Physical AI
10 pages

Interactive tutorials

3 self-contained, interactive guides — 10 pages in all — with live simulations you can poke at: fire a LiDAR pulse, watch a SLAM map drift, corrupt a point cloud, or compare how 30 companies build their data engines. Each opens as a full-screen interactive page.

LiDAR & the Autonomy Stack

~75 min · 6 parts

A five-part interactive series walking up the stack from the physical sensor to the data engine everything depends on — point clouds, perception, SLAM, corruption, robustness, and building a simulator. Grounded in published benchmarks; figures current as of early 2026.

LiDARPerceptionSimulationSeriesOpen tutorial →
  1. Series overview

    The landing page — read the five parts in order, or jump to whatever you need.

  2. Part 1 — How LiDAR works

    Light timed to the nanosecond, point clouds, the five hardware types and their parameters, and 2025–26 market pricing. Fire a pulse and watch the round-trip.

  3. Part 2 — The autonomy stack

    What consumes the points: the perception pipeline, SLAM (build a map live and watch it drift), sensor fusion, and the point-cloud representations that carry meaning into a model.

  4. Part 3 — Point clouds as data

    How defects become silent model biases. Break a clean cloud six ways in the Corruption Lab — sparsity, occlusion, noise, motion, weather, ghosting.

  5. Part 4 — Robustness to sensor failure

    The robustness paradox, resolved: corrupt the inputs, never the labels. Drop a sensor and compare a naïve model against a dropout-trained one.

  6. Part 5 — Building a LiDAR simulator

    Assemble a synthetic cloud stage by stage — raycast, raydrop, intensity, noise — and close the domain gap to a real reference. Why raydrop is the crux.

SLAM & Localization

~45 min · 3 parts

Three interactive field guides on how self-driving cars know where they are: a tour of the SLAM back-end (ORB-SLAM, LOAM, Cartographer), the localization spectrum the industry is converging on, and why one LiDAR sweep does localization and perception at once.

SLAMLocalizationMappingOpen tutorial →
  1. SLAM Atlas — an interactive field guide

    The heart of every modern system — front-end, back-end, filtering vs. smoothing, and the factor graphs (g2o, GTSAM, Ceres) that make it fast.

  2. Where am I? — AV localization in 2026

    There is no single winner; the frontier is a spectrum, and the industry is quietly converging toward the middle.

  3. One sweep, two jobs

    Why a single LiDAR scan serves localization and perception together — your three intuitions, graded, and the correction that unlocks the rest.

Physical AI Data Strategy Explorer

~40 min

A deep dive into 30 companies across self-driving and robotics in the US, China, and beyond — how they collect real-world data, manufacture synthetic data, auto-label, and evaluate. The 2025–26 shift: the flywheel collapsing into a single foundation/world model that drives, simulates, and evaluates at once.

Data engineStrategyIndustryOpen tutorial →