Connect with us

Robotics

Advancements in Human-Robot-Computer Research

Published

 on

The automated experimental facility, called the Intelligent Towing Tank (ITT), conducted around 100,000 total experiments in its first year of operation. What would normally take a PhD student to complete within five years of experiments, the ITT was able to do within weeks. The development of the ITT in the MIT Sea Grant Hydrodynamics Laboratory takes us further into the area of human-robot-computer research. 

The ITT automatically and adaptively performs, analyzes, and designs experiments. The experiments are focused on exploring vortex-induced vibrations (VIVs). VIVs are important for engineering offshore ocean structures such as marine drilling risers, which are responsible for connecting underwater oil wells to the surface. With VIVs, there are a high number of parameters involved.

The ITT is guided by active learning, and it conducts a series of experiments. Within the experiments, the parameters for each next experiment are selected by a computer. The system uses an “explore-and-exploit” methodology, which helps greatly reduce the number of experiments required for mapping and exploring the complex aspects of VIVs.

PhD candidate Dixia Fan began the project while searching for a way to reduce the thousand or so experiments that needed to be conducted by hand. That led to the development of the ITT system. 

A paper was published last month in the journal Science Robotics. 

Fan is now a postdoc, and the project was worked on by a team of researchers from the MIT Sea Grant College Program and MIT’s Department of Mechanical Engineering, École Normale Supérieure de Rennes, and Brown University. The new project showcases the type of cooperation that can take place between humans, computers, and robots in order to make scientific discoveries at a faster pace.

The ITT is a 33-foot tank, and it works without interruption or suspension. The researchers would like to see the system used in a variety of different disciplines, which could lead to the creation of new models in nonlinear systems. 

The ITT allowed Fan and his collaborators to explore a wider parametric space. “If we performed traditional techniques on the problem we study, it would take 950 years to finish the experiment,” he explained. 

In order to shorten the long time it would take for the experiment, Fan and the team integrated a Gaussian process regression learning algorithm into the ITT. By doing this, the researchers were able to reduce the amount of experiments needed, down to a few thousand. 

The robotic system is capable of automatically conducting an initial sequence of experiments. It then takes partial control over the parameters of the next experiment. 

Fan was awarded an MIT Mechanical Engineering de Florez Award for “Outstanding Ingenuity and Creative Judgement” in the development of the ITT. 

According to Michael Triantafyllou, Henry L. and Grace Doherty Professor in Ocean Science and Engineering, and also Fan’s doctoral advisor, “Dixia’s design of the Intelligent Towing Tank is an outstanding example of using novel methods to reinvigorate mature fields.”

Triantafyllou was a co-author on the paper and the director of the MIT Sea Grant College Program. 

“MIT Sea Grant has committed resources and funded projects using deep-learning methods in ocean-related problems for several years that are already paying off,” he said.

MIT is funded by the National Oceanic and Atmospheric Administration and administered by the National Sea Grant Program. It is a federal-institute partnership that combines research and engineering at MIT to help tackle ocean-related issues, 

Other contributors to the paper include George Karniadakis from Brown University, affiliated with MIT Sea Grant; Gurvan Jodin from ENS Rennes; MIT PhD candidate in mechanical engineering Yu Ma; and Thomas Consi, Luca Bonfiglio, and Lily Keyes from MIT Sea Grant.

 

Spread the love

Robotics

Researchers Develop New Theory on Animal Sensing Which Could be Used in Robotics

Published

 on

All animals, from insects to humans, rely on their senses as some of the most important tools for survival. Sensory organs like eyes, ears and noses are used while searching for food or detecting threats. However, the actual position and orientation of the sense organs are not intuitive, and the currently deployed theories are not able to make predictions about the position and orientation. 

That is now changing with new developments coming out of Northwestern University. A team of researchers has come up with a new theory that is in fact able to predict the movement of an animal’s sensory organs, specifically when that animal is searching for something important like food. 

The research was published Sept. 22 in the journal eLife

Energy-Constrained Proportional Betting

The newly developed theory, termed energy-constrained proportional betting, was applied to four different species of animals, and it involved three different senses, including vision and smell. The team demonstrated how the theory could predict the observed sensing behavior of each animal.

