Tag Archives: learns
#434303 Making Superhumans Through Radical ...
Imagine trying to read War and Peace one letter at a time. The thought alone feels excruciating. But in many ways, this painful idea holds parallels to how human-machine interfaces (HMI) force us to interact with and process data today.
Designed back in the 1970s at Xerox PARC and later refined during the 1980s by Apple, today’s HMI was originally conceived during fundamentally different times, and specifically, before people and machines were generating so much data. Fast forward to 2019, when humans are estimated to produce 44 zettabytes of data—equal to two stacks of books from here to Pluto—and we are still using the same HMI from the 1970s.
These dated interfaces are not equipped to handle today’s exponential rise in data, which has been ushered in by the rapid dematerialization of many physical products into computers and software.
Breakthroughs in perceptual and cognitive computing, especially machine learning algorithms, are enabling technology to process vast volumes of data, and in doing so, they are dramatically amplifying our brain’s abilities. Yet even with these powerful technologies that at times make us feel superhuman, the interfaces are still crippled with poor ergonomics.
Many interfaces are still designed around the concept that human interaction with technology is secondary, not instantaneous. This means that any time someone uses technology, they are inevitably multitasking, because they must simultaneously perform a task and operate the technology.
If our aim, however, is to create technology that truly extends and amplifies our mental abilities so that we can offload important tasks, the technology that helps us must not also overwhelm us in the process. We must reimagine interfaces to work in coherence with how our minds function in the world so that our brains and these tools can work together seamlessly.
Embodied Cognition
Most technology is designed to serve either the mind or the body. It is a problematic divide, because our brains use our entire body to process the world around us. Said differently, our minds and bodies do not operate distinctly. Our minds are embodied.
Studies using MRI scans have shown that when a person feels an emotion in their gut, blood actually moves to that area of the body. The body and the mind are linked in this way, sharing information back and forth continuously.
Current technology presents data to the brain differently from how the brain processes data. Our brains, for example, use sensory data to continually encode and decipher patterns within the neocortex. Our brains do not create a linguistic label for each item, which is how the majority of machine learning systems operate, nor do our brains have an image associated with each of these labels.
Our bodies move information through us instantaneously, in a sense “computing” at the speed of thought. What if our technology could do the same?
Using Cognitive Ergonomics to Design Better Interfaces
Well-designed physical tools, as philosopher Martin Heidegger once meditated on while using the metaphor of a hammer, seem to disappear into the “hand.” They are designed to amplify a human ability and not get in the way during the process.
The aim of physical ergonomics is to understand the mechanical movement of the human body and then adapt a physical system to amplify the human output in accordance. By understanding the movement of the body, physical ergonomics enables ergonomically sound physical affordances—or conditions—so that the mechanical movement of the body and the mechanical movement of the machine can work together harmoniously.
Cognitive ergonomics applied to HMI design uses this same idea of amplifying output, but rather than focusing on physical output, the focus is on mental output. By understanding the raw materials the brain uses to comprehend information and form an output, cognitive ergonomics allows technologists and designers to create technological affordances so that the brain can work seamlessly with interfaces and remove the interruption costs of our current devices. In doing so, the technology itself “disappears,” and a person’s interaction with technology becomes fluid and primary.
By leveraging cognitive ergonomics in HMI design, we can create a generation of interfaces that can process and present data the same way humans process real-world information, meaning through fully-sensory interfaces.
Several brain-machine interfaces are already on the path to achieving this. AlterEgo, a wearable device developed by MIT researchers, uses electrodes to detect and understand nonverbal prompts, which enables the device to read the user’s mind and act as an extension of the user’s cognition.
Another notable example is the BrainGate neural device, created by researchers at Stanford University. Just two months ago, a study was released showing that this brain implant system allowed paralyzed patients to navigate an Android tablet with their thoughts alone.
These are two extraordinary examples of what is possible for the future of HMI, but there is still a long way to go to bring cognitive ergonomics front and center in interface design.
