A new design for a nuclear battery that generates electricity from the radioactive decay of americium is unprecedentedly efficient

Smart TVs from Samsung and LG monitor what you are watching even when you are using the screens to display a feed from a connected laptop or video game console

Google, Microsoft and others have taken big steps towards error-free devices, hinting that quantum computers that solve real problems aren’t far away

Gears just a few micrometres wide can be carved from silicon using a beam of electrons, enabling tiny robots or machines that could interact with human cells

It is thought that humans can only maintain relationships with around 150 people, a figure known as Dunbar's number, but it seems that AI models can outstrip this and reach consensus in far bigger groups

The UK government's decision to return the Chagos Islands to Mauritius surprisingly threatens the extinction of millions of website addresses ending in ".io", and no one is quite sure what will happen next

A new way to store numbers in computers can dynamically prioritise accuracy or range, depending on need, allowing software to quickly switch between very large and small numbers

Next-generation phone networks could dramatically outperform current ones thanks to a new technique for transmitting multiple streams of data over a wide range of frequencies

A new supercapacitor design that uses only water, clay and graphene could source material on Mars and be more sustainable and accessible than traditional batteries

The US Census Bureau processes data before publishing it in order to keep personal information private – but a new approach could maintain the same privacy while improving accuracy

One day, doctors might be able to 3D print copies of your organs in order to test a variety of drugs, thanks to a new technique that uses light and sound for rapid printing

Seven major datasets used to train audio-generating AI models are three times more likely to use the words "man" or "men" than "woman" or "women", raising fears of bias

That’s not his deal, you guys.

Treat yourself to a Becky Lynch book signing, games with the Dropout stars, Kevin Smith’s Dogma, and so much more!

Ronnie O'Sullivan has agreed to compete in new snooker events.

Mike Tyson has not fought professionally since suffering a stoppage defeat to Kevin McBride in 2005.

Emma Raducanu struck a deal to return to one of her favourite tournaments.

The software used to control a robot is normally highly adapted to its specific physical set up. But now researchers have created a single general-purpose robotic control policy that can operate robotic arms, wheeled robots, quadrupeds, and even drones.

One of the biggest challenges when it comes to applying machine learning to robotics is the paucity of data. While computer vision and natural language processing can piggyback off the vast quantities of image and text data found on the Internet, collecting robot data is costly and time-consuming.

To get around this, there have been growing efforts to pool data collected by different groups on different kinds of robots, including the Open X-Embodiment and DROID datasets. The hope is that training on diverse robotics data will lead to “positive transfer,” which refers to when skills learned from training on one task help to boost performance on another.

The problem is that robots often have very different embodiments—a term used to describe their physical layout and suite of sensors and actuators—so the data they collect can vary significantly. For instance, a robotic arm might be static, have a complex arrangement of joints and fingers, and collect video from a camera on its wrist. In contrast, a quadruped robot is regularly on the move and relies on force feedback from its legs to maneuver. The kinds of tasks and actions these machines are trained to carry out are also diverse: The arm may pick and place objects, while the quadruped needs keen navigation.

That makes training a single AI model for robots on these large collections of data challenging, says Homer Walke, a Ph.D. student at the University of California, Berkeley. So far, most attempts have either focused on data from a narrower selection of similar robots or researchers have manually tweaked data to make observations from different robots more similar. But in research to be presented at the Conference on Robot Learning (CoRL) in Munich in November, they unveiled a new model called CrossFormer that can train on data from a diverse set of robots and control them just as well as specialized control policies.

“We want to be able to train on all of this data to get the most capable robot,” says Walke. “The main advance in this paper is working out what kind of architecture works the best for accommodating all these varying inputs and outputs.”

How to control diverse robots with the same AI model

The team used the same model architecture that powers large language model, known as a transformer. In many ways, the challenge the researchers were trying to solve is not dissimilar to that facing a chatbot, says Walke. In language modeling, the AI has to to pick out similar patterns in sentences with different lengths and word orders. Robot data can also be arranged in a sequence much like a written sentence, but depending on the particular embodiment, observations and actions vary in length and order too.

“Words might appear in different locations in a sentence, but they still mean the same thing,” says Walke. “In our task, an observation image might appear in different locations in the sequence, but it’s still fundamentally an image and we still want to treat it like an image.”

UC Berkeley/Carnegie Mellon University

Most machine learning approaches work through a sequence one element at a time, but transformers can process the entire stream of data at once. This allows them to analyze the relationship between different elements and makes them better at handling sequences that are not standardized, much like the diverse data found in large robotics datasets.

Walke and his colleagues aren’t the first to train transformers on large-scale robotics data. But previous approaches have either trained solely on data from robotic arms with broadly similar embodiments or manually converted input data to a common format to make it easier to process. In contrast, CrossFormer can process images from cameras positioned above a robot, at head height or on a robotic arms wrist, as well as joint position data from both quadrupeds and robotic arms, without any tweaks.

The result is a single control policy that can operate single robotic arms, pairs of robotic arms, quadrupeds, and wheeled robots on tasks as varied as picking and placing objects, cutting sushi, and obstacle avoidance. Crucially, it matched the performance of specialized models tailored for each robot and outperformed previous approaches trained on diverse robotic data. The team even tested whether the model could control an embodiment not included in the dataset—a small quadcopter. While they simplified things by making the drone fly at a fixed altitude, CrossFormer still outperformed the previous best method.

“That was definitely pretty cool,” says Ria Doshi, an undergraduate student at Berkeley. “I think that as we scale up our policy to be able to train on even larger sets of diverse data, it’ll become easier to see this kind of zero shot transfer onto robots that have been completely unseen in the training.”

