Maplab: An Open Framework for Research in Visual-Inertial Mapping and Localization

By Thomas Schneider, Marcin Dymczyk, Marius Fehr, Kevin Egger, Simon Lynen, Igor Gilitschenski, Roland Yves Siegwart. 2017

284 citations recorded by the source corpus.

Robust and accurate visual-inertial estimation is crucial to many of today's challenges in robotics. Being able to localize against a prior map and obtain accurate and drift-free pose estimates can push the applicability of such systems even further. Most of the currently available solutions, however, either focus on a single session use case, lack localization capabilities, or do not provide an end-to-end pipeline. We believe that only a complete system, combining state-of-the-art algorithms, scalable multisession mapping tools, and a flexible user interface, can become an efficient research platform. We, therefore, present maplab, an open, research-oriented visual-inertial mapping framework for processing and manipulating multisession maps, written in C++. On the one hand, maplab can be seen as a ready-to-use visual-inertial mapping and localization system. On the other hand, maplab provides the research community with a collection of multisession mapping tools that include map merging, visual-inertial batch optimization, and loop closure. Furthermore, it includes an online frontend that can create visual-inertial maps and also track a global drift-free pose within a localization map. In this letter, we present the system architecture, five use cases, and evaluations of the system on public datasets. The source code of maplab is freely available for the benefit of the robotics research community.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Aerospace Engineering

In Computer Vision and Pattern Recognition

Citations in the corpus

Visual-Inertial Navigation: A Concise Review (2019, background): “In particular, whether or not performing loop closures in VINS either via mapping [83, 101, 102] and/or place recognition [103–108] is one of the key differences between VIO and SLAM.”
Kimera: an Open-Source Library for Real-Time Metric-Semantic Localization and Mapping (2019, methodology): “Voxblox++ [14] relies on RGB-D sensing, wheel odometry, and pre-built maps using maplab [26] to obtain visual-inertial pose estimates.”
OpenVINS: A Research Platform for Visual-Inertial Estimation (2020, methodology): “ROVIO [6] – We use the ROVIO implementation within maplab [43], which is a monocular iterative EKF-based approach that performs minimization on the direct image intensity patches allowing for tracking of non-corner features such as high gradient lines.”
A Survey on Aerial Swarm Robotics (2018, background): “State-ofthe-art visual-inertial SLAM frameworks are often able to process multi-session maps [193], [194], making them ideal for merging maps acquired by multiple robots into globally consistent representations.”
LDSO: Direct Sparse Odometry with Loop Closure (2018, methodology): “Later, a similar visual-inertial weighted least-squares optimization strategy was adapted in maplab [10] for batch map optimization without marginalization, but as a camera tracking frontend, a Kalman Filter based estimator minimizing the photometric error between tracked image patches is used.”
Visual-Inertial Teach and Repeat for Aerial Inspection (2018, background): “maplab [7], ORB-SLAM2 [8], OKVIS [9], ROVIO [10] and”