A qualitative spatio-temporal abstraction of a disaster space

  • Authors:
  • Zina M. Ibrahim;Ahmed Y. Tawfik

  • Affiliations:
  • School of Computer Science, University of Windsor, Ontario, Canada;School of Computer Science, University of Windsor, Ontario, Canada

  • Venue:
  • SARA'05 Proceedings of the 6th international conference on Abstraction, Reformulation and Approximation
  • Year:
  • 2005

Quantified Score

Hi-index 0.00

Visualization

Abstract

This paper presents an abstraction of a vague and rapidly-changing environment, an urban disaster space, and a reasoning engine which recognizes and describes the motion of rescue agents as they traverse the disaster space. More specifically, we present a qualitative abstraction of the Robocup Rescue simulation environment, and implement a commentator engine, which constructs a qualitative representation of the changes in the environment and produces descriptions of the agents' motion by recognizing patterns which motion can take. The patterns recognized are elements of a set of formalizations that qualify each type of motion pattern based on a qualitative representation of vague spatiotemporal moving objects. We also present a set of performance metrics to evaluate our qualitative representation.