This new theory could have implications within the field of robotics, possibly improving robot performance when it comes to collecting information. It could also make a difference in the development of autonomous vehicles, specifically improving their response to uncertainty. 

Malcolm A. Maclver led the promising research. He is also a professor of biomedical and mechanical engineering in Northwestern’s McCormick School of Engineering, as well as a professor of neurobiology in the Weinberg College of Arts and Sciences. 

“Animals make their living through movement,” Maclver said. “To find food and mates and to identify threats, they need to move. Our theory provides insight into how animals gamble on how much energy to expend to get the useful information they need.”

The new theory sheds light into the different motions of sensory organs, and the resulting algorithm generated simulated sensory organ movements. These generated movements agreed with the real-life sensory organ movements from fish, mammals and insects. 

Chen Chen is a Ph.D student in Maclver’s lab and the first author, while Todd D. Murphey, professor of mechanical engineering at McCormick, is a co-author. 

Gambling Energy

Movement costs a lot of energy for animals, and they spend that energy while gambling that the locations they are moving to will be informative. The amount of food-derived energy that they are willing to spend is proportional to the expected value of those locations, according to the researchers.

“While most theories predict how an animal will behave when it largely already knows where something is, ours is a prediction for when the animal knowns very little — a situation in life and critical to survival,” Murphey says. 

The research focused on the gymnotid electric fish from South America, and experiments were performed in Maclver’s lab. It was not all new data however, as the team utilized past published datasets on the blind eastern American mole, the American cockroach and the hummingbird hawkmoth. 

The three senses that were focused on include electrosense with the electric fish, vision with the moth and smell with the mole and roach.

The newly-developed theory leads to more energy and time being preserved when moving around to gather information. At the same time, there is enough information to guide tracking and other exploratory behaviors common among animals. 

“When you look at a cat’s ears, you’ll often see them swiveling to sample different locations of space,” Maclver said. “This is an example of how animals are constantly positioning their sensory organs to help them absorb information from the environment. It turns out there is a lot going on below the surface in the movement of sense organs like ears and eyes and noses.”

 

Spread the love
Continue Reading

Robotics

Human Brain’s Light Processing Ability Could Lead to Better Robotic Sensing

Published

 on

The human brain often serves as inspiration for artificial intelligence (AI), and that is the case once again as a team of Army researchers has managed to improve robotic sensing by looking at how the human brain processes bright and contrasting light. The new development can help lead to the collaboration between autonomous agents and humans.

According to the researchers, it is important for machine sensing to be effective across changing environments, which leads to developments in autonomy.

The research was published in the Journal of Vision

100,000-to-1 Display Capability

Andre Harrison is a researcher at the U.S. Army Combat Capabilities Development Command’s Army Research Laboratory. 

“When we develop machine learning algorithms, real-world images are usually compressed to a narrower range, as a cellphone camera does, in a process called tone mapping,” Harrison said. “This can contribute to the brittleness of machine vision algorithms because they are based on artificial images that don’t quite match the patterns we see in the real world.” 

The team of researchers developed a system with 100,000-to-1 display capability, which enabled them to gain insight into the brain’s computing process in the real-world. According to Harrison, this allowed the team to implement biological resilience into sensors.

The current vision algorithms still have a long way to go before becoming ideal. This has to do with the limited range in luminance, at around 100-to-1 ratio, due to the algorithms being based on human and animal studies with computer monitors. The 100-to-1 ratio is less-than-ideal in the real world, where the variation can go all the way up to 100,000-to-1. This high ratio is termed high dynamic range, or HDR.

Dr. Chou Po Hung is an Army researcher. 

“Changes and significant variations in light can challenge Army systems — drones flying under a forest canopy could be confused by reflectance changes when wind blows through the leaves, or autonomous vehicles driving on rough terrain might not recognize potholes nor other obstacles because the lighting conditions are slightly different from those of which their vision algorithms were trained,” Hung said. 

The Human Brain’s Compressing Capability

The human brain is capable of automatically compressing the 100,000-to-1 input into a narrower range, and this is what allows humans to interpret shape. The team of researchers set out to understand this process by studying early visual processing under HDR. The team looked toward simple features such as HDR luminance. 

