Real time data association for FastSLAM.

J. Nieto, J. Guivant, E. Nebot, and S. Thrun.

The ability to simultaneously localise a robot and accurately map its surroundings is considered by many to be a key prerequisite of truly autonomous robots. This paper presents a real-world implementation of FastSLAM, an algorithm that recursively estimates the full posterior distribution of both robot pose and landmark locations. In particular, we present an extension to FastSLAM that addresses the data association problem using a nearest neighbour technique. Building on this, we also present a novel multiple hypothesis tracking implementation (MHT) to handle uncertainty in the data association. Finally an extension to the multi-robot case is introduced. Our algorithm has been run successfully using a number of data sets obtained in outdoor environments. Experimental results are presented that demonstrate the performance of the algorithms when compared with standard Kalman Filter-based approaches.

The full paper is available in PDF and gzipped Postscript

@INPROCEEDINGS{Nieto02b,
  AUTHOR	= {J. Nieto and J. Guivant and E. Nebot and S. Thrun},
  TITLE		= {Real Time Data Association for {FastSLAM}},
  YEAR		= {2003},
  BOOKTITLE      = {Proceedings of the IEEE International Conference on Robotics and Automation (ICRA)},
  ADDDRESS      = {Taipei, Taiwan}
}