Design and Summary Analysis Draft 2
According to the article, “Soft Robotic Arm…”
(2020), Massachusetts Institute of Technology (MIT) researchers have developed
a soft robot that can know its position in a 3D environment that uses its
sensorized skin. Soft robots are not ready for users as it need more testing in
real world environments to have a final design.
These soft robots use soft sensors that
are conductive silicone sheets that had been cut into kirigami patterns. These
soft sensors have “piezoresistive” properties, that are able to change in
electrical resistance when it is strained. When the soft sensors are deforms as
the soft robots are stretching and compressing the electrical resistance
is converted into an output voltage that is then used as a signal correlation
to that movement. Soft sensors are able to be fabricated using off the shelf materials.
Soft robots have an advantage compared to
robots with the traditional rigid design. Because of its infinite number of
movements that the soft robots are able to make at any time it needs a flexible
sensor. They do not rely on cameras to provide feedback which
is unideal for actual soft robot applications. “Think of your own body: You
can close your eyes and reconstruct the world based on feedback from your skin,”
(Rus,n.d). One of the future goals of soft robots is too able to make
artificial limbs that can move decorously and manipulate objects in the
environment.
One soft robot is comprised of three
segments each segment comprises four fluidic actuators in a total of 12 to move
the soft robot arm. The soft sensor is fused one sensor over each segment.
Each soft sensor
is covering and gathering data from one embedded actuator in the soft robot.
The soft sensor
is been fused using plasma bonding. Plasma bonding is a technique that
energizes a part of a surface of the soft sensor material to make a bond to
another material. Using a handheld plasma bonding device, it takes a couple of
hours to shape many of sensors that can be able to bond with the soft robots.
At MIT computer science and artificial
laboratory (CSAIL), they want to use these soft robots for instance to orient
and control automatically by themselves. They want these soft robots to pick
items up and interact with the environments as it will be the first step towards
a more sophisticated automated control.
Soft robots have its ability to have an
infinite number of movements due to that it has its limitation in the
“control”. MIT researchers built a neural network that are able to do away with
most of the heavy lifting by filtering out the noise to capture useful feedback
signals. Now MIT researchers have developed a new type of soft robots that
reduces the number of variables needed for their latest model to process.
In an experiment that took place an hour and a
half, MIT researchers make the soft robots swing around and extend themselves
in random configurations. MIT researchers used the traditional motion capture
system to collect data from the soft robot’s movement.
MIT researchers also want to explore new
sensor designs to improved sensitivity to develop new soft robot models. These
new soft robots are able to have deep-learning and improved sensitivity that
will reduce the required training for all new soft robots. The current neural network
and sensor skin are not sensitive to capture subtle motions or dynamic
movements. The first step in learning the base of approach in making a soft
robotic control. “Like our soft robots, living systems don’t have to be totally
precise. Humans are not precise machines, compared to our rigid robotic
counterparts, and we do just fine,” (Truby,n.d).
Matheson, R. (2020, February 15).
"Sensorized" Skin Enables Soft Robotic Arm to Feel Its Own Way At
MIT.
Retrieved from www.therobotreport.com/sensorized-skin-enables-soft-robotic-arm-feel-own-way-mit/
Matheson, R. (2020, February 16). Soft Robotic
Arm Uses Flexible Sensors To Understand Its Position control engineering.
Retrieved from www.controleng.com/articles/soft-robotic-arm-uses-flexible-sensors-to-understand-its-position/
Mod, S. (2020, March 4). New
"Sensitized" Skin Gives Robots A Better Sense Of Motion.
Retrieved from www.engineersgarage.com/news/new-sensitized-skin-gives-robots-a-better-sense-of-motion/
Modic, E. (2020, February 21). Soft Robotic
Arm Uses Flexible Sensors To Understand Its Position.
Retrieved from www.todaysmedicaldevelopments.com/article/3d-robot-skin-flexible-sensors-artificial-intelligence-mit/
Comments
Post a Comment