MAY 11, 2020 5:51 PM PDT

New development in soft robotics

Soft material robotics are often more resilient and adaptable than conventional robotics, but there is one shortcoming - the presence of stiff control sensors limits their flexibility. So researchers from the Graduate School of Information Science and Technology at UTokyo are trying to fix that by creating embedded sensors that can replace traditional sensors. 

The team utilized a machine learning technique called reservoir computing to design the sensors for soft-bodied robots that are needed for their core functioning and behaviors. In reservoir computing,  information about a system is fed into a special artificial neural network in real-time, making the model forever-adaptable. 

The system in which the researchers applied this technique is called PAM, or pneumatic artificial muscles. "Take for example a robot with pneumatic artificial muscles, rubber and fiber-based fluid-driven systems which expand and contract to move," said Associate Professor Kohei Nakajima from the Graduate School of Information Science and Technology. "PAMs inherently suffer random mechanical noise and hysteresis, which is essentially material stress over time. Accurate laser-based monitors help maintain control through feedback, but these rigid sensors restrict a robot's movement, so we came up with something new." 

"We found the electrical resistance of PAM material changes depending on its shape during a contraction. So we pass this data to the network so it can accurately report on the state of the PAM," said Nakajima. "Ordinary rubber is an insulator, so we incorporated carbon into our material to more easily read its varying resistance. We found the system emulated the existing laser-displacement sensor with equally high accuracy in a range of test conditions."

Photo: Pixabay

This system opens new doors for soft material robotics, especially with robots that work with humans as wearable rehabilitation devices or biomedical robots. But the researchers aren’t stopping there - they think their findings have even bigger implications. 

"Our study suggests reservoir computing could be used in applications besides robotics. Remote-sensing applications, which need real-time information processed in a decentralized manner, could greatly benefit," said Nakajima. "And other researchers who study neuromorphic computing -- intelligent computer systems -- might also be able to incorporate our ideas into their own work to improve the performance of their systems."

Sources: Eureka Alert, UTokyo

About the Author
  • Kathryn is a curious world-traveller interested in the intersection between nature, culture, history, and people. She has worked for environmental education non-profits and is a Spanish/English interpreter.
You May Also Like
AUG 28, 2020
Chemistry & Physics
Interacting Time Crystals and the Future of Time Keeping
AUG 28, 2020
Interacting Time Crystals and the Future of Time Keeping
Time crystals, also known as the space-time crystals, is a newly discovered state of matter that demonstrates distinct s ...
AUG 31, 2020
Cell & Molecular Biology
Using Green Light to Create Molecular Bonds
AUG 31, 2020
Using Green Light to Create Molecular Bonds
In a first, researchers have used acidity and alkalinity - pH as a switch that can turn a green light-activated bonding ...
SEP 03, 2020
Chemistry & Physics
Nuclear Pioneers Joined Force to Fast-Track Clean Energy Tech
SEP 03, 2020
Nuclear Pioneers Joined Force to Fast-Track Clean Energy Tech
Last week, TerraPower, a Bill Gates-backed nuclear startup, announced its latest project - a collaboration with GE Hitac ...
SEP 06, 2020
Chemistry & Physics
The fluid dynamics of pelagic snails' movement
SEP 06, 2020
The fluid dynamics of pelagic snails' movement
Warm water pelagic snails don’t get much attention, but they certainly should. The snails move between ocean surfa ...
SEP 14, 2020
Chemistry & Physics
Using a laser to cool a polyatomic molecule has never been done before - until now
SEP 14, 2020
Using a laser to cool a polyatomic molecule has never been done before - until now
Scientists from Harvard have devised a technique that allows them to slow down a polyatomic molecule using a laser. This ...
OCT 17, 2020
Chemistry & Physics
Improving carbon capture technologies using membranes
OCT 17, 2020
Improving carbon capture technologies using membranes
Researchers from the International Institute for Carbo-Neutral Energy Research (I2CNER), Kyushu University and NanoMembr ...
Loading Comments...