Medulla: Hardware Communication Skills

WARNING

All the cameras were tested on Windows 11 only.

SUMMARY

Medulla is a module in the Telekinesis SDK for connecting to cameras and sensors. It provides tools to interface with various 2D and 3D cameras, and integrate them into Telekinesis applications.

When to Use Medulla?

Use Medulla for robotics applications that require camera and sensor connectivity, such as:

• Streaming camera data for vision pipelines
• Orchestrating multiple cameras for robot perception and control
• Connecting cameras to Physical AI agents

What Does Medulla Provide?

Medulla includes a collection of modular skills for:

• 2D and 3D camera interfacing
• Data acquisition and preprocessing
• Time-synchronized sensor streams
• Integration with Telekinesis modules (Vitreous, Retina, Cornea, Pupil, Neuroplan)

How to Use Medulla?

To use the skills from Medulla, simply use:

from telekinesis.medulla.cameras import webcam

Here is a minimal example:

from telekinesis.medulla.cameras import webcam

camera = webcam.Webcam(name="my_webcam_camera", camera_id=0)
camera.connect()
image = camera.capture_color_image()
print(image)
camera.disconnect()

Overview of Skills

SDK Call	Description
connect	Open a connection to the camera hardware.
disconnect	Cleanly release the camera connection.
capture_color_image	Capture a single color frame as a NumPy array.
capture_depth_image	Capture a single depth frame in metres.
capture_pointcloud	Capture a single colour-mapped 3D point cloud.
stream_live_color_video	Stream continuous color frames in a loop.
stream_live_depth_video	Stream continuous depth frames in a loop.
stream_pointcloud	Stream a continuous colour-mapped point cloud.
get_parameter	Read a camera parameter (exposure, frame rate, etc.).
set_parameter	Write a camera parameter.
publish_video_with_babyros	Stream live video over BabyROS using a server/client split.