|
Size: 1446
Comment: presentation
|
Size: 2884
Comment:
|
| Deletions are marked like this. | Additions are marked like this. |
| Line 5: | Line 5: |
| <!> '''Disclaimer:''' RT-SLAM is still in development and has no official release. It is provided as-is, there is no standalone installation. | |
| Line 6: | Line 7: |
| <!> '''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 to people who do not want to get their hands dirty. | |
| Line 11: | Line 11: |
| * '''genericity''': sensor models, landmark types, landmark models, reparametrization from one landmark model to another one, estimating biases; * '''speed''': real time at 60 fps, VGA, gray level; * '''flexibility''': different estimation/image processing sequencing (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. |
* '''genericity''': for sensor models, landmark types, landmark models, landmarks reparametrization, biases estimation; * '''speed''': real time at 60 fps (VGA, gray level) on a decent machine (at least one Core2 core at 2.2GHz) * '''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. |
| Line 17: | Line 17: |
| For now it provides: * '''Landmarks''': Anchored Homogeneous Points (Inverse Depth) that can be reparametrized into Euclidean Points; * '''Sensors''': Pinhole cameras; * '''Prediction''': Constant velocity model, inertial sensor; * '''Data association''': Active search, 1-point Ransac, and mixed strategies. |
|
| Line 22: | Line 26: |
| * [[rtslam/Installation|Installation procedure]] | * [[rtslam/Installation|Installation guide]] |
| Line 24: | Line 28: |
| * [[http://homepages.laas.fr/croussil/doc/jafar/group__rtslam.html|Developer reference]] | * [[http://homepages.laas.fr/croussil/doc/jafar/group__rtslam.html|Developer guide]] * Contact: jafar@laas.fr, cyril.roussillon@laas.fr |
| Line 29: | Line 33: |
| ||<tablestyle="width:100%;text-align:center;" style="border:0px"> {{attachment:rtslam3D.png|3D view|width=400px}}||<style="border:0px"> {{attachment:rtslam2D.png|2D view|width=400px}} || | |
| Line 30: | Line 35: |
| * [[http://homepages.laas.fr/croussil/videos/2010-11-29_rtslam_grande-salle_q25.avi|Demo 1]] (v.a, 1'33, 23Mo, H264 AVI): hand held alone camera at 60 fps indoor, with several loop closures. * [[http://homepages.laas.fr/croussil/videos/2011-02-15_rtslam-inertial-high-dyn.avi|Demo 2]] (v.b, 1'06, 20Mo, H264 AVI): hand held IMU+camera at 50 fps indoor, with very high dynamic. * [[http://homepages.laas.fr/croussil/videos/2011-06-09_rtslam-inertial-robot-grass.avi|Demo 3]] (v.a, 1'25, 27Mo, H264 AVI): IMU+camera on a rover robot on grass, with short term memory (lost landmarks are removed, no loop closure) * [[/Material|Additional videos referenced in papers]] |
|
| Line 34: | Line 43: |
| * Inertial and Odometry Slam | * Inertial Slam * Odometry Slam |
| Line 36: | Line 46: |
| * Segment Slam | * Segments Slam == Authors == * [[http://homepages.laas.fr/jsola|Joan Solà]] * [[http://homepages.laas.fr/croussil|Cyril Roussillon]] * [[http://homepages.laas.fr/agonzale|Aurélien Gonzalez]] * [[http://homepages.laas.fr/nmansard|Nicolas Mansard]] * [[http://homepages.laas.fr/jmcodol|Jean-Marie Codol]] |
RT-SLAM
RT-SLAM stands for Real Time SLAM (Simultaneous Localization And Mapping).
Disclaimer: RT-SLAM is still in development and has no official release. It is provided as-is, there is no standalone installation.
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) on a decent machine (at least one Core2 core at 2.2GHz)
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, inertial sensor;
Data association: Active search, 1-point Ransac, and mixed strategies.
Documentation
Screenshots and videos
|
|
Demo 1 (v.a, 1'33, 23Mo, H264 AVI): hand held alone camera at 60 fps indoor, with several loop closures.
Demo 2 (v.b, 1'06, 20Mo, H264 AVI): hand held IMU+camera at 50 fps indoor, with very high dynamic.
Demo 3 (v.a, 1'25, 27Mo, H264 AVI): IMU+camera on a rover robot on grass, with short term memory (lost landmarks are removed, no loop closure)
Roadmap
- Stabilize and make a release
- Inertial Slam
- Odometry Slam
- Multimap Slam
- Segments Slam