A hybrid data-driven framework combining finite element simulations and transfer learning predicts fiber-reinforced soft actuator bending deformation with high precision.

Hello everyone. This is Sekiguchi-kun.When you watch videos of robots moving, they appear to move exactly as programmed, without a single error. An arm extends smoothly to grab a part, or a mobile ...

UC Berkeley researchers use agentic AI to generate, test, and refine robot-control programs, reducing training data and ...

The new model is up to twice as successful at some tasks.

What I am about to write is a story from the late 1990s, when I was involved in the development of Automated Guided Vehicles ...

In recent months, artificial intelligence agents that can reason, plan and use external tools to accomplish multistep tasks ...

Professor Ken Goldberg has long had doubts about how quickly robot capabilities could advance. But new AI models are leading ...

Researchers have developed a novel adaptive fuzzy sliding mode controller (AFSMC) designed to enhance the trajectory tracking ...

Ai2 released ToyBlocks on November 6, 2026, as the first environment in its FoundationWorlds framework, pairing an open robot ...

Can you train robots almost entirely in simulation? A new UK startup says yes, and has raised $40 million to prove themselves right.