By blending 2D images with foundation models to build 3D feature fields, a new MIT method helps robots understand and manipulate nearby objects with open-ended language prompts.

Researchers coaxed a family of generative AI models to work together to solve multistep robot manipulation problems.

Some researchers see formal specifications as a way for autonomous systems to "explain themselves" to humans. But a new study finds that we aren't understanding.

MIT engineers develop a long, curved touch sensor that could enable a robot to grasp and manipulate objects in multiple ways.

Designed to ensure safer skies, “Air-Guardian” blends human intuition with machine precision, creating a more symbiotic relationship between pilot and aircraft.

With a new technique, a robot can reason efficiently about moving objects using more than just its fingertips.

Mens, Manus and Machina (M3S) will design technology, training programs, and institutions for successful human-machine collaboration.

Produced with techniques borrowed from Japanese paper-cutting, the strong metal lattices are lighter than cork and have customizable mechanical properties.

Researchers develop a machine-learning technique that can efficiently learn to control a robot, leading to better performance with fewer data.

Researchers discover how to control the anomalous Hall effect and Berry curvature to create flexible quantum magnets for use in computers, robotics, and sensors.