3. INTRODUCTION
Leonardo is a highly expressive robot research platform made in
collaboration with Stan Winston Studio.
Leonardo does not resemble any real creature, but instead has the
appearance of a fanciful being. Its face was designed to be
expressive and communicative since it is a social robot. The
fanciful, purposefully young look is supposed to encourage humans
to interact with it in the same way they would with a child or pet.
4. PURPOSE
The goal of creating Leonardo was to make a
social robot. Its motors, sensors, and cameras
allow it to mimic human expression, interact with
limited objects, and track objects. This helps
humans react to the robot in a more familiar way.
Leonardo’s programming blends with
psychological theory so that he learns more
naturally, interacts more naturally, and
collaborates more naturally with humans.
5. Characteristics
Leonardo has 69 degrees of freedom — 32 of those are in the face
alone. As a result, Leonardo is capable of near-human facial
expression (constrained by its creature-like appearance). Although
highly articulated, Leonardo is not designed to walk. Instead, its
degrees of freedom were selected for their expressive and
communicative functions. It can gesture and is able to manipulate
objects in simple ways. Standing at about 2.5 feet tall, it is the most
complex robot. Leonardo is the most expressive robot in the world
today.
6. DESIGN
There are approximately sixty motors in
the small space of the robot body that
make the expressive movement of the
robot possible.
A camera mounted in the robot’s right
eye captures faces.
A buffer of up to 200 views of the face is
used to create a model of the person
whenever they introduce themself via
speech.
Leonardo can track objects and faces
visually using a collection of visual feature
detectors that include color, skin tone,
shape, and motion.
7. HARDWARE
Commercial motor-driver and motion-controller packages are
designed with a completely different application in mind
Both 8-axis and 16-axis control packages have been developed.
4 of the 16-axis motor controller packages are used to control
Leonardo. A single 8-axis package is used to control Robot
Communication.
8. The motor drivers are standard FET H-bridges;
recent advances in FET process technology permit
surprisingly switching at relatively low (1-10kHz)
frequencies reduces switching losses.
The interference due to the low switching
frequency (which is completely unacceptable for
an organic looking robot) is eliminated by using a
variable-mean spread-spectrum control signal,
rather than traditional PWM.
9. LEARNING
Leonardo learns through spatial scaffolding. One of the ways a teacher teaches
is by positioning objects near to the student that they expect the student to
use. This same technique, spatial scaffolding, can be used with Leonardo, who is
taught to build a sailboat from virtual blocks, using only the red and blue
blocks. Whenever it tries to use a green block, the teacher pulls the “forbidden”
color away and moves the red and blue blocks into the robot’s space. Leonardo
learns, in this way, to build the boat using red and blue blocks only.
Another way that Leo learns is by mimicry. The same way infants learn to
understand and manipulate their world is helpful for the social robot. By
mimicking human facial expressions and body movement, Leo can distinguish
between self and other.
10. Interacting
Leonardo has access to that help it interact naturally with
humans.
Leonardo also can achieve something like empathy, however, by
examining the data it gets from mimicking human facial
expressions, body language, and speech. In a similar way, humans
can understand what other humans might be feeling based on
shared attention and perspective.
11. Collaborating
Leonardo can work together with a human to solve a common problem as much
as his body allows. He’s more effective at working shoulder-to-shoulder with a
human because of the theory of mind work that is blended with his programming.
All of Leonardo’s social skills work together so it can work alongside humans.
When a human asks it to do a task, it can indicate what it knows or doesn’t know
and what it can and cannot do. Communicating through expression and gesture
and through perceiving expression, gesture, and speech, the robot is able to work
as part of a team.
12. SensateSkin
Giving the robot a sense of touch will be useful for
detecting contact with objects, sensing unexpected
collisions, as well as knowing when it is touching its own
body. Other important tactile attributes relate to affective
content—whether it is pleasure from a hug, a ticking
gesture, or pain from someone grabbing the robot’s arm
too hard, to name a few.
The goal of this project is to develop a synthetic skin
capable of detecting temperature, proximity, and
pressure with acceptable resolution over the entire body,
while still retaining the look and feel of its organic
counterpart.