Tag Archives: of
#439399 An overview of Humanoid tech in 2021
Some of the most advanced humanoid robots we saw in 2021.
Posted in Human Robots
#439934 New Spiking Neuromorphic Chip Could ...
When it comes to brain computing, timing is everything. It’s how neurons wire up into circuits. It’s how these circuits process highly complex data, leading to actions that can mean life or death. It’s how our brains can make split-second decisions, even when faced with entirely new circumstances. And we do so without frying the brain from extensive energy consumption.
To rephrase, the brain makes an excellent example of an extremely powerful computer to mimic—and computer scientists and engineers have taken the first steps towards doing so. The field of neuromorphic computing looks to recreate the brain’s architecture and data processing abilities with novel hardware chips and software algorithms. It may be a pathway towards true artificial intelligence.
But one crucial element is lacking. Most algorithms that power neuromorphic chips only care about the contribution of each artificial neuron—that is, how strongly they connect to one another, dubbed “synaptic weight.” What’s missing—yet tantamount to our brain’s inner working—is timing.
This month, a team affiliated with the Human Brain Project, the European Union’s flagship big data neuroscience endeavor, added the element of time to a neuromorphic algorithm. The results were then implemented on physical hardware—the BrainScaleS-2 neuromorphic platform—and pitted against state-of-the-art GPUs and conventional neuromorphic solutions.
“Compared to the abstract neural networks used in deep learning, the more biological archetypes…still lag behind in terms of performance and scalability” due to their inherent complexity, the authors said.
In several tests, the algorithm compared “favorably, in terms of accuracy, latency, and energy efficiency” on a standard benchmark test, said Dr. Charlotte Frenkel at the University of Zurich and ETH Zurich in Switzerland, who was not involved in the study. By adding a temporal component into neuromorphic computing, we could usher in a new era of highly efficient AI that moves from static data tasks—say, image recognition—to one that better encapsulates time. Think videos, biosignals, or brain-to-computer speech.
To lead author Dr. Mihai Petrovici, the potential goes both ways. “Our work is not only interesting for neuromorphic computing and biologically inspired hardware. It also acknowledges the demand … to transfer so-called deep learning approaches to neuroscience and thereby further unveil the secrets of the human brain,” he said.
Let’s Talk Spikes
At the root of the new algorithm is a fundamental principle in brain computing: spikes.
Let’s take a look at a highly abstracted neuron. It’s like a tootsie roll, with a bulbous middle section flanked by two outward-reaching wrappers. One side is the input—an intricate tree that receives signals from a previous neuron. The other is the output, blasting signals to other neurons using bubble-like ships filled with chemicals, which in turn triggers an electrical response on the receiving end.
Here’s the crux: for this entire sequence to occur, the neuron has to “spike.” If, and only if, the neuron receives a high enough level of input—a nicely built-in noise reduction mechanism—the bulbous part will generate a spike that travels down the output channels to alert the next neuron.
But neurons don’t just use one spike to convey information. Rather, they spike in a time sequence. Think of it like Morse Code: the timing of when an electrical burst occurs carries a wealth of data. It’s the basis for neurons wiring up into circuits and hierarchies, allowing highly energy-efficient processing.
So why not adopt the same strategy for neuromorphic computers?
A Spartan Brain-Like Chip
Instead of mapping out a single artificial neuron’s spikes—a Herculean task—the team honed in on a single metric: how long it takes for a neuron to fire.
The idea behind “time-to-first-spike” code is simple: the longer it takes a neuron to spike, the lower its activity levels. Compared to counting spikes, it’s an extremely sparse way to encode a neuron’s activity, but comes with perks. Because only the latency to the first time a neuron perks up is used to encode activation, it captures the neuron’s responsiveness without overwhelming a computer with too many data points. In other words, it’s fast, energy-efficient, and easy.
The team next encoded the algorithm onto a neuromorphic chip—the BrainScaleS-2, which roughly emulates simple “neurons” inside its structure, but runs over 1,000 times faster than our biological brains. The platform has over 500 physical artificial neurons, each capable of receiving 256 inputs through configurable synapses, where biological neurons swap, process, and store information.
The setup is a hybrid. “Learning” is achieved on a chip that implements the time-dependent algorithm. However, any updates to the neural circuit—that is, how strongly one neuron connects to another—is achieved through an external workstation, something dubbed “in-the-loop training.”
In a first test, the algorithm was challenged with the “Yin-Yang” task, which requires the algorithm to parse different areas in the traditional Eastern symbol. The algorithm excelled, with an average of 95 percent accuracy.
The team next challenged the setup with a classic deep learning task—MNIST, a dataset of handwritten numbers that revolutionized computer vision. The algorithm excelled again, with nearly 97 percent accuracy. Even more impressive, the BrainScaleS-2 system took less than one second to classify 10,000 test samples, with extremely low relative energy consumption.
