RT-SLAM

RT-SLAM stands for Real Time SLAM (Simultaneous Localization And Mapping).

Disclaimer: RT-SLAM is currently in development and has no official release. It is provided as-is, there is no standalone installation, there is some code to adapt for your own use, and it is generally not advised (yet) to people who do not want to get their hands dirty.

Presentation

RT-SLAM is a fast Slam library and test framework based on EKF. Its main qualities are:

• genericity: for sensor models, landmark types, landmark models, landmarks reparametrization, biases estimation;

• speed: real time at 60 fps, VGA, gray level;

• flexibility: different estimation/image processing sequencing strategies (active search), independent base brick for a hierarchical multimap and multirobots architecture;

• robustness: near-optimal repartition of landmarks, data association errors detection (gating, ransac);

• developer-friendly: visualization tools (2D and 3D), offline replay step by step, logs, simulation.

For now it provides:

• Landmarks: Anchored Homogeneous Points (Inverse Depth) that can be reparametrized into Euclidean Points;

• Sensors: Pinhole cameras;

• Prediction: Constant velocity model;

• Data association: Active search, 1-point Ransac, and mixed strategies.

Documentation

• Installation guide

• User guide

• Developer guide

• Contact: jafar@laas.fr, cyril.roussillon@laas.fr

Screenshots and videos

• Demo 1 (v.a, 1'33, 23Mo): hand held alone camera at 60 fps indoor, with several loop closures.

• Demo 2 (v.a, 1'06, 20Mo): hand held IMU+camera at 50 fps indoor, with very high dynamic.

Roadmap

• Stabilize and make a release
• Inertial Slam
• Odometry Slam
• Multimap Slam
• Segments Slam

Authors

• Joan Solà

• Cyril Roussillon

• Aurélien Gonzalez

• Nicolas Mansard

• Jean-Marie Codol