Tag Archives: reliable

#434643 Sensors and Machine Learning Are Giving ...

According to some scientists, humans really do have a sixth sense. There’s nothing supernatural about it: the sense of proprioception tells you about the relative positions of your limbs and the rest of your body. Close your eyes, block out all sound, and you can still use this internal “map” of your external body to locate your muscles and body parts – you have an innate sense of the distances between them, and the perception of how they’re moving, above and beyond your sense of touch.

This sense is invaluable for allowing us to coordinate our movements. In humans, the brain integrates senses including touch, heat, and the tension in muscle spindles to allow us to build up this map.

Replicating this complex sense has posed a great challenge for roboticists. We can imagine simulating the sense of sight with cameras, sound with microphones, or touch with pressure-pads. Robots with chemical sensors could be far more accurate than us in smell and taste, but building in proprioception, the robot’s sense of itself and its body, is far more difficult, and is a large part of why humanoid robots are so tricky to get right.

Simultaneous localization and mapping (SLAM) software allows robots to use their own senses to build up a picture of their surroundings and environment, but they’d need a keen sense of the position of their own bodies to interact with it. If something unexpected happens, or in dark environments where primary senses are not available, robots can struggle to keep track of their own position and orientation. For human-robot interaction, wearable robotics, and delicate applications like surgery, tiny differences can be extremely important.

Piecemeal Solutions
In the case of hard robotics, this is generally solved by using a series of strain and pressure sensors in each joint, which allow the robot to determine how its limbs are positioned. That works fine for rigid robots with a limited number of joints, but for softer, more flexible robots, this information is limited. Roboticists are faced with a dilemma: a vast, complex array of sensors for every degree of freedom in the robot’s movement, or limited skill in proprioception?

New techniques, often involving new arrays of sensory material and machine-learning algorithms to fill in the gaps, are starting to tackle this problem. Take the work of Thomas George Thuruthel and colleagues in Pisa and San Diego, who draw inspiration from the proprioception of humans. In a new paper in Science Robotics, they describe the use of soft sensors distributed through a robotic finger at random. This placement is much like the constant adaptation of sensors in humans and animals, rather than relying on feedback from a limited number of positions.

The sensors allow the soft robot to react to touch and pressure in many different locations, forming a map of itself as it contorts into complicated positions. The machine-learning algorithm serves to interpret the signals from the randomly-distributed sensors: as the finger moves around, it’s observed by a motion capture system. After training the robot’s neural network, it can associate the feedback from the sensors with the position of the finger detected in the motion-capture system, which can then be discarded. The robot observes its own motions to understand the shapes that its soft body can take, and translate them into the language of these soft sensors.

“The advantages of our approach are the ability to predict complex motions and forces that the soft robot experiences (which is difficult with traditional methods) and the fact that it can be applied to multiple types of actuators and sensors,” said Michael Tolley of the University of California San Diego. “Our method also includes redundant sensors, which improves the overall robustness of our predictions.”

The use of machine learning lets the roboticists come up with a reliable model for this complex, non-linear system of motions for the actuators, something difficult to do by directly calculating the expected motion of the soft-bot. It also resembles the human system of proprioception, built on redundant sensors that change and shift in position as we age.

In Search of a Perfect Arm
Another approach to training robots in using their bodies comes from Robert Kwiatkowski and Hod Lipson of Columbia University in New York. In their paper “Task-agnostic self-modeling machines,” also recently published in Science Robotics, they describe a new type of robotic arm.

Robotic arms and hands are getting increasingly dexterous, but training them to grasp a large array of objects and perform many different tasks can be an arduous process. It’s also an extremely valuable skill to get right: Amazon is highly interested in the perfect robot arm. Google hooked together an array of over a dozen robot arms so that they could share information about grasping new objects, in part to cut down on training time.