Putting these results into context, the team next compared BrainScaleS-2’s performance—armed with the new algorithm—to commercial and other neuromorphic platforms. Take SpiNNaker, a massive, parallel distributed architecture that also mimics neural computing and spikes. The new algorithm was over 100 times faster at image recognition while consuming just a fraction of the power SpiNNaker consumes. Similar results were seen with True North, the harbinger IBM neuromorphic chip.
What Next?
The brain’s two most valuable computing features—energy efficiency and parallel processing—are now heavily inspiring the next generation of computer chips. The goal? Build machines that are as flexible and adaptive as our own brains while using just a fraction of the energy required for our current silicon-based chips.
Yet compared to deep learning, which relies on artificial neural networks, biologically-plausible ones have languished. Part of this, explained Frenkel, is the difficultly of “updating” these circuits through learning. However, with BrainScaleS-2 and a touch of timing data, it’s now possible.
At the same time, having an “external” arbitrator for updating synaptic connections gives the whole system some time to breathe. Neuromorphic hardware, similar to the messiness of our brain computation, is littered with mismatches and errors. With the chip and an external arbitrator, the whole system can learn to adapt to this variability, and eventually compensate for—or even exploit—its quirks for faster and more flexible learning.
For Frenkel, the algorithm’s power lies in its sparseness. The brain, she explained, is powered by sparse codes that “could explain the fast reaction times…such as for visual processing.” Rather than activating entire brain regions, only a few neural networks are needed—like whizzing down empty highways instead of getting stuck in rush hour traffic.
Despite its power, the algorithm still has hiccups. It struggles with interpreting static data, although it excels with time sequences—for example, speech or biosignals. But to Frenkel, it’s the start of a new framework: important information can be encoded with a flexible but simple metric, and generalized to enrich brain- and AI-based data processing with a fraction of the traditional energy costs.
“[It]…may be an important stepping-stone for spiking neuromorphic hardware to finally demonstrate a competitive advantage over conventional neural network approaches,” she said.
Image Credit: Classifying data points in the Yin-Yang dataset, by Göltz and Kriener et al. (Heidelberg / Bern) Continue reading
Posted in Human Robots
#439849 Boots Full of Nickels Help Mini Cheetah ...
As quadrupedal robots learn to do more and more dynamic tasks, they're likely to spend more and more time not on their feet. Not falling over, necessarily (although that's inevitable of course, because they're legged robots after all)—but just being in flight in one way or another. The most risky of flight phases would be a fall from a substantial height, because it's almost certain to break your very expensive robot and any payload it might have.
Falls being bad is not a problem unique to robots, and it's not surprising that quadrupeds in nature have already solved it. Or at least, it's already been solved by cats, which are able to reliably land on their feet to mitigate fall damage. To teach quadrupedal robots this trick, roboticists from the University of Notre Dame have been teaching a Mini Cheetah quadruped some mid-air self-righting skills, with the aid of boots full of nickels.
If this research looks a little bit familiar, it's because we recently covered some work from ETH Zurich that looked at using legs to reorient their SpaceBok quadruped in microgravity. This work with Mini Cheetah has to contend with Earth gravity, however, which puts some fairly severe time constraints on the whole reorientation thing with the penalty for failure being a smashed-up robot rather than just a weird bounce. When we asked the ETH Zurich researchers what might improve the performance of SpaceBok, they told us that “heavy shoes would definitely help,” and it looks like the folks from Notre Dame had the same idea, which they were able to implement on Mini Cheetah.
Mini Cheetah's legs (like the legs of many robots) were specifically designed to be lightweight because they have to move quickly, and you want to minimize the mass that moves back and forth with every step to make the robot as efficient as possible. But for a robot to reorient itself in mid air, it's got to start swinging as much mass around as it can. Each of Mini Cheetah's legs has been modified with 3D printed boots, packed with two rolls of American nickels each, adding about 500g to each foot—enough to move the robot around like it needs to. The reason why nickel boots are important is because the only way that Mini Cheetah has of changing its orientation while falling is by flailing its legs around. When its legs move one way, its body will move the other way, and the heavier the legs are, the more force they can exert on the body.
