robomimic
Imitation-learning research library from Stanford/TRI with algorithms, datasets, and eval pipelines.
Tools around the LeRobot dataset format: conversion, visualization, and recording.
This entry covers tooling around the LeRobot dataset format—conversion, visualization, and recording utilities that keep teleop logs and training data aligned. In practice you will mostly live inside the main LeRobot repo and Hub dataset cards, but treating “format tools” as a first-class concern prevents silent train/serve skew.
Anyone standardizing on LeRobotDataset for multi-robot data.
Imitation-learning research library from Stanford/TRI with algorithms, datasets, and eval pipelines.
Content reviewed 2026-07-23