MIT researchers have invented a way to efficiently optimize the control and design of soft robots for target tasks, which has traditionally been a monumental undertaking in computation.

The new training method doesn't use sensors or onboard control tweaks, but a single camera that watches the robot's movements and uses visual data.

Researchers have invented a way to efficiently optimize the control and design of soft robots for target tasks, which has traditionally been a monumental undertaking in computation.

For robots to be predictable and adaptive, they need a priority-based architecture and a new legal model, argues a researcher ...

"Smartphone control enables control [of robots] away from the home, and the ability for the manufacturer to more easily provide variables [to] enhance the experience for the buyer." ...

A new machine-learning technique can train and control a reconfigurable soft robot that can dynamically change its shape to complete a task. The researchers also built a simulator that can ...

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

Researchers created a biohybrid robot that uses electrical signals in mycelium to move around.

Robot placed under the control of a fungal overlord A mushroom's response to environmental changes can be used to control a robot.

ANYmal-D, the badminton-playing quadruped robot from ETH Zurich, combines artificial intelligence with whole-body coordination to rally with human players for up to 10 shots.