Skip to main content

SO-101 workshop

A browser page to connect the arm, calibrate it, and run the tasks. Distances are metres. Joint angles are degrees.

Clear the table before the arm moves. Torque off lets it fall, so support it.

Start the page

Install uv, then:

uvx --python 3.13 so101-workshop@latest run

From this folder:

uvx --python 3.13 --from . so101-workshop run

Open the address it prints (http://127.0.0.1:8020). --port 8033 changes the port. --mock runs the page with no arm. --no-viewer hides the 3D view.

Use Python 3.13. On Linux, add your user to the dialout group and install libgl1. The arm is /dev/ttyACM0 on Linux, COM* on Windows, and /dev/cu.usbmodem* on macOS.

First time

  1. Plug in the USB adapter. Under Hardware, find the port.
  2. Press Start motor calibration. Set every joint to the middle of its travel, then move every joint except wrist roll through its range, including the gripper.
  3. Connect the arm and the camera. The default camera is the reCamera.

Tasks

The Tasks tabs are the exercises.

Tab What it does
Teleop Drive the gripper. WASD moves X and Y, Q/E moves Z, F/V tilts, Z/C twists, space toggles the gripper, H homes, R rests.
Click and go Click the table. The gripper moves 20 mm above that point.
Click and pick Click the table. The gripper opens, picks, returns to rest, and opens.
Detect and pick Click a box. The arm picks the centre of that box.

Key teleop in the top bar keeps the keys working on every tab. The red E-stop turns torque off.

Detect and pick uses the boxes from the reCamera. To run YOLO on this computer instead, install the extra and set detector: local in workshop.yaml:

uv sync --python 3.13 --extra yolo

A RealSense needs uv sync --python 3.13 --extra vision. camera_realsense.yaml is the D405. camera_usbcam.yaml is a USB camera (device is the video index). camera_demo.yaml is a fake camera for trying the page.

Run the code

From this folder, once:

uv sync --python 3.13 --extra twin --extra yolo

--mock does not move a real arm. --live does.

uv run python scripts/keyboard_control.py --live
uv run python scripts/twin.py --live
uv run python scripts/get_pose.py --live
uv run python scripts/arm_move.py --live
uv run python scripts/gripper.py --live
uv run python application/click_and_go.py --live
uv run python application/click_and_pick.py --live
uv run python application/detect_and_pick.py --live
uv run python application/pick_and_place.py --live
uv run python calibration/hand_eye.py
uv run python calibration/auto_hand_eye.py --live
uv run python detection/inference.py

keyboard_control.py is the same keys as the page, plus P for the pose and Esc to stop. twin.py only shows the arm. arm_move.py homes, visits three points, and rests. Change POINTS in that file, and the heights and delays at the top of pick_and_place.py and detect_and_pick.py, before a live run.

from so101_control import SO101

with SO101.connect(mock=True) as arm:
    arm.home()
    arm.move_to(0.20, 0.00, 0.10)
    arm.grip()
    arm.release()
    arm.rest()

SO101.connect(mock=False) uses the port in config/robot.yaml.

Metadata

Release files for so101-workshop 0.1.5

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

Source distribution (sdist)

Source distribution for so101-workshop 0.1.5
File Size Uploaded Provenance Actions
so101_workshop-0.1.5.tar.gz 6.1 MB Without provenance Details for so101_workshop-0.1.5.tar.gz

Built distribution (wheel)

Table of built distributions (wheels) for so101-workshop 0.1.5
File Interpreter ABI Platform Actions
so101_workshop-0.1.5-py3-none-any.whl Python 3 none any Details for so101_workshop-0.1.5-py3-none-any.whl

Total release size: 12.2 MB

Release files / so101_workshop-0.1.5.tar.gz

Download URL so101_workshop-0.1.5.tar.gz
Size 6.1 MB
Tags Source
SHA-256 checksum
How to use checksums
5479b806c40c60ff6b9da33bccf37df8272b160aabd23a53ea092a4496ee050f
BLAKE2b-256 checksum
How to use checksums
c5030ebd0b41e6cd6bbfc31d0f2eec7403e2780c8eab85f3d3932766e1bf4fae
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via uv/0.12.8 {"installer":{"name":"uv","version":"0.12.8","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"22.04","id":"jammy","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}

Release files / so101_workshop-0.1.5-py3-none-any.whl

Download URL so101_workshop-0.1.5-py3-none-any.whl
Size 6.1 MB
Tags Python 3
SHA-256 checksum
How to use checksums
dbbc18148d07e24c36efd2bde121b23e5b797cc3370e390c911c57d8b5f7bc4a
BLAKE2b-256 checksum
How to use checksums
417e684ce1dd803cbf71d50ab554db65f5cf9825b2ef9bd97618fbce129e43c7
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via uv/0.12.8 {"installer":{"name":"uv","version":"0.12.8","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"22.04","id":"jammy","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}

Security for so101-workshop 0.1.5

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

No provenance found

None of the files in this release were uploaded with provenance metadata.

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

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