Individually training a robot arm to perform every individual task takes time and reduces the adaptability of your robot: either you need an ML algorithm with a huge dataset of experiences, or, even worse, you need to hard-code thousands of different motions. Kwiatkowski and Lipson attempt to overcome this by developing a robotic system that has a “strong sense of self”: a model of its own size, shape, and motions.

They do this using deep machine learning. The robot begins with no prior knowledge of its own shape or the underlying physics of its motion. It then repeats a series of a thousand random trajectories, recording the motion of its arm. Kwiatkowski and Lipson compare this to a baby in the first year of life observing the motions of its own hands and limbs, fascinated by picking up and manipulating objects.

Again, once the robot has trained itself to interpret these signals and build up a robust model of its own body, it’s ready for the next stage. Using that deep-learning algorithm, the researchers then ask the robot to design strategies to accomplish simple pick-up and place and handwriting tasks. Rather than laboriously and narrowly training itself for each individual task, limiting its abilities to a very narrow set of circumstances, the robot can now strategize how to use its arm for a much wider range of situations, with no additional task-specific training.

Damage Control
In a further experiment, the researchers replaced part of the arm with a “deformed” component, intended to simulate what might happen if the robot was damaged. The robot can then detect that something’s up and “reconfigure” itself, reconstructing its self-model by going through the training exercises once again; it was then able to perform the same tasks with only a small reduction in accuracy.

Machine learning techniques are opening up the field of robotics in ways we’ve never seen before. Combining them with our understanding of how humans and other animals are able to sense and interact with the world around us is bringing robotics closer and closer to becoming truly flexible and adaptable, and, eventually, omnipresent.

But before they can get out and shape the world, as these studies show, they will need to understand themselves.

Image Credit: jumbojan / Shutterstock.com Continue reading

Posted in Human Robots

#434611 This Week’s Awesome Stories From ...

The Rise of the Robot Reporter
Jaclyn Paiser | The New York Times
“In addition to covering company earnings for Bloomberg, robot reporters have been prolific producers of articles on minor league baseball for The Associated Press, high school football for The Washington Post and earthquakes for The Los Angeles Times.”

Penny-Sized Ionocraft Flies With No Moving Parts
Evan Ackerman | IEEE Spectrum
“Electrohydrodynamic (EHD) thrusters, sometimes called ion thrusters, use a high strength electric field to generate a plasma of ionized air. …Magical, right? No moving parts, completely silent, and it flies!”

Making New Drugs With a Dose of Artificial Intelligence
Cade Metz | The New York Times
“…DeepMind won the [protein folding] competition by a sizable margin—it improved the prediction accuracy nearly twice as much as experts expected from the contest winner. DeepMind’s victory showed how the future of biochemical research will increasingly be driven by machines and the people who oversee those machines.”

Nano-Switches Made Out of Graphene Could Make Our Devices Even Smaller
Emerging Technology From the arXiv | MIT Technology Review
“For the first time, physicists have built reliable, efficient graphene nanomachines that can be fabricated on silicon chips. They could lead to even greater miniaturization.”

The Problem With Big DNA
Sarah Zhang | The Atlantic
“It took researchers days to search through thousands of genome sequences. Now it takes just a few seconds. …As sequencing becomes more common, the number of publicly available bacterial and viral genomes has doubled. At the rate this work is going, within a few years multiple millions of searchable pathogen genomes will be available—a library of DNA and disease, spread the world over.”

Fire (and Lots of It): Berkeley Researcher on the Only Way to Fix Cryptocurrency
Dan Goodin | Ars Technica
“Weaver said, there’s no basis for the promises that cryptocurrencies’ decentralized structure and blockchain basis will fundamentally transform commerce or economics. That means the sky-high valuations spawned by those false promises are completely unjustified. …To support that conclusion, Weaver recited an oft-repeated list of supposed benefits of cryptocurrencies and explained why, after closer scrutiny, he believed them to be myths.”

Image Credit: Katya Havok / Shutterstock.com Continue reading

Posted in Human Robots

#434559 Can AI Tell the Difference Between a ...

