Scientists have trained the ANYmal quadruped robot to play badminton, and it's good enough to complete in a 10-shot rally ...

Google DeepMind and Intrinsic developed AI that uses graph neural networks and reinforcement learning to automate multi-robot ...

In the company's latest video, a humanoid robot can be seen walking and crouching while it performs various tasks.

A research article by scientists at the Nanjing University of Aeronautics and Astronautics developed a neural control algorithm to coordinate the adhesive toes and limbs of the climbing robot. The ...

Boston Dynamics claimed that building AI generalist robots is the most viable path to creating scalable humanoid robots.

The system uses a machine learning technique called attention-based map encoding, trained through reinforcement learning.

Unitree Robotics has launched the R1, a remarkable humanoid robot capable of walking, running, dancing, cartwheeling, and even kung-fu kicks. It can also respond to voice commands and hold basic ...

This golf robot uses a Microsoft Kinect camera and a neural network to line up putts It doesn't get the ball in the hole every time, but at least it won't whine about its 401k.

Boston Dynamics' engineers push Spot to new limits, testing daring backflips to make the robot dog tougher and smarter.