Tag Archives: signal

#437182 MIT’s Tiny New Brain Chip Aims for AI ...

The human brain operates on roughly 20 watts of power (a third of a 60-watt light bulb) in a space the size of, well, a human head. The biggest machine learning algorithms use closer to a nuclear power plant’s worth of electricity and racks of chips to learn.

That’s not to slander machine learning, but nature may have a tip or two to improve the situation. Luckily, there’s a branch of computer chip design heeding that call. By mimicking the brain, super-efficient neuromorphic chips aim to take AI off the cloud and put it in your pocket.

The latest such chip is smaller than a piece of confetti and has tens of thousands of artificial synapses made out of memristors—chip components that can mimic their natural counterparts in the brain.

In a recent paper in Nature Nanotechnology, a team of MIT scientists say their tiny new neuromorphic chip was used to store, retrieve, and manipulate images of Captain America’s Shield and MIT’s Killian Court. Whereas images stored with existing methods tended to lose fidelity over time, the new chip’s images remained crystal clear.

“So far, artificial synapse networks exist as software. We’re trying to build real neural network hardware for portable artificial intelligence systems,” Jeehwan Kim, associate professor of mechanical engineering at MIT said in a press release. “Imagine connecting a neuromorphic device to a camera on your car, and having it recognize lights and objects and make a decision immediately, without having to connect to the internet. We hope to use energy-efficient memristors to do those tasks on-site, in real-time.”

A Brain in Your Pocket
Whereas the computers in our phones and laptops use separate digital components for processing and memory—and therefore need to shuttle information between the two—the MIT chip uses analog components called memristors that process and store information in the same place. This is similar to the way the brain works and makes memristors far more efficient. To date, however, they’ve struggled with reliability and scalability.

To overcome these challenges, the MIT team designed a new kind of silicon-based, alloyed memristor. Ions flowing in memristors made from unalloyed materials tend to scatter as the components get smaller, meaning the signal loses fidelity and the resulting computations are less reliable. The team found an alloy of silver and copper helped stabilize the flow of silver ions between electrodes, allowing them to scale the number of memristors on the chip without sacrificing functionality.

While MIT’s new chip is promising, there’s likely a ways to go before memristor-based neuromorphic chips go mainstream. Between now and then, engineers like Kim have their work cut out for them to further scale and demonstrate their designs. But if successful, they could make for smarter smartphones and other even smaller devices.

“We would like to develop this technology further to have larger-scale arrays to do image recognition tasks,” Kim said. “And some day, you might be able to carry around artificial brains to do these kinds of tasks, without connecting to supercomputers, the internet, or the cloud.”

Special Chips for AI
The MIT work is part of a larger trend in computing and machine learning. As progress in classical chips has flagged in recent years, there’s been an increasing focus on more efficient software and specialized chips to continue pushing the pace.

Neuromorphic chips, for example, aren’t new. IBM and Intel are developing their own designs. So far, their chips have been based on groups of standard computing components, such as transistors (as opposed to memristors), arranged to imitate neurons in the brain. These chips are, however, still in the research phase.

Graphics processing units (GPUs)—chips originally developed for graphics-heavy work like video games—are the best practical example of specialized hardware for AI and were heavily used in this generation of machine learning early on. In the years since, Google, NVIDIA, and others have developed even more specialized chips that cater more specifically to machine learning.

The gains from such specialized chips are already being felt.

In a recent cost analysis of machine learning, research and investment firm ARK Invest said cost declines have far outpaced Moore’s Law. In a particular example, they found the cost to train an image recognition algorithm (ResNet-50) went from around $1,000 in 2017 to roughly $10 in 2019. The fall in cost to actually run such an algorithm was even more dramatic. It took $10,000 to classify a billion images in 2017 and just $0.03 in 2019.

Some of these declines can be traced to better software, but according to ARK, specialized chips have improved performance by nearly 16 times in the last three years.

As neuromorphic chips—and other tailored designs—advance further in the years to come, these trends in cost and performance may continue. Eventually, if all goes to plan, we might all carry a pocket brain that can do the work of today’s best AI.

Image credit: Peng Lin Continue reading

Posted in Human Robots

#436403 Why Your 5G Phone Connection Could Mean ...

Will getting full bars on your 5G connection mean getting caught out by sudden weather changes?

The question may strike you as hypothetical, nonsensical even, but it is at the core of ongoing disputes between meteorologists and telecommunications companies. Everyone else, including you and I, are caught in the middle, wanting both 5G’s faster connection speeds and precise information about our increasingly unpredictable weather. So why can’t we have both?

Perhaps we can, but because of the way 5G networks function, it may take some special technology—specifically, artificial intelligence.

The Bandwidth Worries
Around the world, the first 5G networks are already being rolled out. The networks use a variety of frequencies to transmit data to and from devices at speeds up to 100 times faster than existing 4G networks.