Scarcely a day goes by without another headline about neural networks: some new task that deep learning algorithms can excel at, approaching or even surpassing human competence. As the application of this approach to computer vision has continued to improve, with algorithms capable of specialized recognition tasks like those found in medicine, the software is getting closer to widespread commercial use—for example, in self-driving cars. Our ability to recognize patterns is a huge part of human intelligence: if this can be done faster by machines, the consequences will be profound.

Yet, as ever with algorithms, there are deep concerns about their reliability, especially when we don’t know precisely how they work. State-of-the-art neural networks will confidently—and incorrectly—classify images that look like television static or abstract art as real-world objects like school-buses or armadillos. Specific algorithms could be targeted by “adversarial examples,” where adding an imperceptible amount of noise to an image can cause an algorithm to completely mistake one object for another. Machine learning experts enjoy constructing these images to trick advanced software, but if a self-driving car could be fooled by a few stickers, it might not be so fun for the passengers.

These difficulties are hard to smooth out in large part because we don’t have a great intuition for how these neural networks “see” and “recognize” objects. The main insight analyzing a trained network itself can give us is a series of statistical weights, associating certain groups of points with certain objects: this can be very difficult to interpret.

Now, new research from UCLA, published in the journal PLOS Computational Biology, is testing neural networks to understand the limits of their vision and the differences between computer vision and human vision. Nicholas Baker, Hongjing Lu, and Philip J. Kellman of UCLA, alongside Gennady Erlikhman of the University of Nevada, tested a deep convolutional neural network called VGG-19. This is state-of-the-art technology that is already outperforming humans on standardized tests like the ImageNet Large Scale Visual Recognition Challenge.

They found that, while humans tend to classify objects based on their overall (global) shape, deep neural networks are far more sensitive to the textures of objects, including local color gradients and the distribution of points on the object. This result helps explain why neural networks in image recognition make mistakes that no human ever would—and could allow for better designs in the future.

In the first experiment, a neural network was trained to sort images into 1 of 1,000 different categories. It was then presented with silhouettes of these images: all of the local information was lost, while only the outline of the object remained. Ordinarily, the trained neural net was capable of recognizing these objects, assigning more than 90% probability to the correct classification. Studying silhouettes, this dropped to 10%. While human observers could nearly always produce correct shape labels, the neural networks appeared almost insensitive to the overall shape of the images. On average, the correct object was ranked as the 209th most likely solution by the neural network, even though the overall shapes were an exact match.

A particularly striking example arose when they tried to get the neural networks to classify glass figurines of objects they could already recognize. While you or I might find it easy to identify a glass model of an otter or a polar bear, the neural network classified them as “oxygen mask” and “can opener” respectively. By presenting glass figurines, where the texture information that neural networks relied on for classifying objects is lost, the neural network was unable to recognize the objects by shape alone. The neural network was similarly hopeless at classifying objects based on drawings of their outline.

If you got one of these right, you’re better than state-of-the-art image recognition software. Image Credit: Nicholas Baker, Hongjing Lu, Gennady Erlikhman, Philip J. Kelman. “Deep convolutional networks do not classify based on global object shape.” Plos Computational Biology. 12/7/18. / CC BY 4.0
When the neural network was explicitly trained to recognize object silhouettes—given no information in the training data aside from the object outlines—the researchers found that slight distortions or “ripples” to the contour of the image were again enough to fool the AI, while humans paid them no mind.

The fact that neural networks seem to be insensitive to the overall shape of an object—relying instead on statistical similarities between local distributions of points—suggests a further experiment. What if you scrambled the images so that the overall shape was lost but local features were preserved? It turns out that the neural networks are far better and faster at recognizing scrambled versions of objects than outlines, even when humans struggle. Students could classify only 37% of the scrambled objects, while the neural network succeeded 83% of the time.

