Skip to main content

Module 9: Edge AI & On-Board Intelligence

NVIDIA Orin, Neuromorphic Chips & Real-Time Inference

Duration: 6 hours · Level: Advanced · Lessons: 3

G1 cannot depend on the cloud. Build a complete on-board AI stack that runs foundation models, locomotion controllers, and safety monitors within the compute and power budget of a mobile humanoid.

Prerequisites​

Learning outcomes

By the end of this module you will be able to:

  • Design the compute architecture for on-board VLA inference
  • Apply quantization and model compression for edge deployment
  • Understand neuromorphic computing for ultra-low power sensing

Lessons in this module​

  1. 9.1 — NVIDIA Jetson AGX Orin: The Humanoid Brain · 50 min
  2. 9.2 — Model Compression for Edge Deployment · 55 min
  3. 9.3 — Neuromorphic Computing & Event Cameras · 55 min

👉 Start here: 9.1 — NVIDIA Jetson AGX Orin: The Humanoid Brain