As with everything robotics, getting the hardware to do what you want it to do is only half the battle. Or sometimes much, much less than half the battle. The challenge with Mini Cheetah flipping itself over is that it has a very, very small amount of time to figure out how to do it properly. It has to detect that it's falling, figure out what orientation it's in, make a plan of how to get itself feet down, and then execute on that plan successfully. The robot doesn't have enough time to put a whole heck of a lot of thought into things as it starts to plummet, so the technique that the researchers came up with to enable it to do what it needs to do is called a “reflex” approach. Vince Kurtz, first author on the paper describing this technique, explains how it works:
While trajectory optimization algorithms keep getting better and better, they still aren't quite fast enough to find a solution from scratch in the fraction of a second between when the robot detects a fall and when it needs to start a recovery motion. We got around this by dropping the robot a bunch of times in simulation, where we can take as much time as we need to find a solution, and training a neural network to imitate the trajectory optimizer. The trained neural network maps initial orientations to trajectories that land the robot on its feet. We call this the “reflex” approach, since the neural network has basically learned an automatic response that can be executed when the robot detects that it's falling.This technique works quite well, but there are a few constraints, most of which wouldn't seem so bad if we weren't comparing quadrupedal robots to quadrupedal animals. Cats are just, like, super competent at what they do, says Kurtz, and being able to mimic their ability to rapidly twist themselves into a favorable landing configuration from any starting orientation is just going to be really hard for a robot to pull off:
The more I do robotics research the more I appreciate how amazing nature is, and this project is a great example of that. Cats can do a full 180° rotation when dropped from about shoulder height. Our robot ran up against torque limits when rotating 90° from about 10ft off the ground. Using the full 3D motion would be a big improvement (rotating sideways should be easier because the robot's moment of inertia is smaller in that direction), though I'd be surprised if that alone got us to cat-level performance.
The biggest challenge that I see in going from 2D to 3D is self-collisions. Keeping the robot from hitting itself seems like it should be simple, but self-collisions turn out to impose rather nasty non-convex constraints that make it numerically difficult (though not impossible) for trajectory optimization algorithms to find high-quality solutions.Lastly, we asked Kurtz to talk a bit about whether it's worth exploring flexible actuated spines for quadrupedal robots. We know that such spines offer many advantages (a distant relative of Mini Cheetah had one, for example), but that they're also quite complex. So is it worth it?
This is an interesting question. Certainly in the case of the falling cat problem a flexible spine would help, both in terms of having a naturally flexible mass distribution and in terms of controller design, since we might be able to directly imitate the “bend-and-twist” motion of cats. Similarly, a flexible spine might help for tasks with large flight phases, like the jumping in space problems discussed in the ETH paper.
With that being said, mid-air reorientation is not the primary task of most quadruped robots, and it's not obvious to me that a flexible spine would help much for walking, running, or scrambling over uneven terrain. Also, existing hardware platforms with rigid backs like the Mini Cheetah are quite capable and I think we still haven't unlocked the full potential of these robots. Control algorithms are still the primary limiting factor for today's legged robots, and adding a flexible spine would probably make for even more difficult control problems.Mini Cheetah, the Falling Cat: A Case Study in Machine Learning and Trajectory Optimization for Robot Acrobatics, by Vince Kurtz, He Li, Patrick M. Wensing, and Hai Lin from University of Notre Dame, is available on arXiv. Continue reading
Posted in Human Robots
#439842 AI-Powered Brain Implant Eases Severe ...
Sarah hadn’t laughed in five years.
At 36 years old, the avid home cook has struggled with depression since early childhood. She tried the whole range of antidepressant medications and therapy for decades. Nothing worked. One night, five years ago, driving home from work, she had one thought in her mind: this is it. I’m done.
Luckily she made it home safe. And soon she was offered an intriguing new possibility to tackle her symptoms—a little chip, implanted into her brain, that captures the unique neural signals encoding her depression. Once the implant detects those signals, it zaps them away with a brief electrical jolt, like adding noise to an enemy’s digital transmissions to scramble their original message. When that message triggers depression, hijacking neural communications is exactly what we want to do.
Flash forward several years, and Sarah has her depression under control for the first time in her life. Her suicidal thoughts evaporated. After quitting her tech job due to her condition, she’s now back on her feet, enrolled in data analytics classes and taking care of her elderly mother. “For the first time,” she said, “I’m finally laughing.”
Sarah’s recovery is just one case. But it signifies a new era for the technology underlying her stunning improvement. It’s one of the first cases in which a personalized “brain pacemaker” can stealthily tap into, decipher, and alter a person’s mood and introspection based on their own unique electrical brain signatures. And while those implants have achieved stunning medical miracles in other areas—such as allowing people with paralysis to walk again—Sarah’s recovery is some of the strongest evidence yet that a computer chip, in a brain, powered by AI, can fundamentally alter our perception of life. It’s the closest to reading and repairing a troubled mind that we’ve ever gotten.
“We haven’t been able to do this kind of personalized therapy previously in psychiatry,” said study lead Dr. Katherine Scangos at UCSF. “This success in itself is an incredible advancement in our knowledge of the brain function that underlies mental illness.”
Brain Pacemaker
The key to Sarah’s recovery is a brain-machine interface.
Roughly the size of a matchbox, the implant sits inside the brain, silently listening to and decoding its electrical signals. Using those signals, it’s possible to control other parts of the brain or body. Brain implants have given people with lower body paralysis the ability to walk again. They’ve allowed amputees to control robotic hands with just a thought. They’ve opened up a world of sensations, integrating feedback from cyborg-like artificial limbs that transmit signals directly into the brain.
