Overview
In this course, you will learn how to train and deploy a perception model using synthetic data generation (SDG) for dynamic robotic tasks.
You will analyze the role of perception models, use simulation for SDG, apply domain randomization techniques, and evaluate the effectiveness of a trained model. Through hands-on exercises, you will generate synthetic data, learn how to train a custom AI perception model, and integrate it into a robotic workflow.
This course is designed for students familiar with robotics and Isaac Sim, as well as users interested in applying SDG to various robotic disciplines.
By the end of this course, you will have the skills to develop and deploy robust perception models for real-world robotic applications.
Course Description & Learning Outcomes
Analyze the role of perception models in dynamic robotic tasks.
Apply domain randomization with Replicator to generate synthetic data.
Evaluate the effectiveness of a trained AI perception model.
Use a workflow for training and deploying a perception model using SDG.
Recommended Prerequisites
This is the third course in the Getting Started With Isaac Sim learning path. Please complete Ingesting Robot Assets and Simulating Your Robot in Isaac Sim before beginning this course.Basic Python knowledge and familiarity with robotics concepts.A Linux machine meeting Isaac Sim's system requirements is necessary for this course and for properly running simulations.
Schedule
End Date: 31 Dec 2032, Friday
Location: Online
Pricing
Course fees: 0
Skills Covered
PROFICIENCY LEVEL GUIDE
Beginner: Introduce the subject matter without the need to have any prerequisites.
Proficient: Requires learners to have prior knowledge of the subject.
Expert: Involves advanced and more complex understanding of the subject.
- Robotics (Proficiency level: Beginner)
