Over the past decades, roboticists have introduced a wide range of systems that can effectively tackle some real-world ...

Embodied learning for object-centric robotic manipulation is a rapidly developing and challenging area in embodied AI. It is ...

MIT this week showcased a new model for training robots. Rather than the standard set of focused data used to teach robots new tasks, the method goes big, mimicking the massive troves of information ...

A UK research team recently developed a groundbreaking "robot learning method" to address this issue. Their approach can teach robots up to 1,000 diverse movements in a single day. The method was ...

A simulation-trained DoorMan system helps a Unitree G1 outperform human operators in door opening speed and reliability.

A monthly overview of things you need to know as an architect or aspiring architect. Unlock the full InfoQ experience by logging in! Stay updated with your favorite authors and topics, engage with ...

Over the past decades, roboticists have introduced a wide range of advanced systems that can move around in their ...

Short, stumpy robots learned how to play soccer — and improved their skills dramatically thanks to a new AI training technique that combines several pre-existing methods. When you purchase through ...

A new meta-learning framework inspired by how babies explore the world could help robots adapt faster, handle objects safely, and interact more naturally with humans.

Ancient mudras offer a blueprint for smoother robot hand movement and could inspire new approaches to motor training and ...