“The brain has more than 30 visual areas, and we still have only a rudimentary understanding of how these areas process the eye’s image into an understanding of 3D shape,” Hung continued. “Our results with HDR luminance studies, based on human behavior and scalp recordings, show just how little we truly know about how to bridge the gap from laboratory to real-world environments. But, these findings break us out of that box, showing that our previous assumptions from standard computer monitors have limited ability to generalize to the real world, and they reveal principles that can guide our modeling toward the correct mechanisms.” 

By discovering how light and contrast edges interact in the brain’s visual representation, algorithms will be more effective at reconstructing the 3D world under real-world luminance. When estimating 3D shape from 2D information, there are always ambiguities, but this new discovery allows for them to be corrected.

“Through millions of years of evolution, our brains have evolved effective shortcuts for reconstructing 3D from 2D information,” Hung said. “It’s a decades-old problem that continues to challenge machine vision scientists, even with the recent advances in AI.”

The team’s discovery is also important for the development of AI-devices like radar and remote speech understanding, which utilize wide dynamic range sensing. 

“The issue of dynamic range is not just a sensing problem,” Hung said. “It may also be a more general problem in brain computation because individual neurons have tens of thousands of inputs. How do you build algorithms and architectures that can listen to the right inputs across different contexts? We hope that, by working on this problem at a sensory level, we can confirm that we are on the right track, so that we can have the right tools when we build more complex Als.” 

Spread the love
Continue Reading

Robotics

Researchers Develop First Microscopic Robots Capable of “Walking”

Published

 on

Image: Cornell University

In what is a breakthrough within the field of robotics, researchers have created the first microscopic robots capable of being controlled through their incorporated semiconductor components. The robots are able to “walk” with only standard electronic signals.

The microscopic robots are the size of a paramecium, and they will act as the foundation for further projects. Some of those could include complex versions with silicon-based intelligence, the mass production of such robots, and versions capable of moving through human tissue and blood.

The work was a collaboration led by Cornell University, which included Itai Cohen, professor of physics. Other members of the team included Paul McEuen, the John A. Newman Professor of Physical Science, as well as Marc Miskin, assistant professor at the University of Pennsylvania.

Their work was published Aug. 26 in Nature, titled “Electronically Integrated, Mass-Manufactured, Microscopic Robots.”

Previous Nanoscale Projects

The newly developed microscopic robots were built upon previous work done by Cohen and McEuen. Some of their previous nanoscale projects involved microscopic sensors and graphene-based origami machines. 

The new microscopic robots are approximately 5 microns thick, 40 microns wide, and anywhere between 40 to 70 microns in length. One micron is just one-millionth of a meter. 

Each robot has a simple circuit that is made from silicon photovoltaics and four electrochemical actuators. The silicon photovoltaics act as the torso and brain, while the electrochemical actuators act as the legs.

Controlling the Microscopic Robots

In order to control the robots, the researchers flash laser pulses at different photovoltaics, with each one making up a seperate set of legs. The robots are able to walk when the laser is toggled back and forth between the front and back photovoltaics.

The robots only operate at a low voltage of 200 millivolts, and they run on just 10 nanowatts of power. The material is strong for such a small object, and they are able to be fabricated parallel since they are constructed with standard lithographic processes. On just a four inch silicon wafer, there can be around 1 million bots.

The team is now looking at how to make the robots more powerful through electronics and onboard computation. 

It is possible that future versions of microrobots could act in swarms and complete tasks like restructuring materials, suturing blood vessels, or be sent to the human brain. 

“Controlling a tiny robot is maybe as close as you can come to shrinking yourself down. I think machines like these are going to take us into all kinds of amazing worlds that are too small to see,” said Miskin.

“This research breakthrough provides exciting scientific opportunity for investigating new questions relevant to the physics of active matter and may ultimately lead to futuristic robotic materials,” said Sam Stanton. 

Stanton is program manager for the Army Research Office, which supported the microscopic robot research. 

A video of Itai Cohen explaining the technology can be found here.

Spread the love
Continue Reading