Category: Robotics and Automation

By Riccardo Bevilacqua, University of Florida.

If we are serious about long-term human presence in space, such as manned bases on the moon or Mars, we must figure out how to streamline human-robot interactions.

Right now, even the most basic of robots seem to have impenetrable brains. When I bought an autonomous vacuum cleaner, one that roams the house on its own, I thought I was going to save time and be able to enjoy a book or a movie, or play longer with the kids. I ended up robot-proofing every room, making sure wires and cables are out of the way, closing doors, placing electronic signposts for the robot to follow and much more – often daily. I cannot fully understand or predict what the system will do, so I don’t trust it. As a result, I play it safe, and spend time doing things to accommodate the needs I imagine the robot might have.

As a space roboticist, I think about this sort of problem happening in orbit. Imagine an astronaut on a spacewalk, working on repairing something damaged on the outside of the spacecraft. Several tools might be needed, and parts to mend or replace others. An autonomous spacecraft could serve as a floating toolbox, holding parts and tools until they’re needed, and staying close to the astronaut as she moves around the area needing to be fixed. Another robot could be clamping parts together before they are permanently fastened.

How will these robots know where they’ll be needed to go next, to be useful but not in the way? How will the astronaut know whether the robots are planning to move to the place she actually needs? What if something comes loose unexpectedly – can the person and the machinery figure out how to stay out of each other’s way while handling the situation efficiently? In weightless space, spatial orientation is difficult and the dynamics of moving around one another are not intuitive.

Problems around effective communication between people and their machines – particularly about actions and intentions – arise throughout the field of robotics. They must be solved if we are to fully take advantage of the potential robots enable for us.

Feeling safe crossing the road

Understanding robots is already an increasing problem here on Earth. One day I found myself walking down a California road where autonomous cars are tested. I asked myself, “How would I know if a driverless vehicle is going to stop at the crosswalk?” I have always relied on eye contact and cues from the driver, but those options may be soon gone.

Robots have trouble understanding us, too. I recently read of an autonomous car unable to process a situation where a bicycle rider balanced himself for some time at an intersection, without putting his feet down. The onboard algorithms could not determine if the biker was going or staying.

When we look at space exploration and defense, we find similar problems. NASA has not used the full abilities of some of its Mars rovers, simply because the engineers could not be sure what would happen if the metallic pets were free to explore and investigate the Red Planet on their own. The humans didn’t trust the machines, so they prevented them from doing as much as they could.

The Department of Defense often uses crews of 10 or more trained personnel to support a single unmanned aerial vehicle up in the sky. Is such a drone really autonomous? Does it require the people, or do the people need it? In any case, how do they interact?

What is “autonomy,” really?

Do drones need people or do people need drones?
U.S. Air Force

While “autonomy” means “self-governance” (from Greek), no man is an island; the same appears to be valid for our robotic creations. Today we see robots as agents able to operate independently – like my vacuum cleaner – but still part of a team – the family’s efforts to keep the house clean. If they are truly working with us, rather than instead of us, then communication is key, as well as the ability to infer intent. We may go solo for most duties, but sooner or later we will need to be able to connect with the rest of the team.

The problem is that autonomous machines and humans do not fully understand each other, and often speak in languages each other does not know – and has not yet started to learn.

The question for the future is how we transmit intent between humans and robots, in both directions. How do we learn to understand – and then to trust – machines? How do they learn to trust us? What cues might each offer the other? Understanding intentions and trusting our fellow humans is already a bumpy ride, but at least we have known cues we can rely on – like pedestrian-driver eye contact at a crosswalk. We need to find new ways to read robots’ minds, the same way they need to be able to understand ours.

Perhaps an astronaut could be given a specialized display to show what the helper spacecraft’s intentions are, much like the gauges in an airplane cockpit show the plane’s status to the pilot. Maybe the displays would be embedded in a helmet visor, or enhanced by sounds that have specific meanings. But what information would they transmit, and how would they know it?

These questions are open ground for new work, the type of learning we’ll need to find to unlock an exciting future of unimaginable exploration in which a new species, the robot, can lead us farther than ever before.

Riccardo Bevilacqua, Associate Professor of Mechanical and Aerospace Engineering, University of Florida

This article was originally published on The Conversation. Read the original article.

Featured Photo Credit:  NASA Johnson/flickr

Now, Check Out:

• Monkeys Drive Robotic Wheelchairs Just by Thinking
• SciFi-like Almost-Human Robots are Almost Here
• Here’s a Novel Way To Teach Robots to do Useful Things
• New Foam Metal Could Enable ‘Transformers-Like’ Capabilities [Video]
• Breakthrough ‘Stentrode’ Aims to Enable Thought Control for Exoskeletons [Video]

If you haven’t heard of Nanyang Technological University in Singapore, then it’s time to put them on your robotics research radar – a recent news release from NTU reveals some startlingly-incredible new robots that are amazingly human-like.

