Data Collection#
In this module, we’ll explain a data collection workflow focused on systematically gathering high-quality datasets for imitation learning using state machine-based workflows in simulation environments.
The module teaches how to define and automate a robotic ultrasound scanning process using distinct states.
Learning Objectives#
By the end of this chapter, you will be able to:
Leverage state machines for data collection
Perform scene randomization in Isaac Sim
Collect and curate datasets for imitation learning