An anonymous reader quotes a report from The Guardian: Swarms of tiny robots, each no larger than a speck of dust, could be deployed to cure stubborn infected sinuses before being blown out through the nose into a tissue, researchers have claimed. The micro-robots are a fraction of the width of a human hair and have been inserted successfully into animal sinuses in pre-clinical trials by researchers at universities in China and Hong Kong. Swarms are injected into the sinus cavity via a duct threaded through the nostril and guided to their target by electromagnetism, where they can be made to heat up and catalyze chemical reactions to wipe out bacterial infections. There are hopes the precisely targeted technology could eventually reduce reliance on antibiotics and other generalized medicines. [...] The latest breakthrough, based on animal rather than human trials, involves magnetic particles "doped" with copper atoms which clinicians insert with a catheter before guiding to their target under a magnetic field. The swarms can be heated up by reacting to light from an optical fibre that is also inserted into the body as part of the therapy. This allows the micro-robots to loosen up and penetrate viscous pus that forms a barrier to the infection site. The light source also prompts the micro-robots to disrupt bacterial cell walls and release reactive oxygen species that kill the bacteria. The study, published in Nature Robotics, showed the robots were capable of eradicating bacteria from pig sinuses and could clear infections in live rabbits with "no obvious tissue damage." The researchers have produced a model of how the technology could work on a human being, with the robot swarms being deployed in operating theatre conditions, allowing doctors to see their progress by using X-rays. Future applications could include tackling bacterial infections of the respiratory tract, stomach, intestine, bladder and urethra, they suggested. "Our proposed micro-robotic therapeutic platform offers the advantages of non-invasiveness, minimal resistance, and drug-free intervention," they said.

Read more of this story at Slashdot.

Google DeepMind has launched Gemini Robotics On-Device, a new language model that enables robots to perform complex tasks locally without internet connectivity. TechCrunch reports: Building on the company's previous Gemini Robotics model that was released in March, Gemini Robotics On-Device can control a robot's movements. Developers can control and fine-tune the model to suit various needs using natural language prompts. In benchmarks, Google claims the model performs at a level close to the cloud-based Gemini Robotics model. The company says it outperforms other on-device models in general benchmarks, though it didn't name those models. In a demo, the company showed robots running this local model doing things like unzipping bags and folding clothes. Google says that while the model was trained for ALOHA robots, it later adapted it to work on a bi-arm Franka FR3 robot and the Apollo humanoid robot by Apptronik. Google claims the bi-arm Franka FR3 was successful in tackling scenarios and objects it hadn't "seen" before, like doing assembly on an industrial belt. Google DeepMind is also releasing a Gemini Robotics SDK. The company said developers can show robots 50 to 100 demonstrations of tasks to train them on new tasks using these models on the MuJoCo physics simulator.

Read more of this story at Slashdot.

An anonymous reader quotes a report from Ars Technica: The robot built by [Yuntao Ma and his team at ETH Zurich] was called ANYmal and resembled a miniature giraffe that plays badminton by holding a racket in its teeth. It was a quadruped platform developed by ANYbotics, an ETH Zurich spinoff company that mainly builds robots for the oil and gas industries. "It was an industry-grade robot," Ma said. The robot had elastic actuators in its legs, weighed roughly 50 kilograms, and was half a meter wide and under a meter long. On top of the robot, Ma's team fitted an arm with several degrees of freedom produced by another ETH Zurich spinoff called Duatic. This is what would hold and swing a badminton racket. Shuttlecock tracking and sensing the environment were done with a stereoscopic camera. "We've been working to integrate the hardware for five years," Ma said. Along with the hardware, his team was also working on the robot's brain. State-of-the-art robots usually use model-based control optimization, a time-consuming, sophisticated approach that relies on a mathematical model of the robot's dynamics and environment. "In recent years, though, the approach based on reinforcement learning algorithms became more popular," Ma told Ars. "Instead of building advanced models, we simulated the robot in a simulated world and let it learn to move on its own." In ANYmal's case, this simulated world was a badminton court where its digital alter ego was chasing after shuttlecocks with a racket. The training was divided into repeatable units, each of which required that the robot predict the shuttlecock's trajectory and hit it with a racket six times in a row. During this training, like a true sportsman, the robot also got to know its physical limits and to work around them. The idea behind training the control algorithms was to develop visuo-motor skills similar to human badminton players. The robot was supposed to move around the court, anticipating where the shuttlecock might go next and position its whole body, using all available degrees of freedom, for a swing that would mean a good return. This is why balancing perception and movement played such an important role. The training procedure included a perception model based on real camera data, which taught the robot to keep the shuttlecock in its field of view while accounting for the noise and resulting object-tracking errors. Once the training was done, the robot learned to position itself on the court. It figured out that the best strategy after a successful return is to move back to the center and toward the backline, which is something human players do. It even came with a trick where it stood on its hind legs to see the incoming shuttlecock better. It also learned fall avoidance and determined how much risk was reasonable to take given its limited speed. The robot did not attempt impossible plays that would create the potential for serious damage -- it was committed, but not suicidal. But when it finally played humans, it turned out ANYmal, as a badminton player, was amateur at best. The findings have been published in the journal Science Robotics. You can watch a video of the four-legged robot playing badminton on YouTube.

