Information Technology Reference
In-Depth Information
Don't Touch Me, I'm Fine:
Robot Autonomy Using an Artificial Innate
Immune System
Mark Neal
1
,JanFeyereisl
2
, Rosario Rascuna
3
, and Xiaolei Wang
4
1
Computer Science, University of Wales, Aberystwyth, UK
2
School of Computer Science, University of Nottingham, UK
3
CCNR, University of Sussex, UK
4
Electrical and Communications Engineering, Helsinki University
of Technology, Espoo, Finland
ARTIST Network: Student Spring School, Aberystwyth, UK
April 2006
Abstract.
A model for integration of low-level responses to damage,
potential damage and component failure in robots is presented. This
model draws on the notion of inflammation and introduces an exten-
sible, sub-symbolic mechanism for modulating high-level behaviour us-
ing the notion of artificial inflammation. Preliminary results obtained
via simulation are presented and demonstrate the potential benefits of
such a scheme. Additionally the system maps the robot's physiological
state-space, which is defined in terms of the levels and sources of inflam-
matory response. This is achieved using Kohonen's Self-Organizing Map
algorithm to arrange the states experienced during the lifetime of the
robot. The future use of this map for diagnosis and localization of faults
and for the generation of specific high-level remediation behaviour is also
discussed.
Keywords:
Artificial Immune Systems, Human Immune Systems, In-
nate Immunity, TLR, PAMPs, Inflammation, SOM, Robot.
1
Introduction
With a few rare exceptions such as [10,4], the innate immune system has been
neglected in artificial immune systems [3], especially in the field of robotics which
appears to have much to be gained from such an approach. The functions mak-
ing up this part of the immune system, offer a number of useful analogies that
can be exploited in a robotic system. In the quest for autonomy an artificial in-
nate immune system can be applied in order to create systems which are aware
of their own state. This could allow them to maintain a “healthy”, homeostatic
balance and achieve self suciency. In order to achieve this a robot must contain
a number of proprioceptive
1
sensors, monitoring various state measures across
1
proprioceptive: sensing internal body state.