One of the bandwidths used is between 24.25 and 24.45 gigahertz (GHz). In a recent FCC auction, telecommunications companies paid a combined $2 billion for the 5G usage rights for this spectrum in the US.

However, meteorologists are concerned that transmissions near the lower end of that range can interfere with their ability to accurately measure water vapor in the atmosphere. Wired reported that acting chief of the National Oceanic and Atmospheric Administration (NOAA), Neil Jacobs, told the US House Subcommittee on the Environment that 5G interference could substantially cut the amount of weather data satellites can gather. As a result, forecast accuracy could drop by as much as 30 percent.

Among the consequences could be less time to prepare for hurricanes, and it may become harder to predict storms’ paths. Due to the interconnectedness of weather patterns, measurement issues in one location can affect other areas too. Lack of accurate atmospheric data from the US could, for example, lead to less accurate forecasts for weather patterns over Europe.

The Numbers Game
Water vapor emits a faint signal at 23.8 GHz. Weather satellites measure the signals, and the data is used to gauge atmospheric humidity levels. Meteorologists have expressed concern that 5G signals in the same range can disturb those readings. The issue is that it would be nigh on impossible to tell whether a signal is water vapor or an errant 5G signal.

Furthermore, 5G disturbances in other frequency bands could make forecasting even more difficult. Rain and snow emit frequencies around 36-37 GHz. 50.2-50.4 GHz is used to measure atmospheric temperatures, and 86-92 GHz clouds and ice. All of the above are under consideration for international 5G signals. Some have warned that the wider consequences could set weather forecasts back to the 1980s.

Telecommunications companies and interest organizations have argued back, saying that weather sensors aren’t as susceptible to interference as meteorologists fear. Furthermore, 5G devices and signals will produce much less interference with weather forecasts than organizations like NOAA predict. Since very little scientific research has been carried out to examine the claims of either party, we seem stuck in a ‘wait and see’ situation.

To offset some of the possible effects, the two groups have tried to reach a consensus on a noise buffer between the 5G transmissions and water-vapor signals. It could be likened to limiting the noise from busy roads or loud sound systems to avoid bothering neighboring buildings.

The World Meteorological Organization was looking to establish a -55 decibel watts buffer. In Europe, regulators are locked in on a -42 decibel watts buffer for 5G base stations. For comparison, the US Federal Communications Commission has advocated for a -20 decibel watts buffer, which would, in reality, allow more than 150 times more noise than the European proposal.

How AI Could Help
Much of the conversation about 5G’s possible influence on future weather predictions is centered around mobile phones. However, the phones are far from the only systems that will be receiving and transmitting signals on 5G. Self-driving cars and the Internet of Things are two other technologies that could soon be heavily reliant on faster wireless signals.

Densely populated areas are likely going to be the biggest emitters of 5G signals, leading to a suggestion to only gather water-vapor data over oceans.

Another option is to develop artificial intelligence (AI) approaches to clean or process weather data. AI is playing an increasing role in weather forecasting. For example, in 2016 IBM bought The Weather Company for $2 billion. The goal was to combine the two companies’ models and data in IBM’s Watson to create more accurate forecasts. AI would also be able to predict increases or drops in business revenues due to weather changes. Monsanto has also been investing in AI for forecasting, in this case to provide agriculturally-related weather predictions.

Smartphones may also provide a piece of the weather forecasting puzzle. Studies have shown how data from thousands of smartphones can help to increase the accuracy of storm predictions, as well as the force of storms.

“Weather stations cost a lot of money,” Cliff Mass, an atmospheric scientist at the University of Washington in Seattle, told Inside Science, adding, “If there are already 20 million smartphones, you might as well take advantage of the observation system that’s already in place.”

Smartphones may not be the solution when it comes to finding new ways of gathering the atmospheric data on water vapor that 5G could disrupt. But it does go to show that some technologies open new doors, while at the same time, others shut them.

Image Credit: Image by Free-Photos from Pixabay Continue reading

Posted in Human Robots

#436188 The Blogger Behind “AI ...

Sure, artificial intelligence is transforming the world’s societies and economies—but can an AI come up with plausible ideas for a Halloween costume?

Janelle Shane has been asking such probing questions since she started her AI Weirdness blog in 2016. She specializes in training neural networks (which underpin most of today’s machine learning techniques) on quirky data sets such as compilations of knitting instructions, ice cream flavors, and names of paint colors. Then she asks the neural net to generate its own contributions to these categories—and hilarity ensues. AI is not likely to disrupt the paint industry with names like “Ronching Blue,” “Dorkwood,” and “Turdly.”

Shane’s antics have a serious purpose. She aims to illustrate the serious limitations of today’s AI, and to counteract the prevailing narrative that describes AI as well on its way to superintelligence and complete human domination. “The danger of AI is not that it’s too smart,” Shane writes in her new book, “but that it’s not smart enough.”

