Part Overview
This part covers the conceptual vocabulary of agents, environments, embodiment, and closed-loop intelligence. It connects formal ideas with the tools and labs needed to build working systems.
Chapters: 3. Each chapter includes theory, recipes, practical code, a library shortcut, and exercises.
Foundations of Embodied AI gives the reader a working layer of the embodied AI stack. Later chapters assume this layer when agents must perceive, plan, act, and recover from mistakes.
This chapter develops from static ai to embodied ai as part of the embodied AI stack.
- 1.1 Static prediction vs. embodied interaction
- 1.2 Why intelligence needs a world; the perception-action loop
- 1.3 Agents, environments, observations, actions, rewards, constraints
- 1.4 Physical vs. simulated embodiment
- 1.5 The "Physical AI" framing and why 2023-2026 changed the field
This chapter develops the agent-environment interface as part of the embodied AI stack.
- 2.1 Agents and environments formally
- 2.2 State, observation, hidden variables, partial observability
- 2.3 Action types: discrete, continuous, symbolic, motor-level, chunked
- 2.4 Rewards, goals, costs, constraints
- 2.5 Episodes, horizons, trajectories, discounting
This chapter develops embodied system architectures as part of the embodied AI stack.
- 3.1 The canonical stack: sense, perceive, estimate, predict, plan, control, act
- 3.2 Classical modular robotics pipeline
- 3.3 End-to-end learned policy pipeline
- 3.4 Hybrid and hierarchical architectures
- 3.5 Reactive vs. deliberative agents
Part I now frames each chapter around a visible learning contract: concept depth, concrete examples, exercises, diagrams, labs, tool shortcuts, misconception checks, research context, and construct-matched evaluation. This keeps the foundations readable while preparing readers for the mathematical and simulation-heavy chapters that follow.
What's Next?
After this part, Part II: Mathematical, Robotics, and Control Foundations extends the stack.