borglab/gtsam

GTSAM is a library of C++ classes that implement smoothing and mapping (SAM) in robotics and vision, using factor graphs and Bayes networks as the underlying computing paradigm rather than sparse matrices.

What it solves

It provides a way to perform smoothing and mapping (SAM) for robotics and vision. Instead of relying on traditional sparse matrices, it uses a more flexible computing paradigm to handle the complex optimization problems associated with robot localization and mapping.

How it works

GTSAM implements these solutions using Factor Graphs and Bayes Networks. It optimizes states by building a factor graph, linearizing and solving in tangent spaces, retracting the results back to manifolds, and iterating until the system converges.

Who it’s for

It is designed for researchers and engineers working in robotics and computer vision who need to estimate the state of a system (like a robot's position and orientation) over time.

Highlights

  • Support for C++, Python, and MATLAB wrappers.
  • Specialized handling for IMU data via a state-of-the-art preintegration scheme on manifolds.
  • Support for automatic differentiation through GTSAM Expressions.
  • Ability to optimize using non-GTSAM types via C++ traits.

Related

  • Project
    RainerKuemmerle/g2o

    A C++ framework for optimizing graph-based nonlinear error functions, commonly used for SLAM and Bundle Adjustment in robotics and computer vision.

  • Project
    symforce-org/symforce

    A symbolic computation and code generation library for robotics that transforms mathematical expressions into optimized C++ code for tasks like SLAM and motion planning.

  • Project
    koide3/gtsam_points

    A collection of GTSAM factors and optimizers specifically designed for range-based SLAM and 3D point cloud registration.

  • Project
    MOLAorg/mola

    A modular C++ and ROS 2 framework for robotics localization and SLAM, enabling configurable pipelines for LiDAR odometry and high-precision mapping.

  • Project
    introlab/rtabmap

    RTAB-Map is a SLAM (Simultaneous Localization and Mapping) library and standalone application that enables robots to map unknown environments and track their position.