Artificial IntelligenceFeatured briefing
First-hand information for everyone
Robots that handle objects today tend to rely on their hands or simple end-effectors. Humans, by contrast, routinely press, brace and slide
A team of researchers reports a modular system that uses vision and a small onboard language model to give unmanned aerial vehicles (UAVs) c
Spacecraft inspection — the work of photographing and identifying parts of a satellite or space station from a nearby servicer or inspection
A team of researchers has released a preprint describing Spark-0, a new approach that aims to make robots better at contact-rich, dexterous
Robots that learn from video and language typically train to predict the next action and use that as the main supervision signal. A new pape
Engineers have long admired how animals navigate cluttered environments using tiny, energy‑sipping brains. A new study on arXiv takes a step
Roboticists have long hoped for generalist policies—single controllers that can perform many different tasks—because they promise to shortcu
Robots and autonomous systems increasingly rely on learned models that predict how people and other agents will move. Modern diffusion-based
Robots that learn from watching humans or other robots often rely on machine-learning policies to turn sensory inputs into actions. In recen
A new preprint on arXiv (arXiv:2610.08789v1) describes an algorithm called QF3 — “Fast Flow RL with Filtered Q‑Gradients” — that aims to mak