Disruptive Innovation Happens When You Step Outside Your Existing Users
Most of today’s interfaces are designed by a narrow population, made up predominantly of white, non-disabled men who are prolific in the use of technology (you may recall The New York Times viral article from 2016, Artificial Intelligence’s White Guy Problem). If you ask this population if there is a problem with today’s HMIs, most will say no, and this is because the technology has been designed to serve them.
This lack of diversity means a limited perspective is being brought to interface design, which is problematic if we want HMI to evolve and work seamlessly with the brain. To use cognitive ergonomics in interface design, we must first gain a more holistic understanding of how people with different abilities understand the world and how they interact with technology.
Underserved groups, such as people with physical disabilities, operate on what Clayton Christensen coined in The Innovator’s Dilemma as the fringe segment of a market. Developing solutions that cater to fringe groups can in fact disrupt the larger market by opening a downward, much larger market.
Learning From Underserved Populations
When technology fails to serve a group of people, that group must adapt the technology to meet their needs.
The workarounds created are often ingenious, specifically because they have not been arrived at by preferences, but out of necessity that has forced disadvantaged users to approach the technology from a very different vantage point.
When a designer or technologist begins learning from this new viewpoint and understanding challenges through a different lens, they can bring new perspectives to design—perspectives that otherwise can go unseen.
Designers and technologists can also learn from people with physical disabilities who interact with the world by leveraging other senses that help them compensate for one they may lack. For example, some blind people use echolocation to detect objects in their environments.
The BrainPort device developed by Wicab is an incredible example of technology leveraging one human sense to serve or compliment another. The BrainPort device captures environmental information with a wearable video camera and converts this data into soft electrical stimulation sequences that are sent to a device on the user’s tongue—the most sensitive touch receptor in the body. The user learns how to interpret the patterns felt on their tongue, and in doing so, become able to “see” with their tongue.
Key to the future of HMI design is learning how different user groups navigate the world through senses beyond sight. To make cognitive ergonomics work, we must understand how to leverage the senses so we’re not always solely relying on our visual or verbal interactions.
Radical Inclusion for the Future of HMI
Bringing radical inclusion into HMI design is about gaining a broader lens on technology design at large, so that technology can serve everyone better.
Interestingly, cognitive ergonomics and radical inclusion go hand in hand. We can’t design our interfaces with cognitive ergonomics without bringing radical inclusion into the picture, and we also will not arrive at radical inclusion in technology so long as cognitive ergonomics are not considered.
This new mindset is the only way to usher in an era of technology design that amplifies the collective human ability to create a more inclusive future for all.
Image Credit: jamesteohart / Shutterstock.com Continue reading
Posted in Human Robots
#434260 The Most Surprising Tech Breakthroughs ...
Development across the entire information technology landscape certainly didn’t slow down this year. From CRISPR babies, to the rapid decline of the crypto markets, to a new robot on Mars, and discovery of subatomic particles that could change modern physics as we know it, there was no shortage of headline-grabbing breakthroughs and discoveries.
As 2018 comes to a close, we can pause and reflect on some of the biggest technology breakthroughs and scientific discoveries that occurred this year.
I reached out to a few Singularity University speakers and faculty across the various technology domains we cover asking what they thought the biggest breakthrough was in their area of expertise. The question posed was:
“What, in your opinion, was the biggest development in your area of focus this year? Or, what was the breakthrough you were most surprised by in 2018?”
I can share that for me, hands down, the most surprising development I came across in 2018 was learning that a publicly-traded company that was briefly valued at over $1 billion, and has over 12,000 employees and contractors spread around the world, has no physical office space and the entire business is run and operated from inside an online virtual world. This is Ready Player One stuff happening now.
For the rest, here’s what our experts had to say.
