Graph-SLAM maps

1. Text .graph file format

This file format was (to the best of my knowledge) first used in public software with TORO, and since then has been employed by other libraries and programs published in OpenSLAM.org.

Graphs in both 2D (x,y,phi) or 3D (x,y,z,yaw,pitch,roll) are supported. Files consist of plain text which is interpreted line by line. The first word in each line determines the type of that entry.
The following entry types exist:

• VERTEX2: A 2D node

  VERTEX2 id x y phi

  id is a unique identifier for each node. phi is in radians.

• VERTEX3: A 3D node

  VERTEX3 id x y z roll pitch yaw

  id is a unique identifier for each node. yaw,pitch and roll are in radians.

• EDGE2: A 2D pose constraint

  EDGE2 from_id to_id Ax Ay Aphi inf_xx inf_xy inf_yy inf_pp inf_xp inf_yp

• EDGE3: A 3D pose constraint

  EDGE3 from_id to_id Ax Ay Az Aroll Apitch Ayaw inf_11 inf_12 .. inf_16 inf_22 .. inf_66

• EQUIV: A “topological loop closure”, forcing two nodes to actually become the same. 

  EQUIV id1 id2

• FIX: Defines “fixed” keyframes, that works as “anchors” to help the optimization problem to have one single solution. Fixes poses do not change during optimization.

  FIX id1

2. Binary .graphbin file format

This format may be used if I/O disk performance is an issue. It consists of direct binary serializations of the corresponding objects, that is:

// Write:
CNetworkOfPoses2D  graph;
CFileGZOutputStream("my_graph.graphbin") << graph;

// Read:
CNetworkOfPoses2D graph;
CFileGZInputStream("my_graph.graphbin") >> graph;

3. Related C++ code

• The application graph-slam.
• The example graph_slam_demo
• A generic template class (mrpt::graphs::CNetworkOfPoses<>) provides loading/saving functionality for graphs in both text and binary formats as described above. Typedefs exists for the most common cases of 2D and 3D graphs with information matrices: mrpt::graphs::CNetworkOfPoses2DInf and mrpt::graphs::CNetworkOfPoses3DInf

Libraries:

•  mrpt-graphs contains abstract graph datatypes.
•  mrpt-graphslam contains graph-slam algorithms (Levenberg-Marquardt graph of constrainst optimization, etc.).

4. Example graph maps

The following graph-SLAM maps have been rendered with the C++ classes mentioned above, and the .graph files are those published wih TORO on OpenSLAM.org:

This view shows how the graph-slam program (by means functions in the namespace mrpt::opengl::graph_tools ) can show the mismatches between the pose of nodes and the constraints in the edges: