Your source for the latest research news

Showing posts with label Robotics. Show all posts
Showing posts with label Robotics. Show all posts

Friday, 17 April 2020

Making Big Data Processing More Energy Efficient Using Magnetic Circuits


The rapid progression of technology has led to a huge increase in energy usage to process the massive troves of data generated by devices. But researchers in the Cockrell School of Engineering at The University of Texas at Austin have found a way to make the new generation of smart computers more energy efficient.

Traditionally, silicon chips have formed the building blocks of the infrastructure that powers computers. But this research uses magnetic components instead of silicon and discovers new information about how the physics of the magnetic components can cut energy costs and requirements of training algorithms — neural networks that can think like humans and do things like recognize images and patterns.



"Right now, the methods for training your neural networks are very energy-intensive," said Jean Anne Incorvia, an assistant professor in the Cockrell School's Department of Electrical and Computer Engineering. "What our work can do is help reduce the training effort and energy costs."

The researchers' findings were published this week in IOP Nanotechnology. Incorvia led the study with first author and second-year graduate student Can Cui. Incorvia and Cui discovered that spacing magnetic nanowires, acting as artificial neurons, in certain ways naturally increases the ability for the artificial neurons to compete against each other, with the most activated ones winning out. Achieving this effect, known as “lateral inhibition,” traditionally requires extra circuitry within computers, which increases costs and takes more energy and space.

Incorvia said their method provides an energy reduction of 20 to 30 times the amount used by a standard back-propagation algorithm when performing the same learning tasks.

The same way human brains contain neurons, new-era computers have artificial versions of these integral nerve cells. Lateral inhibition occurs when the neurons firing the fastest are able to prevent slower neurons from firing. In computing, this cuts down on energy use in processing data.

Incorvia explains that the way computers operate is fundamentally changing. A major trend is the concept of neuromorphic computing, which is essentially designing computers to think like human brains. Instead of processing tasks one at a time, these smarter devices are meant to analyze huge amounts of data simultaneously. These innovations have powered the revolution in machine learning and artificial intelligence that has dominated the technology landscape in recent years.



This research focused on interactions between two magnetic neurons and initial results on interactions of multiple neurons. The next step involves applying the findings to larger sets of multiple neurons as well as experimental verification of their findings.


Bibliography:

Can Cui, Otitoaleke Gideon Akinola, Naimul Hassan, Christopher Bennett, Matthew Marinella, Joseph Friedman, Jean Anne Currivan Incorvia.

Maximized Lateral Inhibition in Paired Magnetic Domain Wall Racetracks for Neuromorphic Computing.

Nanotechnology, 2020;

DOI: 10.1088/1361-6528/ab86e8

Friday, 3 April 2020

Engineers create shape-changing, free-roaming soft robot


A new type of robot combines traditional and soft robotics, making it safe but sturdy. Once inflated, it can change shape and move without being attached to a source of energy or air.

Advances in soft robotics could someday allow robots to work alongside humans, helping them lift heavy objects or carrying them out of danger. As a step toward that future, Stanford University researchers have developed a new kind of soft robot that, by borrowing features from traditional robotics, is safe while still retaining the ability to move and change shape.

"A significant limitation of most soft robots is that they have to be attached to a bulky air compressor or plugged into a wall, which prevents them from moving," said Nathan Usevitch, a graduate student in mechanical engineering at Stanford. "So, we wondered: What if we kept the same amount of air within the robot all the time?"

From that starting point, the researchers ended up with a human-scale soft robot that can change its shape, allowing it to grab and handle objects and roll in controllable directions. Their invention is described in a paper published March 18 in Science Robotics.

"The casual description of this robot that I give to people is Baymax from the movie Big Hero 6 mixed with Transformers. In other words, a soft, human-safe robot mixed with robots that can dramatically change their shape," said Usevitch.

A combination of many robots

The simplest version of this squishy robot is an inflated tube that runs through three small machines that pinch it into a triangle shape. One machine holds the two ends of the tube together; the other two drive along the tube, changing the overall shape of the robot by moving its corners. The researchers call it an "isoperimetric robot" because, although the shape changes dramatically, the total length of the edges -- and the amount of air inside -- remains the same.

