AI + UAS · Education

AI + Uncrewed Aircraft

Autonomy for drones, sim-first and NDAA-clean: build the whole stack — control, perception, estimation, planning, and the multi-agent swarm, where the code you write is the code that flies the aircraft — on-device, so the boundary is the aircraft's own, and staying aloft under wind and GPS-loss is viability held under disturbance.

Beginner → Skilled·5 modules·10 lessons
▶ Start the course ← All courses
Module 1

Flight & Control

Model a quadrotor as a rigid body with four thrusters, size it to hover, and close a control loop that holds an altitude — the foundation every later module stands on.

  1. L1Hover a QuadrotorSize the four rotor speeds so total thrust exactly cancels weight, holding a hover to machine precision.→
  2. L2Close the LoopAdd a PD controller on altitude that drives the quad from the ground to a target height and holds it with no steady-state drift.→
Module 2

Perception

Turn raw pixels into things an aircraft can act on — detect a target in a frame and estimate motion between frames — the onboard-vision half of autonomy.

  1. L2Find the TargetDetect a bright target in a noisy image and report its pixel centroid, the input a tracker or a controller acts on.→
  2. L3Estimate MotionEstimate how far the scene shifted between two frames — optical flow — the GPS-free motion cue behind position hold and VIO.→
Module 3

State Estimation

Fuse noisy, partial measurements into one trustworthy estimate of where the aircraft is and how fast — from the linear Kalman filter to the nonlinear EKF that real autopilots (PX4's EKF2) run.

  1. L3Fuse the SensorsFuse a noisy altitude sensor with an accelerometer through a Kalman filter that beats either sensor alone.→
  2. L4Track Through a TurnEstimate a turning aircraft's 2-D position from noisy range fixes with an Extended Kalman Filter — linearizing a nonlinear measurement, the way a real autopilot's EKF2 does.→
Module 4

Planning & Learned Control

Decide where to go and how to get there — plan a mission over a map, and let a policy learn control a hand-tuned gain can't match.

  1. L2Plan a MissionOrder a set of survey waypoints into a short tour so the aircraft covers the area without wasting battery on backtracking.→
  2. L3Learn to FlyTune a control gain by trying and scoring rollouts, beating a fixed baseline — the seed of learned control.→
Module 5

The Multi-Agent Swarm

Make many aircraft act as one — hold a formation with no leader, and see the whole fleet flown by the real deterministic solver.

  1. L3Formation Without a LeaderDrive a group of drones into an even line using only local averaging — leaderless consensus that survives a dropout.→
  2. L4The Swarm BenchFly the whole fleet through the real deterministic WGSL solver, and understand why the same controller flies the aircraft.→
See it live

Anatomy demonstrations

The machines behind this course, taken apart three ways — the body, the one rule, and the small learned brain. Guess before you look; an open core proves every number on the page.

DemonstrationAnatomy of FlightAn eVTOL, hardware to brain →DemonstrationAnatomy of SwimmingThe third medium: underwater →The whole series →
Foundations

From the interactive textbook

The ideas under this course as live explorables — each runs the real Rust library and re-derives its own result.

Ch. 2 · CoordinationAgreement, and the one number behind itOpen the chapter ↗Ch. 3 · SafetyThe command it will not obeyOpen the chapter ↗Ch. 6 · PerceptionThe estimator that stays honestOpen the chapter ↗Ch. 7 · PlanningAs fast as the motors allowOpen the chapter ↗Ch. 12 · MappingRevising the pastOpen the chapter ↗Ch. 15 · GuidanceLanding a rocketOpen the chapter ↗Ch. 16 · GeometryTurning to fitOpen the chapter ↗The full textbook →