Tag Archives: inspiration

#435716 Watch This Drone Explode Into Maple Seed ...

As useful as conventional fixed-wing and quadrotor drones have become, they still tend to be relatively complicated, expensive machines that you really want to be able to use more than once. When a one-way trip is all that you have in mind, you want something simple, reliable, and cheap, and we’ve seen a bunch of different designs for drone gliders that more or less fulfill those criteria.

For an even simpler gliding design, you want to minimize both airframe mass and control surfaces, and the maple tree provides some inspiration in the form of samara, those distinctive seed pods that whirl to the ground in the fall. Samara are essentially just an unbalanced wing that spins, and while the natural ones don’t steer, adding an actuated flap to the robotic version and moving it at just the right time results in enough controllability to aim for a specific point on the ground.

Roboticists at the Singapore University of Technology and Design (SUTD) have been experimenting with samara-inspired drones, and in a new paper in IEEE Robotics and Automation Letters they explore what happens if you attach five of the drones together and then separate them in mid air.

Image: Singapore University of Technology and Design

The drone with all five wings attached (top left), and details of the individual wings: (a) smaller 44.9-gram wing for semi-indoor testing; (b) larger 83.4-gram wing able to carry a Pixracer, GPS, and magnetometer for directional control experiments.

Fundamentally, a samara design acts as a decelerator for an aerial payload. You can think of it like a parachute: It makes sure that whatever you toss out of an airplane gets to the ground intact rather than just smashing itself to bits on impact. Steering is possible, but you don’t get a lot of stability or precision control. The RA-L paper describes one solution to this, which is to collaboratively use five drones at once in a configuration that looks a bit like a helicopter rotor.

And once the multi-drone is right where you want it, the five individual samara drones can split off all at once, heading out on their own missions. It's quite a sight:

The concept features a collaborative autorotation in the initial stage of drop whereby several wings are attached to each other to form a rotor hub. The combined form achieves higher rotational energy and a collaborative control strategy is possible. Once closer to the ground, they can exit the collaborative form and continue to descend to unique destinations. A section of each wing forms a flap and a small actuator changes its pitch cyclically. Since all wing-flaps can actuate simultaneously in collaborative mode, better maneuverability is possible, hence higher resistance against environmental conditions. The vertical and horizontal speeds can be controlled to a certain extent, allowing it to navigate towards a target location and land softly.

The samara autorotating wing drones themselves could conceivably carry small payloads like sensors or emergency medical supplies, with these small-scale versions in the video able to handle an extra 30 grams of payload. While they might not have as much capacity as a traditional fixed-wing glider, they have the advantage of being able to descent vertically, and can perform better than a parachute due to their ability to steer. The researchers plan on improving the design of their little drones, with the goal of increasing the rotation speed and improving the control performance of both the individual drones and the multi-wing collaborative version.

“Dynamics and Control of a Collaborative and Separating Descent of Samara Autorotating Wings,” by Shane Kyi Hla Win, Luke Soe Thura Win, Danial Sufiyan, Gim Song Soh, and Shaohui Foong from Singapore University of Technology and Design, appears in the current issue of IEEE Robotics and Automation Letters.
[ SUTD ]

< Back to IEEE Journal Watch Continue reading

Posted in Human Robots

#435632 DARPA Subterranean Challenge: Tunnel ...

The Tunnel Circuit of the DARPA Subterranean Challenge starts later this week at the NIOSH research mine just outside of Pittsburgh, Pennsylvania. From 15-22 August, 11 teams will send robots into a mine that they've never seen before, with the goal of making maps and locating items. All DARPA SubT events involve tunnels of one sort or another, but in this case, the “Tunnel Circuit” refers to mines as opposed to urban underground areas or natural caves. This month’s challenge is the first of three discrete events leading up to a huge final event in August of 2021.

While the Tunnel Circuit competition will be closed to the public, and media are only allowed access for a single day (which we'll be at, of course), DARPA has provided a substantial amount of information about what teams will be able to expect. We also have details from the SubT Integration Exercise, called STIX, which was a completely closed event that took place back in April. STIX was aimed at giving some teams (and DARPA) a chance to practice in a real tunnel environment.

