Skip to main content

PhysicalAI SO-101 Plugin

Physical AI Studio catalog definitions, hardware drivers, and URDF assets for single-arm and bimanual SO-101 robots, built for PhysicalAI.

Installation

uv add physicalai-so101-plugin

Installing the package registers SO101_Follower, SO101_Leader, BimanualSO101_Follower, and BimanualSO101_Leader with the Physical AI Studio robot catalog. It provides SO101, BimanualSO101, SO101Calibration, and SO101JointCalibration.

from physicalai_so101_plugin import BimanualSO101, SO101

left = SO101(port="/dev/ttyUSB0", calibration="left-calibration.json")
right = SO101(port="/dev/ttyUSB1", calibration="right-calibration.json")
bimanual = BimanualSO101(left=left, right=right)

URDF assets

This package vendors the Simulation/SO101 directory from TheRobotStudio/SO-ARM100 at revision fda892cba81032c46c40976a48c9ceadbf40a9ca.

from physicalai_so101_plugin import get_urdf_path

follower_urdf = get_urdf_path() / "so101-follower/so101_follower.urdf"
leader_urdf = get_urdf_path() / "so101-leader/urdf/so101_leader.urdf"
bimanual_follower_urdf = get_urdf_path() / "so101-follower/so101_bimanual_follower.urdf"
bimanual_leader_urdf = get_urdf_path() / "so101-leader/urdf/so101_bimanual_leader.urdf"

The bimanual models mount the left and right arms 0.4 m apart. Each model uses the matching role-specific single-arm mesh tree. Leader meshes live beside the URDFs under so101-leader/urdf/meshes/; leader descriptions include the leader handle and trigger meshes.

Bimanual examples

Calibration examples and a teleoperation recipe are bundled under examples/. Run the recipe from the repository root after editing the serial ports and calibration paths:

uv run physicalai run --config packages/physicalai-so101-plugin/examples/runtime/bimanual_teleop.yaml

Development

uv sync
uv run pytest packages/physicalai-so101-plugin/tests

Metadata

Release files for physicalai-so101-plugin 0.1.0

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for physicalai-so101-plugin 0.1.0
File Size Uploaded
physicalai_so101_plugin-0.1.0.tar.gz 11.3 MB Details

Built distribution (wheel)

Table of built distributions (wheels) for physicalai-so101-plugin 0.1.0
File Interpreter ABI Platform
physicalai_so101_plugin-0.1.0-py3-none-any.whl Python 3 none any Details

Total release size: 22.7 MB

Release files / physicalai_so101_plugin-0.1.0.tar.gz

Download URL physicalai_so101_plugin-0.1.0.tar.gz
Size 11.3 MB
Tags Source
SHA-256 checksum
How to use checksums
c5871ab97dc7519c2a358a1b0767d6ff41da24607b91fada32466f31afacf06c
BLAKE2b-256 checksum
How to use checksums
0fc0035014c7cdfea2398ea68aaa5db9e5d12f17ca781df0bdb316c745315bf4
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/7.0.0 CPython/3.13.13

Release files / physicalai_so101_plugin-0.1.0-py3-none-any.whl

Download URL physicalai_so101_plugin-0.1.0-py3-none-any.whl
Size 11.4 MB
Tags Python 3
SHA-256 checksum
How to use checksums
07a117f453bef724d00d4dca5eb89c02cae79536e7f71c468722169192355cb4
BLAKE2b-256 checksum
How to use checksums
ba57ddd0fa0ce7fd0eb9bb97f039f762da34c36398220ba32de25be7dcec5a7e
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/7.0.0 CPython/3.13.13

Release history Release notifications | RSS feed

This release

0.1.0 This release

2 release files

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page