Many recent solutions to the RGB-D SLAM problem use the pose-graph optimization approach, which marginalizes out the actual depth measurements. In this paper we employ the same type of factor graph optimization, but we investigate the gains coming from maintaining a map of RGB-D point features and modeling the spatial uncertainty of these features. We demonstrate that RGB-D SLAM accuracy can be increased by employing uncertainty models reflecting the actual errors introduced by measurements and image processing. The new approach is validated in simulations and in experiments involving publicly available data sets to ensure that our results are verifiable.

 

 

References

 

  1. D. Belter, M. Nowicki, P. Skrzypczyński, Modeling spatial uncertainty of point features in feature-based RGB-D SLAM, Machine Vision and Applications, vol. 29(5), pp. 827-844, 2018 (pdf)
  2. Dominik Belter, Michał Nowicki, Piotr Skrzypczyński, Improving Accuracy of Feature-based RGB-D SLAM  by Modeling Spatial Uncertainty of Point Features, IEEE International Conference on Robotics and Automation, May 16-21, Stockholm, Sweden, pp. 1279-1284, 2016 (pdf)