Share Email Print

Proceedings Paper

Probabilistic tracking and real-time assessment of physical systems
Author(s): R. Wade Brittain; Bruce D'Ambrosio
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

In order for long-range autonomous robots to be successful, they must be able to maintain accurate information about their location, available resources, and the state of critical components. We propose here a methodology that incorporates traditional, sensor-based tracking methods with discrete probabilistic representations of system state. Further, we extend the use of the Gaussian distribution to include a richer set of mathematical descriptions of system performance under specific failure conditions. The extended representations are then used to statistically test for these failure conditions by predicting the most likely values for observable parameters given the system state. This technique is then combined with first-order extended Kalman filtering to yield a probabilistic framework for tracking and fault detection in domains with nonlinear dynamics.

Paper Details

Date Published: 1 March 1994
PDF: 17 pages
Proc. SPIE 2244, Knowledge-Based Artificial Intelligence Systems in Aerospace and Industry, (1 March 1994); doi: 10.1117/12.169409
Show Author Affiliations
R. Wade Brittain, Oregon State Univ. (United States)
Bruce D'Ambrosio, Oregon State Univ. (United States)

Published in SPIE Proceedings Vol. 2244:
Knowledge-Based Artificial Intelligence Systems in Aerospace and Industry
Wray Buntine; Doug H. Fisher, Editor(s)

© SPIE. Terms of Use
Back to Top