via The University of Tokyo
Combined muscles and sensors made from soft materials allow for flexible robots
Robots can be made from soft materials, but the flexibility of such robots is limited by the inclusion of rigid sensors necessary for their control. Researchers created embedded sensors, to replace rigid sensors, that offer the same functionality but afford the robot greater flexibility. Soft robots can be more adaptable and resilient than more traditional rigid designs. The team used cutting-edge machine learning techniques to create their design.
Automation is an increasingly important subject, and core to this concept are the often paired fields of robotics and machine learning. The relationship between machine learning and robotics is not just limited to the behavioral control of robots, but is also important for their design and core functions. A robot which operates in the real world needs to understand its environment and itself in order to navigate and perform tasks.
If the world was entirely predictable, then a robot would be fine moving around without the need to learn anything new about its environment. But reality is unpredictable and ever changing, so machine learning helps robots adapt to unfamiliar situations. Although this is theoretically true for all robots, it is especially important for soft-bodied robots as the physical properties of these are intrinsically less predictable than their rigid counterparts.
“Take for example a robot with pneumatic artificial muscles (PAM), 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 at University of Tokyo. “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.”
Nakajima and his team thought if they could model a PAM in real time, then they could maintain good control of it. However, given the ever-changing nature of PAMs, this is not realistic with traditional methods of mechanical modeling. So the team turned to a powerful and established machine learning technique called reservoir computing. This is where information about a system, in this case the PAM, is fed into a special artificial neural network in real time, so the model is ever changing and thus adapts to the environment.
“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.”
Thanks to this method, a new generation of soft robotic technology may be possible. This could include robots that work with humans, for example wearable rehabilitation devices or biomedical robots, as the extra soft touch means interactions with them are gentle and safe.
“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.”
The Latest Updates from Bing News & Google News
Go deeper with Bing News on:
- People trust robots more than themselves with money, according to global studyon February 23, 2021 at 4:35 am
Research shows growing confidence among consumers and business leaders that robots handle finance tasks better than people 2020 has changed our relationship with money and people now trust robots ...
- Soft gel could power robot muscles that grow stronger with a workouton February 22, 2021 at 8:07 am
Our muscles get stronger when put under stress and now robot ones could do the same, thanks to a soft gel that becomes harder when exposed to vibration ...
- UC San Diego's electronics-free soft robot only needs pressurized air to moveon February 19, 2021 at 3:52 am
Engineers from the University of California San Diego have developed a four-legged soft robot that doesn't need electronic components to work.
- Thin, flexible pump could make soft robots even softeron February 18, 2021 at 9:57 am
Soft-bodied robots move via pneumatic "muscles" that are selectively inflated or deflated. And while the muscles themselves may be soft and squishy, they're usually hooked up to hard, unwieldy pumps.
- Air-powered robot uses no electronicson February 18, 2021 at 6:08 am
University of California San Diego engineers have created a soft quadruped robot that doesn’t require any electronics to work. The robot only needs a constant source of pressurized air to ...
Go deeper with Google Headlines on:
Go deeper with Bing News on:
- Thamama supporting ADNOC’s production, efficiency goalson February 22, 2021 at 8:44 am
ADNOC’s Thamama Center of Excellence has generated $1.1 billion in value since opening in 2017, the NOC revealed at its Innovation Week virtual event.
- Adnoc’s Thamama Centre generates $1.1b in business since 2017on February 22, 2021 at 4:53 am
Thamama is a key part of Adnoc's ongoing strategic investments in advanced technology, digitalisation and AI to drive greater efficiencies.
- ADNOC's Thamama Center Generates $1.1b in Business Valueon February 22, 2021 at 4:05 am
The Abu Dhabi National Oil Company (ADNOC) announced on Monday that its Thamama Center of Excellence (Thamama) has generated $1.1 billion (AED4.04 billion) in business value since its inception in ...
- EROS Digital Elevation Model Offers New, High-Resolution View of Lake Powellon February 16, 2021 at 10:56 am
Topobathymetric elevation model of Lake Powell. USGS image created by Sandra Poppenga, Dean Tyler, and Jeff Danielson. Topobathymetric digital elevation is key to estimating water capacity in Lake ...
- RRSP Investors: Hold This Value Stock for 20 Yearson February 12, 2021 at 4:01 pm
Computer Modelling Group (CMG) licenses reservoir simulation software ... computational speed, and parallel computing ability. The company provides clients with technologically advanced tools ...