Two robots, with very different functions, were unveiled in their mind-bending press release:

Say hello to Nadine, a “receptionist” at Nanyang Technological University (NTU Singapore). She is friendly, and will greet you back. Next time you meet her, she will remember your name and your previous conversation with her.

She looks almost like a human being, with soft skin and flowing brunette hair. She smiles when greeting you, looks at you in the eye when talking, and can also shake hands with you. And she is a humanoid.

Unlike conventional robots, Nadine has her own personality, mood and emotions. She can be happy or sad, depending on the conversation. She also has a good memory, and can recognise the people she has met, and remembers what the person had said before.

Nadine is the latest social robot developed by scientists at NTU. The doppelganger of its creator, Prof Nadia Thalmann, Nadine is powered by intelligent software similar to Apple’s Siri or Microsoft’s Cortana. Nadine can be a personal assistant in offices and homes in future. And she can be used as social companions for the young and the elderly.

A humanoid like Nadine is just one of the interfaces where the technology can be applied. It can also be made virtual and appear on a TV or computer screen, and become a low-cost virtual social companion.

With further progress in robotics sparked by technological improvements in silicon chips, sensors and computation, physical social robots such as Nadine are poised to become more visible in offices and homes in future.

The rise of social robots

Prof Thalmann, the director of the Institute for Media Innovation who led the development of Nadine, said these social robots are among NTU’s many exciting new media innovations that companies can leverage for commercialisation.

“Robotics technologies have advanced significantly over the past few decades and are already being used in manufacturing and logistics. As countries worldwide face challenges of an aging population, social robots can be one solution to address the shrinking workforce, become personal companions for children and the elderly at home, and even serve as a platform for healthcare services in future,” explained Prof Thalmann, an expert in virtual humans and a faculty from NTU’s School of Computer Engineering.

“Over the past four years, our team at NTU have been fostering cross-disciplinary research in social robotics technologies – involving engineering, computer science, linguistics, psychology and other fields – to transform a virtual human, from within a computer, into a physical being that is able to observe and interact with other humans.

“This is somewhat like a real companion that is always with you and conscious of what is happening. So in future, these socially intelligent robots could be like C-3PO, the iconic golden droid from Star Wars, with knowledge of language and etiquette.”

Telepresence robot lets people be in two or more places at once

Nadine’s robot-in-arms, EDGAR, was also put through its paces at NTU’s new media showcase, complete with a rear-projection screen for its face and two highly articulated arms.

EDGAR is a tele-presence robot optimised to project the gestures of its human user. By standing in front of a specialised webcam, a user can control EDGAR remotely from anywhere in the world. The user’s face and expressions will be displayed on the robot’s face in real time, while the robot mimics the person’s upper body movements.

EDGAR can also deliver speeches by autonomously acting out a script. With an integrated webcam, he automatically tracks the people he meets to engage them in conversation, giving them informative and witty replies to their questions.

Such social robots are ideal for use at public venues, such as tourist attractions and shopping centres, as they can offer practical information to visitors.

Led by Assoc Prof Gerald Seet from the School of Mechanical & Aerospace Engineering and the BeingThere Centre at NTU, this made-in-Singapore robot represents three years of research and development.

“EDGAR is a real demonstration of how telepresence and social robots can be used for business and education,” added Prof Seet. “Telepresence provides an additional dimension to mobility. The user may project his or her physical presence at one or more locations simultaneously, meaning that geography is no longer an obstacle.

“In future, a renowned educator giving lectures or classes to large groups of people in different locations at the same time could become commonplace. Or you could attend classes or business meetings all over the world using robot proxies, saving time and travel costs.”

Given that some companies have expressed interest in the robot technologies, the next step for these NTU scientists is to look at how they can partner with industry to bring them to the market.

Ready or not, here they come!

 

Source: NTU.edu.sg – “NTU scientists unveil social and telepresence robots” 

Featured Photo Credit: NTU Robotics

Babies learn about the world by exploring how their bodies move in space, grabbing toys, pushing things off tables, and by watching and imitating what adults are doing.

But when roboticists want to teach a robot how to do a task, they typically either write code or physically move a robot’s arm or body to show it how to perform an action.

Now scientists have demonstrated that robots can “learn” much like children—by amassing data through exploration, watching a human do something, and determining how to perform that task on its own.

“You can look at this as a first step in building robots that can learn from humans in the same way that infants learn from humans,” says senior author Rajesh Rao, professor of computer science and engineering at the University of Washington.