Humans vastly outperform machines at classifying object (a) as a bear, while the machine learning algorithm has few problems classifying the bear in figure (b). Image Credit: Nicholas Baker, Hongjing Lu, Gennady Erlikhman, Philip J. Kelman. “Deep convolutional networks do not classify based on global object shape.” Plos Computational Biology. 12/7/18. / CC BY 4.0
“This study shows these systems get the right answer in the images they were trained on without considering shape,” Kellman said. “For humans, overall shape is primary for object recognition, and identifying images by overall shape doesn’t seem to be in these deep learning systems at all.”

Naively, one might expect that—as the many layers of a neural network are modeled on connections between neurons in the brain and resemble the visual cortex specifically—the way computer vision operates must necessarily be similar to human vision. But this kind of research shows that, while the fundamental architecture might resemble that of the human brain, the resulting “mind” operates very differently.

Researchers can, increasingly, observe how the “neurons” in neural networks light up when exposed to stimuli and compare it to how biological systems respond to the same stimuli. Perhaps someday it might be possible to use these comparisons to understand how neural networks are “thinking” and how those responses differ from humans.

But, as yet, it takes a more experimental psychology to probe how neural networks and artificial intelligence algorithms perceive the world. The tests employed against the neural network are closer to how scientists might try to understand the senses of an animal or the developing brain of a young child rather than a piece of software.

By combining this experimental psychology with new neural network designs or error-correction techniques, it may be possible to make them even more reliable. Yet this research illustrates just how much we still don’t understand about the algorithms we’re creating and using: how they tick, how they make decisions, and how they’re different from us. As they play an ever-greater role in society, understanding the psychology of neural networks will be crucial if we want to use them wisely and effectively—and not end up missing the woods for the trees.

Image Credit: Irvan Pratama / Shutterstock.com Continue reading

Posted in Human Robots

#433954 The Next Great Leap Forward? Combining ...

The Internet of Things is a popular vision of objects with internet connections sending information back and forth to make our lives easier and more comfortable. It’s emerging in our homes, through everything from voice-controlled speakers to smart temperature sensors. To improve our fitness, smart watches and Fitbits are telling online apps how much we’re moving around. And across entire cities, interconnected devices are doing everything from increasing the efficiency of transport to flood detection.

In parallel, robots are steadily moving outside the confines of factory lines. They’re starting to appear as guides in shopping malls and cruise ships, for instance. As prices fall and the artificial intelligence (AI) and mechanical technology continues to improve, we will get more and more used to them making independent decisions in our homes, streets and workplaces.

Here lies a major opportunity. Robots become considerably more capable with internet connections. There is a growing view that the next evolution of the Internet of Things will be to incorporate them into the network, opening up thrilling possibilities along the way.

Home Improvements
Even simple robots become useful when connected to the internet—getting updates about their environment from sensors, say, or learning about their users’ whereabouts and the status of appliances in the vicinity. This lets them lend their bodies, eyes, and ears to give an otherwise impersonal smart environment a user-friendly persona. This can be particularly helpful for people at home who are older or have disabilities.

We recently unveiled a futuristic apartment at Heriot-Watt University to work on such possibilities. One of a few such test sites around the EU, our whole focus is around people with special needs—and how robots can help them by interacting with connected devices in a smart home.

Suppose a doorbell rings that has smart video features. A robot could find the person in the home by accessing their location via sensors, then tell them who is at the door and why. Or it could help make video calls to family members or a professional carer—including allowing them to make virtual visits by acting as a telepresence platform.

Equally, it could offer protection. It could inform them the oven has been left on, for example—phones or tablets are less reliable for such tasks because they can be misplaced or not heard.

Similarly, the robot could raise the alarm if its user appears to be in difficulty.Of course, voice-assistant devices like Alexa or Google Home can offer some of the same services. But robots are far better at moving, sensing and interacting with their environment. They can also engage their users by pointing at objects or acting more naturally, using gestures or facial expressions. These “social abilities” create bonds which are crucially important for making users more accepting of the support and making it more effective.

