Spectral analysis for long-term robotic mapping

@article{Krajnk2014SpectralAF,
  title={Spectral analysis for long-term robotic mapping},
  author={Tom{\'a}{\vs} Krajn{\'i}k and Jaime Pulido Fentanes and Grzegorz Cielniak and Christian Dondrup and Tom Duckett},
  journal={2014 IEEE International Conference on Robotics and Automation (ICRA)},
  year={2014},
  pages={3706-3711}
}
This paper presents a new approach to mobile robot mapping in long-term scenarios. So far, the environment models used in mobile robotics have been tailored to capture static scenes and dealt with the environment changes by means of `memory decay'. While these models keep up with slowly changing environments, their utilization in dynamic, real world environments is difficult. The representation proposed in this paper models the environment's spatio-temporal dynamics by its frequency spectrum… CONTINUE READING

Similar Papers

Figures, Tables, Results, and Topics from this paper.

Key Quantitative Results

  • On average, the proposed model represented the environment state with 98% accuracy while stationary models achieved 95% accuracy.
  • Moreover, we demonstrate that the representation allows prediction of future states of the environment with accuracies ranging from 88% to 99%, which enables easy detection of unexpected (anomalous) environment states.

Citations

Publications citing this paper.
SHOWING 1-10 OF 42 CITATIONS

Persistent localization and life-long mapping in changing environments using the Frequency Map Enhancement

  • 2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
  • 2016
VIEW 5 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Spatio-temporal exploration strategies for long-term autonomy of mobile robots

  • Robotics and Autonomous Systems
  • 2017
VIEW 7 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

A Poisson-spectral model for modelling temporal patterns in human data observed by a robot

  • 2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
  • 2016
VIEW 5 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Lifelong Information-Driven Exploration to Complete and Refine 4-D Spatio-Temporal Maps

  • IEEE Robotics and Automation Letters
  • 2016
VIEW 4 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Life-long spatio-temporal exploration of dynamic environments

  • 2015 European Conference on Mobile Robots (ECMR)
  • 2015
VIEW 7 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Long-term topological localisation for service robots in dynamic environments using spectral maps

  • 2014 IEEE/RSJ International Conference on Intelligent Robots and Systems
  • 2014
VIEW 5 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

LONG–TERM AUTONOMY OF MOBILE ROBOTS IN CHANGING ENVIRONMENTS

VIEW 5 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

The When, Where, and How: An Adaptive Robotic Info-Terminal for Care Home Residents - A Long-Term Study

  • 2017 12th ACM/IEEE International Conference on Human-Robot Interaction (HRI
  • 2017
VIEW 2 EXCERPTS
CITES BACKGROUND
HIGHLY INFLUENCED

References

Publications referenced by this paper.
SHOWING 1-10 OF 21 REFERENCES

Conditional transition maps: Learning motion patterns in dynamic environments

  • 2013 IEEE/RSJ International Conference on Intelligent Robots and Systems
  • 2013
VIEW 1 EXCERPT

Visual Localization System for Mobile Robotics

T. Krajnı́k, M. Nitsche
  • International Conference on Advanced Robotics, 2013.
  • 2013
VIEW 1 EXCERPT

Towards lifelong visual maps

  • 2009 IEEE/RSJ International Conference on Intelligent Robots and Systems
  • 2009
VIEW 1 EXCERPT