State of the Art SLAM techniques

Best Stereo SLAMs in 2017 are reviewed.

Namely, (in arbitrary order)

• EKF-SLAM based, 
• Keyframe based, 
• Joint BA optimization based, 
• RSLAM, 
• S-PTAM, 
• LSD-SLAM,  

Best RGB-D SLAMs in 2017 are also reviewed.

• KinectFusion, 
• Kintinuouns, 
• DVO-SLAM, 
• ElasticFusion, 
• RGB-D SLAM,  

See my keypoints of the best Stereo SLAMs.


Stereo SLAM

Conditionally Independent Divide and Conquer EKF-SLAM [5] 

• operate in large environments than other approaches at that time
• uses both  close and far points
• far points whose depth cannot be reliably estimated due to little disparity in the stereo camera 
• uses an inverse depth parametrization [6]
• shows empirically points can be triangulated reliably, if their depth is less than about 40 times the stereo baseline.

   

- Keyframe-based  Stereo SLAM

  - uses BA optimization in a local area to archive scalability.

  - [8]: joint optimization of BA (point-pose constraints) in a inner window

     -  pose-graph (pose-pose constraints) in an outer window of keyframes

     - achieves the constant time complexity by limiting the size of these windows

     - at the expense of not guaranteeing global consistency.

  - [9]: RSLAM uses a relative representation of landmarks and poses

    - performs relative BA in an active area, constrained by constant-time

    - able to close loops

    - allows to expand active areas at both sides of a loop

    - not enforcing global consistency

  - [10]:S-PTAM 

    - performs local BA

    - lacks large loop closing

 - [11]: LSD-SLAM

   - a semi-dense direct approach

   - minimizes photometric error in image regions with high gradient.

   - More robust than feature-based to 

     -  motion blur

     - low textured environments

   - severely degraded performance by unmodeled effects

     - rolling shutter

     - non-lambertian reflectance.

RGB-D SLAM

- KinectFusion [4]

   - fused all depth data from the sensor into a volumetric dense model

   - uses ICP with the model to track the camera pose.

   - limited to small workspace due to volumetric representation

   - lack of loop closing

- Kintinuous [12]:

  - operate in large environments

  - uses a rolling cyclical buffer

  - does loop closing with place recognition and pose graph optimization

- RGB-D SLAM [13]:

  - feature-based system

  - front-end computes frame-to-frame motion by feature matching and ICP.

  - back-end performs pose-graph optimization with loop closure constraints from a heuristic search.

- DVO-SLAM [14]:

  - optimizes a pose-graph

  - computes keyframe-to-keyframe constraints from a visual odometry

  - a visual odometry minimizes both photometric and depth error.

  - searches for loop candidates in a heuristic manner over all previous frames

  - not relying on place recognition.

- ElasticFusion [15]:

  - builds a surfel-based map of the environment.

  - a map-centric approach that doe do poses

  - performs loop closing with a non-rigid deformation to the map

  - not using the standard pose-graph optimization

  - impressive detail reconstruction

  - impressive localization accuracy

  - implementation limited to a room-size map due to the complexity scales with the number of surfels in the map.

Reference
[5] L. M. Paz, P. Pinie ́s, J. D. Tardo ́s, and J. Neira, “Large-scale 6-DOF SLAM with stereo-in-hand,” IEEE Trans. Robot., vol. 24, no. 5, pp. 946–957, 2008.


[6] J. Civera, A. J. Davison, and J. M. M. Montiel, “Inverse depth parametrization for monocular SLAM,” IEEE Trans. Robot., vol. 24, no. 5, pp. 932–945, 2008.


[7] H. Strasdat, J. M. M. Montiel, and A. J. Davison, “Visual SLAM: Why filter?” Image and Vision Computing, vol. 30, no. 2, pp. 65–77, 2012.


[8] H. Strasdat, A. J. Davison, J. M. M. Montiel, and K. Konolige, “Double window optimisation for constant time visual SLAM,” in IEEE Int. Conf. Comput. Vision (ICCV), 2011, pp. 2352–2359.


[9] C. Mei, G. Sibley, M. Cummins, P. Newman, and I. Reid, “RSLAM: A system for large-scale mapping in constant-time using stereo,” Int. J. Comput. Vision, vol. 94, no. 2, pp. 198–214, 2011.


[10] T. Pire, T. Fischer, J. Civera, P. De Cristo ́foris, and J. J. Berlles, “Stereo parallel tracking and mapping for robot localization,” in IEEE/RSJ Int. Conf. Intell. Robots and Syst. (IROS), 2015, pp. 1373–1378.


[11] J. Engel, J. Stueckler, and D. Cremers, “Large-scale direct SLAM with stereo cameras,” in IEEE/RSJ Int. Conf. Intell. Robots and Syst. (IROS), 2015.


[12] T. Whelan, M. Kaess, H. Johannsson, M. Fallon, J. J. Leonard, and J. McDonald, “Real-time large-scale dense RGB-D SLAM with volu- metric fusion,” Int. J. Robot. Res., vol. 34, no. 4-5, pp. 598–626, 2015.

[13] F.Endres,J.Hess,J.Sturm,D.Cremers,andW.Burgard,“3-Dmapping with an RGB-D camera,” IEEE Trans. Robot., vol. 30, no. 1, pp. 177– 187, 2014.

[14] C. Kerl, J. Sturm, and D. Cremers, “Dense visual SLAM for RGB-D cameras,” in IEEE/RSJ Int. Conf. Intell. Robots and Syst. (IROS), 2013. [15] T. Whelan, R. F. Salas-Moreno, B. Glocker, A. J. Davison, and S. Leutenegger, “ElasticFusion: Real-time dense SLAM and light source

estimation,” Int. J. Robot. Res., vol. 35, no. 14, pp. 1697–1716, 2016.