The book, which came out on Tuesday, is called You Look Like a Thing and I Love You. It takes its odd title from a list of AI-generated pick-up lines, all of which would at least get a person’s attention if shouted, preferably by a robot, in a crowded bar. Shane’s book is shot through with her trademark absurdist humor, but it also contains real explanations of machine learning concepts and techniques. It’s a painless way to take AI 101.

She spoke with IEEE Spectrum about the perils of placing too much trust in AI systems, the strange AI phenomenon of “giraffing,” and her next potential Halloween costume.

Janelle Shane on . . .

The un-delicious origin of her blog
“The narrower the problem, the smarter the AI will seem”
Why overestimating AI is dangerous
Giraffing!
Machine and human creativity

The un-delicious origin of her blog IEEE Spectrum: You studied electrical engineering as an undergrad, then got a master’s degree in physics. How did that lead to you becoming the comedian of AI?
Janelle Shane: I’ve been interested in machine learning since freshman year of college. During orientation at Michigan State, a professor who worked on evolutionary algorithms gave a talk about his work. It was full of the most interesting anecdotes–some of which I’ve used in my book. He told an anecdote about people setting up a machine learning algorithm to do lens design, and the algorithm did end up designing an optical system that works… except one of the lenses was 50 feet thick, because they didn’t specify that it couldn’t do that.
I started working in his lab on optics, doing ultra-short laser pulse work. I ended up doing a lot more optics than machine learning, but I always found it interesting. One day I came across a list of recipes that someone had generated using a neural net, and I thought it was hilarious and remembered why I thought machine learning was so cool. That was in 2016, ages ago in machine learning land.
Spectrum: So you decided to “establish weirdness as your goal” for your blog. What was the first weird experiment that you blogged about?
Shane: It was generating cookbook recipes. The neural net came up with ingredients like: “Take ¼ pounds of bones or fresh bread.” That recipe started out: “Brown the salmon in oil, add creamed meat to the mixture.” It was making mistakes that showed the thing had no memory at all.
Spectrum: You say in the book that you can learn a lot about AI by giving it a task and watching it flail. What do you learn?
Shane: One thing you learn is how much it relies on surface appearances rather than deep understanding. With the recipes, for example: It got the structure of title, category, ingredients, instructions, yield at the end. But when you look more closely, it has instructions like “Fold the water and roll it into cubes.” So clearly this thing does not understand water, let alone the other things. It’s recognizing certain phrases that tend to occur, but it doesn’t have a concept that these recipes are describing something real. You start to realize how very narrow the algorithms in this world are. They only know exactly what we tell them in our data set.
BACK TO TOP↑ “The narrower the problem, the smarter the AI will seem” Spectrum: That makes me think of DeepMind’s AlphaGo, which was universally hailed as a triumph for AI. It can play the game of Go better than any human, but it doesn’t know what Go is. It doesn’t know that it’s playing a game.
Shane: It doesn’t know what a human is, or if it’s playing against a human or another program. That’s also a nice illustration of how well these algorithms do when they have a really narrow and well-defined problem.
The narrower the problem, the smarter the AI will seem. If it’s not just doing something repeatedly but instead has to understand something, coherence goes down. For example, take an algorithm that can generate images of objects. If the algorithm is restricted to birds, it could do a recognizable bird. If this same algorithm is asked to generate images of any animal, if its task is that broad, the bird it generates becomes an unrecognizable brown feathered smear against a green background.
Spectrum: That sounds… disturbing.
Shane: It’s disturbing in a weird amusing way. What’s really disturbing is the humans it generates. It hasn’t seen them enough times to have a good representation, so you end up with an amorphous, usually pale-faced thing with way too many orifices. If you asked it to generate an image of a person eating pizza, you’ll have blocks of pizza texture floating around. But if you give that image to an image-recognition algorithm that was trained on that same data set, it will say, “Oh yes, that’s a person eating pizza.”
BACK TO TOP↑ Why overestimating AI is dangerous Spectrum: Do you see it as your role to puncture the AI hype?
Shane: I do see it that way. Not a lot of people are bringing out this side of AI. When I first started posting my results, I’d get people saying, “I don’t understand, this is AI, shouldn’t it be better than this? Why doesn't it understand?” Many of the impressive examples of AI have a really narrow task, or they’ve been set up to hide how little understanding it has. There’s a motivation, especially among people selling products based on AI, to represent the AI as more competent and understanding than it actually is.
Spectrum: If people overestimate the abilities of AI, what risk does that pose?
Shane: I worry when I see people trusting AI with decisions it can’t handle, like hiring decisions or decisions about moderating content. These are really tough tasks for AI to do well on. There are going to be a lot of glitches. I see people saying, “The computer decided this so it must be unbiased, it must be objective.”

