Tech Briefs Magazine - April 2022 - MD-14

Bendable Robot Arm Guided by Augmented Reality
The highly customizable robotic arm can be twisted and turned in all directions.
Imperial College London, United Kingdom
R
esearchers at the Imperial
College London have created
a flexible robotic arm that
can be guided by an individual
using augmented reality (AR)
goggles. The highly customizable
robotic arm can be twisted
and turned in all directions and
used in areas like spacecraft
maintenance, manufacturing,
and injury rehabilitation.
Instead of being constrained
by rigid limbs and firm joints,
the
versatile arm is
robotics but no experience with
manipulating malleable robots
specifically. The subjects were able
to adjust the robot accurately, and
the results are published in Robotics
& Automation Magazine.
readily
people
bendable into a wide variety of
shapes. In practice,
working alongside the robot
would manually bend the arm
into the precise shape needed
for each task, a level of flexibility
made possible by the slippery
layers of mylar sheets inside,
which slide over one another
and can lock into place. However,
configuring the robot into specific
shapes without guidance has proven to
be difficult for users.
To enhance the robot's user-friendliness,
The
AR template turns green to indicate successful configuration. (Photo:
Imperial College London)
researchers at Imperial's REDS
(Robotic manipulation: Engineering,
Design, and Science) Lab have designed
a system for users to see in AR how to
configure their robot. Wearing mixed reality
smart glasses and through motion
tracking cameras, users see templates and
designs in front of them superimposed
onto their real-world environment. They
then adjust the robotic arm until it
matches the template, which turns green
on successful configuration so that the
robot can be locked into place.
" One of the key issues in adjusting
these robots is accuracy in their new
position. We humans aren't great at
making sure the new position matches
the template, which is why we looked to
AR for help, " said senior author of the
paper Dr. Nicolas Rojas. " We've shown
that AR can simplify working alongside
our malleable robot. The approach
gives users a range of easy-to-create
robot positions, for all sorts of applications,
without needing so much technical
expertise. "
The researchers tested the system on
five men aged 20-26 with experience in
Although the pool of participants
was narrow, the researchers say their
initial findings show that AR could
be a successful approach to adapting
malleable robots following further
testing and user training.
Potential applications include
manufacturing and building and
vehicle maintenance. Because the
arm is lightweight, it could also be
used on spacecraft where lowweight
instruments are preferred.
It is also gentle enough that it
could be used in injury rehabilitation,
helping a patient perform an
exercise while their physiotherapist
performs another.
The researchers are still in the process
of perfecting the robot as well as its AR
component. Next, they will look into introducing
touch and audio elements to
the AR to boost its accuracy in configuring
the robot.
ening the
They are also looking into strengthrobots.
Although their
flexibility and softness make them
easier to configure and safer to work
alongside humans, they are less rigid
while in the locked position, which
could affect precision and accuracy.
For more information, contact Caroline
Brogan at caroline.brogan@imperial.ac.uk;
207-594-341.
Soft Sensor Boosts Fingertip Sensitivity for Robots
A soft haptic sensor uses computer vision and a deep neural network to accurately estimate where
objects come into contact with it.
Max Planck Institute for Intelligent Systems, Stuttgart, Germany
I
n a paper published in Nature Machine
Intelligence, a team of scientists at the
Max Planck Institute for Intelligent
Systems (MPI-IS) introduced a robust
soft haptic sensor named " Insight " that
14
uses computer vision and a deep neural
network to accurately estimate where
objects come into contact with the sensor
and how large the applied forces are.
The research project is a significant step
toward robots being able to feel their
environment as accurately as humans
and animals. Like its natural counterpart,
the fingertip sensor is very sensitive,
robust, and high resolution.
Motion Design, April 2022
MD Tech Briefs 0422_2.indd 14
Cov
ToC
3/15/22 7:37 AM

http://info.hotims.com/82320-844 http://info.hotims.com/82320-844

Tech Briefs Magazine - April 2022

Table of Contents for the Digital Edition of Tech Briefs Magazine - April 2022