To help incentivize the various EU test sites, our apartment also hosts the likes of the European Robotic League Service Robot Competition—a sort of Champions League for robots geared to special needs in the home. This brought academics from around Europe to our laboratory for the first time in January this year. Their robots were tested in tasks like welcoming visitors to the home, turning the oven off, and fetching objects for their users; and a German team from Koblenz University won with a robot called Lisa.

Robots Offshore
There are comparable opportunities in the business world. Oil and gas companies are looking at the Internet of Things, for example; experimenting with wireless sensors to collect information such as temperature, pressure, and corrosion levels to detect and possibly predict faults in their offshore equipment.

In the future, robots could be alerted to problem areas by sensors to go and check the integrity of pipes and wells, and to make sure they are operating as efficiently and safely as possible. Or they could place sensors in parts of offshore equipment that are hard to reach, or help to calibrate them or replace their batteries.

The likes of the ORCA Hub, a £36m project led by the Edinburgh Centre for Robotics, bringing together leading experts and over 30 industry partners, is developing such systems. The aim is to reduce the costs and the risks of humans working in remote hazardous locations.

ORCA tests a drone robot. ORCA
Working underwater is particularly challenging, since radio waves don’t move well under the sea. Underwater autonomous vehicles and sensors usually communicate using acoustic waves, which are many times slower (1,500 meters a second vs. 300m meters a second for radio waves). Acoustic communication devices are also much more expensive than those used above the water.

This academic project is developing a new generation of low-cost acoustic communication devices, and trying to make underwater sensor networks more efficient. It should help sensors and underwater autonomous vehicles to do more together in future—repair and maintenance work similar to what is already possible above the water, plus other benefits such as helping vehicles to communicate with one another over longer distances and tracking their location.

Beyond oil and gas, there is similar potential in sector after sector. There are equivalents in nuclear power, for instance, and in cleaning and maintaining the likes of bridges and buildings. My colleagues and I are also looking at possibilities in areas such as farming, manufacturing, logistics, and waste.

First, however, the research sectors around the Internet of Things and robotics need to properly share their knowledge and expertise. They are often isolated from one another in different academic fields. There needs to be more effort to create a joint community, such as the dedicated workshops for such collaboration that we organized at the European Robotics Forum and the IoT Week in 2017.

To the same end, industry and universities need to look at setting up joint research projects. It is particularly important to address safety and security issues—hackers taking control of a robot and using it to spy or cause damage, for example. Such issues could make customers wary and ruin a market opportunity.

We also need systems that can work together, rather than in isolated applications. That way, new and more useful services can be quickly and effectively introduced with no disruption to existing ones. If we can solve such problems and unite robotics and the Internet of Things, it genuinely has the potential to change the world.

Mauro Dragone, Assistant Professor, Cognitive Robotics, Multiagent systems, Internet of Things, Heriot-Watt University

This article is republished from The Conversation under a Creative Commons license. Read the original article.

Image Credit: Willyam Bradberry/Shutterstock.com Continue reading

Posted in Human Robots

#433852 How Do We Teach Autonomous Cars To Drive ...

Autonomous vehicles can follow the general rules of American roads, recognizing traffic signals and lane markings, noticing crosswalks and other regular features of the streets. But they work only on well-marked roads that are carefully scanned and mapped in advance.

Many paved roads, though, have faded paint, signs obscured behind trees and unusual intersections. In addition, 1.4 million miles of U.S. roads—one-third of the country’s public roadways—are unpaved, with no on-road signals like lane markings or stop-here lines. That doesn’t include miles of private roads, unpaved driveways or off-road trails.

What’s a rule-following autonomous car to do when the rules are unclear or nonexistent? And what are its passengers to do when they discover their vehicle can’t get them where they’re going?

Accounting for the Obscure
Most challenges in developing advanced technologies involve handling infrequent or uncommon situations, or events that require performance beyond a system’s normal capabilities. That’s definitely true for autonomous vehicles. Some on-road examples might be navigating construction zones, encountering a horse and buggy, or seeing graffiti that looks like a stop sign. Off-road, the possibilities include the full variety of the natural world, such as trees down over the road, flooding and large puddles—or even animals blocking the way.