The limitations of one AI model for all robots

The team admits there’s still work to do, however. The model is too big for any of the robots’ embedded chips and instead has to be run from a server. Even then, processing times are only just fast enough to support real-time operation, and Walke admits that could break down if they scale up the model. “When you pack so much data into a model it has to be very big and that means running it for real-time control becomes difficult.”

One potential workaround would be to use an approach called distillation, says Oier Mees, a postdoctoral research at Berkley and part of the CrossFormer team. This essentially involves training a smaller model to mimic the larger model, and if successful can result in similar performance for a much smaller computational budget.

But of more importance than the computing resource problem is that the team failed to see any positive transfer in their experiments, as CrossFormer simply matched previous performance rather than exceeding it. Walke thinks progress in computer vision and natural language processing suggests that training on more data could be the key.

Others say it might not be that simple. Jeannette Bohg, a professor of robotics at Stanford University, says the ability to train on such a diverse dataset is a significant contribution. But she wonders whether part of the reason why the researchers didn’t see positive transfer is their insistence on not aligning the input data. Previous research that trained on robots with similar observation and action data has shown evidence of such cross-overs. “By getting rid of this alignment, they may have also gotten rid of this significant positive transfer that we’ve seen in other work,” Bohg says.

It’s also not clear if the approach will boost performance on tasks specific to particular embodiments or robotic applications, says Ram Ramamoorthy, a robotics professor at Edinburgh University. The work is a promising step towards helping robots capture concepts common to most robots, like “avoid this obstacle,” he says. But it may be less useful for tackling control problems specific to a particular robot, such as how to knead dough or navigate a forest, which are often the hardest to solve.

The end to this bloody stalemate must come with negotiation, and Putin should not wait until Trump is in the White House, says Guardian columnist Simon Jenkins

To restore the rule of law, Trump's Department of Justice must investigate those who subverted our constitutional order.

Most people work just hard enough not to get fired and get paid just enough money not to quit. -George Carlin Every four years, presidential opinion polling reliably causes regime media to misplace...

Although I am loath to use the phrase, I don't think it's remiss to call Donald Trump's victory last week a vibeshift.

Other Democrats lambasted him. The Tufts political science department spurned him. But Moulton is raising concerns the left needs to take seriously.

Meta had huge success last year with its flagship Quest 3 VR headset and it is back with a significantly cheaper 3S device that compromises on visuals but still delivers a great experience

EA FC 25 players can snag some big freebies this week, with EA Sports celebrating the Ballon d'Or in style for all Ultimate Team players with some of the best players around.

Scientists say geoengineering, or doing things like intentionally increasing Earth’s reflectivity or blocking the sun, is a “really big deal” in slowing down climate change. Here are the ideas they are proposing.

Certain strains of E. coli are capable of causing severe disease, by rapidly spreading through the human digestive system, wreaking havoc throughout the bloodstream, and eventually damaging the delicate kidneys. That's the situation right now during a large outbreak in Alberta, with hundreds of children now affected.

In this week's issue of our environment newsletter, we look at the carbon capture potential of the world's oceans and what effect beavers are having in the Arctic (spoiler: it's not good).

Researchers calculated that if 30 per cent of vehicles in Chicago currently running on combustion engines were converted to electric, the reduction in pollution would save billions in health care costs every year. 

Local officials are beginning to certify the results of this year's presidential election in a process that, so far, has been playing out quietly, in stark contrast to the tumultuous certification period four years ago that followed then-President Donald Trump's loss.

House Speaker Mike Johnson is seeking a smooth re-election to another term wielding the gavel, but a small group of discontent conservatives are again vying to shake things up at the top.

Every stock trader should consider a virtual private network to safeguard their trading, according to tech guru Kurt "CyberGuy" Knutsson.

Getting virus alerts on your iPhone? Tech expert Kurt “CyberGuy" Knutsson helps you learn how to handle fake scam alerts and boost security.

Club captain Jordan Henderson, summer signing Naby Keita and centre back Joe Gomez were all absent for the shock midweek Champions League defeat to Red Star Belgrade..

The company behind Pornhub and other popular pornographic sites broke Canadian privacy law by allowing intimate images to be shared on its websites without the direct knowledge or consent of everyone depicted, the federal privacy commissioner has ruled. The Office of the Privacy Commissioner’s (OPC) investigation into Aylo (formerly MindGeek), one of the world’s largest […]

If rumours are true and this one should be, I started it, we have a special edition of the Weekend show where we talk about the evolution of the role of the CIO with two incredible CIOs as the CIO Association of Canada turns 20. Don’t miss it.  MUSIC UP Can HP make you love […]

Kaseya, a provider of unified IT management and security software for managed service providers (MSPs) and small to midsize business (SMBs), today released its 2024 MSP Benchmark Report, which surveyed close to 1,000 MSPs from the Americas, EMEA (Europe, Middle East and Africa) and APAC (Asia Pacific) regions and includes responses from both IT professionals […]

A new study suggests there could be water miles under the dusty surface of Mars, with enough water to fill a global-sized ocean a mile deep.

Iowa archaeologists have unearthed a 13,600-year-old mastodon skull in pristine condition during a nearly two-week excavation at an eroding creek bank in Wayne County.

Venomous Blue Sea Dragons are washing up on the sandy shores of the Outer Banks in North Carolina, and National Park officials advise to admire them from a distance.

The sun blasted a coronal mass at Earth earlier this week, and after back-to-back major hurricanes, some are concerned it could impact the power grid.

SpaceX pulled off a stunning achievement this week, conducting four launches in less than 48 hours with huge implications for the future of space exploration.