TOP SCEINCE
A technique for more effective multipurpose robots
Let’s say you want to train a robot so it understands how to use tools and can then quickly learn to make repairs around your house with a hammer, wrench, and screwdriver. To do that, you would need an enormous amount of data demonstrating tool use.
It is difficult to efficiently incorporate data from so many sources in one machine-learning model, so many methods use just one type of data to train a robot. But robots trained this way, with a relatively small amount of task-specific data, are often unable to perform new tasks in unfamiliar environments.
In an effort to train better multipurpose robots, MIT researchers developed a technique to combine multiple sources of data across domains, modalities, and tasks using a type of generative AI known as diffusion models.
They train a separate diffusion model to learn a strategy, or policy, for completing one task using one specific dataset. Then they combine the policies learned by the diffusion models into a general policy that enables a robot to perform multiple tasks in various settings.
In simulations and real-world experiments, this training approach enabled a robot to perform multiple tool-use tasks and adapt to new tasks it did not see during training. The method, known as Policy Composition (PoCo), led to a 20 percent improvement in task performance when compared to baseline techniques.
“Addressing heterogeneity in robotic datasets is like a chicken-egg problem. If we want to use a lot of data to train general robot policies, then we first need deployable robots to get all this data. I think that leveraging all the heterogeneous data available, similar to what researchers have done with ChatGPT, is an important step for the robotics field,” says Lirui Wang, an electrical engineering and computer science (EECS) graduate student and lead author of a paper on PoCo.
Wang’s coauthors include Jialiang Zhao, a mechanical engineering graduate student; Yilun Du, an EECS graduate student; Edward Adelson, the John and Dorothy Wilson Professor of Vision Science in the Department of Brain and Cognitive Sciences and a member of the Computer Science and Artificial Intelligence Laboratory (CSAIL); and senior author Russ Tedrake, the Toyota Professor of EECS, Aeronautics and Astronautics, and Mechanical Engineering, and a member of CSAIL. The research will be presented at the Robotics: Science and Systems Conference.
Combining disparate datasets
A robotic policy is a machine-learning model that takes inputs and uses them to perform an action. One way to think about a policy is as a strategy. In the case of a robotic arm, that strategy might be a trajectory, or a series of poses that move the arm so it picks up a hammer and uses it to pound a nail.
Datasets used to learn robotic policies are typically small and focused on one particular task and environment, like packing items into boxes in a warehouse.
“Every single robotic warehouse is generating terabytes of data, but it only belongs to that specific robot installation working on those packages. It is not ideal if you want to use all of these data to train a general machine,” Wang says.
The MIT researchers developed a technique that can take a series of smaller datasets, like those gathered from many robotic warehouses, learn separate policies from each one, and combine the policies in a way that enables a robot to generalize to many tasks.
They represent each policy using a type of generative AI model known as a diffusion model. Diffusion models, often used for image generation, learn to create new data samples that resemble samples in a training dataset by iteratively refining their output.
But rather than teaching a diffusion model to generate images, the researchers teach it to generate a trajectory for a robot. They do this by adding noise to the trajectories in a training dataset. The diffusion model gradually removes the noise and refines its output into a trajectory.
This technique, known as Diffusion Policy, was previously introduced by researchers at MIT, Columbia University, and the Toyota Research Institute. PoCo builds off this Diffusion Policy work.
The team trains each diffusion model with a different type of dataset, such as one with human video demonstrations and another gleaned from teleoperation of a robotic arm.
Then the researchers perform a weighted combination of the individual policies learned by all the diffusion models, iteratively refining the output so the combined policy satisfies the objectives of each individual policy.
Greater than the sum of its parts
“One of the benefits of this approach is that we can combine policies to get the best of both worlds. For instance, a policy trained on real-world data might be able to achieve more dexterity, while a policy trained on simulation might be able to achieve more generalization,” Wang says.
Because the policies are trained separately, one could mix and match diffusion policies to achieve better results for a certain task. A user could also add data in a new modality or domain by training an additional Diffusion Policy with that dataset, rather than starting the entire process from scratch.
The researchers tested PoCo in simulation and on real robotic arms that performed a variety of tools tasks, such as using a hammer to pound a nail and flipping an object with a spatula. PoCo led to a 20 percent improvement in task performance compared to baseline methods.
“The striking thing was that when we finished tuning and visualized it, we can clearly see that the composed trajectory looks much better than either one of them individually,” Wang says.
In the future, the researchers want to apply this technique to long-horizon tasks where a robot would pick up one tool, use it, then switch to another tool. They also want to incorporate larger robotics datasets to improve performance.
“We will need all three kinds of data to succeed for robotics: internet data, simulation data, and real robot data. How to combine them effectively will be the million-dollar question. PoCo is a solid step on the right track,” says Jim Fan, senior research scientist at NVIDIA and leader of the AI Agents Initiative, who was not involved with this work.