“If the algorithm’s task is to replicate human hiring decisions, it’s going to glom onto gender bias and race bias.”
—Janelle Shane, AI Weirdness blogger
That’s another thing I find myself highlighting in the work I’m doing. If the data includes bias, the algorithm will copy that bias. You can’t tell it not to be biased, because it doesn’t understand what bias is. I think that message is an important one for people to understand.
If there’s bias to be found, the algorithm is going to go after it. It’s like, “Thank goodness, finally a signal that’s reliable.” But for a tough problem like: Look at these resumes and decide who’s best for the job. If its task is to replicate human hiring decisions, it’s going to glom onto gender bias and race bias. There’s an example in the book of a hiring algorithm that Amazon was developing that discriminated against women, because the historical data it was trained on had that gender bias.
Spectrum: What are the other downsides of using AI systems that don’t really understand their tasks?
Shane: There is a risk in putting too much trust in AI and not examining its decisions. Another issue is that it can solve the wrong problems, without anyone realizing it. There have been a couple of cases in medicine. For example, there was an algorithm that was trained to recognize things like skin cancer. But instead of recognizing the actual skin condition, it latched onto signals like the markings a surgeon makes on the skin, or a ruler placed there for scale. It was treating those things as a sign of skin cancer. It’s another indication that these algorithms don’t understand what they’re looking at and what the goal really is.
BACK TO TOP↑ Giraffing Spectrum: In your blog, you often have neural nets generate names for things—such as ice cream flavors, paint colors, cats, mushrooms, and types of apples. How do you decide on topics?
Shane: Quite often it’s because someone has written in with an idea or a data set. They’ll say something like, “I’m the MIT librarian and I have a whole list of MIT thesis titles.” That one was delightful. Or they’ll say, “We are a high school robotics team, and we know where there’s a list of robotics team names.” It’s fun to peek into a different world. I have to be careful that I’m not making fun of the naming conventions in the field. But there’s a lot of humor simply in the neural net’s complete failure to understand. Puns in particular—it really struggles with puns.
Spectrum: Your blog is quite absurd, but it strikes me that machine learning is often absurd in itself. Can you explain the concept of giraffing?
Shane: This concept was originally introduced by [internet security expert] Melissa Elliott. She proposed this phrase as a way to describe the algorithms’ tendency to see giraffes way more often than would be likely in the real world. She posted a whole bunch of examples, like a photo of an empty field in which an image-recognition algorithm has confidently reported that there are giraffes. Why does it think giraffes are present so often when they’re actually really rare? Because they’re trained on data sets from online. People tend to say, “Hey look, a giraffe!” And then take a photo and share it. They don’t do that so often when they see an empty field with rocks.
There’s also a chatbot that has a delightful quirk. If you show it some photo and ask it how many giraffes are in the picture, it will always answer with some non zero number. This quirk comes from the way the training data was generated: These were questions asked and answered by humans online. People tended not to ask the question “How many giraffes are there?” when the answer was zero. So you can show it a picture of someone holding a Wii remote. If you ask it how many giraffes are in the picture, it will say two.
BACK TO TOP↑ Machine and human creativity Spectrum: AI can be absurd, and maybe also creative. But you make the point that AI art projects are really human-AI collaborations: Collecting the data set, training the algorithm, and curating the output are all artistic acts on the part of the human. Do you see your work as a human-AI art project?
Shane: Yes, I think there is artistic intent in my work; you could call it literary or visual. It’s not so interesting to just take a pre-trained algorithm that’s been trained on utilitarian data, and tell it to generate a bunch of stuff. Even if the algorithm isn’t one that I’ve trained myself, I think about, what is it doing that’s interesting, what kind of story can I tell around it, and what do I want to show people.

The Halloween costume algorithm “was able to draw on its knowledge of which words are related to suggest things like sexy barnacle.”
—Janelle Shane, AI Weirdness blogger
Spectrum: For the past three years you’ve been getting neural nets to generate ideas for Halloween costumes. As language models have gotten dramatically better over the past three years, are the costume suggestions getting less absurd?
Shane: Yes. Before I would get a lot more nonsense words. This time I got phrases that were related to real things in the data set. I don’t believe the training data had the words Flying Dutchman or barnacle. But it was able to draw on its knowledge of which words are related to suggest things like sexy barnacle and sexy Flying Dutchman.
Spectrum: This year, I saw on Twitter that someone made the gothy giraffe costume happen. Would you ever dress up for Halloween in a costume that the neural net suggested?
Shane: I think that would be fun. But there would be some challenges. I would love to go as the sexy Flying Dutchman. But my ambition may constrict me to do something more like a list of leg parts.
BACK TO TOP↑ Continue reading

Posted in Human Robots

#435765 The Four Converging Technologies Giving ...

How each of us sees the world is about to change dramatically.

For all of human history, the experience of looking at the world was roughly the same for everyone. But boundaries between the digital and physical are beginning to fade.

The world around us is gaining layer upon layer of digitized, virtually overlaid information—making it rich, meaningful, and interactive. As a result, our respective experiences of the same environment are becoming vastly different, personalized to our goals, dreams, and desires.