“If you want people who don’t know anything about computer programming to be able to teach a robot, the way to do it is through demonstration—showing the robot how to clean your dishes, fold your clothes, or do household chores. But to achieve that goal, you need the robot to be able to understand those actions and perform them on their own.”

The research, which combines child development research from the Institute for Learning & Brain Sciences Lab (I-LABS) with machine learning approaches, is published in a paper in the journal PLOS ONE.

For the study, researchers developed a new probabilistic model aimed at solving a fundamental challenge in robotics: building robots that can learn new skills by watching people and imitating them.

The roboticists collaborated with Andrew Meltzoff, psychology professor and I-LABS co-director, whose research has shown that children as young as 18 months can infer the goal of an adult’s actions and develop alternate ways of reaching that goal themselves.

In one example, infants saw an adult try to pull apart a barbell-shaped toy, but the adult failed to achieve that goal because the toy was stuck together and his hands slipped off the ends. The infants watched carefully and then decided to use alternate methods— they wrapped their tiny fingers all the way around the ends and yanked especially hard — duplicating what the adult intended to do.

‘SECRET SAUCE’ FOR INNOVATION

 

[nextpagelink][/nextpagelink]

Researches at Seoul National University have designed a micro-robot that does not need a power source, such as batteries to provide electricity, in order for it to move. The design was inspired by nature, pine cone seeds, to be exact, and in fact uses humidity changes in its environment to create locomotion.

An excellent and informative article on the News Wise website provides the details about this exciting new robot and what kinds of things it could do:

The mechanism involved in plant movement is much simpler than that of animals using muscles. To generate motion, plants and some seeds — such as mimosa leaves, Venus flytraps and pine cones — simply harness the supply or deprival of water from plant tissues.

The future of bio-inspired engineering or robotics will greatly benefit from lessons learned from plants, according to a group of Seoul National University researchers.

The mechanism involved in plant movement is much simpler than that of animals using muscles. To generate motion, plants and some seeds — such as mimosa leaves, Venus flytraps and pine cones — simply harness the supply or deprival of water from plant tissues.

The future of bio-inspired engineering or robotics will greatly benefit from lessons learned from plants, according to a group of Seoul National University researchers.

The pure simplicity of the manner by which pine cones and seeds respond to changes in environmental humidity with motion is at the heart of the group’s work.

“Some seeds consist of a head that contains all its genetic information, along with a long appendage called an ‘awn’ that is responsible for locomotion — just like an animal’s sperm,” explained Ho-Young Kim, a professor in the Department of Mechanical and Aerospace Engineering at Seoul National University. “Awns are composed of two tissue layers: one that swells with humidity (active), and another that’s insensitive to humidity change (inactive).”

If environmental humidity increases, the bilayer bends from changes in length-wise swelling. Periodic humidity changes cause the bilayer to bend and unbend repeatedly — meaning that changes in environmental humidity can be converted to mechanical work.

“We mimicked the bilayer structure to make an actuator that can generate motions by using environmental humidity change,” Kim said. “Plants move slowly — one cycle of bending and unbending can take an entire day. To increase the response speed of the bilayer, we had to develop a novel way to fabricate the active layer. Its response speed increases with the surface-area-to-volume ratio of the layer because humidity can be absorbed more rapidly, so we deposited active nanoscale fibers onto an inactive layer.

To create locomotion, the team designed and attached legs, and then their tiny robot could move under its own power. But how do you make it really move?

It turns out that the team has that figured out too, and they have provided a mathematical model to help other researchers choose an optimal fast speed based on the robot’s size.

For more details like these, please see the amazing article on the newswise website.

 

Source: NewsWise.com – “Tiny Robots Inspired by Pine Cones”

 

A team at Stanford University has been working for a decade on designing an electronic fabric that can replicate the functions of actual human skin. The ultimate goal of the research is to be able to create prosthetic limbs that can send signals to the nervous system just like normal skin, which could someday enable Luke Skywalker-like prosthetic limbs.

The new plastic “skin” can detect how hard it is being pressed and generate an electric signal to deliver sensory input directly to a living brain cell.

The work takes another step toward replicating one aspect of touch, the sensory mechanism that enables us to distinguish the pressure difference between a limp handshake and a firm grip.

Zhenan Bao, a professor of chemical engineering at Stanford University, has spent a decade trying to develop a material that mimics skin’s ability to flex and heal, while also serving as the sensor net that sends touch, temperature, and pain signals to the brain. Ultimately she wants to create a flexible electronic fabric embedded with sensors that could cover a prosthetic limb and replicate some of skin’s sensory functions.

