BIOLOGICALLY INSPIRED INTELLIGENT ROBOTS USING
ARTIFICIAL MUSCLE
Artificial
Intelligence is a branch of Science
which deals with helping machines finds solutions to complex problems in a more
human-like fashion. This generally involves borrowing characteristics from
human intelligence, and applying them as algorithms in a computer friendly way.
A more or less flexible or efficient approach can be taken depending on the
requirements established, which influences how artificial the intelligent
behavior appears.
Humans throughout history have
always sought to mimic the appearance, mobility, functionality, intelligent
operation, and thinking process of biological creatures. This field of
biologically inspired technology, having the moniker biometrics, has evolved
from making static copies of human and animals in the form of statues to the
emergence of robots that operate with realistic appearance and behavior. This
paper covers the current state-of-the-art and challenges to making biomimetic
robots using artificial muscles.
Introduction:
AI
is generally associated with Computer
Science, but it has many important links with other fields such as Math’s, Psychology, Cognition,
Biology and Philosophy, among many others. The
ability to combine knowledge from all these fields will ultimately benefit the
progress in the quest of creating an intelligent artificial being. Advances in medicine have led to the
availability of artificial blood, replacement
joints, heart valves, and heart-lung machines that are common implanted. device.
Muscle is a critically needed organ and its availability in an artificial form
for medical use can greatly contribute to the improvement of the quality of
life of many humans. Thus these electroactive polymers (EAP) that are also
known as artificial muscles can potentially address this need. These materials
are human made actuators that have the closest operation similarity to
biological muscles.
Motivation of Artificial Intelligence:
Computers
are fundamentally well suited to performing mechanical computations, using
fixed programmed rules. This allows artificial machines to perform simple
monotonous tasks efficiently and reliably, which humans are ill-suited to. For
more complex problems, things get more difficult... Unlike humans, computers
have trouble understanding specific situations, and adapting to new situations.
Artificial Intelligence aims to improve machine behavior in tackling such complex
tasks.
Technology:
There
are many different approaches to Artificial Intelligence, some are obviously
more suited than others in some cases, but any working alternative can be
defended. Over the years, trends have emerged based on the state of mind of
influential researchers, funding opportunities as well as available computer
hardware.
Artificial life through robotics:
Laws of Robotics:
1. A robot may not injure a
human being or, through inaction, allow a human being to come to harm.
2. A robot must obey the
orders given it by human beings except where such orders would conflict with
the first law.
3. A robot must protect its
own existence as long as such protection does not conflict with the first or
second law.
Robotics has been an evolution of the field of automation
where there was a desire to emulate biologically inspired characteristics of
manipulation and mobility. In recent years, significant advances have been made
in robotics, artificial intelligence and others fields allowing to make
sophisticate biologically inspired robots [Bar-Cohen and Brea zeal.
Biologically inspired robotics is a subset of the interdisciplinary field of
biomimetics. Technology progress resulted in machines that can recognize facial
expressions, understand speech, and perform mobility very similar to living
creatures including walking, hopping, and swimming. Further, advances in
polymer sciences led to the emergence of artificial muscles using Electro
active Polymer (EAP) materials that show functional characteristics remarkably
similar to biological muscles. Making
creatures that behave like the biological model is a standard procedure for the
animatronics industry that is quite well graphically animates the appearance
and behavior of such creatures. However, engineering such biomimetic
intelligent creatures as realistic robots is still challenge due to the need to
physical and technological constraints.
Artificial muscles:
Muscles are the key to the
mobility and manipulation capability of biological creatures and when creating
biomimetic it is essential to create actuators that emulate muscles. The
potential to make such actuators is increasingly becoming feasible with the
emergence of the electro active polymers (EAP), which are also known as
artificial muscles [Bar-Cohen, 2001]. These materials have functional
similarities to biological muscles, including resilience, damage tolerance, and
large actuation strains. Moreover, these materials can be used to make
mechanical devices with no traditional components like gears, and bearings,
which are responsible to their high costs, weight and premature failures. The
large displacement that can be obtained with EAP using low mass, low power and,
in some of these materials also low voltage, makes them attractive actuators.