DIGITAL BIOLOGY
Dr. Tiffany Vora | Faculty Director and Vice Chair, Digital Biology and Medicine, Singularity University
“That’s easy: CRISPR babies. I knew it was technically possible, and I’ve spent two years predicting it would happen first in China. I knew it was just a matter of time but I failed to predict the lack of oversight, the dubious consent process, the paucity of publicly-available data, and the targeting of a disease that we already know how to prevent and treat and that the children were at low risk of anyway.
I’m not convinced that this counts as a technical breakthrough, since one of the girls probably isn’t immune to HIV, but it sure was a surprise.”
For more, read Dr. Vora’s summary of this recent stunning news from China regarding CRISPR-editing human embryos.
QUANTUM COMPUTING
Andrew Fursman | Co-Founder/CEO 1Qbit, Faculty, Quantum Computing, Singularity University
“There were two last-minute holiday season surprise quantum computing funding and technology breakthroughs:
First, right before the government shutdown, one priority legislative accomplishment will provide $1.2 billion in quantum computing research over the next five years. Second, there’s the rise of ions as a truly viable, scalable quantum computing architecture.”
*Read this Gizmodo profile on an exciting startup in the space to learn more about this type of quantum computing
ENERGY
Ramez Naam | Chair, Energy and Environmental Systems, Singularity University
“2018 had plenty of energy surprises. In solar, we saw unsubsidized prices in the sunny parts of the world at just over two cents per kwh, or less than half the price of new coal or gas electricity. In the US southwest and Texas, new solar is also now cheaper than new coal or gas. But even more shockingly, in Germany, which is one of the least sunny countries on earth (it gets less sunlight than Canada) the average bid for new solar in a 2018 auction was less than 5 US cents per kwh. That’s as cheap as new natural gas in the US, and far cheaper than coal, gas, or any other new electricity source in most of Europe.
In fact, it’s now cheaper in some parts of the world to build new solar or wind than to run existing coal plants. Think tank Carbon Tracker calculates that, over the next 10 years, it will become cheaper to build new wind or solar than to operate coal power in most of the world, including specifically the US, most of Europe, and—most importantly—India and the world’s dominant burner of coal, China.
Here comes the sun.”
GLOBAL GRAND CHALLENGES
Darlene Damm | Vice Chair, Faculty, Global Grand Challenges, Singularity University
“In 2018 we saw a lot of areas in the Global Grand Challenges move forward—advancements in robotic farming technology and cultured meat, low-cost 3D printed housing, more sophisticated types of online education expanding to every corner of the world, and governments creating new policies to deal with the ethics of the digital world. These were the areas we were watching and had predicted there would be change.
What most surprised me was to see young people, especially teenagers, start to harness technology in powerful ways and use it as a platform to make their voices heard and drive meaningful change in the world. In 2018 we saw teenagers speak out on a number of issues related to their well-being and launch digital movements around issues such as gun and school safety, global warming and environmental issues. We often talk about the harm technology can cause to young people, but on the flip side, it can be a very powerful tool for youth to start changing the world today and something I hope we see more of in the future.”
BUSINESS STRATEGY
Pascal Finette | Chair, Entrepreneurship and Open Innovation, Singularity University
“Without a doubt the rapid and massive adoption of AI, specifically deep learning, across industries, sectors, and organizations. What was a curiosity for most companies at the beginning of the year has quickly made its way into the boardroom and leadership meetings, and all the way down into the innovation and IT department’s agenda. You are hard-pressed to find a mid- to large-sized company today that is not experimenting or implementing AI in various aspects of its business.
On the slightly snarkier side of answering this question: The very rapid decline in interest in blockchain (and cryptocurrencies). The blockchain party was short, ferocious, and ended earlier than most would have anticipated, with a huge hangover for some. The good news—with the hot air dissipated, we can now focus on exploring the unique use cases where blockchain does indeed offer real advantages over centralized approaches.”