The isoperimetric robot is a descendent of three types of robots: soft robots, truss robots and collective robots. Soft robots are lightweight and compliant, truss robots have geometric forms that can change shape and collective robots are small robots that work together, making them particularly strong in the face of single-part failures.



"We're basically manipulating a soft structure with traditional motors," said Sean Follmer, assistant professor of mechanical engineering and co-senior author of the paper. "It makes for a really interesting class of robots that combines many of the benefits of soft robots with all of the knowledge we have about more classic robots."

To make a more complex version of the robot, the researchers simply attach several triangles together. By coordinating the movements of the different motors, they can cause the robot to perform different behaviors, such as picking up a ball by engulfing it on three sides or altering the robot's center of mass to make it roll.

"A key understanding we developed was that to create motion with a large, soft pneumatic robot, you don't actually need to pump air in and out," said Elliot Hawkes, assistant professor of mechanical engineering at the University of California, Santa Barbara and co-senior author of the paper. "You can use the air you already have and just move it around with these simple motors; this method is more efficient and lets our robot move much more quickly."


From outer space to your living room

The field of soft robotics is relatively young, which means people are still figuring out the best applications for these new creations. Their safe-but-sturdy softness may make them useful in homes and workplaces, where traditional robots could cause injury. Squishy robots are also appealing as tools for disaster response.

Other exciting possibilities for the isoperimetric robot could lie off-planet. "This robot could be really useful for space exploration -- especially because it can be transported in a small package and then operates untethered after it inflates," said Zachary Hammond, a graduate student in mechanical engineering at Stanford and co-lead author of the paper, with Usevitch. "On another planet, it could use its shape-changing ability to traverse complicated environments, squeezing through tight spaces and spreading over obstacles."

For now, the researchers are experimenting with different shapes for their supple robot and considering plopping it in water to see if it can swim. They are also exploring even more new soft robot types, each with their own features and benefits.



"This research highlights the power of thinking about how to design and build robots in new ways," said Allison Okamura, professor of mechanical engineering and co-author of the paper. "The creativity of robot design is expanding with this type of system and that's something we'd really like to encourage in the robotics field."

This research was funded by the National Science Foundation and the Defense Advanced Research Projects Agency.


Bibliography:

Nathan S. Usevitch, Zachary M. Hammond, Mac Schwager, Allison M. Okamura, Elliot W. Hawkes, Sean Follmer.

An untethered isoperimetric soft robot.

Science Robotics, 2020; 5 (40): eaaz0492

DOI: 10.1126/scirobotics.aaz0492

Tuesday, 5 November 2019

A Russian startup is selling humanoid robots whose appearance may be that of your choice

On the left, the humanoid robot "Robo-C" from Promobot. On the right, the chairman of the board of directors of the company, having served as a model. | Promobot

A Russian startup named Promobot, founded in 2015, has recently put up for sale one of its most successful creations: a realistic humanoid robot, whose appearance can be that of your choice. It's not quite the autonomous android that you could imagine - it can only move the head and neck and has a fixed bust. But society is still a milestone in consumer robotics.

Please support by visiting the ads in the post your little click can help us to keep posting stuff beneficial for general knowlege, please leave a comment if you have any suggestions:
And Please follow us on Twitter 
Thank you 😊

" Everyone will now be able to order a robot with any appearance, for professional or personal use, " Aleksei Iuzhakov, Chairman of Promobot's Board of Directors , said in a press release, encouraging a short time. after the people present to "imagine a replica of Michael Jordan selling basketball uniforms, or William Shakespeare reading his own texts in a museum".


Promobot's Robo-C is not (yet?) Able to walk, but his neck and torso each have three degrees of freedom of movement, reads the website of the StartUp

His face has 18 moving parts, which allow the robot to produce 600 micro-expressions. Its artificial intelligence has 100,000 speech modules. What to give, potentially, realistic expressions to the creation. However, for the moment and according to what we have seen, there is still work to be done on the coherence of the moving parts with the different parts of the face (see video at the end of the article).

