Perception
GTSAM (Georgia Tech Smoothing and Mapping) is a widely used C++ library for state estimation in robotics and computer vision. Instead of operating directly on sparse matrices, it models problems as factor graphs and Bayes networks, enabling efficient solutions to smoothing and mapping (SAM) tasks such as SLAM, visual odometry, sensor fusion and calibration.
The library provides a rich set of factors, variables and optimizers (including Levenberg-Marquardt nonlinear optimization and iSAM/iSAM2 for incremental estimation). It is developed by the BORG Lab at the Georgia Institute of Technology (Georgia Tech) and released under the BSD-3-Clause license.
GTSAM has Python wrappers and is used as the core optimization engine in many SLAM and navigation systems — for example, as a dependency of StrataSLAM.
Software that performs simultaneous localization and mapping (SLAM).
A compiled, high-performance, general-purpose programming language. The primary implementation language of the ONNX Runtime core.
A high-level interpreted language dominant in machine learning. ONNX Runtime provides an official Python API.
Permissive open-source license with three clauses.
No version history.