Welcome to Web 3.0, or the Spatial Web. In version 1.0, static documents and read-only interactions limited the internet to one-way exchanges. Web 2.0 provided quite an upgrade, introducing multimedia content, interactive web pages, and participatory social media. Yet, all this was still mediated by two-dimensional screens.

Today, we are witnessing the rise of Web 3.0, riding the convergence of high-bandwidth 5G connectivity, rapidly evolving AR eyewear, an emerging trillion-sensor economy, and powerful artificial intelligence.

As a result, we will soon be able to superimpose digital information atop any physical surrounding—freeing our eyes from the tyranny of the screen, immersing us in smart environments, and making our world endlessly dynamic.

In the third post of our five-part series on augmented reality, we will explore the convergence of AR, AI, sensors, and blockchain and dive into the implications through a key use case in manufacturing.

A Tale of Convergence
Let’s deconstruct everything beneath the sleek AR display.

It all begins with graphics processing units (GPUs)—electric circuits that perform rapid calculations to render images. (GPUs can be found in mobile phones, game consoles, and computers.)

However, because AR requires such extensive computing power, single GPUs will not suffice. Instead, blockchain can now enable distributed GPU processing power, and blockchains specifically dedicated to AR holographic processing are on the rise.

Next up, cameras and sensors will aggregate real-time data from any environment to seamlessly integrate physical and virtual worlds. Meanwhile, body-tracking sensors are critical for aligning a user’s self-rendering in AR with a virtually enhanced environment. Depth sensors then provide data for 3D spatial maps, while cameras absorb more surface-level, detailed visual input. In some cases, sensors might even collect biometric data, such as heart rate and brain activity, to incorporate health-related feedback in our everyday AR interfaces and personal recommendation engines.

The next step in the pipeline involves none other than AI. Processing enormous volumes of data instantaneously, embedded AI algorithms will power customized AR experiences in everything from artistic virtual overlays to personalized dietary annotations.

In retail, AIs will use your purchasing history, current closet inventory, and possibly even mood indicators to display digitally rendered items most suitable for your wardrobe, tailored to your measurements.

In healthcare, smart AR glasses will provide physicians with immediately accessible and maximally relevant information (parsed from the entirety of a patient’s medical records and current research) to aid in accurate diagnoses and treatments, freeing doctors to engage in the more human-centric tasks of establishing trust, educating patients and demonstrating empathy.

Image Credit: PHD Ventures.
Convergence in Manufacturing
One of the nearest-term use cases of AR is manufacturing, as large producers begin dedicating capital to enterprise AR headsets. And over the next ten years, AR will converge with AI, sensors, and blockchain to multiply manufacturer productivity and employee experience.

(1) Convergence with AI
In initial application, digital guides superimposed on production tables will vastly improve employee accuracy and speed, while minimizing error rates.

Already, the International Air Transport Association (IATA) — whose airlines supply 82 percent of air travel — recently implemented industrial tech company Atheer’s AR headsets in cargo management. And with barely any delay, IATA reported a whopping 30 percent improvement in cargo handling speed and no less than a 90 percent reduction in errors.

With similar success rates, Boeing brought Skylight’s smart AR glasses to the runway, now used in the manufacturing of hundreds of airplanes. Sure enough—the aerospace giant has now seen a 25 percent drop in production time and near-zero error rates.

Beyond cargo management and air travel, however, smart AR headsets will also enable on-the-job training without reducing the productivity of other workers or sacrificing hardware. Jaguar Land Rover, for instance, implemented Bosch’s Re’flekt One AR solution to gear technicians with “x-ray” vision: allowing them to visualize the insides of Range Rover Sport vehicles without removing any dashboards.

And as enterprise capabilities continue to soar, AIs will soon become the go-to experts, offering support to manufacturers in need of assembly assistance. Instant guidance and real-time feedback will dramatically reduce production downtime, boost overall output, and even help customers struggling with DIY assembly at home.

Perhaps one of the most profitable business opportunities, AR guidance through centralized AI systems will also serve to mitigate supply chain inefficiencies at extraordinary scale. Coordinating moving parts, eliminating the need for manned scanners at each checkpoint, and directing traffic within warehouses, joint AI-AR systems will vastly improve workflow while overseeing quality assurance.

After its initial implementation of AR “vision picking” in 2015, leading courier company DHL recently announced it would continue to use Google’s newest smart lens in warehouses across the world. Motivated by the initial group’s reported 15 percent jump in productivity, DHL’s decision is part of the logistics giant’s $300 million investment in new technologies.

And as direct-to-consumer e-commerce fundamentally transforms the retail sector, supply chain optimization will only grow increasingly vital. AR could very well prove the definitive step for gaining a competitive edge in delivery speeds.

As explained by Vital Enterprises CEO Ash Eldritch, “All these technologies that are coming together around artificial intelligence are going to augment the capabilities of the worker and that’s very powerful. I call it Augmented Intelligence. The idea is that you can take someone of a certain skill level and by augmenting them with artificial intelligence via augmented reality and the Internet of Things, you can elevate the skill level of that worker.”

