PAI-110 · Education

Programming Physical AI

One simulated differential-drive rover, commanded at three rising depths — visual blocks, Python scripting, and bare-metal MCU — re-solving the same tasks at each depth until you can choose the right level of abstraction for a physical-AI task and prove it.

Beginner → Skilled·5 modules·14 lessons
▶ Start the course ← All courses
Module 1

One Loop, Visible — Visual Control

Make the rover sense, decide, and act with drag-and-drop blocks, and see the Python each block runs.

  1. L0The Embodied LoopWire a sense->decide->act loop that drives the rover forward and halts it within 0.25 m of the goal with no overshoot.→
  2. L1React and AvoidBuild a reactive rule-based behavior using conditionals so the rover avoids an obstacle and still reaches the goal with zero collisions.→
  3. L2Blocks Are PythonRead the Python generated by a block program and correctly predict the effect of editing a single generated line before running it.→
Module 2

Into the Code — Classical Control

Re-implement and surpass block behaviors in real Python: read sensors into a state estimate, close a PID loop, plan with a state machine.

  1. L2Reading the WorldWrite control(obs) that reads the rover's goal_bearing each step and steers toward the goal pad, turning the differential-drive wheels so the rover reaches the goal within tolerance instead of driving blind.→
  2. L2The PID LoopWrite a proportional heading controller in Python control(obs) that eases the rover onto a goal pad within a tight 0.12 m tolerance, with no overshoot or weave.→
  3. L2Plan With a State MachineDesign a finite-state controller in Python control(obs) that switches modes (SEEK far away, ARRIVE up close, AVOID near a wall) to drive the real MuJoCo rover onto the goal pad and settle within tolerance.→
Module 3

Make It Learn — Policies in Sim

Replace hand-tuned control with learned behavior: classify, train an RL policy, and clone a demonstration in-sim.

  1. L3Learn From DataTrain a simple classifier mapping sensor readings to a discrete action and run it on the rover, meeting held-out accuracy >= 0.85 and goal completion with zero collisions.→
  2. L3Reinforcement LearningDefine a reward function and train an RL policy in-sim to convergence (smoothed reward >= 6.0) with a greedy rollout that reaches the goal safely and efficiently.→
  3. L3Imitation and Sim-to-RealClone a demonstrated trajectory with behavioral cloning to RMSE <= 0.12 m and correctly explain why a sim-perfect policy can fail on real hardware.→
Module 4

Down to the Metal — Embedded Rust

Drop below Python: write real no_std embedded Rust firmware against the rover's peripheral HAL, compiled to WASM and run as the actual control loop.

  1. L4GPIO, Peripherals & the Control LoopWrite your first no_std Rust firmware: own the rover's peripherals, blink a GPIO LED, and drive the motors from the control loop to reach the goal.→
  2. L4Timers, PWM & Proportional DriveUse PWM motor channels and the millisecond clock to replace bang-bang control with a smooth proportional controller that settles in the pad without overshoot.→
  3. L4Async Tasks & the Real-Time LoopStructure firmware the Embassy way — concurrent concerns on one real-time loop — by running a navigator AND a fixed-rate LED heartbeat off the millisecond clock, without blocking.→
Module 5

Capstone — Autonomy, Then Optimized

Build full rover autonomy in Python, then move the critical control loop to the metal and prove the timing win.

  1. L3Full Autonomy in PythonCombine perception and control into one robust control(obs) that reliably drives the differential-drive rover to the goal pad within tolerance on real MuJoCo physics, fixing a partial starter controller.→
  2. L4Optimize the Critical Loop to the MetalRe-implement the full autonomy control loop as no_std embedded Rust firmware against the rover HAL — proportional steer-and-ease plus a non-blocking heartbeat — and prove it lands the rover inside a tight 0.12 m tolerance running directly on the metal.→