A faster, better way to train general-purpose robots
Inspired by large language models, researchers develop a training technique that pools diverse data to teach robots new skills.
Combining next-token prediction and video diffusion in computer vision and robotics
A new method can train a neural network to sort corrupted data while anticipating next steps. It can make flexible plans for robots, generate high-quality video, and help AI agents navigate digital environments.
How AI is improving simulations with smarter sampling techniques
MIT CSAIL researchers created an AI-powered method for low-discrepancy sampling, which uniformly distributes data points to boost simulation accuracy.
Helping robots zero in on the objects that matter
A new method called Clio enables robots to quickly map a scene and identify the items they need to complete a given set of tasks.
For developing designers, there’s magic in 2.737 (Mechatronics)
Mechatronics combines electrical and mechanical engineering, but above all else it’s about design.
Engineering and matters of the heart
Professor Ellen Roche is creating the next generation of medical devices to help repair hearts, lungs, and other tissues.
AI assistant monitors teamwork to promote effective collaboration
An AI team coordinator aligns agents’ beliefs about how to achieve a task, intervening when necessary to potentially help with tasks in search and rescue, hospitals, and video games.
MIT engineers design tiny batteries for powering cell-sized robots
These zinc-air batteries, smaller than a grain of sand, could help miniscule robots sense and respond to their environment.
A new model offers robots precise pick-and-place solutions
SimPLE learns to pick, regrasp, and place objects using the objects’ computer-aided design model.
Helping robots practice skills independently to adapt to unfamiliar environments
A new algorithm helps robots practice skills like sweeping and placing objects, potentially helping them improve at important tasks in houses, hospitals, and factories.
Precision home robots learn with real-to-sim-to-real
CSAIL researchers introduce a novel approach allowing robots to be trained in simulations of scanned home environments, paving the way for customized household automation accessible to anyone.
Flying high to enable sustainable delivery, remote care
Drone company founders with MIT Advanced Study Program roots seek to bring aerial delivery to the mainstream.
Creating and verifying stable AI-controlled systems in a rigorous and flexible way
Neural network controllers provide complex robots with stability guarantees, paving the way for the safer deployment of autonomous vehicles and industrial machines.
Designing for outer space
With NASA planning permanent bases in space and on the moon, MIT students develop prototypes for habitats far from planet Earth.
Researchers use large language models to help robots navigate
The method uses language-based inputs instead of costly visual data to direct a robot through a multistep navigation task.