A new deep learning model from Cardiff University helps robots choose safer, more reliable paths—marking a shift from acrobatics to real-world navigation.

At UC Berkeley, researchers in Sergey Levine's Robotic AI and Learning Lab eyed a table where a tower of 39 Jenga blocks ...

The company has been using reinforcement learning to help fallen robots right themselves. Agility shut off Digit’s obstacle avoidance for the above video to force a fall.

Slowly, but surely, the Baxter robot is learning. It starts as a series of random grasps — the big, red robot pokes and prods clumsily at objects on the table in front of it. The robot is ...

Robots are moving further from sci-fi into everyday reality. They can now assist with doing housework, giving directions and even performing surgery. They're still a few years off, but here are a ...

A collaboration between developmental psychologists and computer scientists has demonstrated that robots can "learn" much like babies - by experiencing the world and eventually imitating humans.