The capability of EAPs to emulate muscles offers robotic capabilities that have
been in the realm of science fiction when relying on existing actuators.
 |
|
|
FIGURE
1: A graphic illustration of the grand
challenge for the development of EAP actuated robotics – an arm wrestling match
against human.
Unfortunately, the EAP materials
that have been developed so far are still exhibiting low conversion efficiency,
are not robust, and there are no standard commercial materials available for
consideration in practical applications. In order to be able to take these
materials from the development phase to application as effective actuators,
there is a need for an established infrastructure. For this purpose, it is
necessary to develop comprehensive understanding of EAP materials' behavior, as
well as effective processing, shaping and characterization techniques. The
technology of artificial muscles is still in its emerging stages but the
increased resources, the growing number of investigators conducting research
related to EAP, and the improved collaboration among developers, users, and
sponsors are leading to a rapid progress.
Robots, which could build other
robots, tried to protect humans from everything until people could not do
anything by themselves. Biggest supporters of AI research is military. One of
the reasons is that in "...a nuclear age, a new generation of very
intelligent computers incorporating AI could actually defend the country
better, faster, and more rationally than humans.
Biometric robots using EAP:
Mimicking nature would
significantly expand the functionality of robots allowing performance of tasks that are currently
impossible. As technology evolves, great number of biologically inspired robots
actuated by EAP materials emulating biological creatures is expected to emerge.
The challenges to making such robots can be seen graphically in Figure 2 where
humanlike and dog-like robots are shown to hop and express joy. Both tasks are
easy for humans and dogs to do but are extremely complex to perform by existing
robots.
FIGURE
2: Making a joyfully hopping human-like and
dog-like robots actuated by EAP materials are great challenges for biomimetic
robots
FIGURE
3: An android head and a robotic hand that are
serving as biomimetic platforms for the development of artificial muscles.
Categories of EAP:
EAP can be divided into two major categories based on their activation
mechanism including ionic and electronic. The electronic EAP are driven by
Coulomb forces and they include: Dielectric EAP (shown in Fig.4a),
Electrostrictive Graft Elastomers, Electrostrictive Paper, Electro-Viscoelastic
Elastomers, Ferroelectric Polymers and Liquid Crystal Elastomers (LCE). This
type of EAP materials can be made to hold the induced displacement while
activated under a DC voltage, allowing them to be considered forrobotic
applications. These materials have a greater mechanical energy density and they
can be operated in
air with no major constraints. However, the
electronic EAP require a high activation fields (>30-V/μm) that may be close
to the breakdown level. In contrast to the electronic EAP, ionic EAP are
materials that involve
mobility or diffusion of ions and they
consist of two electrodes and an electrolyte. The activation of the ionic EAP
can be made by as low as 1-2 Volts and mostly a bending displacement is
induced. The ionic
EAP include Carbon Nanotubes (CNT),
Conductive Polymers (CP), Electro Rheological Fluids (ERF), Ionic Polymer Gels
(IPG), and Ionic Polymer Metallic Composite (IPMC) (shown in Fig.4b). Their
disadvantages are the need to maintain wetness and they pose difficulties to
sustain constant displacement under activation of a DC voltage (except for
conductive polymers).
a. Dielectric EAP in relaxed (top) and
activated states (bottom)
b. IPMC in relaxed (left) and activated
states (right)
Examples of EAP materials in relaxed and
activated states.
The induced displacement of both the electronic and ionic EAP materials
can be designed geometrically to bend, stretch or contract. Any of the existing
EAP materials can be made to bend with a significant bending response, offering
an actuator with an easy to see reaction.
FIGURE4a. Dielectric EAP in relaxed (top) and
activated states (bottom).
FIGURE4b. IPMC in relaxed (left) and
activated states (right)