Already, large producers like Goodyear, thyssenkrupp, and Johnson Controls are using the Microsoft HoloLens 2—priced at $3,500 per headset—for manufacturing and design purposes.

Perhaps the most heartening outcome of the AI-AR convergence is that, rather than replacing humans in manufacturing, AR is an ideal interface for human collaboration with AI. And as AI merges with human capital, prepare to see exponential improvements in productivity, professional training, and product quality.

(2) Convergence with Sensors
On the hardware front, these AI-AR systems will require a mass proliferation of sensors to detect the external environment and apply computer vision in AI decision-making.

To measure depth, for instance, some scanning depth sensors project a structured pattern of infrared light dots onto a scene, detecting and analyzing reflected light to generate 3D maps of the environment. Stereoscopic imaging, using two lenses, has also been commonly used for depth measurements. But leading technology like Microsoft’s HoloLens 2 and Intel’s RealSense 400-series camera implement a new method called “phased time-of-flight” (ToF).

In ToF sensing, the HoloLens 2 uses numerous lasers, each with 100 milliwatts (mW) of power, in quick bursts. The distance between nearby objects and the headset wearer is then measured by the amount of light in the return beam that has shifted from the original signal. Finally, the phase difference reveals the location of each object within the field of view, which enables accurate hand-tracking and surface reconstruction.

With a far lower computing power requirement, the phased ToF sensor is also more durable than stereoscopic sensing, which relies on the precise alignment of two prisms. The phased ToF sensor’s silicon base also makes it easily mass-produced, rendering the HoloLens 2 a far better candidate for widespread consumer adoption.

To apply inertial measurement—typically used in airplanes and spacecraft—the HoloLens 2 additionally uses a built-in accelerometer, gyroscope, and magnetometer. Further equipped with four “environment understanding cameras” that track head movements, the headset also uses a 2.4MP HD photographic video camera and ambient light sensor that work in concert to enable advanced computer vision.

For natural viewing experiences, sensor-supplied gaze tracking increasingly creates depth in digital displays. Nvidia’s work on Foveated AR Display, for instance, brings the primary foveal area into focus, while peripheral regions fall into a softer background— mimicking natural visual perception and concentrating computing power on the area that needs it most.

Gaze tracking sensors are also slated to grant users control over their (now immersive) screens without any hand gestures. Conducting simple visual cues, even staring at an object for more than three seconds, will activate commands instantaneously.

And our manufacturing example above is not the only one. Stacked convergence of blockchain, sensors, AI and AR will disrupt almost every major industry.

Take healthcare, for example, wherein biometric sensors will soon customize users’ AR experiences. Already, MIT Media Lab’s Deep Reality group has created an underwater VR relaxation experience that responds to real-time brain activity detected by a modified version of the Muse EEG. The experience even adapts to users’ biometric data, from heart rate to electro dermal activity (inputted from an Empatica E4 wristband).

Now rapidly dematerializing, sensors will converge with AR to improve physical-digital surface integration, intuitive hand and eye controls, and an increasingly personalized augmented world. Keep an eye on companies like MicroVision, now making tremendous leaps in sensor technology.

While I’ll be doing a deep dive into sensor applications across each industry in our next blog, it’s critical to first discuss how we might power sensor- and AI-driven augmented worlds.

(3) Convergence with Blockchain
Because AR requires much more compute power than typical 2D experiences, centralized GPUs and cloud computing systems are hard at work to provide the necessary infrastructure. Nonetheless, the workload is taxing and blockchain may prove the best solution.

A major player in this pursuit, Otoy aims to create the largest distributed GPU network in the world, called the Render Network RNDR. Built specifically on the Ethereum blockchain for holographic media, and undergoing Beta testing, this network is set to revolutionize AR deployment accessibility.

Alphabet Chairman Eric Schmidt (an investor in Otoy’s network), has even said, “I predicted that 90% of computing would eventually reside in the web based cloud… Otoy has created a remarkable technology which moves that last 10%—high-end graphics processing—entirely to the cloud. This is a disruptive and important achievement. In my view, it marks the tipping point where the web replaces the PC as the dominant computing platform of the future.”

Leveraging the crowd, RNDR allows anyone with a GPU to contribute their power to the network for a commission of up to $300 a month in RNDR tokens. These can then be redeemed in cash or used to create users’ own AR content.

In a double win, Otoy’s blockchain network and similar iterations not only allow designers to profit when not using their GPUs, but also democratize the experience for newer artists in the field.

And beyond these networks’ power suppliers, distributing GPU processing power will allow more manufacturing companies to access AR design tools and customize learning experiences. By further dispersing content creation across a broad network of individuals, blockchain also has the valuable potential to boost AR hardware investment across a number of industry beneficiaries.

