Intelligent automated control of advanced life support systems
Project goals
Effective automatic control of Advance Life Support Systems (ALSS)
which manage the resources of planetary and space habitats
is a crucial component of space exploration.
An ALSS is a coupled dynamical system which can be
extremely sensitive and difficult to predict.
We are interested in studying the use of machine learning methods
such as the genetic algorithm (GA) on the problem of learning
how to control an ALSS.
We have implemented an ALSS simulator that models the basic processes
occurring in the Bioregenerative Planetary Life Support System Test
Complex (BIO-Plex) developed by NASA Johnson Space Center.
We use this simulation to explore the effectiveness of GA approaches
to learning effective ALSS control strategies for multiple
optimization problems.
Approach
Our studies focus on the effectiveness of the
proportional GA (PGA)
applied to ALSS control.
Publications
Annie S. Wu and Ivan I. Garibay (2004)
Intelligent automated control of life support systems using
proportional representations.
IEEE Transactions on Systems, Man, and Cybernetics, Part B,
pp. 1423-1434, June 2004.
[Info]
