This is the course Collegica was started for. In 2020 it became clear that the whole of robotics — frames and transforms, ROS, perception, navigation — could be taught without a lab, because the simulators had got good enough to run in a browser and Python was already the language of the field.
What you need
A browser. That is the whole list. No ROS install, no Ubuntu partition, no hardware. Enough Python to write a loop and a class; no robotics and no linear algebra beyond school level — the maths arrives when it is needed and not before.
On Collegica
- A Drone Simulator That Looks Right — a browser drone lab read from its source code, its numbers checked against a real Crazyflie, research simulators (CARLA-Air and CARLA 1.0) run on a home server, and the steps from a browser tab to a real drone
- Words In, Joints Out — vision-language-action models, from RT-2 to π0.7: the one shape nearly all of them share, which ones you can download and under what licence, and what they ask of you before they will move your robot
- Train the Robot Before You Build It — NVIDIA’s robotics stack read from the outside: Warp and Newton, Isaac Sim and Isaac Lab, Cosmos and GR00T, Jetson — what each piece is, what it runs on, what it costs to try, and the one part that ran on a machine with no GPU at all
- From a Walkthrough Video to a Training World — how NVIDIA turns real places into simulated ones: Gaussian splats, 3DGUT, NuRec and OpenUSD — what the 3D file really contains in Isaac Sim, and what a robot cannot do inside it
Status
The syllabus is being written, and the course will appear here module by module. Announcements go out through the newsletter.