From the Hugging Face Hub to robot hardware with Strands Agents and LeRobot

Summary

Strands Robots integrates Hugging Face’s LeRobot stack with Strands Agents to connect dataset recording, policy execution, simulation, hardware deployment, and fleet coordination in one agent loop. Its integration keeps LeRobot responsible for hardware drivers, calibration, recording, and dataset handling, while Strands supplies AgentTools, a shared Robot abstraction, policy providers, and a Zenoh peer mesh; simulation and hardware use the same LeRobotDataset format. The walkthrough records demonstrations in MuJoCo, optionally pushes them to the Hub, runs policies through a common interface, and switches from simulation to a physical SO-101 with mode="real". The companion script and notebook run the default simulation workflow on a laptop without hardware, a GPU, or Hugging Face credentials, although the default Mock policy produces structurally valid but behaviorally unhelpful random demonstrations.

Takeaways

1. 1

   The simulation recorder uses the same LeRobotDataset structure as hardware recording, including parquet data for joint states and actions and per-camera MP4 files.

2. 2

   The Mock policy generates placeholder random joint actions, producing a structurally valid dataset but not a useful grasping demonstration; GR00T or LerobotLocal can be substituted for real policy behavior.

3. 3

   The default example runs on a laptop without hardware, a GPU, or Hugging Face credentials, while local GR00T inference requires an NVIDIA GPU with at least 16 GB of video memory and Docker.