RoboCup Rescue


The assignment for the RoboCup Rescue Simulation League is to build an Multi-Agent Community for Rescue Operations in Simulated Systems. The University of Amsterdam has participated in the 2003 competition, both in Germany and Italy, and participate remotely in the Rescue Middle Earth competition 2004.

Specific for our approach is all agents have a nearly equivalent WorldModel. A communication protocol is designed that allows to synchronised the WorldModel between all agents via the centers on a regular basis (every 4 cycles). The agents do not have to base their decisions on their own possible actions, but can also take into account the possible actions of their teammates. This makes it possible to adapt a GameTree approach.

This research leaded to the following publications:

  • S.B.M. Post, M.L. Fassaert, A. Visser "The high-level communication model for multiagent coordination in the RoboCupRescue Simulator", in D. Polani, B. Browning, A. Bonarini, K. Yoshida (Eds.), RoboCup 2003, Lecture Notes on Artificial Intelligence, Springer Verlag, Berlin. (Portable Document Format 143 Kb)
  • M.L. Fassaert, S.B.M. Post, A. Visser "The common knowledge model of a team of rescue agents", 1th International Workshop on Synthetic Simulation and Robotics to Mitigate Earthquake Disaster, Padova, Italy, 6 July 2003. (Portable Document Format 251 Kb)

And the following thesis:

  • A. Abbo, S. Peelen, 'Progressive Deepening for GameTrees: An application for RoboRescue', June 2004, Bsc-thesis University of Amsterdam (255 Kb)
  • S.B.M. Post, M.L. Fassaert, 'A communication and coordination model for `RoboCupRescue' agents', June 2004, Msc-thesis University of Amsterdam


Documents for the Qualification
  • @ Most recent Team Description (8 pages version, Springer LNAI format)
  • @ Our Logfile for the classification for Rescue Middle Earth.
  • @ Our Logfile for the classification.
  • @ Our original Logfile for that game.