“This is the first time a flexible, skin-like material has been able to detect pressure and also transmit a signal to a component of the nervous system,” Bao says.

The heart of the technique is a two-ply plastic construct: the top layer creates a sensing mechanism and the bottom layer acts as the circuit to transport electrical signals and translate them into biochemical stimuli compatible with nerve cells. The top layer in the new work features a sensor that can detect pressure over the same range as human skin, from a light finger tap to a firm handshake.

Five years ago, researchers first described how to use plastics and rubbers as pressure sensors by measuring the natural springiness of their molecular structures. They then increased this natural pressure sensitivity by indenting a waffle pattern into the thin plastic, which further compresses the plastic’s molecular springs.

To exploit this pressure-sensing capability electronically, the team scattered billions of carbon nanotubes through the waffled plastic. Putting pressure on the plastic squeezes the nanotubes closer together and enables them to conduct electricity.

This allowed the plastic sensor to mimic human skin, which transmits pressure information to the brain as short pulses of electricity, similar to Morse code. Increasing pressure on the waffled nanotubes squeezes them even closer together, allowing more electricity to flow through the sensor, and those varied impulses are sent as short pulses to the sensing mechanism. Remove pressure, and the flow of pulses relaxes, indicating light touch. Remove all pressure and the pulses cease entirely.

COLD WATER OR HOT COFFEE

The team then hooked this pressure-sensing mechanism to the second ply of their artificial skin, a flexible electronic circuit that could carry pulses of electricity to nerve cells.

Researchers have been developing flexible electronics that can bend without breaking. For the new project, they worked with researchers from PARC, a Xerox company, which has a technology that uses an inkjet printer to deposit flexible circuits onto plastic. Covering a large surface is important to making artificial skin practical, and the PARC collaboration offered that prospect.

Finally the team had to prove that the electronic signal could be recognized by a biological neuron. It did this by adapting a technique that combines genetics and optics, called optogenetics. Researchers bioengineer cells to make them sensitive to specific frequencies of light, then use light pulses to switch cells, or the processes being carried on inside them, on and off.

For the new experiment, reported in the journal Science, team members engineered a line of neurons to simulate a portion of the human nervous system. They translated the electronic pressure signals from the artificial skin into light pulses, which activated the neurons, proving that the artificial skin could generate a sensory output compatible with nerve cells.

Optogenetics was only used as an experimental proof of concept—other methods of stimulating nerves are likely to be used in real prosthetic devices. The team has already shown that direct stimulation of neurons with electrical pulses is possible.

Bao’s team envisions developing different sensors to replicate, for instance, the ability to distinguish corduroy versus silk, or a cold glass of water from a hot cup of coffee—but this will take time. There are six types of biological sensing mechanisms in the human hand, and the experiment reports success in just one of them.

But the current two-ply approach means the team can add sensations as it develops new mechanisms. And the inkjet printing fabrication process suggests how a network of sensors could be deposited over a flexible layer and folded over a prosthetic hand.

“We have a lot of work to take this from experimental to practical applications,” Bao says. “But after spending many years in this work, I now see a clear path where we can take our artificial skin.”

 

Reproduced from Futurity.org “FAKE SKIN SENDS PRESSURE SIGNALS TO BRAIN CELLS” in full with a new title, introductory paragraph, and additional article links removed under  the Attribution 4.0 International license.

Featured Photo Credit: Bao Lab

 

Back in 2013, researchers at the Wyss Institute at Harvard created a robotic bee that could take off, hover and fly along a preset pathway.  Although the bee has to be tethered for power and navigational computing, researchers hope to conquer that limitation sometime in the future.

And now, a great article on Popular Science reports that the RoboBees have a new trick, they can swim:

The bees are so small and light that the surface tension of the water prevents them from delicately sinking into a glass. But the researchers found that if the bees cannonball into the water, they turn into very happy swimmers. As it turns out, moving through the air and moving through water aren’t that different for the RoboBees—they simply flap their wings more slowly underwater.

This great video from the IEEE Spectrum YouTube channel shows a RoboBee in action, both flying and swimming:

The PopSci article reports that RoboBees will not be replacing or assisting real bees with the task of pollinating flowers any time soon, saying:

For now, the researchers are focused on expanding the RoboBee’s basic capabilities, including new tricks like swimming. And even if we got to a point where RoboBees were able to pollinate crops, the robotic option would remain far more expensive than the natural, biological source of inspiration.

So, although RoboBees are pretty limited in what they can do now, we have to agree with the final conclusion of the article, “But they’re still incredibly cool.”

 

Source: PopSci.com – “FLYING ROBOT BEES CAN NOW SWIM, TOO”

Featured Photo Credit: Wyss Institute/Harvard