Part X: Sensor Fusion, World Models, and Spatial AI
Chapter 53  [R]

World Models and Predictive Sensing

Placeholder chapter page. Sections are produced by the book-skills pipeline.

Sections

  1. 53.1 What a world model is and why sensing needs one
  2. 53.2 Latent state-space and recurrent world models (DreamerV3)
  3. 53.3 Joint-embedding predictive architectures (I-JEPA, V-JEPA 2)
  4. 53.4 Generative interactive world models (Genie)
  5. 53.5 Planning and control in latent space
  6. 53.6 Predictive sensing and anticipation
  7. 53.7 Evaluation of world models (physical-reasoning benchmarks)

Lab 53

train a small latent world model on a sensor sequence and use it for prediction/anomaly anticipation.