Tag Archives: we
#435579 RoMeLa’s Newest Robot Is a ...
A few years ago, we wrote about NABiRoS, a bipedal robot from Dennis Hong’s Robotics & Mechanisms Laboratory (RoMeLa) at UCLA. Unlike pretty much any other biped we’d ever seen, NABiRoS had a unique kinematic configuration that had it using its two legs to walk sideways, which offered some surprising advantages.
As it turns out, bipeds aren’t the only robots that can potentially benefit from a bit of a kinematic rethink. RoMeLa has redesigned quadrupedal robots too—rather than model them after a quadrupedal animal like a dog or a horse, RoMeLa’s ALPHRED robots use four legs arranged symmetrically around the body of the robot, allowing it to walk, run, hop, and jump, as well as manipulate and carry objects, karate chop through boards, and even roller skate on its butt. This robot can do it all.
Impressive, right? This is ALPHRED 2, and its predecessor, the original ALPHRED, was introduced at IROS 2018. Both ALPHREDs are axisymmetric about the vertical axis, meaning that they don’t have a front or a back and are perfectly happy to walk in any direction you like. Traditional quadrupeds like Spot or Laikago can also move sideways and backwards, but their leg arrangement makes them more efficient at moving in one particular direction, and also results in some curious compromises like a preference for going down stairs backwards. ANYmal is a bit more flexible in that it can reverse its knees, but it’s still got that traditional quadrupedal two-by-two configuration.
ALPHRED 2’s four symmetrical limbs can be used for a whole bunch of stuff. It can do quadrupedal walking and running, and it’s able to reach stable speeds of up to 1.5 m/s. If you want bipedal walking, it can do that NABiRoS-style, although it’s still a bit fragile at the moment. Using two legs for walking leaves two legs free, and those legs can turn into arms. A tripedal compromise configuration, with three legs and one arm, is more stable and allows the robot to do things like push buttons, open doors, and destroy property. And thanks to passive wheels under its body, ALPHRED 2 can use its limbs to quickly and efficiently skate around:
The impressive performance of the robot comes courtesy of a custom actuator that RoMeLa designed specifically for dynamic legged locomotion. They call it BEAR, or Back-Drivable Electromechanical Actuator for Robots. These are optionally liquid-cooled motors capable of proprioceptive sensing, consisting of a DC motor, a single stage 10:1 planetary gearbox, and channels through the back of the housing that coolant can be pumped through. The actuators have a peak torque of 32 Nm, and a continuous torque of about 8 Nm with passive air cooling. With liquid cooling, the continuous torque jumps to about 21 Nm. And in the videos above, ALPHRED 2 isn’t even running the liquid cooling system, suggesting that it’s capable of much higher sustained performance.
Photo: RoMeLa
Using two legs for walking leaves two legs free, and those legs can turn into arms.
RoMeLa has produced a bunch of very creative robots, and we appreciate that they also seem to produce a bunch of very creative demos showing why their unusual approaches are in fact (at least in some specific cases) somewhat practical. With the recent interest in highly dynamic robots that can be reliably useful in environments infested with humans, we can’t wait to see what kinds of exciting tricks the next (presumably liquid-cooled) version will be able to do.
[ RoMeLa ] Continue reading
Posted in Human Robots
#435575 How an AI Startup Designed a Drug ...
Discovering a new drug can take decades, billions of dollars, and untold man hours from some of the smartest people on the planet. Now a startup says it’s taken a significant step towards speeding the process up using AI.
The typical drug discovery process involves carrying out physical tests on enormous libraries of molecules, and even with the help of robotics it’s an arduous process. The idea of sidestepping this by using computers to virtually screen for promising candidates has been around for decades. But progress has been underwhelming, and it’s still not a major part of commercial pipelines.
Recent advances in deep learning, however, have reignited hopes for the field, and major pharma companies have started tying up with AI-powered drug discovery startups. And now Insilico Medicine has used AI to design a molecule that effectively targets a protein involved in fibrosis—the formation of excess fibrous tissue—in mice in just 46 days.
The platform the company has developed combines two of the hottest sub-fields of AI: the generative adversarial networks, or GANs, which power deepfakes, and reinforcement learning, which is at the heart of the most impressive game-playing AI advances of recent years.
In a paper in Nature Biotechnology, the company’s researchers describe how they trained their model on all the molecules already known to target this protein as well as many other active molecules from various datasets. The model was then used to generate 30,000 candidate molecules.
Unlike most previous efforts, they went a step further and selected the most promising molecules for testing in the lab. The 30,000 candidates were whittled down to just 6 using more conventional drug discovery approaches and were then synthesized in the lab. They were put through increasingly stringent tests, but the leading candidate was found to be effective at targeting the desired protein and behaved as one would hope a drug would.
The authors are clear that the results are just a proof-of-concept, which company CEO Alex Zhavoronkov told Wired stemmed from a challenge set by a pharma partner to design a drug as quickly as possible. But they say they were able to carry out the process faster than traditional methods for a fraction of the cost.
