Medulla: Hardware Communication Skills
SUMMARY
Medulla is a module in the Telekinesis SDK for connecting to cameras. 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 connectivity and integration, 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)
Installation
Medulla requires BabyROS. Follow the official documentation to install it.
Install Medulla via the Telekinesis SDK:
bash
pip install telekinesis-ai[medulla]TIP
Camera drivers and vendor SDKs require additional installation steps. See each camera's documentation page for details.
Install the additional dependencies for running the examples:
bash
pip install telekinesis-ai[examples]How to Use Medulla?
python
from telekinesis.medulla.cameras import webcam
camera = webcam.Webcam(name="my_webcam", camera_id=0)
camera.connect()
image = camera.capture_single_color_frame()
print(image)
camera.disconnect()Supported Cameras
| Vendor | Status |
|---|---|
| Webcam | Available |
| IDS | Available |
| Intel RealSense | Available |
| ZIVID | Coming Soon |
| SensoPart | Coming Soon |
| MechMind | Coming Soon |
| Azure Kinect | Coming Soon |