Researchers at MIT have developed a robot capable of assembling “building blocks called voxels to build an object with almost any shape,” reports Alex Wilkins for New Scientist. “You can get furniture-scale objects really fast in a very sustainable way, because you can reuse these modular components and ask a robot to reassemble them into different large-scale objects,” says graduate student Alexander Htet Kyaw.
Researchers at MIT have developed a new virtual training program for four-legged robots by taking “popular computer simulation software that follows the principles of real-world physics and inserting a generative AI model to produce artificial environments,” reports Jeremy Hsu for New Scientist. “Despite never being able to ‘see’ the real world during training, the robot successfully chased real-world balls and climbed over objects 88 per cent of the time after the AI-enhanced training,” writes Hsu. "When the robot relied solely on training by a human teacher, it only succeeded 15 per cent of the time.”
Researchers at MIT have developed a new model for training robots dubbed Heterogeneous Pretrained Transformers (HPT), reports Brain Heater for TechCrunch. The new model “pulls together information from different sensors and different environments,” explains Heater. “A transformer was then used to pull together the data into training models. The larger the transformer, the better the output. Users then input the robot design, configuration, and the job they want done.”
MIT researchers have developed a new training technique called Heterogeneous Pretrained Transformers (HPT) that could help make general-purpose robots more efficient and adaptable, reports Christopher Isak for TechAcute. “The main advantage of this technique is its ability to integrate data from different sources into a unified system,” explains Isak. “This approach is similar to how large language models are trained, showing proficiency across many tasks due to their extensive and varied training data. HPT enables robots to learn from a wide range of experiences and environments.”
Researchers at MIT have developed “Clio,” a new technique that “enables robots to make intuitive, task-relevant decisions,” reports Jennifer Kite-Powell for Forbes. The team’s new approach allows “a robot to quickly map a scene and identify the items they need to complete a given set of tasks,” writes Kite-Powell.
Researchers at MIT have developed a “set of wearable robotic limbs to help astronauts recover from falls,” reports Amy Gunia for CNN. “The so-called ‘SuperLimbs’ are designed to extend from a backpack containing the astronauts’ life support system,” explains Gunia. “When the wearer falls over, an extra pair of limbs can extend out to provide leverage to help them stand, conserving energy for other tasks.”
On October 8, the MIT Museum is hosting a “Techno, Art, and Music Robots talk with artist and engineer Moritz Simon Geist,” reports The Boston Globe. The talk will focus on “the intersection of music and robotics,” writes The Boston Globe.
Researchers at MIT have developed a new method that “enables robots to intuitively identify relevant areas of a scene based on specific tasks,” reports Baba Tamim for Interesting Engineering. “The tech adopts a distinctive strategy to make robots effective and efficient at sorting a cluttered environment, such as finding a specific brand of mustard on a messy kitchen counter,” explains Tamim.
Researchers at MIT have developed “AstroAnts,” autonomous, magnetic, robotic rovers roughly the size of a Hot Wheels toy car designed to monitor space vehicles and other hard-to-reach machinery, reports Jesus Diaz for Fast Company. “The idea is that, by constantly watching over the temperature and structural integrity of their cosmic rides, spaceships will be more resilient to the extreme conditions of space and astronauts will be safer,” explains Diaz.
Boston Globe columnist Scott Kirsner spotlights Prof. Mitchel Resnick, Prof. Neil Gershenfeld, and the late Prof. Emeritus Woodie Flowers and their work developing programs that “get kids excited about, and more proficient in, STEM.” Kirsner underscores: “Each of the initiatives brings some of the hands-on problem solving, messiness, and collaborative prototyping elements of MIT’s culture into the wider world. And they’ve all had a big impact on the way kids learn about technology.”
Prof. Michael Strano joins “Somewhere on Earth” podcast host Gareth Mitchell to discuss how he and his colleagues developed tiny batteries that could be used to power cell-sized robots. Roughly the thickness of a human hair, the new battery can create a current by capturing oxygen. “I would say we're making the LEGOs, the building blocks that go into robots,” Strano says. “We’re building the parts and it's an exciting time for the field.”
Researchers at MIT have developed tiny batteries capable of powering cell-sized robots that can “execute tasks as varied as targeting drug delivery inside the human body to checking pipelines for gas leaks,” reports Brian Heater for TechCrunch. “Despite the barely visible size, the researchers say the batteries can generate up to 1 volt, which can be used to power a sensor, circuit or even a moving actuator.”
The final round of the Zero Robotics competition at the MIT Media Lab featured high school students from around the country facing off in a programming challenge using the SPHERES satellites aboard the International Space Station, reports Glenn Jones for NBC Boston. The event “welcomed about 70 middle schoolers from diverse backgrounds to participant in the finals of a robotics competition that featured live dialogue with astronauts on the International Space Station.”
MIT researchers have developed “a robotic system that can rotate different types of fruit and vegetable using its fingers on one hand, while the other arm is made to peel,” reports Alex Wilkins for New Scientist. “These additional steps of doing rotation are something which is very straightforward to humans, we don’t even think about it,” Prof. Pulkit Agrawal. “But for a robot, this becomes challenging.”
Researchers at MIT have developed a new method for “training home robots in simulation,” reports Brain Heater for TechCrunch. “Simulation has become a bedrock element of robot training in recent decades,” explains Heater. “It allows robots to try and fail at tasks thousands — or even millions — of times in the same amount of time it would take to do it once in the real world.”