By the end of this guide, you have covered a complete learning path from Jetson platform basics and development tools to computer vision, offline LLMs, generative AI, ROS robotics, and practical Jetson application cases.
- Jetson platform basics, system setup, common developer tools, and remote debugging methods
- Core development capabilities including CUDA, TensorRT, Docker, PyTorch, and TensorFlow
- Computer vision workflows, model training, and edge deployment
- Offline text LLMs, vision-language models, and speech interaction pipelines
- ROS1, ROS2, and practical robotics development on Jetson
- Pick one main direction to go deeper: vision, robotics, offline LLMs, or multimodal applications.
- Build a complete project by combining Module 5, Module 7, and Module 9.
- Reuse the environment setup, deployment, remote development, and debugging methods from this course in your own Jetson projects.
- If you prefer edge AI application development, start with a computer vision or offline LLM demo and then expand it into a full system.
- If you prefer robotics, combine ROS2, vision, and speech modules into navigation, perception, or interaction projects.
- If you already have some development experience, turn the patterns in this repository into your own project template and deployment scripts.