A software framework for multi player robot games

  • Authors:
  • Søren Tranberg Hansen;Santiago Ontañón

  • Affiliations:
  • Danish Technological Institute, Center For Robot Technology, Odense M, Denmark;Artificial Intelligence Research Institute, Spanish Council for Scientific Research, Bellaterra, Spain

  • Venue:
  • ICSR'10 Proceedings of the Second international conference on Social robotics
  • Year:
  • 2010

Quantified Score

Hi-index 0.00

Visualization

Abstract

Robot games have been proposed as a way to motivate people to do physical exercises while playing. Although this area is very new, both commercial and scientific robot games have been developed mainly based on interaction with a single user and a robot. The goal of this paper is to describe a generic software framework which can be used to create games where multiple players can play against a mobile robot. The paper shows how an adaptive AI system (D2) developed for real-time strategy (RTS) computer games can be successfully applied in a robotics context using the robotics control framework Player/Stage. D2 is based on Case-Based Planning which learns from demonstration. Using the proposed framework, the paper shows how a robot learns a strategy for an implementation of a simple game.