For more general background on SubT, here are some articles to get you all caught up:

SubT: The Next DARPA Challenge for Robotics

Q&A with DARPA Program Manager Tim Chung

Meet The First Nine Teams

It makes sense to take a closer look at what happened at April's STIX exercise, because it is (probably) very similar to what teams will experience in the upcoming Tunnel Circuit. STIX took place at Edgar Experimental Mine in Colorado, and while no two mines are the same (and many are very, very different), there are enough similarities for STIX to have been a valuable experience for teams. Here's an overview video of the exercise from DARPA:

DARPA has also put together a much more detailed walkthrough of the STIX mine exercise, which gives you a sense of just how vast, complicated, and (frankly) challenging for robots the mine environment is:

So, that's the kind of thing that teams had to deal with back in April. Since the event was an exercise, rather than a competition, DARPA didn't really keep score, and wouldn't comment on the performance of individual teams. We've been trolling YouTube for STIX footage, though, to get a sense of how things went, and we found a few interesting videos.

Here's a nice overview from Team CERBERUS, which used drones plus an ANYmal quadruped:

Team CTU-CRAS also used drones, along with a tracked robot:

Team Robotika was brave enough to post video of a “fatal failure” experienced by its wheeled robot; the poor little bot gets rescued at about 7:00 in case you get worried:

So that was STIX. But what about the Tunnel Circuit competition this week? Here's a course preview video from DARPA:

It sort of looks like the NIOSH mine might be a bit less dusty than the Edgar mine was, but it could also be wetter and muddier. It’s hard to tell, because we’re just getting a few snapshots of what’s probably an enormous area with kilometers of tunnels that the robots will have to explore. But DARPA has promised “constrained passages, sharp turns, large drops/climbs, inclines, steps, ladders, and mud, sand, and/or water.” Combine that with the serious challenge to communications imposed by the mine itself, and robots will have to be both physically capable, and almost entirely autonomous. Which is, of course, exactly what DARPA is looking to test with this challenge.

Lastly, we had a chance to catch up with Tim Chung, Program Manager for the Subterranean Challenge at DARPA, and ask him a few brief questions about STIX and what we have to look forward to this week.

IEEE Spectrum: How did STIX go?

Tim Chung: It was a lot of fun! I think it gave a lot of the teams a great opportunity to really get a taste of what these types of real world environments look like, and also what DARPA has in store for them in the SubT Challenge. STIX I saw as an experiment—a learning experience for all the teams involved (as well as the DARPA team) so that we can continue our calibration.

What do you think teams took away from STIX, and what do you think DARPA took away from STIX?

I think the thing that teams took away was that, when DARPA hosts a challenge, we have very audacious visions for what the art of the possible is. And that's what we want—in my mind, the purpose of a DARPA Grand Challenge is to provide that inspiration of, ‘Holy cow, someone thinks we can do this!’ So I do think the teams walked away with a better understanding of what DARPA's vision is for the capabilities we're seeking in the SubT Challenge, and hopefully walked away with a better understanding of the technical, physical, even maybe mental challenges of doing this in the wild— which will all roll back into how they think about the problem, and how they develop their systems.

This was a collaborative exercise, so the DARPA field team was out there interacting with the other engineers, figuring out what their strengths and weaknesses and needs might be, and even understanding how to handle the robots themselves. That will help [strengthen] connections between these university teams and DARPA going forward. Across the board, I think that collaborative spirit is something we really wish to encourage, and something that the DARPA folks were able to take away.

What do we have to look forward to during the Tunnel Circuit?

The vision here is that the Tunnel Circuit is representative of one of the three subterranean subdomains, along with urban and cave. Characteristics of all of these three subdomains will be mashed together in an epic final course, so that teams will have to face hints of tunnel once again in that final event.

Without giving too much away, the NIOSH mine will be similar to the Edgar mine in that it's a human-made environment that supports mining operations and research. But of course, every site is different, and these differences, I think, will provide good opportunities for the teams to shine.

Again, we'll be visiting the NIOSH mine in Pennsylvania during the Tunnel Circuit and will post as much as we can from there. But if you’re an actual participant in the Subterranean Challenge, please tweet me @BotJunkie so that I can follow and help share live updates.

