"In robot manipulation, learning is a promising alternative to traditional engineering methods and has demonstrated great success, especially in pick-and-place tasks," says Cui, ...

SHANGHAI, Dec. 30, 2024 /PRNewswire/ -- AgiBot, a leading robotics startup today releases by far the largest humanoid manipulation dataset: AgiBot World. AgiBot World, the first large-scale ...

In a step toward robots that can learn on the fly like humans do, a new approach expands training data sets for robots that work with soft objects like ropes and fabrics, or in cluttered environments.

References [1] A robotic skill transfer learning framework of dynamic manipulation for fabric placement. Computers in Industry (2025). [2] Flattening and folding towels with a single-arm robot ...

Robot dog teaches itself to walk, roll over and navigate obstacles after just ONE hour of training as scientists hope to eventually teach it to play fetch and obey verbal commands ...

Now, a new deep learning technique developed by researchers at MIT, Carnegie Mellon University, and the University of California at San Diego, shows promise to make robotics systems more stable in ...

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.

A fully autonomous robot that can quickly and reliably test materials, boosting both speed and accuracy in self-driving labs. It’s like giving your lab assistant a P ...

We are seeking excellent candidates at post-doctoral level to participate in new research endeavours, related to robot learning, manipulation, and AI for autonomous physical systems. The projects ...