GTSAM 4.1 is a BSD-licensed C++ library that implements sensor fusion for robotics and computer vision applications, including SLAM (Simultaneous Localization and Mapping), VO (Visual Odometry), and SFM (Structure from Motion). It uses factor graphs and Bayes networks as the underlying computing paradigm rather than sparse matrices to optimize for the most probable configuration or an optimal plan. Coupled with a capable sensor front-end (not provided here), GTSAM powers many impressive autonomous systems, in both academia and industry.
Recent Tweets
Posts
LOST in Triangulation
Reducing the uncertainty about the uncertainties, part 3: Adjoints and covariances
Reducing the uncertainty about the uncertainties, part 2: Frames and manifolds
Reducing the uncertainty about the uncertainties, part 1: Linear and nonlinear
Mount Rainier's Eigenvectors
Frank Dellaert, August 30, 2020
Releasing GTSAM 4.0.3
Author: Fan Jiang
Geometry and Variable Naming Conventions
Author: Samarth Brahmbhatt
What are Factor Graphs?
By Frank Dellaert, @fdellaert on Twitter
LQR Control Using Factor Graphs
Look Ma, No RANSAC
Author: Varun Agrawal
Website: varunagrawal.github.ioLegged Robot Factors Part I
Author: Ross Hartley
email: m.ross.hartley@gmail.comLaunching gtsam.org
Today we launched GTSAM’s new web presence, gtsam.org. The site is hosted by Github Pages, and is generated via Jekyll, a simple static website generator.
Moving to Github!
GTSAM is now live on Github. Github is doing so many things right, in addition to being the go-to platform for open source: it has free continuous integration for open source projects, it supports building great web-sites, and it is itself supporting many great efforts such as VS-code and Atom. While we initially launched GTSAM on Bitbucket because of its unlimited private repos, we felt we could hold out no longer. Github, here we come :-)
subscribe via RSS