Tech Briefs Magazine - June 2021 - MD-22

they needed a way to determine
the position and orientation
of an object being
tracked. Typical approaches
involve LiDAR systems and
light-field cameras, both of
which suffer from significant
limitations. Others use metamaterials
or multiple cameras.
Hardware alone was not
enough to produce the de -
sired results.
The team built an optical
setup and enabled a neural
network to decipher the
positional information. The
neural network is trained to
search for specific objects in
the entire scene and then
focus only on the object of
interest; for example, a pe -
destrian in traffic or an object moving
into your lane on a highway. The technology
works particularly well for stable
systems, such as automated manufacturFocal
stack images of a point object are simulated by focusing a green laser beam
onto a graphene-based transparent photodetector array. Graphene detectors produce
surprisingly high photo-response while only absorbing a very small portion of light.
(Image: Robert Coelius/Michigan Engineering, Communications and Marketing)
ing, or projecting human body structures
in 3D for the medical community.
The type of algorithms the team
developed are unlike traditional signal
processing algorithms
used for long-standing im -
aging technologies such as
X-ray and MRI. The team
demonstrated success track -
ing a beam of light as well
as an actual ladybug with a
stack of two 4×4 (16-pixel)
graphene photodetector ar -
rays. They also proved that
their technique is scalable:
it would take as few as 4,000
pixels for some practical
applications and 400×600pixel
arrays for many more.
The technology could be
used with other materials.
Additional advantages of
graphene are that it doesn't
require artificial illumination
and it's environmentally
friendly. Mass production would require
a new manufacturing infrastructure.
For more information, contact Nicole
Casal Moore at ncmoore@umich.edu.
AI and Wearable Cameras Combined in SelfWalking
Robotic Exoskeletons
Exoskeleton legs are capable of thinking and making control decisions on their own using
artificial intelligence technology.
University of Waterloo, Ontario, Canada
Researchers are developing exo skel -
eton legs capable of thinking and
making control decisions on their own
using sophisticated artificial intelligence
(AI) technology. The ExoNet
system combines computer
vision and deep-learning AI to
mimic how able-bodied people
walk by seeing their surroundings
and ad justing their
movements.
Exoskeleton legs operated
by motors already exist but
they must be manually controlled
by users via smartphone
applications or joysticks. Each
time the user wants to perform
a new locomotor activity, they
have to stop, take out their
smartphone, and select the
desired mode. To address that
limitation, the researchers fit22
Cov
ToC
ted
exo skeleton users with wearable cameras
and are now optimizing AI computer
software to process the video feed to
accurately recognize stairs, doors, and
other features of the surrounding environment.
The
next phase of the project will
involve sending instructions to motors so
that robotic exoskeletons can
climb stairs, avoid obstacles, or
take other appropriate actions
based on analysis of the user's current
movement and the up coming
terrain. The control approach
would not necessarily require
human thought. Similar to cars
that drive themselves, the au ton -
omous exoskeletons would walk
by themselves.
The self-walking robotic exoskeleton legs can think and make control decisions on
their own using artificial intelligence.
The researchers are improving
the energy efficiency of the mo -
tors by using human motion to
self-charge the batteries.
For more information, contact
Chris Wilson-Smith at chris.ws@
uwaterloo.ca; 519-888-4451.
Motion Design, June 2021
http://www.abpi.net/ntbpdfclicks/l.php?202106TBNAV
Tech Briefs Magazine - June 2021

Table of Contents for the Digital Edition of Tech Briefs Magazine - June 2021