[ DARPA Subterranean Challenge ] Continue reading

Posted in Human Robots

#435423 Moving Beyond Mind-Controlled Limbs to ...

Brain-machine interface enthusiasts often gush about “closing the loop.” It’s for good reason. On the implant level, it means engineering smarter probes that only activate when they detect faulty electrical signals in brain circuits. Elon Musk’s Neuralink—among other players—are readily pursuing these bi-directional implants that both measure and zap the brain.

But to scientists laboring to restore functionality to paralyzed patients or amputees, “closing the loop” has broader connotations. Building smart mind-controlled robotic limbs isn’t enough; the next frontier is restoring sensation in offline body parts. To truly meld biology with machine, the robotic appendage has to “feel one” with the body.

This month, two studies from Science Robotics describe complementary ways forward. In one, scientists from the University of Utah paired a state-of-the-art robotic arm—the DEKA LUKE—with electrically stimulating remaining nerves above the attachment point. Using artificial zaps to mimic the skin’s natural response patterns to touch, the team dramatically increased the patient’s ability to identify objects. Without much training, he could easily discriminate between the small and large and the soft and hard while blindfolded and wearing headphones.

In another, a team based at the National University of Singapore took inspiration from our largest organ, the skin. Mimicking the neural architecture of biological skin, the engineered “electronic skin” not only senses temperature, pressure, and humidity, but continues to function even when scraped or otherwise damaged. Thanks to artificial nerves that transmit signals far faster than our biological ones, the flexible e-skin shoots electrical data 1,000 times quicker than human nerves.

Together, the studies marry neuroscience and robotics. Representing the latest push towards closing the loop, they show that integrating biological sensibilities with robotic efficiency isn’t impossible (super-human touch, anyone?). But more immediately—and more importantly—they’re beacons of hope for patients who hope to regain their sense of touch.

For one of the participants, a late middle-aged man with speckled white hair who lost his forearm 13 years ago, superpowers, cyborgs, or razzle-dazzle brain implants are the last thing on his mind. After a barrage of emotionally-neutral scientific tests, he grasped his wife’s hand and felt her warmth for the first time in over a decade. His face lit up in a blinding smile.

That’s what scientists are working towards.

Biomimetic Feedback
The human skin is a marvelous thing. Not only does it rapidly detect a multitude of sensations—pressure, temperature, itch, pain, humidity—its wiring “binds” disparate signals together into a sensory fingerprint that helps the brain identify what it’s feeling at any moment. Thanks to over 45 miles of nerves that connect the skin, muscles, and brain, you can pick up a half-full coffee cup, knowing that it’s hot and sloshing, while staring at your computer screen. Unfortunately, this complexity is also why restoring sensation is so hard.

The sensory electrode array implanted in the participant’s arm. Image Credit: George et al., Sci. Robot. 4, eaax2352 (2019)..
However, complex neural patterns can also be a source of inspiration. Previous cyborg arms are often paired with so-called “standard” sensory algorithms to induce a basic sense of touch in the missing limb. Here, electrodes zap residual nerves with intensities proportional to the contact force: the harder the grip, the stronger the electrical feedback. Although seemingly logical, that’s not how our skin works. Every time the skin touches or leaves an object, its nerves shoot strong bursts of activity to the brain; while in full contact, the signal is much lower. The resulting electrical strength curve resembles a “U.”

The LUKE hand. Image Credit: George et al., Sci. Robot. 4, eaax2352 (2019).
The team decided to directly compare standard algorithms with one that better mimics the skin’s natural response. They fitted a volunteer with a robotic LUKE arm and implanted an array of electrodes into his forearm—right above the amputation—to stimulate the remaining nerves. When the team activated different combinations of electrodes, the man reported sensations of vibration, pressure, tapping, or a sort of “tightening” in his missing hand. Some combinations of zaps also made him feel as if he were moving the robotic arm’s joints.

