NEWS ROBOTICS
Scientists develop
soft tactile sensor
SENSOR WITH SKIN-COMPARABLE CHARACTERISTICS COULD
HELP ROBOTS ACCOMPLISH MORE CHALLENGING TASKS.
NEIL TYLER REPORTS
A joint research team co-led by City
University of Hong Kong (CityU)
has developed a new soft tactile
sensor with skin-comparable
characteristics. According to
scientists, a robotic gripper using
the sensor would be able to
accomplish a range of challenging
tasks such as stably grasping
fragile objects or threading a
needle.
The research has provided new
insight into tactile sensor design
and could contribute to various
applications in the robotics eld,
such as smart prosthetics and
human-robot interaction.
A main characteristic of human
skin is its ability to sense the
shear force, meaning the force that
makes two objects slip or slide
over each other when coming into
contact. By sensing the magnitude,
direction and the subtle change of
shear force, our skin can act as
feedback and allow us to adjust
how we should hold an object
stably with our hands and ngers
or how tight we should grasp it.
This new sensor comes in
a multi-layered structure like
human skin and includes a
exible and specially magnetised
lm of about 0.5mm as the top
layer. When an external force is
exerted on it, it can detect the
change of the magnetic eld due
to the lm’s deformation. More
importantly, it can “decouple”, or
decompose, the external force
automatically into two components
- normal force (the force applied
perpendicularly to the object) and
shear force, providing the accurate
measurement of these two forces
respectively.
The sensor also possesses
another human skin-like
characteristic - the tactile “superresolution”
that allows it to
locate the stimuli’s position as
accurately as possible.
“We have developed an
ef cient tactile super-resolution
algorithm using deep learning
and achieved a 60-fold
improvement of the localisation
accuracy for contact position,
which is the best among superresolution
methods reported
so far,” said Dr Shen Yajing,
Associate Professor at CityU’s
Department of Biomedical
Engineering (BME).
This ef cient tactile superresolution
algorithm can help
improve the physical resolution
of a tactile sensor array with
the least number of sensing
units, so reducing the number of
wirings and the time required for
signal transmitting.
SLAMcore offers
‘out-of-the-box’
robot navigation
ABB launches next generation cobots
ABB has extended its collaborative
robot (cobot) portfolio with
the launch of the GoFa and
SWIFTI cobot families, offering
higher payloads and speeds to
complement YuMi and Single Arm
YuMi in ABB’s cobot line-up.
Designed to be stronger, faster
and more capable these cobots
are intended to help accelerate
the company’s expansion into
high-growth segments such as:
electronics, healthcare, consumer
goods, logistics and food and
beverage, and meeting the growing
demand for automation across
multiple industries.
GoFa and SWIFTI are intuitively
designed so that customers
don’t have to rely on in-house
programming specialists.
Sami Atiya, President of ABB’s
Robotics & Discrete Automation
Business Area said, “These robots
are easy to use and con gure
and they are backed by our
global network of on-call, on-line
service experts to ensure that
businesses of all sizes and new
sectors of the economy, far beyond
manufacturing, can embrace
robots for the rst time.”
ABB’s cobot portfolio
expansion looks to respond to
four key megatrends including
individualised consumers, labour
shortages, digitalisation and
uncertainty that are transforming
business and driving automation
into new sectors of the economy.
A global survey of 1650 large
and small businesses found that
84 percent said they will introduce
or increase the use of robotics
and automation in the next
decade, while 85 per cent said
the pandemic had been “game
changing” for their business and
industry, with it acting as a catalyst
for accelerating investment in
automation.
SLAMcore, a specialist in Spatial
Intelligence for autonomous
robot location and mapping, has
added new dense 2.5D mapping
capabilities to its latest software
release.
Robots require maps of their
surroundings and the objects
within it to navigate effectively
- these maps can include point
clouds, 2D at maps, 2.5D dense
maps (with heights), 3D maps
and semantic maps which identify
objects (people/tables/chairs/
windows).
One of the main challenges of
robot mapping is that it requires
signi cant compute power,
processing time and memory to
create these maps.
In response, SLAMcore has
developed software that uses
stereo cameras and inertial
sensors to build 2.5D height maps
in real-time. The occupied space
is represented as a series of
columns of different heights which
show what space is lled. Using
these rich 2.5D maps, robots
and autonomous devices know
where objects are and can safely
plot routes through real-world
environments.
SLAMcore software is designed
to run fast prototypes out-of-the
box with Intel RealSense depth
cameras (D435i or D455) and has
been optimised for x86 and Nvidia
Jetson processors. The software
can be further customised for
production systems to run on
a wide range of cost-effective
hardware from Raspberry Pi to
GPU based systems.
8 9 March 2021 www.newelectronics.co.uk
/www.newelectronics.co.uk