On the consumer side, startups like Scanetchain are also entering the blockchain-AR space for a different reason. Allowing users to scan items with their smartphone, Scanetchain’s app provides access to a trove of information, from manufacturer and price, to origin and shipping details.

Based on NEM (a peer-to-peer cryptocurrency that implements a blockchain consensus algorithm), the app aims to make information far more accessible and, in the process, create a social network of purchasing behavior. Users earn tokens by watching ads, and all transactions are hashed into blocks and securely recorded.

The writing is on the wall—our future of brick-and-mortar retail will largely lean on blockchain to create the necessary digital links.

Final Thoughts
Integrating AI into AR creates an “auto-magical” manufacturing pipeline that will fundamentally transform the industry, cutting down on marginal costs, reducing inefficiencies and waste, and maximizing employee productivity.

Bolstering the AI-AR convergence, sensor technology is already blurring the boundaries between our augmented and physical worlds, soon to be near-undetectable. While intuitive hand and eye motions dictate commands in a hands-free interface, biometric data is poised to customize each AR experience to be far more in touch with our mental and physical health.

And underpinning it all, distributed computing power with blockchain networks like RNDR will democratize AR, boosting global consumer adoption at plummeting price points.

As AR soars in importance—whether in retail, manufacturing, entertainment, or beyond—the stacked convergence discussed above merits significant investment over the next decade. The augmented world is only just getting started.

Join Me
(1) A360 Executive Mastermind: Want even more context about how converging exponential technologies will transform your business and industry? Consider joining Abundance 360, a highly selective community of 360 exponentially minded CEOs, who are on a 25-year journey with me—or as I call it, a “countdown to the Singularity.” If you’d like to learn more and consider joining our 2020 membership, apply here.

Share this with your friends, especially if they are interested in any of the areas outlined above.

(2) Abundance-Digital Online Community: I’ve also created a Digital/Online community of bold, abundance-minded entrepreneurs called Abundance-Digital. Abundance-Digital is Singularity University’s ‘onramp’ for exponential entrepreneurs — those who want to get involved and play at a higher level. Click here to learn more.

This article originally appeared on Diamandis.com

Image Credit: Funky Focus / Pixabay Continue reading

Posted in Human Robots

#435731 Video Friday: NASA Is Sending This ...

Video Friday is your weekly selection of awesome robotics videos, collected by your Automaton bloggers. We’ll also be posting a weekly calendar of upcoming robotics events for the next few months; here’s what we have so far (send us your events!):

MARSS 2019 – July 1-5, 2019 – Helsinki, Finland
ICRES 2019 – July 29-30, 2019 – London, UK
DARPA SubT Tunnel Circuit – August 15-22, 2019 – Pittsburgh, PA, USA
Let us know if you have suggestions for next week, and enjoy today’s videos.

The big news today is that NASA is sending a robot to Saturn’s moon Titan. A flying robot. The Dragonfly mission will launch in 2026 and arrive in 2034, but you knew that already, because last January, we posted a detailed article about the concept from the Applied Physics Lab at Johns Hopkins University. And now it’s not a concept anymore, yay!

Again, read all the details plus an interview in 2018 article.

[ NASA ]

A robotic gripping arm that uses engineered bacteria to “taste” for a specific chemical has been developed by engineers at the University of California, Davis, and Carnegie Mellon University. The gripper is a proof-of-concept for biologically-based soft robotics.

The new device uses a biosensing module based on E. coli bacteria engineered to respond to the chemical IPTG by producing a fluorescent protein. The bacterial cells reside in wells with a flexible, porous membrane that allows chemicals to enter but keeps the cells inside. This biosensing module is built into the surface of a flexible gripper on a robotic arm, so the gripper can “taste” the environment through its fingers.

When IPTG crosses the membrane into the chamber, the cells fluoresce and electronic circuits inside the module detect the light. The electrical signal travels to the gripper’s control unit, which can decide whether to pick something up or release it.

[ UC Davis ]

The Toyota Research Institute (TRI) is taking on the hard problems in manipulation research toward making human-assist robots reliable and robust. Dr. Russ Tedrake, TRI Vice President of Robotics Research, explains how we are exploring the challenges and addressing the reliability gap by using a robot loading dishes in a dishwasher as an example task.

[ TRI ]

The Tactile Telerobot is the world’s first haptic telerobotic system that transmits realistic touch feedback to an operator located anywhere in the world. It is the product of joint collaboration between Shadow Robot Company, HaptX, and SynTouch. All Nippon Airways funded the project’s initial research and development.

What’s really unique about this is the HaptX tactile feedback system, which is something we’ve been following for several years now. It’s one of the most magical tech experiences I’ve ever had, and you can read about it here and here.

[ HaptX ]

Thanks Andrew!

I love how snake robots can emulate some of the fanciest moves of real snakes, and then also do bonkers things that real snakes never do.

[ Matsuno Lab ]

Here are a couple interesting videos from the Human-Robot Interaction Lab at Tufts.

