provide a theoretical foundation for
the field.
Morphological computation. As
noted earlier, evolutionary robotics
builds on the concept of embodied
cognition, which holds that intelligent behavior arises out of interactions between brain, body, and environment. 27 An important corollary
of embodied cognition is that, given
the right body plan, a robot (or animal) can achieve a given task with
less control complexity than another robot with an inappropriate
body plan. For example, a soft robot hand can grip a complex object
simply by enclosing it: the inner
surface of the hand passively conforms to the object. A robot hand
composed of hard material must
carefully compute how to grasp the
object. It has been argued that the
physical aspect of a robot—its morphology—can actually perform computations that would otherwise have
to be performed by the robot’s control policy if situated in an unsuitable body plan. This phenomenon
of morphological computation25
cannot be completely abstracted
away from the physical substrate that
gives rise to it in the way a Turing Machine can. Practitioners in this area
would greatly benefit from the aid
of theoretical computer scientists to
formalize this concept.
Dynamical systems theory. Dynamical systems theory is increasingly a
useful tool for creating controllers
for autonomous robots. 2 Often these
controllers take the form of artificial
neural networks that have their own
intrinsic dynamics: they exhibit complex temporal patterns spontaneously. Evolutionary algorithms can then
be used to shape the parameters of
these networks such that they can be
pushed by incoming sensor stimuli to
fall into desired attractor states. For
example, a neural network that falls
into a periodic attractor may generate a rhythmic gait in a legged robot.
However, it has been demonstrated
that a one-to-one mapping between a
basin of attraction in a neural network
and a distinct robot behavior may be
overly simplistic, 14 indicating there is
much work to be done at the interface
of dynamical systems theory and evolutionary robotics.
Information theory. Typically in an
evolutionary robotics experiment, the
“fitness” of a robot is measured based
on its ability to perform a given behavior, such as how far it can walk or
how well it can grasp an object. Surprisingly, it has been found that maximizing certain information-theoretic
measures within the neural network
of evolving robots can lead to useful
behavior. 28 Why information maximization produces desired behaviors
rather than useless, random, or uninteresting behavior remains mostly unresolved, although some progress has
been made in this direction. 8
In addition to helping with the synthesis of behavior, information theory
can also be used to analyze evolved behaviors. Williams et al. have recently
shown37 that information flow—the
transfer of information from one variable to another—can be employed
to measure how behaving robots
“offload” computed information to
their body and/or their environment.
This technique therefore holds promise for formalizing the concept of morphological computation. 25
challenges
There are a number of challenges currently facing the field, including transferring evolved robots from simulation to physical machines; scalability
issues; and the difficulty of defining
appropriate fitness functions for automatically measuring behavior.
The Reality Gap Problem. Both
biological and artificial evolution are
notorious for exploiting the poten-
tial relationship between the animal
(or robot) and its environment to
produce new behaviors. For instance
the lightweight property of feathers,
which are thought to have originally
evolved for heat regulation, was later
exploited for flight.e
As an example of the exploitative
tendencies of evolutionary algo-
rithms applied to robots, a robot was
initially designed to brachiate along
a suspended beam. 10 The robot was
composed of a main body slung un-
der two arms, and a heavy battery pack
attached to the main body. Gradually,
the evolutionary algorithm discovered
e This tendency of evolution to repurpose traits
is known as “exaptation.”
control policies for the robot that ex-
ploited, rather than fought against
the weight of the batteries. These con-
trol policies would cause the robot to
move such that the battery pack swung
forward under the robot’s body before
it changed hand holds. This would
cause the robot’s center of mass to
move forward, thus requiring much
less force to release contact with the
beam and grasp it further forward.
This mimics the way primates exploit
the weight of their bodies like a pen-
dulum to bring them into reach of a
new tree limb. It is also reminiscent
of the energy-saving passive dynam-
ics of bipedal locomotion (see more
details in the supplemental material).