Home' Army Acquisition Logistics and Technology Magazine : Army ALT January-March 2017 Contents Sensor information is provided to the
algorithms responsible for estimating self-
motion and interaction with the world.
Robots can be programmed with their
own versions of mental models, com-
plete with mechanisms for learning and
adaptation that help encode knowledge
about themselves and the environment in
which they operate. R ather than “mental
models,” we call these “world models.”
‘IN FORM AND MOVING HOW
EXPRESS AND ADMIRABLE’
Consider a robot acting while assuming
a model of its own motion in the world.
If the behavior the robot actually expe-
riences deviates significantly from the
behavior the robot expects, the discrep-
ancy will lead to poor performance: a
“wobbly” robot that is slow and confused,
not unlike a human after too many alco-
holic beverages. If the actual motion is
closer to the anticipated model, the robot
can be very quick and accurate with less
burden on the sensing aspect to correct
for erroneous modeling.
Of course, the environment itself greatly
affects how the robot moves through the
world. While gravity can fortunately be
assumed constant on Earth, other con-
ditions can change how a robot might
interact with the environment. For
instance, a robot traveling through mud
would have a much different experi-
ence than one moving on asphalt. The
best modeling would be designed to
change depending on the environment.
We know there are many models to be
learned and applied, and the real issue
is knowing which model to apply for a
Robotics today are developed in labora-
tory environments with little exposure
to the variability of the world outside
the lab, which can cause a robot’s abil-
ity to perceive and react to fail in the
unstructured outdoors. Limited envi-
ronmental exposure during model
learning and subsequent poor adapta-
tion or performance is said to be the
result of “over-fitting,” or using a model
created from a small subset of experi-
ences to maneuver according to a much
broader set of experiences.
At ARL, we are researching specific
advances to address these areas of sens-
ing, modeling self-motion and modeling
robotic interaction with the world, with
the understanding that doing so will
enable great enhancements in the opera-
tional speed of autonomous vehicles.
Specifically, we are working on knowing
when a nd under what conditions different
methods of sensing work well or may not
work well. Given this knowledge, we can
balance how these sensors are combined
to aid the robot’s motion estimation.
A much faster estimate is available as well
through development of techniques to
automatically estimate accurate models
of the world and of robot self-motion.
With the learned and applied models, the
robot can act and plan on a much quicker
timescale than what might be possible
with only direct sensor measurements.
Finally, we know that these models of
motion should change depending on
which of the many diverse environmen-
tal conditions the robot finds itself in.
To further enhance robot reliability in
a more general sense, we are working on
how to best model the world such that a
collection of knowledge can be leveraged
to help select an appropriate model of
robot motion for the current conditions.
If we can master these capabilities, then
Rosie can be ready for operation, lacking
only her signature attitude.
For more information about ARL col-
laboration opportunities in the science for
maneuver, go to http://www.arl.army.
DR. JOSEPH CONROY is an electronics
engineer in ARL’s Micro and Nano
Materials and Devices Branch, Adelphi,
Maryland. He holds a doctorate, an M.S .
and a B.S ., all in aerospace engineering
and all from the University of Maryland,
MR. EARL JARED SHAMWELL is a
systems engineer with General Technical
Services LLC, providing contract support
to ARL’s Micro and Nano Materials and
Devices Branch. He is working on his doc-
torate in neuroscience from the University
of Maryland, College Park, and holds a B.A .
in economics and philosophy from Colum-
WIRED FOR DISCOVERY
Earl Jared Shamwell, one of the authors, sets up
a multisensor robotics test bed to collect images,
light detection and ranging data and inertial
measurements. Researchers aim to improve
robotic performance by closing the gap
between what a robot expects to happen and
what actually happens. (Photo by Jhi Scott, ARL)
Links Archive Army ALT October-December 2016 Army ALT April-June 2017 Navigation Previous Page Next Page