Design and Summary Analysis Draft 4
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. As reported by Matheson, proponents said, “they are being inspired by living organisms and is build from highly compliant materials. Soft robotic are safer, more adaptable, and more resilient alternatives to traditional rigid robots”. The soft robot can be deformed, and because it is fully autonomous, this makes it a challenge as a soft robot can move in a virtually infinite number of directions at any given moment.
The soft robot has one distinctive function, which is movement, and two features that a 3-axis robot does not have, which are the fluidic actuator and the soft sensor.
One of the features of soft robots is their
soft
sensors. Soft robots use soft sensors that are conductive silicone sheets that had been
cut into kirigami patterns. These soft sensors have “piezoresistive”
properties, that can change in electrical resistance when it is strained. When
the soft sensors are deformed 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. In contrast, a 3-axis robot needs
a range of sensors that need to be placed on the robot-like 3D vision and force-torque
sensor.
MIT researchers also want to explore a new
type of sensor which is designed to improve sensitivity to develop new soft
robot models. These new soft robots can have a feature called deep learning. This
will improve sensitivity that will reduce the required training for all new
soft robots. The current neural network with sensor skin is not sensitive to capture
subtle motions or dynamic movements. As reported by Matheson, Truby
said, “Like our soft robots, living systems don’t have to be
precise. Humans are not precise machines, compared to our rigid robotic
counterparts, and we do just fine”.
Another main feature of soft robots is
their fluidic actuators. 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 with one sensor over each segment. The 3-axis
robot needs only 3 motors to be able to move.
At MIT computer science and artificial
laboratory (CSAIL), they want to use these soft robots features 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.
The soft robot has the function of an infinite
number of movements. Due to the function, it has its limitation in “control”.
MIT researchers solve the problem by building the neural network that can do
away with most of the heavy lifting by filtering out unwanted noise to capture
useful feedback signals. In contrast, the 3-axis robot is only able to move on
3-axis. The more axis the robot has the more ways it able to move as 3-axis robots
can move in the X, Y, and Z direction.
In an experiment that took place an hour and a
half, MIT researchers make use of the soft robot's features to make it swing
around and extend themselves in random configurations. MIT researchers used a
traditional motion capture system to collect data from the soft robot’s
movement.
Therefore, a soft robot has its
distinctive features and a function that 3-axis robots do not have. One of the
distinctive functions is its soft sensors that able to be stretch and compress.
Using the soft sensors designs, soft robots are able to have an infinite number
of movements function. A soft robot may be the new type of robot having these
distinctive functions and features that the 3-axis robot is unable to have.
References
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/
Samuel, B. (2014, September 30). 7 Types
of Industrial Robot Sensors
https://blog.robotiq.com/bid/72633/7-Types-of-Industrial-Robot-Sensors
Mathiew, BB
& Robotiq, I (2015, December 9). How Many Axes Does My Robot Need
https://robohub.org/how-many-axes-does-my-robot-need/
Thanks for working on this, Yong Sheng.
ReplyDelete