In all, the team was able to carefully map nearly 120 sensations to different locations on the phantom hand, which they then overlapped with contact sensors embedded in the LUKE arm. For example, when the patient touched something with his robotic index finger, the relevant electrodes sent signals that made him feel as if he were brushing something with his own missing index fingertip.

Standard sensory feedback already helped: even with simple electrical stimulation, the man could tell apart size (golf versus lacrosse ball) and texture (foam versus plastic) while blindfolded and wearing noise-canceling headphones. But when the team implemented two types of neuromimetic feedback—electrical zaps that resembled the skin’s natural response—his performance dramatically improved. He was able to identify objects much faster and more accurately under their guidance. Outside the lab, he also found it easier to cook, feed, and dress himself. He could even text on his phone and complete routine chores that were previously too difficult, such as stuffing an insert into a pillowcase, hammering a nail, or eating hard-to-grab foods like eggs and grapes.

The study shows that the brain more readily accepts biologically-inspired electrical patterns, making it a relatively easy—but enormously powerful—upgrade that seamlessly integrates the robotic arms with the host. “The functional and emotional benefits…are likely to be further enhanced with long-term use, and efforts are underway to develop a portable take-home system,” the team said.

E-Skin Revolution: Asynchronous Coded Electronic Skin (ACES)
Flexible electronic skins also aren’t new, but the second team presented an upgrade in both speed and durability while retaining multiplexed sensory capabilities.

Starting from a combination of rubber, plastic, and silicon, the team embedded over 200 sensors onto the e-skin, each capable of discerning contact, pressure, temperature, and humidity. They then looked to the skin’s nervous system for inspiration. Our skin is embedded with a dense array of nerve endings that individually transmit different types of sensations, which are integrated inside hubs called ganglia. Compared to having every single nerve ending directly ping data to the brain, this “gather, process, and transmit” architecture rapidly speeds things up.

The team tapped into this biological architecture. Rather than pairing each sensor with a dedicated receiver, ACES sends all sensory data to a single receiver—an artificial ganglion. This setup lets the e-skin’s wiring work as a whole system, as opposed to individual electrodes. Every sensor transmits its data using a characteristic pulse, which allows it to be uniquely identified by the receiver.

The gains were immediate. First was speed. Normally, sensory data from multiple individual electrodes need to be periodically combined into a map of pressure points. Here, data from thousands of distributed sensors can independently go to a single receiver for further processing, massively increasing efficiency—the new e-skin’s transmission rate is roughly 1,000 times faster than that of human skin.

Second was redundancy. Because data from individual sensors are aggregated, the system still functioned even when any individual receptors are damaged, making it far more resilient than previous attempts. Finally, the setup could easily scale up. Although the team only tested the idea with 240 sensors, theoretically the system should work with up to 10,000.

The team is now exploring ways to combine their invention with other material layers to make it water-resistant and self-repairable. As you might’ve guessed, an immediate application is to give robots something similar to complex touch. A sensory upgrade not only lets robots more easily manipulate tools, doorknobs, and other objects in hectic real-world environments, it could also make it easier for machines to work collaboratively with humans in the future (hey Wall-E, care to pass the salt?).

Dexterous robots aside, the team also envisions engineering better prosthetics. When coated onto cyborg limbs, for example, ACES may give them a better sense of touch that begins to rival the human skin—or perhaps even exceed it.

Regardless, efforts that adapt the functionality of the human nervous system to machines are finally paying off, and more are sure to come. Neuromimetic ideas may very well be the link that finally closes the loop.

Image Credit: Dan Hixson/University of Utah College of Engineering.. Continue reading

Posted in Human Robots

#434854 New Lifelike Biomaterial Self-Reproduces ...

Life demands flux.

Every living organism is constantly changing: cells divide and die, proteins build and disintegrate, DNA breaks and heals. Life demands metabolism—the simultaneous builder and destroyer of living materials—to continuously upgrade our bodies. That’s how we heal and grow, how we propagate and survive.

What if we could endow cold, static, lifeless robots with the gift of metabolism?

In a study published this month in Science Robotics, an international team developed a DNA-based method that gives raw biomaterials an artificial metabolism. Dubbed DASH—DNA-based assembly and synthesis of hierarchical materials—the method automatically generates “slime”-like nanobots that dynamically move and navigate their environments.