*Author note: snark is welcome and appreciated
ROBOTICS
Hod Lipson | Director, Creative Machines Lab, Columbia University
“The biggest surprise for me this year in robotics was learning dexterity. For decades, roboticists have been trying to understand and imitate dexterous manipulation. We humans seem to be able to manipulate objects with our fingers with incredible ease—imagine sifting through a bunch of keys in the dark, or tossing and catching a cube. And while there has been much progress in machine perception, dexterous manipulation remained elusive.
There seemed to be something almost magical in how we humans can physically manipulate the physical world around us. Decades of research in grasping and manipulation, and millions of dollars spent on robot-hand hardware development, has brought us little progress. But in late 2018, the Berkley OpenAI group demonstrated that this hurdle may finally succumb to machine learning as well. Given 200 years worth of practice, machines learned to manipulate a physical object with amazing fluidity. This might be the beginning of a new age for dexterous robotics.”
MACHINE LEARNING
Jeremy Howard | Founding Researcher, fast.ai, Founder/CEO, Enlitic, Faculty Data Science, Singularity University
“The biggest development in machine learning this year has been the development of effective natural language processing (NLP).
The New York Times published an article last month titled “Finally, a Machine That Can Finish Your Sentence,” which argued that NLP neural networks have reached a significant milestone in capability and speed of development. The “finishing your sentence” capability mentioned in the title refers to a type of neural network called a “language model,” which is literally a model that learns how to finish your sentences.
Earlier this year, two systems (one, called ELMO, is from the Allen Institute for AI, and the other, called ULMFiT, was developed by me and Sebastian Ruder) showed that such a model could be fine-tuned to dramatically improve the state-of-the-art in nearly every NLP task that researchers study. This work was further developed by OpenAI, which in turn was greatly scaled up by Google Brain, who created a system called BERT which reached human-level performance on some of NLP’s toughest challenges.
Over the next year, expect to see fine-tuned language models used for everything from understanding medical texts to building disruptive social media troll armies.”
DIGITAL MANUFACTURING
Andre Wegner | Founder/CEO Authentise, Chair, Digital Manufacturing, Singularity University
“Most surprising to me was the extent and speed at which the industry finally opened up.
While previously, only few 3D printing suppliers had APIs and knew what to do with them, 2018 saw nearly every OEM (or original equipment manufacturer) enabling data access and, even more surprisingly, shying away from proprietary standards and adopting MTConnect, as stalwarts such as 3D Systems and Stratasys have been. This means that in two to three years, data access to machines will be easy, commonplace, and free. The value will be in what is being done with that data.
Another example of this openness are the seemingly endless announcements of integrated workflows: GE’s announcement with most major software players to enable integrated solutions, EOS’s announcement with Siemens, and many more. It’s clear that all actors in the additive ecosystem have taken a step forward in terms of openness. The result is a faster pace of innovation, particularly in the software and data domains that are crucial to enabling comprehensive digital workflow to drive agile and resilient manufacturing.
I’m more optimistic we’ll achieve that now than I was at the end of 2017.”
SCIENCE AND DISCOVERY
Paul Saffo | Chair, Future Studies, Singularity University, Distinguished Visiting Scholar, Stanford Media-X Research Network
“The most important development in technology this year isn’t a technology, but rather the astonishing science surprises made possible by recent technology innovations. My short list includes the discovery of the “neptmoon”, a Neptune-scale moon circling a Jupiter-scale planet 8,000 lightyears from us; the successful deployment of the Mars InSight Lander a month ago; and the tantalizing ANITA detection (what could be a new subatomic particle which would in turn blow the standard model wide open). The highest use of invention is to support science discovery, because those discoveries in turn lead us to the future innovations that will improve the state of the world—and fire up our imaginations.”
ROBOTICS
Pablos Holman | Inventor, Hacker, Faculty, Singularity University
“Just five or ten years ago, if you’d asked any of us technologists “What is harder for robots? Eyes, or fingers?” We’d have all said eyes. Robots have extraordinary eyes now, but even in a surgical robot, the fingers are numb and don’t feel anything. Stanford robotics researchers have invented fingertips that can feel, and this will be a kingpin that allows robots to go everywhere they haven’t been yet.”
