Q2 Symbolic Reasoning about Noisy Dynamic Systems

  • Authors:

  • Stephen P. Linder;Zbigniew Korona;Mieczyslaw M. Kokar

  • Affiliations:

  • Mechanical, Industrial and Manufacturing Engineering, ‘/Northeastern University, Boston, MA 02115, USA;Mechanical, Industrial and Manufacturing Engineering, ‘/Northeastern University, Boston, MA 02115, USA/ e-mail: zbigniew@coe.neu.edu;Electrical and Computer Engineering, Northeastern University, Boston, MA 02115, USA/ e-mail: kokar@coe.neu.edu

  • Venue:
  • Journal of Intelligent and Robotic Systems
  • Year:
  • 1999

Quantified Score

Hi-index 0.00

Visualization

Abstract

Symbolic reasoning about continuous dynamic systems requires consistent qualitative abstraction functions and aconsistent symbolic model. Classically, symbolic reasoning systems have utilized a box partition of the system spaceto achieve qualitative abstraction, but boxes can not provide a consistent abstraction. Our Q2 methodologyabstracts a provably consistent symbolic representation of noise-free general dynamic systems. However, the Q2symbolic representation has not been previously evaluated for efficacy in the presence of noise. We evaluate the effects ofnoise on Q2 symbolic reasoning in the domain of maneuver detection. We demonstrate how the Q2 methodology derives a symbolic abstraction of a general dynamic system model used in evaluating maneuverdetectors. Simulation results represented by ROC curves show that the Q2 based maneuver detector is superiorto a box-based detector. While no method is consistent in the presence of noise, the Q2 methodology is superiorto the classic box’s approach for deriving qualitative decisions about noisy dynamic systems.