At Mississippi State University’s Center for Advanced Vehicular Systems, we have taken up the challenge of training algorithms to respond to circumstances that almost never happen, are difficult to predict and are complex to create. We seek to put autonomous cars in the hardest possible scenario: driving in an area the car has no prior knowledge of, with no reliable infrastructure like road paint and traffic signs, and in an unknown environment where it’s just as likely to see a cactus as a polar bear.

Our work combines virtual technology and the real world. We create advanced simulations of lifelike outdoor scenes, which we use to train artificial intelligence algorithms to take a camera feed and classify what it sees, labeling trees, sky, open paths and potential obstacles. Then we transfer those algorithms to a purpose-built all-wheel-drive test vehicle and send it out on our dedicated off-road test track, where we can see how our algorithms work and collect more data to feed into our simulations.

Starting Virtual
We have developed a simulator that can create a wide range of realistic outdoor scenes for vehicles to navigate through. The system generates a range of landscapes of different climates, like forests and deserts, and can show how plants, shrubs and trees grow over time. It can also simulate weather changes, sunlight and moonlight, and the accurate locations of 9,000 stars.

The system also simulates the readings of sensors commonly used in autonomous vehicles, such as lidar and cameras. Those virtual sensors collect data that feeds into neural networks as valuable training data.

Simulated desert, meadow and forest environments generated by the Mississippi State University Autonomous Vehicle Simulator. Chris Goodin, Mississippi State University, Author provided.
Building a Test Track
Simulations are only as good as their portrayals of the real world. Mississippi State University has purchased 50 acres of land on which we are developing a test track for off-road autonomous vehicles. The property is excellent for off-road testing, with unusually steep grades for our area of Mississippi—up to 60 percent inclines—and a very diverse population of plants.

We have selected certain natural features of this land that we expect will be particularly challenging for self-driving vehicles, and replicated them exactly in our simulator. That allows us to directly compare results from the simulation and real-life attempts to navigate the actual land. Eventually, we’ll create similar real and virtual pairings of other types of landscapes to improve our vehicle’s capabilities.

A road washout, as seen in real life, left, and in simulation. Chris Goodin, Mississippi State University, Author provided.
Collecting More Data
We have also built a test vehicle, called the Halo Project, which has an electric motor and sensors and computers that can navigate various off-road environments. The Halo Project car has additional sensors to collect detailed data about its actual surroundings, which can help us build virtual environments to run new tests in.

The Halo Project car can collect data about driving and navigating in rugged terrain. Beth Newman Wynn, Mississippi State University, Author provided.
Two of its lidar sensors, for example, are mounted at intersecting angles on the front of the car so their beams sweep across the approaching ground. Together, they can provide information on how rough or smooth the surface is, as well as capturing readings from grass and other plants and items on the ground.

Lidar beams intersect, scanning the ground in front of the vehicle. Chris Goodin, Mississippi State University, Author provided
We’ve seen some exciting early results from our research. For example, we have shown promising preliminary results that machine learning algorithms trained on simulated environments can be useful in the real world. As with most autonomous vehicle research, there is still a long way to go, but our hope is that the technologies we’re developing for extreme cases will also help make autonomous vehicles more functional on today’s roads.

Matthew Doude, Associate Director, Center for Advanced Vehicular Systems; Ph.D. Student in Industrial and Systems Engineering, Mississippi State University; Christopher Goodin, Assistant Research Professor, Center for Advanced Vehicular Systems, Mississippi State University, and Daniel Carruth, Assistant Research Professor and Associate Director for Human Factors and Advanced Vehicle System, Center for Advanced Vehicular Systems, Mississippi State University

This article is republished from The Conversation under a Creative Commons license. Read the original article.

Photo provided for The Conversation by Matthew Goudin / CC BY ND Continue reading

Posted in Human Robots