMENT: Esta publicació està redactada en les Normes d'El Puig. Encara que és una obra colectiva, l'encarregat de la redacció final de cada artícul té llibertat per a fer-ho en la normativa d'accentuació de la seua preferència. Este tema és motiu de debat, pero no de divisió, entre nosatres.