Tech Briefs Magazine - February 2022 - MD-10

Software Gives Robots Human Touch
A software makes industrial robots nimbler and almost as sensitive as human hands.
Eureka Robotics, Singapore
A
technology called Dynamis was developed
that makes industrial robots able
to manipulate tiny glass lenses, electronics
components, or engine gears that are millimeters
in size without damaging them.
The proprietary force feedback technology
enables anyone to program
touch-sensitive tasks that are usually
done by humans such as assembly, fine
manipulation, polishing, or sanding -
tasks that require the ability to maintain
consistent contact with a surface.
Known as Force Sensor Robust
Compliance Control, the software powered
by Dynamis requires only a single
parameter to be set: stiffness of the
contact, whether it is soft, medium, or
hard. Dynamis is a complex artificial
intelligence algorithm first deployed
in Eureka's custom-built robots such
as Archimedes, which can handle fragile
optical lenses and mirrors with human-like
dexterity.
Current robots in the market have either
high accuracy but low agility (where
robots perform the same movements
repeatedly such as in a car factory), or
low accuracy but high agility (such as roThe
inventors with a Denso Wave robot equipped with the Dynamis force feedback technology software.
(Photo: Eureka Robotics)
bots handling packages of different sizes
in logistics). By deploying this technology,
robotics engineers can now imbue
robots with both high accuracy and
high agility on a large scale, paving the
way for industrial applications that were
previously very difficult or impossible to
implement.
For more information, visit http://info.
hotims.com/82318-290.
Incorporating Computer Vision and Uncertainty into
AI for Robotic Prosthetics
The software can be integrated with existing hardware to aid people using robotic prosthetics or
exoskeletons.
North Carolina State University, Raleigh, NC
R
esearchers have developed new software
that can enable people using
robotic prosthetics or exoskeletons to
walk in a safer, more natural manner
on different types of terrain. The new
framework incorporates computer vision
into prosthetic leg control and includes
robust artificial intelligence (AI)
algorithms that allow the software to
better account for uncertainty.
Lower-limb robotic prosthetics need
to execute different behaviors based on
the terrain users are walking on. The
new framework allows the AI in robotic
10
prostheses to predict the type of terrain
users will be stepping on, quantify the
uncertainties associated with that prediction,
and then incorporate that uncertainty
into its decision-making.
The researchers focused on distinguishing
among six different terrains
that require adjustments in a robotic
prosthetic's behavior: tile, brick, concrete,
grass, " upstairs, " and " downstairs. "
The new " environmental context "
framework incorporates both hardware
and software elements. The researchers
designed the framework for use with
any lower-limb robotic exoskeleton or
robotic prosthetic device but with one
additional piece of hardware: a camera.
They used cameras worn on eyeglasses
and cameras mounted on the lower-limb
prosthesis itself and evaluated how the
AI was able to make use of computer
vision data from both types of camera,
separately and when used together.
The AI teaches deep-learning systems
how to evaluate and quantify uncertainty
in a way that allows the system to incorporate
uncertainty into its decision-making.
While it is relevant for robotic prosMotion
Design, February 2022
MD Tech Briefs 0222_1.indd 10
Cov
ToC
1/18/22 12:40 PM

http://info.hotims.com/82318-290 http://info.hotims.com/82318-800

Tech Briefs Magazine - February 2022

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