Punishment policy adaptation in a road junction regulation system

Maite Lopez-Sanchez, Sanja Bauk, Natasa Kovac, Juan A. Rodriguez-Aguilar

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

This paper studies the problem of adapting punishment policies in traffic scenarios. It focuses on a two-road junction scenario simulated by means of Simma, a Multi-Agent Based Simulation Tool. Adaptation is based on an adaptive neuro-fuzzy inference system (ANFIS) together with a hybrid learning algorithm (HLA). Basic punishment policy is provided through a knowledge base that specifies the conditions that must hold in order to assign different punishments. The aim of this paper is to show how the ANFIS system can improve this policy unsupervisedly.

Original languageEnglish
Title of host publicationArtificial Intelligence Research and Development
PublisherIOS Press BV
Pages112-119
Number of pages8
ISBN (Print)9781586037987
Publication statusPublished - 2007
Externally publishedYes
Event10th International Conference of the Catalan Association for Artificial Intelligence, CCIA 2007 - Sant Julia de Loria, Andorra
Duration: 25 Oct 200726 Oct 2007

Publication series

NameFrontiers in Artificial Intelligence and Applications
Volume163
ISSN (Print)0922-6389
ISSN (Electronic)1879-8314

Conference

Conference10th International Conference of the Catalan Association for Artificial Intelligence, CCIA 2007
Country/TerritoryAndorra
CitySant Julia de Loria
Period25/10/0726/10/07

Keywords

  • ANFIS
  • Multi-Agent System
  • Policy adaptation
  • Traffic regulation

ASJC Scopus subject areas

  • Artificial Intelligence

Fingerprint

Dive into the research topics of 'Punishment policy adaptation in a road junction regulation system'. Together they form a unique fingerprint.

Cite this