Like humans, the artificial lifelike material used external energy to constantly change the nanobots’ bodies in pre-programmed ways, recycling their DNA-based parts as both waste and raw material for further use. Some “grew” into the shape of molecular double-helixes; others “wrote” the DNA letters inside micro-chips.

The artificial life forms were also rather “competitive”—in quotes, because these molecular machines are not conscious. Yet when pitted against each other, two DASH bots automatically raced forward, crawling in typical slime-mold fashion at a scale easily seen under the microscope—and with some iterations, with the naked human eye.

“Fundamentally, we may be able to change how we create and use the materials with lifelike characteristics. Typically materials and objects we create in general are basically static… one day, we may be able to ‘grow’ objects like houses and maintain their forms and functions autonomously,” said study author Dr. Shogo Hamada to Singularity Hub.

“This is a great study that combines the versatility of DNA nanotechnology with the dynamics of living materials,” said Dr. Job Boekhoven at the Technical University of Munich, who was not involved in the work.

Dissipative Assembly
The study builds on previous ideas on how to make molecular Lego blocks that essentially assemble—and destroy—themselves.

Although the inspiration came from biological metabolism, scientists have long hoped to cut their reliance on nature. At its core, metabolism is just a bunch of well-coordinated chemical reactions, programmed by eons of evolution. So why build artificial lifelike materials still tethered by evolution when we can use chemistry to engineer completely new forms of artificial life?

Back in 2015, for example, a team led by Boekhoven described a way to mimic how our cells build their internal “structural beams,” aptly called the cytoskeleton. The key here, unlike many processes in nature, isn’t balance or equilibrium; rather, the team engineered an extremely unstable system that automatically builds—and sustains—assemblies from molecular building blocks when given an external source of chemical energy.

Sound familiar? The team basically built molecular devices that “die” without “food.” Thanks to the laws of thermodynamics (hey ya, Newton!), that energy eventually dissipates, and the shapes automatically begin to break down, completing an artificial “circle of life.”

The new study took the system one step further: rather than just mimicking synthesis, they completed the circle by coupling the building process with dissipative assembly.

Here, the “assembling units themselves are also autonomously created from scratch,” said Hamada.

DNA Nanobots
The process of building DNA nanobots starts on a microfluidic chip.

Decades of research have allowed researchers to optimize DNA assembly outside the body. With the help of catalysts, which help “bind” individual molecules together, the team found that they could easily alter the shape of the self-assembling DNA bots—which formed fiber-like shapes—by changing the structure of the microfluidic chambers.

Computer simulations played a role here too: through both digital simulations and observations under the microscope, the team was able to identify a few critical rules that helped them predict how their molecules self-assemble while navigating a maze of blocking “pillars” and channels carved onto the microchips.

This “enabled a general design strategy for the DASH patterns,” they said.

In particular, the whirling motion of the fluids as they coursed through—and bumped into—ridges in the chips seems to help the DNA molecules “entangle into networks,” the team explained.

These insights helped the team further develop the “destroying” part of metabolism. Similar to linking molecules into DNA chains, their destruction also relies on enzymes.

Once the team pumped both “generation” and “degeneration” enzymes into the microchips, along with raw building blocks, the process was completely autonomous. The simultaneous processes were so lifelike that the team used a metric commonly used in robotics, finite-state automation, to measure the behavior of their DNA nanobots from growth to eventual decay.

“The result is a synthetic structure with features associated with life. These behaviors include locomotion, self-regeneration, and spatiotemporal regulation,” said Boekhoven.

Molecular Slime Molds
Just witnessing lifelike molecules grow in place like the dance move running man wasn’t enough.

In their next experiments, the team took inspiration from slugs to program undulating movements into their DNA bots. Here, “movement” is actually a sort of illusion: the machines “moved” because their front ends kept regenerating, whereas their back ends degenerated. In essence, the molecular slime was built from linking multiple individual “DNA robot-like” units together: each unit receives a delayed “decay” signal from the head of the slime in a way that allowed the whole artificial “organism” to crawl forward, against the steam of fluid flow.