Digitization of the personality for a "digital immortality"

" The key moment in [Robo-C's] development is the digitization of the personality and the creation of an individual appearance ," Promobot co-founder Oleg Kivokurtsev told CNBC. " As a result, it would be a kind of digital immortality that we can offer to our customers."

The company also plans to manufacture robots for personal use, as a companion or personal assistant. For example, the robot could control smart home systems (in the same way as existing voice assistants). Credits: Promobot

According to CNBC, Promobot is already manufacturing four Robo-C units for its first customers.

One of the robots ordered will be placed in a government service center, where it will perform several functions (including passport scanning). Another will be a clone of Albert Einstein, for an exhibition on the theme of robotics.


The last two will be clone robots of the father and mother of a family from the Middle East, who wants to use androids to "greet the guests". Rather strange this last case of use ... And you,  what do you think? What would you do with such a robot?

Video presentation of Android Robo-C:


Friday, 1 November 2019

MIT develops modular robots that can move, jump, recognize and coordinate


The rise of robotics in recent years has found many practical applications in everyday life. If individual robots perform certain tasks correctly, swarms of robots are usually more efficient. However, achieving optimal communication and coordination between all robots is a big challenge. In an attempt to remedy this situation, a team at MIT's Computer Science and Artificial Intelligence Laboratory (CSAIL) has developed a surprisingly simple concept: self-assembled robotic cubes that can overlap, jump into the air, and roll. On the ground.

Please support by visiting the ads in the post your little click can help us to keep posting stuff beneficial for general knowlege, please leave a comment if you have any suggestions:
And Please follow us on Twitter 
Thank you 😊

Six years after the first iteration of the project, robots can now communicate with each other using a barcode-type system on each side of the block, allowing the modules to identify themselves. The Autonomous Fleet of 16 Blocks can now perform simple tasks or behaviors, such as forming a line or wall, following arrows or a light source.

Inside each modular "M-Block" is a flywheel that rotates at 20,000 rpm using kinetic momentum when the steering wheel is braked. On each edge and each face are permanent magnets allowing two cubes to attach to each other.

Interconnected modular robot swarms: many potential applications

The team envisions powerful applications for inspection and possibly disaster response. Imagine a building in flames where a staircase has disappeared. In the future, you can simply throw M-Blocks on the ground and watch them build a temporary staircase to climb the roof or go down to the basement to rescue the victims.

"'M' means movement, magnetism, and magic, " says Daniela Rus, MIT professor and director of CSAIL. " Movement, because the cubes can move by jumping. Magnetism, because they can connect to others using magnets and, once connected, they can move and connect to form structures. Magic, because we do not see any moving parts and the cube seems to be magically driven . "

Swarms of modular robots could be used in many areas: inspection and rescue, manufacturing, public health, construction, etc. Credits: Jason Dorfman / MIT CSAIL

While the mechanism is quite complex inside, the outside is on the contrary much simpler, allowing more robust connections. Beyond inspection and rescue, researchers also imagine using blocks for tasks such as games, manufacturing and care.

" What's unique in our approach is that it's inexpensive, robust, and potentially easier to fit into millions of modules, " says Romanishin. " M-Blocks can move in a general way. Other robotic systems have much more complicated motion mechanisms, which require many steps, but our system is more scalable . "

A displacement by inertial movement
Previous modular robotic systems typically approach movements using modules with small robotic arms called external actuators. These systems require a lot of coordination, even for the simplest movements, with several commands for a jump.

In 2013, the team developed its mechanism for M-Blocks. They created cubes that move using so-called "inertia forces". This means that, instead of using moving arms, the blocks have a mass inside that they "throw" against the side of the module, causing rotation and movement of the block.

Each module can move in four cardinal directions when it is placed on one of the six faces, giving 24 different directions of movement. Without small arms and appendages protruding from blocks, it's much easier for them to stay safe from damage and avoid collisions.

