Physical AI

Progress from robot simulation and policy learning to deployment on real manipulators and mobile robots. These courses connect control, perception, imitation learning, reinforcement learning, and ROS2 in one hands-on pathway.

TrackCourseWhat you will buildDemo
Physical Simulation Genesis Simulation Advance from Franka control and parallel GPU simulation to ROCm vision, tactile perception, and a guarded language-guided agent with an interactive live HUD. Genesis language-guided Physical AI agent
MuJoCo + PyTorch Move from scripted robot control to imitation learning, vision-language-action policies, PPO, and cross-domain reinforcement learning. MuJoCo + PyTorch demo
MuJoCo MJX Learn robot simulation with MuJoCo and scale it with JAX, MJX, vectorized rollouts, domain randomization, and Playground PPO. MuJoCo MJX demo
Real Deployment Robot Policy Deployment Collect demonstrations on a real SO-101 arm and turn them into deployable ACT and SmolVLA policies. Robot Policy Deployment demo
ROS2 Deployment Deploy perception, mapping, and autonomous navigation on a real LeKiwi robot using an AMD-only ROCm and ROS2 stack. ROS2 Deployment demo

Real hardware tracks

Robot Policy Deployment requires SO-101 arms and cameras. ROS2 Deployment requires a LeKiwi base and ZED 2i. Learners create their own datasets, maps, and policies.