Illusion: Synthetic Data Generation Skills
WARNING
Illusion is not yet released.
This module is under active development and will be available in a future Telekinesis SDK release. In the meantime, you can explore several datasets already generated with Illusion in the Synthetic Datasets section under the Data Engine tab.
INFO
Illusion is a module in the Telekinesis SDK for synthetic data generation.
It provides tools to generate high-quality, annotated datasets for robotics and AI applications, enabling developers to train and validate models without relying solely on real-world data.
Install Telekinesis Skill Library
Create an API key, install
telekinesis-ai and module specific installations and dependencies in a Python environment. Go to the Quickstart
Pick a starter and run your first Skill end-to-end - 2D / 3D vision, webcam capture, robot motion, or a full vision-to-robot pipeline, all visualized in Rerun.
When to Use Illusion?
Use Illusion for robotics applications that require synthetic datasets or augmented data for model training and testing, such as:
- Generating training data for vision-guided pick-and-place
- Creating annotated datasets for object detection or segmentation
- Simulating rare or dangerous scenarios for robot testing
- Producing diverse scenes for robust AI agent perception
- Accelerating model development when real-world data is limited
What Does Illusion Provide?
Illusion includes a collection of modular skills for:
- Procedural scene generation
- Synthetic image and point cloud creation
- Automatic labeling and annotation
- Integration with Telekinesis perception modules (Retina, Cornea, Vitreous)
- Configurable pipelines for large-scale dataset generation