Optimized coordination via barcode communication

On the communication side, other attempts have involved the use of infrared light or radio waves, which can quickly become clumsy: if many robots in a small area are all trying to send signals to each other, quickly leads to confusion. When a system uses radio signals to communicate, they can interfere with each other when there are multiple radio signals in a small volume.

Romanishin has developed algorithms designed to help robots perform simple tasks, or "behaviors," which has led to the idea of ​​a barcode-like system, where robots can detect identity other blocks to which they are connected.

In one experiment, the team ordered the modules to form a line from a random structure, and checked if they could determine the specific way they were connected to each other. Otherwise, they should choose a direction and "roll" until they finish at the end of the line.

Essentially, the blocks used the connection pattern (the way they were connected to each other) to guide the chosen move - and 90% of the M-Blocks managed to form a line.

This video from MIT introduces the recently developed modular robots:



Source

Wednesday, 23 October 2019

Exoskeleton Improves Walking and Running Performance

Robotic clothing


A new "exorroupa" - or a soft robotic exoskeleton - can assist with walking and running, providing significant energy savings in terms of metabolic activity.

Most importantly, robotic clothing allows a net gain of energy in both modalities.

"Robotic exoskeletons tend to be bulky and heavy; and while walking experiences have shown promising results, the energy spent running with the additional weight of the device outweighs the benefits of robotic assistance," said Professor Giuk Lee of the University. Chung-Ang in South Korea.

The problem is that walking and running have a fundamentally different biomechanics, which makes it challenging to create devices that assist both types of gait.

To address this challenge, the Korean team took two approaches. The first was to manufacture the fabric mainly out of cloth, including the belt and the fastening wraps, which allowed to lower the weight of the entire device to only 5 kg. The second was to create a mechanism that allows the assistance mode to be automatically switched between walking and running to achieve maximum assistance efficiency.

An algorithm analyzes data collected by exoskeleton sensors and classifies gait (walking or running), providing feedback to the device and adjusting the assist mode. Treadmill and outdoor testing revealed that the algorithm was able to correctly identify gait more than 99.98% of the time.


Dressing Robot Assist


The exoskeleton's assistance reduced the energy cost of walking at a speed of 1.5 meters per second (4.8 km per hour) by 9.3%, equivalent to losing 7.4 kg. Energy savings during the race (speed of 2.5 meters per second or 9 km per hour) reached 4%, equivalent to a weight loss of 5.7 kg.

"Although changes in metabolic rate are relatively modest, they are of a magnitude similar to those proven to be sufficient to improve maximal walking and running performance. Therefore, we believe these energy savings could result in proportional increases in maximal performance, for example. , on an outdoor race course, "said Professor Lee.

The robotic suit is designed with people with mobility restrictions in mind, particularly those with limited knee function or above-knee amputees. But it can also be used to assist people without physical disabilities.

"We hope this 'dressing robot' will have many uses, such as aiding rehabilitation training for elderly patients and improving the work efficiency of soldiers or firefighters. In the long run, we imagine this exaggeration hanging in the closet all the time, as well as the clothes we wear everyday, "concludes Lee.



Bibliography:

Article: Reducing the metabolic rate of walking and running with a versatile, portable exosuit
Authors: Jinsoo Kim, Giuk Lee, Roman Heimgartner, Dheepak Arumukhom Revi, Nikos Karavas, Ignacio Galiana, Wing Eckert-Erdheim, Patrick Murphy, David Perry, Nicolas Menard, Kim Choe Dabin, Philippe Malcolm, Conor J. Walsh
Magazine: Science
Vol .: 365, Issue 6454, p. 668-672
DOI: 10.1126 / science.aav7536

About Us

we are bunch of Guys who Love Science and Technology, we are aware that our site looks junk but we don't have enough money to make our website much better, Your support will keep us growing, Please visit some ADS in the site that will be considered as donation and Please keep Sharing and join us on Facebook and Twitter. Thank you for reading our articles, Please leave comments if you feel anything, Have a Nice Life