Initialization Techniques for 3D SLAM: a Survey on Rotation Estimation and its Use in Pose Graph Optimization

 

L. Carlone, R. Tron, K. Daniilidis, and F. Dellaert, "Initialization Techniques for 3D SLAM: a Survey on Rotation Estimation and its Use in Pose Graph Optimization", ICRA, 2015.

 

mole2D

 

AbstractPose graph optimization is the non-convex optimization problem underlying pose-based Simultaneous Localization and Mapping (SLAM). If robot orientations were known, pose graph optimization would be a linear least- squares problem, whose solution can be computed efficiently and reliably. Since rotations are the actual reason why SLAM is a difficult problem, in this work we survey techniques for 3D rotation estimation. Rotation estimation has a rich history in three scientific communities: robotics, computer vision, and control theory. We review relevant contributions across these communities, assess their practical use in the SLAM domain, and benchmark their performance on representative SLAM problems. We show that the use of rotation estimation to bootstrap iterative pose graph solvers entails significant boost in convergence speed and robustness. 

 

 

 

 

  

Supplementary material

  • Extra results and visualizations
  • Datasets:
    • click on the figure below to download the corresponding dataset file in g2o format

 

 

                   Sphere-a

      sphere-a      

     

                           Torus

        torus  

  

 

     

                            Cube

        cube        

 

                  Garage

                         Cubicle 

 

                           Rim