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.

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.

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