There are some caveats. For a start, the protein being targeted is already very well known and multiple effective drugs exist for it. That gave the company a wealth of data to train their model on, something that isn’t the case for many of the diseases where we urgently need new drugs.
The company’s platform also only targets the very initial stages of the drug discovery process. The authors concede in their paper that the molecules would still take considerable optimization in the lab before they’d be true contenders for clinical trials.
“And that is where you will start to begin to commence to spend the vast piles of money that you will eventually go through in trying to get a drug to market,” writes Derek Lowe in his blog In The Pipeline. The part of the discovery process that the platform tackles represents a tiny fraction of the total cost of drug development, he says.
Nonetheless, the research is a definite advance for virtual screening technology and an important marker of the potential of AI for designing new medicines. Zhavoronkov also told Wired that this research was done more than a year ago, and they’ve since adapted the platform to go after harder drug targets with less data.
And with big pharma companies desperate to slash their ballooning development costs and find treatments for a host of intractable diseases, they can use all the help they can get.
Image Credit: freestocks.org / Unsplash Continue reading
Posted in Human Robots
#435541 This Giant AI Chip Is the Size of an ...
People say size doesn’t matter, but when it comes to AI the makers of the largest computer chip ever beg to differ. There are plenty of question marks about the gargantuan processor, but its unconventional design could herald an innovative new era in silicon design.
Computer chips specialized to run deep learning algorithms are a booming area of research as hardware limitations begin to slow progress, and both established players and startups are vying to build the successor to the GPU, the specialized graphics chip that has become the workhorse of the AI industry.
On Monday Californian startup Cerebras came out of stealth mode to unveil an AI-focused processor that turns conventional wisdom on its head. For decades chip makers have been focused on making their products ever-smaller, but the Wafer Scale Engine (WSE) is the size of an iPad and features 1.2 trillion transistors, 400,000 cores, and 18 gigabytes of on-chip memory.
The Cerebras Wafer-Scale Engine (WSE) is the largest chip ever built. It measures 46,225 square millimeters and includes 1.2 trillion transistors. Optimized for artificial intelligence compute, the WSE is shown here for comparison alongside the largest graphics processing unit. Image Credit: Used with permission from Cerebras Systems.
There is a method to the madness, though. Currently, getting enough cores to run really large-scale deep learning applications means connecting banks of GPUs together. But shuffling data between these chips is a major drain on speed and energy efficiency because the wires connecting them are relatively slow.
Building all 400,000 cores into the same chip should get round that bottleneck, but there are reasons it’s not been done before, and Cerebras has had to come up with some clever hacks to get around those obstacles.
Regular computer chips are manufactured using a process called photolithography to etch transistors onto the surface of a wafer of silicon. The wafers are inches across, so multiple chips are built onto them at once and then split up afterwards. But at 8.5 inches across, the WSE uses the entire wafer for a single chip.
The problem is that while for standard chip-making processes any imperfections in manufacturing will at most lead to a few processors out of several hundred having to be ditched, for Cerebras it would mean scrapping the entire wafer. To get around this the company built in redundant circuits so that even if there are a few defects, the chip can route around them.
The other big issue with a giant chip is the enormous amount of heat the processors can kick off—so the company has had to design a proprietary water-cooling system. That, along with the fact that no one makes connections and packaging for giant chips, means the WSE won’t be sold as a stand-alone component, but as part of a pre-packaged server incorporating the cooling technology.
There are no details on costs or performance so far, but some customers have already been testing prototypes, and according to Cerebras results have been promising. CEO and co-founder Andrew Feldman told Fortune that early tests show they are reducing training time from months to minutes.
We’ll have to wait until the first systems ship to customers in September to see if those claims stand up. But Feldman told ZDNet that the design of their chip should help spur greater innovation in the way engineers design neural networks. Many cornerstones of this process—for instance, tackling data in batches rather than individual data points—are guided more by the hardware limitations of GPUs than by machine learning theory, but their chip will do away with many of those obstacles.
Whether that turns out to be the case or not, the WSE might be the first indication of an innovative new era in silicon design. When Google announced it’s AI-focused Tensor Processing Unit in 2016 it was a wake-up call for chipmakers that we need some out-of-the-box thinking to square the slowing of Moore’s Law with skyrocketing demand for computing power.
It’s not just tech giants’ AI server farms driving innovation. At the other end of the spectrum, the desire to embed intelligence in everyday objects and mobile devices is pushing demand for AI chips that can run on tiny amounts of power and squeeze into the smallest form factors.
These trends have spawned renewed interest in everything from brain-inspired neuromorphic chips to optical processors, but the WSE also shows that there might be mileage in simply taking a sideways look at some of the other design decisions chipmakers have made in the past rather than just pumping ever more transistors onto a chip.
This gigantic chip might be the first exhibit in a weird and wonderful new menagerie of exotic, AI-inspired silicon.
Image Credit: Used with permission from Cerebras Systems. Continue reading
Posted in Human Robots