BLOCKCHAIN
Nathana Sharma | Blockchain, Policy, Law, and Ethics, Faculty, Singularity University
“2017 was the year of peak blockchain hype. 2018 has been a year of resetting expectations and technological development, even as the broader cryptocurrency markets have faced a winter. It’s now about seeing adoption and applications that people want and need to use rise. An incredible piece of news from December 2018 is that Facebook is developing a cryptocurrency for users to make payments through Whatsapp. That’s surprisingly fast mainstream adoption of this new technology, and indicates how powerful it is.”
ARTIFICIAL INTELLIGENCE
Neil Jacobstein | Chair, Artificial Intelligence and Robotics, Singularity University
“I think one of the most visible improvements in AI was illustrated by the Boston Dynamics Parkour video. This was not due to an improvement in brushless motors, accelerometers, or gears. It was due to improvements in AI algorithms and training data. To be fair, the video released was cherry-picked from numerous attempts, many of which ended with a crash. However, the fact that it could be accomplished at all in 2018 was a real win for both AI and robotics.”
NEUROSCIENCE
Divya Chander | Chair, Neuroscience, Singularity University
“2018 ushered in a new era of exponential trends in non-invasive brain modulation. Changing behavior or restoring function takes on a new meaning when invasive interfaces are no longer needed to manipulate neural circuitry. The end of 2018 saw two amazing announcements: the ability to grow neural organoids (mini-brains) in a dish from neural stem cells that started expressing electrical activity, mimicking the brain function of premature babies, and the first (known) application of CRISPR to genetically alter two fetuses grown through IVF. Although this was ostensibly to provide genetic resilience against HIV infections, imagine what would happen if we started tinkering with neural circuitry and intelligence.”
Image Credit: Yurchanka Siarhei / Shutterstock.com Continue reading
Posted in Human Robots
#433776 Why We Should Stop Conflating Human and ...
It’s common to hear phrases like ‘machine learning’ and ‘artificial intelligence’ and believe that somehow, someone has managed to replicate a human mind inside a computer. This, of course, is untrue—but part of the reason this idea is so pervasive is because the metaphor of human learning and intelligence has been quite useful in explaining machine learning and artificial intelligence.
Indeed, some AI researchers maintain a close link with the neuroscience community, and inspiration runs in both directions. But the metaphor can be a hindrance to people trying to explain machine learning to those less familiar with it. One of the biggest risks of conflating human and machine intelligence is that we start to hand over too much agency to machines. For those of us working with software, it’s essential that we remember the agency is human—it’s humans who build these systems, after all.
It’s worth unpacking the key differences between machine and human intelligence. While there are certainly similarities, it’s by looking at what makes them different that we can better grasp how artificial intelligence works, and how we can build and use it effectively.
Neural Networks
Central to the metaphor that links human and machine learning is the concept of a neural network. The biggest difference between a human brain and an artificial neural net is the sheer scale of the brain’s neural network. What’s crucial is that it’s not simply the number of neurons in the brain (which reach into the billions), but more precisely, the mind-boggling number of connections between them.
But the issue runs deeper than questions of scale. The human brain is qualitatively different from an artificial neural network for two other important reasons: the connections that power it are analogue, not digital, and the neurons themselves aren’t uniform (as they are in an artificial neural network).
This is why the brain is such a complex thing. Even the most complex artificial neural network, while often difficult to interpret and unpack, has an underlying architecture and principles guiding it (this is what we’re trying to do, so let’s construct the network like this…).
Intricate as they may be, neural networks in AIs are engineered with a specific outcome in mind. The human mind, however, doesn’t have the same degree of intentionality in its engineering. Yes, it should help us do all the things we need to do to stay alive, but it also allows us to think critically and creatively in a way that doesn’t need to be programmed.
The Beautiful Simplicity of AI
The fact that artificial intelligence systems are so much simpler than the human brain is, ironically, what enables AIs to deal with far greater computational complexity than we can.