A robot is instructed to perform an action and cannot do it due to lack of sensors. But when another robot is placed nearby, it can execute the instruction by tacitly tapping into the other robot’s mind and using that robot’s sensors for its own actions. Yes, it’s automatic, and yes, it’s the BORG!

Two Nao robots are instructed to perform a dance and are able to do it right after instruction. Moreover, they can switch roles immediately, and even a third different PR2 robot can perform the dance right away, demonstrating the ability of our DIARC architecture to learn quickly and share the knowledge with any type of robot running the architecture.

Compared to Nao, PR2 just sounds… depressed.

[ HRI Lab ]

This work explores the problem of robot tool construction – creating tools from parts available in the environment. We advance the state-of-the-art in robotic tool construction by introducing an approach that enables the robot to construct a wider range of tools with greater computational efficiency. Specifically, given an action that the robot wishes to accomplish and a set of building parts available to the robot, our approach reasons about the shape of the parts and potential ways of attaching them, generating a ranking of part combinations that the robot then uses to construct and test the target tool. We validate our approach on the construction of five tools using a physical 7-DOF robot arm.

[ RAIL Lab ] via [ RSS ]

We like Magazino’s approach to warehouse picking- constrain the problem to something you can reliably solve, like shoeboxes.

Magazino has announced a new pricing model for their robots. You pay 55k euros for the robot itself, and then after that, all you pay to keep the robot working is 6 cents per pick, so the robot is only costing you money for the work that it actually does.

[ Magazino ]

Thanks Florin!

Human-Robot Collaborations are happening across factories worldwide, yet very few are using it for smaller businesses, due to high costs or the difficulty of customization. Elephant Robotics, a new player from Shenzhen, the Silicon Valley of Asia, has set its sight on helping smaller businesses gain access to smart robotics. They created a Catbot (a collaborative robotic arm) that will offer high efficiency and flexibility to various industries.

The Catbot is set to help from education projects, photography, massaging, to being a personal barista or co-playing a table game. The customizations are endless. To increase the flexibility of usage, the Catbot is extremely easy to program from a high precision task up to covering hefty ground projects.

[ Elephant Robotics ]

Thanks Johnson!

Dronistics, an EPFL spin-off, has been testing out their enclosed delivery drone in the Dominican Republic through a partnership with WeRobotics.

[ WeRobotics ]

QTrobot is an expressive humanoid robot designed to help children with autism spectrum disorder and children with special educational needs in learning new skills. QTrobot uses simple and exaggerated facial expressions combined by interactive games and stories, to help children improve their emotional skills. QTrobot helps children to learn about and better understand the emotions and teach them strategies to handle their emotions more effectively.

[ LuxAI ]

Here’s a typical day in the life of a Tertill solar-powered autonomous weed-destroying robot.

$300, now shipping from Franklin Robotics.

[ Tertill ]

PAL Robotics is excited to announce a new TIAGo with two arms, TIAGo++! After carefully listening to the robotics community needs, we used TIAGo’s modularity to integrate two 7-DoF arms to our mobile manipulator. TIAGo++ can help you swiftly accomplish your research goals, opening endless possibilities in mobile manipulation.

[ PAL Robotics ]

Thanks Jack!

You’ve definitely already met the Cobalt security robot, but Toyota AI Ventures just threw a pile of money at them and would therefore like you to experience this re-introduction:

[ Cobalt Robotics ] via [ Toyota AI ]

ROSIE is a mobile manipulator kit from HEBI Robotics. And if you don’t like ROSIE, the modular nature of HEBI’s hardware means that you can take her apart and make something more interesting.

[ HEBI Robotics ]

Learn about Kawasaki Robotics’ second addition to their line of duAro dual-arm collaborative robots, duAro2. This model offers an extended vertical reach (550 mm) and an increased payload capacity (3 kg/arm).

[ Kawasaki Robotics ]

Drone Delivery Canada has partnered with Peel Region Paramedics to pilot its proprietary drone delivery platform to enable rapid first responder technology via drone with the goal to reduce response time and potentially save lives.

[ Drone Delivery Canada ]

In this week’s episode of Robots in Depth, Per speaks with Harri Ketamo, from Headai.

Harri Ketamo talks about AI and how he aims to mimic human decision making with algorithms. Harri has done a lot of AI for computer games to create opponents that are entertaining to play against. It is easy to develop a very bad or a very good opponent, but designing an opponent that behaves like a human, is entertaining to play against and that you can beat is quite hard. He talks about how AI in computer games is a very important story telling tool and an important part of making a game entertaining to play.

This work led him into other parts of the AI field. Harri thinks that we sometimes have a problem separating what is real from what is the type of story telling he knows from gaming AI. He calls for critical analysis of AI and says that data has to be used to verify AI decisions and results.

[ Robots in Depth ]

Thanks Per! Continue reading

Posted in Human Robots