Read more of this story at Slashdot.

Amazon is developing software for humanoid robots that could eventually replace hundreds of thousands of delivery workers, [non-paywalled source] The Information reports. The company is building a "humanoid park" obstacle course at its San Francisco office to test robots that would ride in the back of Amazon's Rivian electric vans and deliver packages to customers, the report said. The indoor testing facility, roughly the size of a coffee shop, will house a Rivian van and serve as a controlled environment before Amazon takes the robots on "field trips" to deliver real packages on actual streets. This summer, Amazon plans to test multiple humanoid models, including a $16,000 unit from China-based Unitree that has gained popularity among robotics developers, the report said. The initiative represents Amazon's most ambitious robotics project yet, extending beyond its existing warehouse automation to tackle the significantly more complex challenge of outdoor package delivery. Amazon currently operates more than 20,000 Rivian vehicles for deliveries and plans to expand its electric fleet to 100,000 vehicles by 2030.

Read more of this story at Slashdot.

An anonymous reader quotes a report from SiliconANGLE: Hugging Face has open-sourced the blueprints of two internally developed robots called HopeJR and Reachy Mini. The company debuted the machines on Thursday. Hugging Face is backed by more than $390 million in funding from Nvidia Corp., IBM Corp. and other investors. It operates a GitHub-like platform for sharing open-source artificial intelligence projects. It says its platform hosts more than 1 million AI models, hundreds of thousands of datasets and various other technical assets. The company started prioritizing robotics last year after launching LeRobot, a section of its platform dedicated to autonomous machines. The portal provides access to AI models for powering robots and datasets that can be used to train those models. Hugging Face released its first hardware blueprint, a robotic arm design called the SO-100, late last year. The SO-100 was developed in partnership with a startup called The Robot Studio. Hugging Face also collaborated with the company on the HopeJR, the first new robot that debuted this week. According to TechCrunch, it's a humanoid robot that can perform 66 movements including walking. HopeJR is equipped with a pair of robotic arms that can be remotely controlled by a human using a pair of specialized, chip-equipped gloves. HopeJR's arms replicate the movements made by the wearer of the gloves. A demo video shared by Hugging Face showed that the robot can shake hands, point to a specific text snippet on a piece of paper and perform other tasks. Hugging Face's other new robot, the Reachy Mini, likewise features an open-source design. It's based on technology that the company obtained through the acquisition of a venture-backed startup called Pollen Robotics earlier this year. Reachy Mini is a turtle-like robot that comes in a rectangular case. Its main mechanical feature is a retractable neck that allows it to follow the user with its head or withdraw into the case. This case, which is stationary, is compact and lightweight enough to be placed on a desk. Hugging Face will offer pre-assembled versions of its open-source Reach Mini and HopeJR robots for $250 and $3,000, with the first units starting to ship by the end of the year.

Read more of this story at Slashdot.

An anonymous reader quotes a report from Axios: Advanced robots don't necessarily need to look like C3PO from "Star Wars" or George Jetson's maid Rosie, despite all the hype over humanoids from Wall Street and Big Tech. In fact, some of the biggest skeptics about human-shaped robots come from within the robotics industry itself. [...] The most productive -- and profitable -- bots are the ones that can do single tasks cheaply and efficiently. "If you look at where robots are really bringing value in a manufacturing environment, it is combining industrial or collaborative robots with mobility," ABB managing director Ali Raja tells Axios. "I don't see that there are any real practical applications where humanoids are bringing in a lot of value." "The reason we have two legs is because whether Darwin or God or whoever made us, we have to figure out how to traverse an infinite number of things," like climbing a mountain or riding a bike, explains Michael Cicco, CEO of Fanuc America Corp. "When you get into the factory, even if it's a million things, it's still a finite number of things that you need to do." Human-shaped robots are over-engineered solutions to most factory chores that could be better solved by putting a robot arm on a wheeled base, he said. "The thing about humanoids is not that it's a human factor. It's that it's more dynamically stable," counters Melonee Wise, chief product officer at Agility Robotics, which is developing a humanoid robot called Digit. When humans grab something heavy, they can shift their weight for better balance. The same is true for a humanoid, she said. Using a robotic arm on a mobile base to pick up something heavy, "it's like I'm a little teapot and you become very unstable," she said, bending at the waist.