Artificial neural networks can hold much more information and data than the human brain, largely due to the type of data that is stored and processed in a neural network. It is discrete and specific, like an entry on an excel spreadsheet.
In the human brain, data doesn’t have this same discrete quality. So while an artificial neural network can process very specific data at an incredible scale, it isn’t able to process information in the rich and multidimensional manner a human brain can. This is the key difference between an engineered system and the human mind.
Despite years of research, the human mind still remains somewhat opaque. This is because the analog synaptic connections between neurons are almost impenetrable to the digital connections within an artificial neural network.
Speed and Scale
Consider what this means in practice. The relative simplicity of an AI allows it to do a very complex task very well, and very quickly. A human brain simply can’t process data at scale and speed in the way AIs need to if they’re, say, translating speech to text, or processing a huge set of oncology reports.
Essential to the way AI works in both these contexts is that it breaks data and information down into tiny constituent parts. For example, it could break sounds down into phonetic text, which could then be translated into full sentences, or break images into pieces to understand the rules of how a huge set of them is composed.
Humans often do a similar thing, and this is the point at which machine learning is most like human learning; like algorithms, humans break data or information into smaller chunks in order to process it.
But there’s a reason for this similarity. This breakdown process is engineered into every neural network by a human engineer. What’s more, the way this process is designed will be down to the problem at hand. How an artificial intelligence system breaks down a data set is its own way of ‘understanding’ it.
Even while running a highly complex algorithm unsupervised, the parameters of how an AI learns—how it breaks data down in order to process it—are always set from the start.
Human Intelligence: Defining Problems
Human intelligence doesn’t have this set of limitations, which is what makes us so much more effective at problem-solving. It’s the human ability to ‘create’ problems that makes us so good at solving them. There’s an element of contextual understanding and decision-making in the way humans approach problems.
AIs might be able to unpack problems or find new ways into them, but they can’t define the problem they’re trying to solve.
Algorithmic insensitivity has come into focus in recent years, with an increasing number of scandals around bias in AI systems. Of course, this is caused by the biases of those making the algorithms, but underlines the point that algorithmic biases can only be identified by human intelligence.
Human and Artificial Intelligence Should Complement Each Other
We must remember that artificial intelligence and machine learning aren’t simply things that ‘exist’ that we can no longer control. They are built, engineered, and designed by us. This mindset puts us in control of the future, and makes algorithms even more elegant and remarkable.
Image Credit: Liu zishan/Shutterstock Continue reading
Posted in Human Robots
#433506 MIT’s New Robot Taught Itself to Pick ...
Back in 2016, somewhere in a Google-owned warehouse, more than a dozen robotic arms sat for hours quietly grasping objects of various shapes and sizes. For hours on end, they taught themselves how to pick up and hold the items appropriately—mimicking the way a baby gradually learns to use its hands.
Now, scientists from MIT have made a new breakthrough in machine learning: their new system can not only teach itself to see and identify objects, but also understand how best to manipulate them.
This means that, armed with the new machine learning routine referred to as “dense object nets (DON),” the robot would be capable of picking up an object that it’s never seen before, or in an unfamiliar orientation, without resorting to trial and error—exactly as a human would.
The deceptively simple ability to dexterously manipulate objects with our hands is a huge part of why humans are the dominant species on the planet. We take it for granted. Hardware innovations like the Shadow Dexterous Hand have enabled robots to softly grip and manipulate delicate objects for many years, but the software required to control these precision-engineered machines in a range of circumstances has proved harder to develop.
This was not for want of trying. The Amazon Robotics Challenge offers millions of dollars in prizes (and potentially far more in contracts, as their $775m acquisition of Kiva Systems shows) for the best dexterous robot able to pick and package items in their warehouses. The lucrative dream of a fully-automated delivery system is missing this crucial ability.
