Patrick F. Riley's Publications

Sorted by DateClassified by Publication TypeClassified by Research Category

On Behavior Classification in Adversarial Environments

Patrick Riley and Manuela Veloso. On Behavior Classification in Adversarial Environments. In Lynne E. Parker, George Bekey, and Jacob Barhen, editors, Distributed Autonomous Robotic Systems 4, pp. 371–380, Springer-Verlag, 2000.

Download

[PDF]165.7kB  [gzipped postscript]40.5kB  

Abstract

In order for robotic systems to be successful in domains with other agents possibly interfering with the accomplishing of goals, the agents must be able to adapt to the opponents' behavior. The more quickly the agents can respond to a new situation, the better they will perform. We present an approach to doing adaptation which relies on classification of the current adversary into predefined adversary classes. For feature extraction, we present a windowing technique to abstract useful but not overly complicated features. In order to take into account the spatial locality of topological differences, we use a previously developed similarity metric. The feature extraction and classification steps are fully implemented in the domain of simulated robotic soccer, and experimental results are presented.

BibTeX

@InCollection{DARS-AdvClass,
  author =	 {Patrick Riley and Manuela Veloso},
  title =	 {On Behavior Classification in Adversarial
                  Environments},
  booktitle =	 {Distributed Autonomous Robotic Systems 4},
  pages =	 {371--380},
  publisher =	 {Springer-Verlag},
  year =	 2000,
  editor =	 {Lynne E. Parker and George Bekey and Jacob Barhen},
  abstract =	 {In order for robotic systems to be successful in
                  domains with other agents possibly interfering with
                  the accomplishing of goals, the agents must be able
                  to adapt to the opponents' behavior. The more
                  quickly the agents can respond to a new situation,
                  the better they will perform. We present an approach
                  to doing adaptation which relies on classification
                  of the current adversary into predefined adversary
                  classes. For feature extraction, we present a
                  windowing technique to abstract useful but not
                  overly complicated features. In order to take into
                  account the spatial locality of topological
                  differences, we use a previously developed
                  similarity metric. The feature extraction and
                  classification steps are fully implemented in the
                  domain of simulated robotic soccer, and experimental
                  results are presented. },
  bib2html_pubtype = {Refereed Conference},
  bib2html_rescat = {Opponent and Teammate Modeling},
  bib2html_funding = {CoABS,ActiveTemplates},
}

Generated by bib2html.pl (written by Patrick Riley ) on Thu Mar 31, 2005 16:21:00