Read more of this story at Slashdot.

An anonymous reader quotes a report from the BBC: A student's robot has beaten the world record for solving a four-by-four Rubik's cube -- by 33 seconds. Matthew Pidden, a 22-year-old University of Bristol student, built and trained the "Revenger" over 15 weeks for his computer science bachelor's degree. The robot solved the cube in 45.305 seconds, obliterating the world record of 1 minute 18 seconds. However, the human record for solving the cube is 15.71 seconds. Mr Pidden's robot uses dual webcams to scan the cube, a custom mechanism to manipulate the faces, and a fully self-built solving algorithm to generate efficient solutions. The student now plans to study for a master's degree in robotics at Imperial College London.

Read more of this story at Slashdot.

An anonymous reader quotes a report from CNBC: There's a new warehouse robot at Amazon that has a sense of touch, allowing it to handle a job previously only done by humans. Amazon unveiled the robot, called Vulcan, Wednesday at an event in Germany. CNBC got an exclusive first look at Vulcan in April, as it stowed items into tall, yellow bins at a warehouse in Spokane, Washington. An up-close look at the "hand" of the robot reveals how it can feel the items it touches using an AI-powered sensor to determine the precise pressure and torque each object needs. This innovative gripper helps give Vulcan the ability to manipulate 75% of the 1 million unique items in inventory at the Spokane warehouse. Amazon has used other robotic arms inside its warehouses since 2021, but those rely on cameras for detection and suction for grasp, limiting what types of objects they can handle. Vulcan can also operate 20 hours a day, according to Aaron Parness, who heads up the Amazon Robotics team that developed the machine. Still, Parness told CNBC that instead of replacing people in its warehouses, Vulcan will create new, higher skilled jobs that involve maintaining, operating, installing and building the robots. When asked if Amazon will fully automate warehouses in the future, Parness said, "not at all." "I don't believe in 100% automation," he said. "If we had to get Vulcan to do 100% of the stows and picks, it would never happen. You would wait your entire life. Amazon understands this." The goal is for Vulcan to handle 100% of the stowing that happens in the top rows of bins, which are difficult for people to reach, Parness said. [...] Amazon said Vulcan is operating at about the same speed as a human worker and can handle items up to 8 pounds. It operates behind a fence, sequestered from human workers to reduce the risk of accidents.

Read more of this story at Slashdot.

Hyundai Motor Group is accelerating its factory automation efforts by deploying Atlas humanoid robots from Boston Dynamics at its Metaplant America facility in Georgia, as part of a broader $21 billion U.S. investment strategy to boost efficiency and local production amid rising tariffs. InterestingEngineering reports: At Hyundai Motor Group Metaplant America, Hyundai already uses Spot robots -- four-legged machines -- for industrial inspections. In addition, the plant features a dedicated robot that removes car doors before the vehicles enter General Assembly, and a fixed robot that reinstalls the doors toward the end of the process -- a technology unique to the Georgia facility. The South Korean automaker has not disclosed how many Atlas robots will be deployed at the facility or what specific tasks they will perform. According to reports, the company plans to further expand the use of robots across its global manufacturing facilities, streamlining processes and enhancing efficiency. [...] The automaker aims to manufacture 300,000 electric and hybrid vehicles annually at the new facility. At its recent Grand Opening Ceremony, the company announced plans to ramp up production to 500,000 units over time, without specifying a timeline.

Read more of this story at Slashdot.

