SO-ARM101 · Hugging Face LeRobot · Open Source

Leader teaches.
Follower learns.

The flagship Hugging Face LeRobot arm. A 6-DoF leader-follower pair that collects demonstrations by teleoperation and trains imitation learning policies that run autonomously on the follower.

Leader
Follower
Teleoperation · Data collection · Policy training
6
Degrees of freedom
2
Arms (leader + follower)
~4hr
Train ACT policy (RTX 3080)
~$220
Assembled pair (standard)
HF
Hugging Face native
Hardware specification

Low-cost. Precise enough
for real policy work.

Architecture
Leader + follower pair
DoF
6 per arm
Follower motors
6× STS3215 (1/345 gearing)
Servo torque
30 kg·cm at 12V
Feedback
360° magnetic encoder
Vision
Wrist + external camera
Compute
NVIDIA Jetson Orin compatible
Build cost
From ~$130 (DIY 3D print)
License
Apache 2.0 (Hugging Face)
Software stack

The full Hugging Face
embodied AI toolkit.

LeRobot (Hugging Face)Core framework
ACT policyAction chunking
Diffusion PolicyBehaviour cloning
PyTorchTraining backend
Hugging Face HubDataset + model sharing
Feetech SDKMotor control
How it learns

Demonstration to
autonomous policy.

A human operates the leader arm. The follower mirrors every movement. Cameras record the scene. The full episode — joint positions, gripper state, camera frames — is saved as a dataset episode.

Repeat for 50–200 episodes. Train an ACT or diffusion policy on those demonstrations. Deploy the policy to the follower arm. It runs autonomously.

Typical task: master in minutes, train in 4 hours.

Arm variants

SO-101 versus the
B601 — when to use which.

SO-ARM101
PoC & research
Low cost. Fast setup. Native LeRobot support. Ideal for demonstrating feasibility on a defined task before committing to industrial hardware.
reBot B601
Pre-production cell
Industrial actuators. ±0.2mm repeatability. Larger reach and payload. For policies moving to a real production environment.
01
Assemble & calibrate
Build or receive the leader-follower pair. Run lerobot-calibrate to synchronise joint zero positions across both arms.
02
Collect demonstrations
Operate the leader arm through the target task. 50–200 episodes recorded to the Hugging Face Hub dataset repository.
03
Train a policy
Run lerobot.scripts.train with your dataset. ACT (52M params) trains in ~4 hours on an RTX 3080. Push checkpoint to HF Hub.
04
Deploy & evaluate
Load the policy checkpoint to the follower arm. Run rollouts. Collect failure cases. Iterate with more demonstrations or a new training run.