This research is funded, in part, by Amazon, the Singapore Defense Science and Technology Agency, the U.S. National Science Foundation, and the Toyota Research Institute.
TOP SCEINCE
Early dark energy could resolve cosmology’s two biggest puzzles
A new study by MIT physicists proposes that a mysterious force known as early dark energy could solve two of the biggest puzzles in cosmology and fill in some major gaps in our understanding of how the early universe evolved.
Now, the MIT team has found that both puzzles could be resolved if the early universe had one extra, fleeting ingredient: early dark energy. Dark energy is an unknown form of energy that physicists suspect is driving the expansion of the universe today. Early dark energy is a similar, hypothetical phenomenon that may have made only a brief appearance, influencing the expansion of the universe in its first moments before disappearing entirely.
Some physicists have suspected that early dark energy could be the key to solving the Hubble tension, as the mysterious force could accelerate the early expansion of the universe by an amount that would resolve the measurement mismatch.
The MIT researchers have now found that early dark energy could also explain the baffling number of bright galaxies that astronomers have observed in the early universe. In their new study, reported in the Monthly Notices of the Royal Astronomical Society, the team modeled the formation of galaxies in the universe’s first few hundred million years. When they incorporated a dark energy component only in that earliest sliver of time, they found the number of galaxies that arose from the primordial environment bloomed to fit astronomers’ observations.
“You have these two looming open-ended puzzles,” says study co-author Rohan Naidu, a postdoc in MIT’s Kavli Institute for Astrophysics and Space Research. “We find that in fact, early dark energy is a very elegant and sparse solution to two of the most pressing problems in cosmology.”
The study’s co-authors include lead author and Kavli postdoc Xuejian (Jacob) Shen, and MIT professor of physics Mark Vogelsberger, along with Michael Boylan-Kolchin at the University of Texas at Austin, and Sandro Tacchella at the University of Cambridge.
Big city lights
Based on standard cosmological and galaxy formation models, the universe should have taken its time spinning up the first galaxies. It would have taken billions of years for primordial gas to coalesce into galaxies as large and bright as the Milky Way.
But in 2023, NASA’s James Webb Space Telescope (JWST) made a startling observation. With an ability to peer farther back in time than any observatory to date, the telescope uncovered a surprising number of bright galaxies as large as the modern Milky Way within the first 500 million years, when the universe was just 3 percent of its current age.
“The bright galaxies that JWST saw would be like seeing a clustering of lights around big cities, whereas theory predicts something like the light around more rural settings like Yellowstone National Park,” Shen says. “And we don’t expect that clustering of light so early on.”
For physicists, the observations imply that there is either something fundamentally wrong with the physics underlying the models or a missing ingredient in the early universe that scientists have not accounted for. The MIT team explored the possibility of the latter, and whether the missing ingredient might be early dark energy.
Physicists have proposed that early dark energy is a sort of antigravitational force that is turned on only at very early times. This force would counteract gravity’s inward pull and accelerate the early expansion of the universe, in a way that would resolve the mismatch in measurements. Early dark energy, therefore, is considered the most likely solution to the Hubble tension.
Galaxy skeleton
The MIT team explored whether early dark energy could also be the key to explaining the unexpected population of large, bright galaxies detected by JWST. In their new study, the physicists considered how early dark energy might affect the early structure of the universe that gave rise to the first galaxies. They focused on the formation of dark matter halos — regions of space where gravity happens to be stronger, and where matter begins to accumulate.
“We believe that dark matter halos are the invisible skeleton of the universe,” Shen explains. “Dark matter structures form first, and then galaxies form within these structures. So, we expect the number of bright galaxies should be proportional to the number of big dark matter halos.”
The team developed an empirical framework for early galaxy formation, which predicts the number, luminosity, and size of galaxies that should form in the early universe, given some measures of “cosmological parameters.” Cosmological parameters are the basic ingredients, or mathematical terms, that describe the evolution of the universe.
Physicists have determined that there are at least six main cosmological parameters, one of which is the Hubble constant — a term that describes the universe’s rate of expansion. Other parameters describe density fluctuations in the primordial soup, immediately after the Big Bang, from which dark matter halos eventually form.
The MIT team reasoned that if early dark energy affects the universe’s early expansion rate, in a way that resolves the Hubble tension, then it could affect the balance of the other cosmological parameters, in a way that might increase the number of bright galaxies that appear at early times. To test their theory, they incorporated a model of early dark energy (the same one that happens to resolve the Hubble tension) into an empirical galaxy formation framework to see how the earliest dark matter structures evolve and give rise to the first galaxies.
“What we show is, the skeletal structure of the early universe is altered in a subtle way where the amplitude of fluctuations goes up, and you get bigger halos, and brighter galaxies that are in place at earlier times, more so than in our more vanilla models,” Naidu says. “It means things were more abundant, and more clustered in the early universe.”