"When Disneyland turns 70 this July, Main Street's Opera House will play host to the return of Walt Disney, who will sit down with audiences to tell his story in robot form," writes Gizmodo. But they point out Walt's granddaughter Johanna Miller wrote a Facebook post opposing the idea in November. ("They are Dehumanizing him. People are not replaceable...") The idea of a Robotic Grampa to give the public a feeling of who the living man was just makes no sense. It would be an imposter... You could never get the casual ness of his talking interacting with the camera his excitement to show and tell people about what is new at the park. You can not add life to one. Empty of a soul or essence of the man. Knowing that he did not want this. Having your predecessors tell you that this was out of bounds.... So so Sad and disappointed. The Facebook post claims that the son of a Disney engineer even remembers Walt saying that he never wanted to be an animatronic himself. And "Members of the Walt Disney family are said to be divided," reports the Los Angeles Times, "with many supporting the animatronic and some others against it, say those in the know who have declined to speak on the record for fear of ruining their relationships." So that Facebook post "raised anew ethical questions that often surround any project attempting to capture the dead via technology," their article adds, "be it holographic representations of performers or digitally re-created cinematic animations. And then some media outlets got a partial preview Wednesday, the Los Angeles Times reports: An early sculpt of what would become the animatronic was revealed, one complete with age spots on Disney's hands and weariness around his eyes — Imagineers stressed their intent is faithful accuracy — but much of the attraction remains secretive. The animatronic wasn't shown, nor did Imagineering provide any images of the figure, which it promises will be one of its most technically advanced. Instead, Imagineering sought to show the care in which it was bringing Disney back to life while also attempting to assuage any fears regarding what has become a much-debated project among the Disney community... Longtime Imagineer Tom Fitzgerald, known for his work on beloved Disney projects such as Star Tours and the Guardians of the Galaxy coaster in Florida, said Wednesday that "A Magical Life" has been in the works for about seven years. Asked directly about ethical concerns in representing the deceased via a robotic figurine, Fitzgerald noted the importance of the Walt Disney story, not only to the company but to culture at large... "What could we do at Disneyland for our audience that would be part of our tool kit vernacular but that would bring Walt to life in a way that you could only experience at the park? We felt the technology had gotten there. We felt there was a need to tell that story in a fresh way...." "Walt Disney — A Magical Life" will walk a fine line when it opens, attempting to inspire a new generation to look into Disney's life while also portraying him as more than just a character in the park's arsenal. "Why are we doing this now?" Fitzgerald says. "For two reasons. One is Disneyland's 70th anniversary is an ideal time we thought to create a permanent tribute to Walt Disney in the Opera House. The other: I grew up watching Walt Disney on television. I guess I'm the old man. He came into our living room every week and chatted and it was very casual and you felt like you knew the man. But a lot of people today don't know Walt Disney was an individual. They think Walt Disney is a company." And now nearly 60 years after his death, Disney will once again grace Main Street, whether or not audiences — or even some members of his family — are ready to greet him.

Read more of this story at Slashdot.

Long-time Slashdot reader AmiMoJo shares an article from Renewables Now: Chinese tech company Leapting has successfully completed its first commercial deployment of photovoltaic (PV) modules with an AI-driven solar module mounting robot in Australia. The Chinese company was tasked with supporting the installation of French Neoen's (EPA:NEOEN) 350-MW/440-MWp Culcairn Solar Farm in New South Wales' Riverina region. Shanghai-based Leapting said this week that its intelligent robot has installed almost 10,000 modules at an "efficient, safe, and stable" pace that has "significantly" reduced the original construction timeline. Litian Intelligent was deployed at the Australian project site in early February. The machine has a 2.5-metre-high robotic arm sitting on a self-guided, self-propelled crawler. Equipped with a navigation system, and visual recognition technology, it can lift and mount PV panels weighing up to 30 kilograms. By replacing labour-intensive manual operations, the robot shortens the module installation cycle by 25%, while the installation efficiency increases three to five times as compared to manual labour and is easily adapted to complex environments, Leapting says. Or, as Clean Technica puts it, "Meet the robot replacing four workers at a time on solar projects." This is part of a broader industrial trend. In the United States, Rosendin Electric demonstrated its own semi-autonomous system in Texas that allowed a two-person team to install 350 to 400 modules per day, a clear step-change from traditional methods. AES Corporation has been developing a robot called Maximo that combines placement and fastening with computer vision. Trina Solar's Trinabot in China operates in a similar space, with prototype systems demonstrating 50-plus modules per hour... In an industry where time-to-energy is critical, shaving weeks off the construction schedule directly reduces costs and increases net revenue... [T]he direction is clear. The future of solar construction will be faster, safer, and more precise — not because of human brawn, but because of robotic repetition. There will still be humans on-site, but their role shifts from lifting panels to managing throughput. Just as cranes and excavators changed civil construction, so too will robots like Leapting's define the next era of solar deployment.

Read more of this story at Slashdot.

New submitter MicroBitz shares a report: SPROUT, short for Soft Pathfinding Robotic Observation Unit, is a flexible, vine-like robot developed by MIT Lincoln Laboratory in collaboration with the University of Notre Dame. Unlike rigid robots or static cameras, SPROUT can "grow" into tight, winding spaces that are otherwise inaccessible, giving first responders a new way to explore, map and assess collapsed structures. Beyond disaster response, the technology could be adapted for inspecting military systems or critical infrastructure in hard-to-reach places, making SPROUT a versatile tool for a variety of high-stakes scenarios. "The urban search-and-rescue environment can be brutal and unforgiving, where even the most hardened technology struggles to operate. The fundamental way a vine robot works mitigates a lot of the challenges that other platforms face," says Chad Council, a member of the SPROUT team, which is led by Nathaniel Hanson. "The mechanical performance of the robots has an immediate effect, but the real goal is to rethink the way sensors are used to enhance situational awareness for rescue teams," adds Hanson. "Ultimately, we want SPROUT to provide a complete operating picture to teams before anyone enters a rubble pile." You can see the SPROUT vine robot in action in a YouTube video from MIT Lincoln Laboratory.

Read more of this story at Slashdot.