Here’s the fun part: the team eventually engineered two molecular slime bots and pitted them against each other, Mario Kart-style. In these experiments, the faster moving bot alters the state of its competitor to promote “decay.” This slows down the competitor, allowing the dominant DNA nanoslug to win in a race.

Of course, the end goal isn’t molecular podracing. Rather, the DNA-based bots could easily amplify a given DNA or RNA sequence, making them efficient nano-diagnosticians for viral and other infections.

The lifelike material can basically generate patterns that doctors can directly ‘see’ with their eyes, which makes DNA or RNA molecules from bacteria and viruses extremely easy to detect, the team said.

In the short run, “the detection device with this self-generating material could be applied to many places and help people on site, from farmers to clinics, by providing an easy and accurate way to detect pathogens,” explained Hamaga.

A Futuristic Iron Man Nanosuit?
I’m letting my nerd flag fly here. In Avengers: Infinity Wars, the scientist-engineer-philanthropist-playboy Tony Stark unveiled a nanosuit that grew to his contours when needed and automatically healed when damaged.

DASH may one day realize that vision. For now, the team isn’t focused on using the technology for regenerating armor—rather, the dynamic materials could create new protein assemblies or chemical pathways inside living organisms, for example. The team also envisions adding simple sensing and computing mechanisms into the material, which can then easily be thought of as a robot.

Unlike synthetic biology, the goal isn’t to create artificial life. Rather, the team hopes to give lifelike properties to otherwise static materials.

“We are introducing a brand-new, lifelike material concept powered by its very own artificial metabolism. We are not making something that’s alive, but we are creating materials that are much more lifelike than have ever been seen before,” said lead author Dr. Dan Luo.

“Ultimately, our material may allow the construction of self-reproducing machines… artificial metabolism is an important step toward the creation of ‘artificial’ biological systems with dynamic, lifelike capabilities,” added Hamada. “It could open a new frontier in robotics.”

Image Credit: A timelapse image of DASH, by Jeff Tyson at Cornell University. Continue reading

Posted in Human Robots

#434786 AI Performed Like a Human on a Gestalt ...

Dr. Been Kim wants to rip open the black box of deep learning.

A senior researcher at Google Brain, Kim specializes in a sort of AI psychology. Like cognitive psychologists before her, she develops various ways to probe the alien minds of artificial neural networks (ANNs), digging into their gory details to better understand the models and their responses to inputs.

The more interpretable ANNs are, the reasoning goes, the easier it is to reveal potential flaws in their reasoning. And if we understand when or why our systems choke, we’ll know when not to use them—a foundation for building responsible AI.

There are already several ways to tap into ANN reasoning, but Kim’s inspiration for unraveling the AI black box came from an entirely different field: cognitive psychology. The field aims to discover fundamental rules of how the human mind—essentially also a tantalizing black box—operates, Kim wrote with her colleagues.

In a new paper uploaded to the pre-publication server arXiv, the team described a way to essentially perform a human cognitive test on ANNs. The test probes how we automatically complete gaps in what we see, so that they form entire objects—for example, perceiving a circle from a bunch of loose dots arranged along a clock face. Psychologist dub this the “law of completion,” a highly influential idea that led to explanations of how our minds generalize data into concepts.

Because deep neural networks in machine vision loosely mimic the structure and connections of the visual cortex, the authors naturally asked: do ANNs also exhibit the law of completion? And what does that tell us about how an AI thinks?

Enter the Germans
The law of completion is part of a series of ideas from Gestalt psychology. Back in the 1920s, long before the advent of modern neuroscience, a group of German experimental psychologists asked: in this chaotic, flashy, unpredictable world, how do we piece together input in a way that leads to meaningful perceptions?

The result is a group of principles known together as the Gestalt effect: that the mind self-organizes to form a global whole. In the more famous words of Gestalt psychologist Kurt Koffka, our perception forms a whole that’s “something else than the sum of its parts.” Not greater than; just different.

Although the theory has its critics, subsequent studies in humans and animals suggest that the law of completion happens on both the cognitive and neuroanatomical level.