“A priori, I would not have expected the abundance of JWST’s early bright galaxies to have anything to do with early dark energy, but their observation that EDE pushes cosmological parameters in a direction that boosts the early-galaxy abundance is interesting,” says Marc Kamionkowski, professor of theoretical physics at Johns Hopkins University, who was not involved with the study. “I think more work will need to be done to establish a link between early galaxies and EDE, but regardless of how things turn out, it’s a clever — and hopefully ultimately fruitful — thing to try.”
“We demonstrated the potential of early dark energy as a unified solution to the two major issues faced by cosmology. This might be an evidence for its existence if the observational findings of JWST get further consolidated,” Vogelsberger concludes. “In the future, we can incorporate this into large cosmological simulations to see what detailed predictions we get.”
This research was supported, in part, by NASA and the National Science Foundation.
TOP SCEINCE
Plant-derived secondary organic aerosols can act as mediators of plant-plant interactions
A new study published in Science reveals that plant-derived secondary organic aerosols (SOAs) can act as mediators of plant-plant interactions. This research was conducted through the cooperation of chemical ecologists, plant ecophysiologists and atmospheric physicists at the University of Eastern Finland.
The study showed that Scots pine seedlings, when damaged by large pine weevils, release VOCs that activate defences in nearby plants of the same species. Interestingly, the biological activity persisted after VOCs were oxidized to form SOAs. The results indicated that the elemental composition and quantity of SOAs likely determines their biological functions.
“A key novelty of the study is the finding that plants adopt subtly different defence strategies when receiving signals as VOCs or as SOAs, yet they exhibit similar degrees of resistance to herbivore feeding,” said Professor James Blande, head of the Environmental Ecology Research Group. This observation opens up the possibility that plants have sophisticated sensing systems that enable them to tailor their defences to information derived from different types of chemical cue.
“Considering the formation rate of SOAs from their precursor VOCs, their longer lifetime compared to VOCs, and the atmospheric air mass transport, we expect that the ecologically effective distance for interactions mediated by SOAs is longer than that for plant interactions mediated by VOCs,” said Professor Annele Virtanen, head of the Aerosol Physics Research Group. This could be interpreted as plants being able to detect cues representing close versus distant threats from herbivores.
The study is expected to open up a whole new complex research area to environmental ecologists and their collaborators, which could lead to new insights on the chemical cues structuring interactions between plants.
TOP SCEINCE
Folded or cut, this lithium-sulfur battery keeps going
Most rechargeable batteries that power portable devices, such as toys, handheld vacuums and e-bikes, use lithium-ion technology. But these batteries can have short lifetimes and may catch fire when damaged. To address stability and safety issues, researchers reporting in ACS Energy Letters have designed a lithium-sulfur (Li-S) battery that features an improved iron sulfide cathode. One prototype remains highly stable over 300 charge-discharge cycles, and another provides power even after being folded or cut.
The team coated iron sulfide cathodes in different polymers and found in initial electrochemical performance tests that polyacrylic acid (PAA) performed best, retaining the electrode’s discharge capacity after 300 charge-discharge cycles. Next, the researchers incorporated a PAA-coated iron sulfide cathode into a prototype battery design, which also included a carbonate-based electrolyte, a lithium metal foil as an ion source, and a graphite-based anode. They produced and then tested both pouch cell and coin cell battery prototypes.
After more than 100 charge-discharge cycles, Wang and colleagues observed no substantial capacity decay in the pouch cell. Additional experiments showed that the pouch cell still worked after being folded and cut in half. The coin cell retained 72% of its capacity after 300 charge-discharge cycles. They next applied the polymer coating to cathodes made from other metals, creating lithium-molybdenum and lithium-vanadium batteries. These cells also had stable capacity over 300 charge-discharge cycles. Overall, the results indicate that coated cathodes could produce not only safer Li-S batteries with long lifespans, but also efficient batteries with other metal sulfides, according to Wang’s team.
The authors acknowledge funding from the National Natural Science Foundation of China; the Natural Science Foundation of Sichuan, China; and the Beijing National Laboratory for Condensed Matter Physics.
-
Solar Energy3 years ago
DLR testing the use of molten salt in a solar power plant in Portugal
-
world news11 months ago
Gulf, France aid Gaza, Russia evacuates citizens
-
Camera11 months ago
DJI Air 3 vs. Mini 4 Pro: which compact drone is best?
-
Camera3 years ago
Charles ‘Chuck’ Geschke, co-founder of Adobe and inventor of the PDF, dies at 81
-
Solar Energy11 months ago
Glencore eyes options on battery recycling project
-
world news11 months ago
Strong majority of Americans support Israel-Hamas hostage deal
-
Camera11 months ago
Sony a9 III: what you need to know
-
TOP SCEINCE6 months ago
Can animals count?