MIT researchers developed a technique to combine robotics training data across domains, modalities, and tasks using generative AI models. They create a combined strategy from several different ...

A robot arm that can flawlessly sort packages inside a computer simulation will, more often than not, fumble the same task ...

Researchers have developed an AI training method that enables robots to transfer skills learned in simulation into real-world ...

Training leap: A new AI method enables robots to transfer simulation-learned skills to real-world tasks with limited additional data. Industry impact: The technique could cut costs and risks in ...

The Genesis Project represents a significant leap forward in the convergence of generative AI and physics simulation, reshaping the way robots are trained and developed. By integrating innovative ...

The latest boom in robotics represents a revolution in the way machines have learned to interact with the world.

Have you ever wondered what it would take to train a robot to walk, grasp objects, or navigate a cluttered room with the same ease as a human? For many, the idea of teaching robots these complex tasks ...

Inside the robotics laboratory of the Toyota Research Institute (TRI) in Cambridge, Massachusetts, a group of robots are busy cooking. There is nothing special about that; robotic chefs have been ...

Universal Robots (UR) today unveiled the UR AI Trainer at GTC 2026 in Silicon Valley. Developed in collaboration with Scale AI, the AI Trainer marks a tectonic shift as robots move from pre-programmed ...

AI is upending the way robots learn, leaving companies and researchers with a need for more data. Getting it means wrestling with a host of ethical and legal questions. Since ChatGPT was released, we ...