Take a look at the drawing below. You immediately “see” a shape that’s actually the negative: a triangle or a square (A and B). Or you further perceive a 3D ball (C), or a snake-like squiggle (D). Your mind fills in blank spots, so that the final perception is more than just the black shapes you’re explicitly given.

Image Credit: Wikimedia Commons contributors, the free media repository.
Neuroscientists now think that the effect comes from how our visual system processes information. Arranged in multiple layers and columns, lower-level neurons—those first to wrangle the data—tend to extract simpler features such as lines or angles. In Gestalt speak, they “see” the parts.

Then, layer by layer, perception becomes more abstract, until higher levels of the visual system directly interpret faces or objects—or things that don’t really exist. That is, the “whole” emerges.

The Experiment Setup
Inspired by these classical experiments, Kim and team developed a protocol to test the Gestalt effect on feed-forward ANNs: one simple, the other, dubbed the “Inception V3,” far more complex and widely used in the machine vision community.

The main idea is similar to the triangle drawings above. First, the team generated three datasets: one set shows complete, ordinary triangles. The second—the “Illusory” set, shows triangles with the edges removed but the corners intact. Thanks to the Gestalt effect, to us humans these generally still look like triangles. The third set also only shows incomplete triangle corners. But here, the corners are randomly rotated so that we can no longer imagine a line connecting them—hence, no more triangle.

To generate a dataset large enough to tease out small effects, the authors changed the background color, image rotation, and other aspects of the dataset. In all, they produced nearly 1,000 images to test their ANNs on.

“At a high level, we compare an ANN’s activation similarities between the three sets of stimuli,” the authors explained. The process is two steps: first, train the AI on complete triangles. Second, test them on the datasets. If the response is more similar between the illusory set and the complete triangle—rather than the randomly rotated set—it should suggest a sort of Gestalt closure effect in the network.

Machine Gestalt
Right off the bat, the team got their answer: yes, ANNs do seem to exhibit the law of closure.

When trained on natural images, the networks better classified the illusory set as triangles than those with randomized connection weights or networks trained on white noise.

When the team dug into the “why,” things got more interesting. The ability to complete an image correlated with the network’s ability to generalize.

Humans subconsciously do this constantly: anything with a handle made out of ceramic, regardless of shape, could easily be a mug. ANNs still struggle to grasp common features—clues that immediately tells us “hey, that’s a mug!” But when they do, it sometimes allows the networks to better generalize.

“What we observe here is that a network that is able to generalize exhibits…more of the closure effect [emphasis theirs], hinting that the closure effect reflects something beyond simply learning features,” the team wrote.

What’s more, remarkably similar to the visual cortex, “higher” levels of the ANNs showed more of the closure effect than lower layers, and—perhaps unsurprisingly—the more layers a network had, the more it exhibited the closure effect.

As the networks learned, their ability to map out objects from fragments also improved. When the team messed around with the brightness and contrast of the images, the AI still learned to see the forest from the trees.

“Our findings suggest that neural networks trained with natural images do exhibit closure,” the team concluded.

AI Psychology
That’s not to say that ANNs recapitulate the human brain. As Google’s Deep Dream, an effort to coax AIs into spilling what they’re perceiving, clearly demonstrates, machine vision sees some truly weird stuff.

In contrast, because they’re modeled after the human visual cortex, perhaps it’s not all that surprising that these networks also exhibit higher-level properties inherent to how we process information.

But to Kim and her colleagues, that’s exactly the point.

“The field of psychology has developed useful tools and insights to study human brains– tools that we may be able to borrow to analyze artificial neural networks,” they wrote.

By tweaking these tools to better analyze machine minds, the authors were able to gain insight on how similarly or differently they see the world from us. And that’s the crux: the point isn’t to say that ANNs perceive the world sort of, kind of, maybe similar to humans. It’s to tap into a wealth of cognitive psychology tools, established over decades using human minds, to probe that of ANNs.

“The work here is just one step along a much longer path,” the authors conclude.

“Understanding where humans and neural networks differ will be helpful for research on interpretability by enlightening the fundamental differences between the two interesting species.”

Image Credit: Popova Alena / Shutterstock.com Continue reading

Posted in Human Robots