Evaluating Multi-Agent Robotic Systems Using Ground Truth (bibtex)
by Freek Stulp, Suat Gedikli and Michael Beetz
Abstract:
A thorough empirical evaluation of multi-agent robotic systems is greatly facilitated if the \em true state of the world over time can be obtained. The accuracy of the beliefs as well as the overall performance can then be measured objectively and efficiently. In this paper we present a system for determining the \em ground truth state of the world, similar to the ceiling cameras used in RoboCup small-size league. We have used this ground truth data to evaluate the accuracy of the self- and object-localization of the robots in our RoboCup mid-size league team, the Agilo RoboCuppers. More complex models of the state estimation module have also been learned. These models provide insight into the workings and shortcomings of this module, and can be used to improve it.
Reference:
Freek Stulp, Suat Gedikli and Michael Beetz, "Evaluating Multi-Agent Robotic Systems Using Ground Truth", In Proceedings of the Workshop on Methods and Technology for Empirical Evaluation of Multi-agent Systems and Multi-robot Teams (MTEE), 2004.
Bibtex Entry:
@InProceedings{stulp04evaluating,
  author =       {Freek Stulp and Suat Gedikli and Michael Beetz},
  title =        {Evaluating Multi-Agent Robotic Systems Using Ground Truth},
  year =         {2004},
  booktitle =    {Proceedings of the Workshop on Methods and Technology for Empirical Evaluation of Multi-agent Systems and Multi-robot Teams (MTEE)},
  bib2html_pubtype  = {Refereed Conference Paper},
  bib2html_rescat   = {Perception, Models},
  bib2html_groups   = {AGILO},
  bib2html_funding  = {AGILO},
  bib2html_keywords = {},
  abstract          = {A thorough empirical evaluation of multi-agent robotic
  systems is greatly facilitated if the {\em true} state of the world over time
  can be obtained. The accuracy of the beliefs as well as the overall
  performance can then be measured objectively and efficiently. In this paper we
  present a system for determining the {\em ground truth} state of the world,
  similar to the ceiling cameras used in RoboCup small-size league. We have used
  this ground truth data to evaluate the accuracy of the self- and
  object-localization of the robots in our RoboCup mid-size league team, the
  Agilo RoboCuppers. More complex models of the state estimation module have
  also been learned. These models provide insight into the workings and
  shortcomings of this module, and can be used to improve it.}
}
Powered by bibtexbrowser