Computational Intelligence - November 2013 - 10

Guest
Editorial

Yang Gao
University of Surrey, United Kingdom
Nicola Policella
eSoC-eSA, germAny
Frank Kirchner
dFKi, germAny

Computational Intelligence
for Space Systems and Operations

C

urrent and future space missions
require an increasing level of
autonomy or intelligence distributed across the space systems that have
computing capabilities to implement
intelligent functionalities for decision
making. Such computational intelligence
(CI) allows spacecraft (vehicles and
robots alike) to respond rapidly to
opportunistic events in deep space when
remote operations are not practical due
to communication latency, or to enable
ground operators to optimize complex
mission (e.g. involving multiple spacecraft) planning and scheduling processes,
and so on. Typical CI approaches that
can be used to improve spacecraft autonomy include mathematical, probabilistic
and statistical modeling, control, automation and optimization, safety and reliability, system identification, monitoring and
fault detection, etc. There are therefore
strong motivations to develop these
expertise areas for answering to the
research challenges posed by astronautics
and space engineering.
The ECSS1 has defined four level of
autonomy for a space system, ranging
from direct operator control of all
actions to the system's control of decision-making and action with only subsequent human intervention (see detailed
definition in Table 1). Although space
system autonomy is often assimilated to
1
The European Committee for Space Standardization
(ECSS) was created in 1993 as the European organization responsible for the creation and publishing of
standards for space projects. See http://ecss.nl/.

Digital Object Identifier 10.1109/MCI.2013.2279557
Date of publication: 16 October 2013

10

The IEEE Task Force on Intelligent Space Systems and
Operations aims to identify design requirements and
drivers of CI approaches for space, and drive in particular
original and theoretical research in CI for space systems/
operations where reliability and robustness are key.
its space (or on-board) segment, the ground
segment can play a crucial role as well. If
performance of a space system need to
be assessed, it is necessary to conceive the
system as a whole and consider implications for the ground segment when the
level of autonomy at the space segment
is increased. In addition, a sufficient level
of autonomy within the ground segment
is often required by the operations of
autonomous spacecraft.
In the past two decades, major space
agencies have undertaken development in
intelligent software employing CI techniques that can demonstrate high autonomy level (i.e. E4 according to the ECSS
standard). For example, NASA 2 has
designed goal-oriented planners such as
EUROPA, ASPEN and CASPER, which
subsequently led to real mission operation
software RAX and ASE, etc. More recent
research endeavor is to extend and apply
these designs to address more complex
space systems involving multiple spacecraft, such as the MISUS project for
multi-rovers. ESA3 has also funded development of the planning software framework APSI, and design studies GOAC
and IRONCAP built on APSI framework for future planetary rover missions.
2
3

www.nasa.gov
www.esa.int

IEEE ComputatIonal IntEllIgEnCE magazInE | novEmbEr 2013

Major research activities have also been
carried out by space industries, research
institutes and universities all over the
world. Taking Mars exploration missions
as an example, the increase in autonomy
level of the rover systems (from Sojourner
of NASA in 1997 to future ESA
ExoMars and sample fetch rovers) has
noticeably improved rover traverse rate
per sol as illustrated in Figure 1.
The IEEE Task Force on Intelligent
Space Systems and Operations4 was set
up within the IEEE Computational
Intelligence Society to promote the
research, development, education and
understanding of applications of computational intelligence in space systems and
operations. The major goals include
establishing more clear definitions of the
emerging field, identifying design
requirements and dr iver s of CI
approaches for space, and driving in particular original and theoretical research
in CI for space systems where reliability
and robustness are key. This special issue
aims to present latest research work from
the scientific community that tackle
space engineering problems using CI
techniques. The three articles selected
from twenty submissions cover a good
range of applications on Mars sample
4

http://www.surrey.ac.uk/ssc/activity/ieee_isso/index.htm

1556-603x/13/$31.00©2013IEEE
http://www.ecss.nl/ http://www.nasa.gov http://www.esa.int
Table of Contents for the Digital Edition of Computational Intelligence - November 2013