But Sarah’s implant is different.
Sensation and movement are generally controlled by relatively well-defined circuits in the outermost layer of the brain: the cortex. Emotion and mood are also products of our brain’s electrical signals, but they tend to stem from deeper neural networks hidden at the center of the brain. One way to tap into those circuits is called deep brain stimulation (DBS), a method pioneered in the ’80s that’s been used to treat severe Parkinson’s disease and epilepsy, particularly for cases that don’t usually respond to medication.
Sarah’s neural implant takes this route: it listens in on the chatter between neurons deep within the brain to decode mood.
But where is mood in the brain? One particular problem, the authors explained, is that unlike movement, there is no “depression brain region.” Rather, emotions are regulated by intricate, intertwining networks across multiple brain regions. Adding to that complexity is the fact that we’re all neural snowflakes—each of us have uniquely personalized brain network connections.
In other words, zapping my circuit to reduce depression might not work for you. DBS, for example, has previously been studied for treating depression. But despite decades of research, it’s not federally approved due to inconsistent results. The culprit? The electrical stimulation patterns used in those trials were constant and engineered to be one-size-fits-all. Have you ever tried buying socks or PJs at a department store, seen the tag that says “one size,” and they don’t fit? Yeah. DBS has brought about remarkable improvements for some people with depression—ill-fitting socks are better than none in a pinch. But with increasingly sophisticated neuroengineering methods, we can do better.
The solution? Let’s make altering your brain more personal.
Unconscious Reprieve
That’s the route Sarah’s psychologist and UCSF neurosurgeon Dr. Edward Chang and colleagues took in the new study.
The first step in detecting depression-related activity in the brain was to be able to listen in. The team implanted 10 electrodes in Sarah’s brain, targeting multiple regions encoding emotion-related circuits. They then recorded electrical signals from these regions over the course of 10 days, while Sarah journaled about how she felt each day—happy or low. In the background, the team peeked into her brain activity patterns, a symphony of electrical signals in multiple frequencies, like overlapping waves on the ocean.
One particular brain wave emerged. It stemmed from the amygdala, a region normally involved in fear, lust, and other powerful emotions. Software-based mapping pinpointed the node as a powerful guide to Sarah’s mental state.
In contrast, another area tucked deep inside the brain, the ventral capsule/ventral striatum (VC/VS), emerged as a place to stimulate with little bouts of electricity to disrupt patterns leading to feelings of depression.
The team next implanted an FDA-approved neural pacemaker into the right brain lobe, with two sensing leads to capture activity from the amygdala and two stimulating wires to zap the VC/VS. The implant was previously used in epilepsy treatments and continuously senses neural activity. It’s both off-the-shelf and programmable, in that the authors could instruct it to detect “pre-specified patterns of activation” related to Sarah’s depressive episodes, and deliver short bursts of electrical stimulation only then. Just randomly stimulating the amygdala could “actually cause more stress and more depression symptoms,” said Dr. Chang in a press conference.
Brain surgery wasn’t easy. But to Sarah, drilling several holes into her brain was less difficult than the emotional pain of her depression. Every day during the trial, she waved a figure-eight-shaped wand over her head, which wirelessly captured 90 seconds of her brain’s electrical activity while reporting on her mental health.
When the stimulator turned on (even when she wasn’t aware it was on), “a joyous feeling just washed over me,” she said.
A New Neurological Future
For now, the results are just for one person. But if repeated—and Sarah could be a unique case—they suggest we’re finally at the point where we can tap into each unique person’s emotional mindset and fundamentally alter their perception of life.
And with that comes intense responsibility. Sarah’s neural “imprint” of her depression is tailored to her. It might be completely different for someone else. It’s something for future studies to dig into. But what’s clear is that it’s possible to regulate a person’s emotions with an AI-powered brain implant. And if other neurological disorders can be decoded in a similar way, we could use brain pacemakers to treat some of our toughest mental foes.
“God, the color differentiation is gorgeous,” said Sarah as her implant turned on. “I feel alert. I feel present.”
Image Credit: Sarah in her community garden, photo by John Lok/UCSF 2021 Continue reading
Posted in Human Robots
#439766 Understanding human-robot interaction ...
Robotic body-weight support (BWS) devices can play a key role in helping people with neurological disorders to improve their walking. The team that developed the advanced body-weight support device RYSEN in 2018 has since gained more fundamental insight in BWS but also concludes that improvement in this field is necessary. They find that recommendations for the optimal therapy settings have to be customized to each device and that developers should be more aware of the interaction between patient and the device. The researchers have published the results of their evaluation in Science Robotics on Wednesday September 22. Continue reading
Posted in Human Robots