MIT CSAIL researchers used AI-generated images to train a robot dog in parkour, without real-world data. Their LucidSim system demonstrates generative AI's potential for creating robotics training data.

"SonicSense gives robots a new way to hear and feel, much like humans, which can transform how current robots perceive and interact with objects."

A breakthrough training system that uses imitation learning opens a "new frontier" in medical robotics, researchers say.

A new snake-like robot has the ability to grow in length and slither into the most inaccessible places.

Inspired by large language models, researchers develop a training technique that pools diverse data to teach robots new skills.

The transition from water to land is one of the most significant events in the history of life on Earth. Now, a team of roboticists, palaeontologists and

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.

MIT CSAIL researchers created an AI-powered method for low-discrepancy sampling, which uniformly distributes data points to boost simulation accuracy.

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.