Page 2 of 3. Back to the latest

From detecting failed rollouts to diagnosing root causes, failure analysis helps robotics teams understand what went wrong and improve robot policies.

Apptronik has one robot, a handful of deep partnerships and a building where humanoids work all day to produce training data. Here's how Apollo works, how the company plans to sell it, and why the data matters as much as the hardware.

1X sold a home humanoid to consumers before most rivals had left the factory floor. Here's how NEO works, how 1X plans to make money, and why the plan rests on data from real homes.

A home robot you train with your phone, a startup betting on touch, a new five-finger hand, a shipyard trying autonomous welding, and NASA's open testbed.

Loss curves and simulation scores only tell part of the story. Here's how robot policy evaluation works, and what a trustworthy benchmark looks like.

An open-source robotics stack learns to work with AI agents, a humanoid gets a real training floor inside a car plant, and the industry gets its first honest count of how many humanoids have shipped.

From identifying weeds to harvesting crops, agricultural AI depends on accurately labeled images and real-world farming data.

A factory in China where robots build robots at a 10-minute pace, a robot brain trained on human hand data alone, a humanoid built to work without a safety cage, and Japan's robot ambulance.

Robotics annotation runs on judgment calls, not just labels. Here's why who does the labeling matters as much as how it's done.