Stephanie writes about robotics, agriculture AI, and the training data behind them, for Labelix.ai, an independent data foundry for robotics and multimodal AI.
6 articles, newest first LinkedIn

Microduck walks, picks things up with its beak and gets back up after a fall. The reason to take it seriously is that owners can train it to move differently.

Define what failure means for the task, search the footage for suspected failures with CreativAI, organize the results in Data Plates, then review and tag each attempt before drawing conclusions.

Franka Robotics builds force-sensitive arms for robot learning labs. Here's how the Franka Research 3 and the two-arm FR3 Duo compare, what buyers should know, and how DROID collected its demonstrations on Franka hardware.

Hugging Face sells two Reachy robots from Pollen Robotics and gives away LeRobot, the software to train them. Here's how the platforms differ, what buyers should know, and why useful robot learning still depends on data quality.

AI can find the moments that matter in hours of robot video and propose labels for them. Here's how CreativAI structures that footage, and where human review turns candidate labels into ones a team can train on.

Recognizing an object doesn't tell a robot how to hold it. Here's how shape, weight, material and clutter each change the problem, and what training data needs to capture.