Articles
Everything in the handbook, newest first. Each piece opens with its conclusions and closes with its sources.
What is physical AI? A working definition
Physical AI is AI that perceives the real world and acts on it through a machine body. What the term covers, how the stack works, and why it is hard.
Vision-language-action models (VLAs), explained
A VLA model turns camera images and a text instruction into robot actions. How they work, how the main architectures differ, and where they fail.
Robot risk assessment: the ISO 12100 method, step by step
How to run a robot risk assessment using ISO 12100: set limits, identify hazards, estimate and evaluate risk, then reduce it — and what AI changes.
Robot safety standards: which one applies to your robot
A map of robot safety standards — ISO 10218, ISO/TS 15066, ISO 3691-4, R15.08, ISO 13482 — and the EU laws behind them, by robot type.
Robot deployment checklist: from pilot to production
Why robot pilots stall and how to avoid it: process selection, site readiness, integration, acceptance criteria, and the metrics that matter in production.
The sim-to-real gap: why simulated robots fail on hardware
The sim-to-real gap is the performance lost when a simulation-trained policy runs on a real robot. What causes it and the techniques used to close it.
Humanoid robot anatomy: actuators, hands, sensors, compute
What is inside a humanoid robot: actuators and transmissions, hands, sensors, onboard compute and batteries — and how each limits capability and safety.
Nothing in this chapter yet.