Incremental Knowledge Acquisition Using Generalised RDR for Soccer Simulation

  • Angela Finlayson
  • Paul Compton
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6232)

Abstract

This paper describes a system that allows soccer coaches to specify the behaviour of agents for the Robocup 2D soccer simulation domain [1]. The work we present is based on Generalised Ripple Down Rules [7,2]and allows the coach to interact directly with the system to incrementally model behaviours along with intermediate features during the knowledge acquisition process. The system was evaluated over a period of 6 months to measure the level of performance of the multi-agent teams created with the system and to gather feedback about the usability of the system. During this period the system was successfully used by four soccer coaches with differing levels of soccer and computer expertise. All coaches were able to use the system to develop teams that could play at a world class level against the finalists from the Robocup 2007 2D simulation tournament. The approach we present is general enough to be applied to any complex planning problem, with the requirement that a rich feature language is developed to support the specific domain.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Copyright information

© Springer-Verlag Berlin Heidelberg 2010

Authors and Affiliations

  • Angela Finlayson
    • 1
  • Paul Compton
    • 1
  1. 1.Department of Artificial Intelligence, School of Computer Science and EngineeringThe University of New South WalesSydneyAustralia

Personalised recommendations