Skip to main content

PhysicalAI Trossen Plugin

Trossen WidowX AI robot drivers and Physical AI Studio catalog definitions for PhysicalAI.

Installation

uv add physicalai-trossen-plugin

The plugin depends on trossen-arm. That SDK does not currently publish wheels for Python 3.14+, so use Python 3.12 or 3.13 when controlling a robot.

Usage

from physicalai_trossen_plugin import WidowXAI

robot = WidowXAI(ip="192.168.1.100", role="follower")

For two arms, construct BimanualWidowXAI from left and right WidowXAI instances. Installing this distribution also registers the Trossen entries in the Physical AI Studio robot catalog.

URDF assets

This package vendors the generated URDFs and mesh assets required by its catalog entries from Trossen trossen_arm_description revision 21d8b360c211c2ad8a065d8f462cbec0207626e7. The source license is preserved at urdf/LICENSE.

from physicalai_trossen_plugin import get_urdf_path

urdf_root = get_urdf_path()
single_arm_follower = urdf_root / "urdf/generated/wxai/wxai_follower.urdf"
single_arm_leader = urdf_root / "urdf/generated/wxai/wxai_leader_left.urdf"
bimanual_follower = urdf_root / "urdf/generated/stationary_ai.urdf"
bimanual_leader = urdf_root / "urdf/generated/stationary_ai_leader.urdf"

The single-arm leader catalog entry uses the left-handed leader model. The bimanual leader model includes left- and right-handed leader arms.

Development

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

Metadata

Release files for physicalai-trossen-plugin 0.1.0

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

Built distribution (wheel)

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

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

Download URL physicalai_trossen_plugin-0.1.0-py3-none-any.whl
Size 2.5 MB
Tags Python 3
SHA-256 checksum
How to use checksums
3092603a67e9f4dde156d30d55b6e8bde136303615941380527f5e0e59762767
BLAKE2b-256 checksum
How to use checksums
9e134a9328c5cea3a98177e3cb51273d31f3deb58feef629213f5d7c0bac3af2
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

1 release file

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