Meanwhile, the Robocup@home challenge—an offshoot of the popular Robocup tournament for soccer-playing robots—aims to make everyone’s dream of having a robot butler a reality. The competition involves teams drilling their robots through simple household tasks that require social interaction or object manipulation, like helping to carry the shopping, sorting items onto a shelf, or guiding tourists around a museum.
Yet all of these endeavors have proved difficult; the tasks often have to be simplified to enable the robot to complete them at all. New or unexpected elements, such as those encountered in real life, more often than not throw the system entirely. Programming the robot’s every move in explicit detail is not a scalable solution: this can work in the highly-controlled world of the assembly line, but not in everyday life.
Computer vision is improving all the time. Neural networks, including those you train every time you prove that you’re not a robot with CAPTCHA, are getting better at sorting objects into categories, and identifying them based on sparse or incomplete data, such as when they are occluded, or in different lighting.
But many of these systems require enormous amounts of input data, which is impractical, slow to generate, and often needs to be laboriously categorized by humans. There are entirely new jobs that require people to label, categorize, and sift large bodies of data ready for supervised machine learning. This can make machine learning undemocratic. If you’re Google, you can make thousands of unwitting volunteers label your images for you with CAPTCHA. If you’re IBM, you can hire people to manually label that data. If you’re an individual or startup trying something new, however, you will struggle to access the vast troves of labeled data available to the bigger players.
This is why new systems that can potentially train themselves over time or that allow robots to deal with situations they’ve never seen before without mountains of labelled data are a holy grail in artificial intelligence. The work done by MIT’s Computer Science and Artificial Intelligence Laboratory (CSAIL) is part of a new wave of “self-supervised” machine learning systems—little of the data used was labeled by humans.
The robot first inspects the new object from multiple angles, building up a 3D picture of the object with its own coordinate system. This then allows the robotic arm to identify a particular feature on the object—such as a handle, or the tongue of a shoe—from various different angles, based on its relative distance to other grid points.
This is the real innovation: the new means of representing objects to grasp as mapped-out 3D objects, with grid points and subsections of their own. Rather than using a computer vision algorithm to identify a door handle, and then activating a door handle grasping subroutine, the DON system treats all objects by making these spatial maps before classifying or manipulating them, enabling it to deal with a greater range of objects than in other approaches.
“Many approaches to manipulation can’t identify specific parts of an object across the many orientations that object may encounter,” said PhD student Lucas Manuelli, who wrote a new paper about the system with lead author and fellow student Pete Florence, alongside MIT professor Russ Tedrake. “For example, existing algorithms would be unable to grasp a mug by its handle, especially if the mug could be in multiple orientations, like upright, or on its side.”
Class-specific descriptors, which can be applied to the object features, can allow the robot arm to identify a mug, find the handle, and pick the mug up appropriately. Object-specific descriptors allow the robot arm to select a particular mug from a group of similar items. I’m already dreaming of a robot butler reliably picking my favourite mug when it serves me coffee in the morning.
Google’s robot arm-y was an attempt to develop a general grasping algorithm: one that could identify, categorize, and appropriately grip as many items as possible. This requires a great deal of training time and data, which is why Google parallelized their project by having 14 robot arms feed data into a single neural network brain: even then, the algorithm may fail with highly specific tasks. Specialist grasping algorithms might require less training if they’re limited to specific objects, but then your software is useless for general tasks.
As the roboticists noted, their system, with its ability to identify parts of an object rather than just a single object, is better suited to specific tasks, such as “grasp the racquet by the handle,” than Amazon Robotics Challenge robots, which identify whole objects by segmenting an image.
This work is small-scale at present. It has been tested with a few classes of objects, including shoes, hats, and mugs. Yet the use of these dense object nets as a way for robots to represent and manipulate new objects may well be another step towards the ultimate goal of generalized automation: a robot capable of performing every task a person can. If that point is reached, the question that will remain is how to cope with being obsolete.
Image Credit: Tom Buehler/CSAIL Continue reading
Posted in Human Robots