Tutorials

Tutorials, engineering notes, and field reports from building robotics applications with Robium.

7 posts

Video cover showing Stack Chan mounted on a LEGO Technic car beside the Robium name

Teaching Stack Chan to drive with LEGO, Pybricks, and Robium

Stack Chan can see and speak, but it needed wheels. In lego-stackchan-drive, we added LEGO motors and taught it to follow lines and drive between guardrails.

robiumstackchanlegopybricks
Illustrated TurtleBot 4 in a furnished home beside a navigation map, with Home Robot and Gemini Robotics ER 2 text

Building a mobile home robot with Gemini Robotics ER 2 and ROS 2 in under an hour

A TurtleBot 4 sends camera and robot state to Gemini Robotics ER 2, while a deterministic guard, ROS 2, and Nav2 stay in charge of motion.

robiumgemini-roboticsturtlebot4turtlebot3
Two simulated ALOHA arms pass a red cube between their grippers

Training and running an ALOHA cube-transfer policy with ACT

Run the official ACT cube-transfer policy locally, see why action chunking mattered, and use the same workflow as a starting point for your own demonstrations.

robiumlerobotimitation-learningact
A blue circular agent pushes a gray T-shaped block toward a green target

Running Diffusion Policy on PushT from a laptop

Run a compact, verified robot-learning experiment on a Mac, then use it to understand when ACT, Diffusion Policy, or a VLA fits.

robiumlerobotimitation-learningdiffusion-policy
Illustrated gray Unitree Go2 on a simulation grid beside Teaching Go2 to Walk, Isaac Lab, NVIDIA, and Robium branding

Training a Unitree Go2 to walk with Isaac Lab, checkpoint by checkpoint

A recovered Isaac Lab run turns policy training into a recorded progression, backed by a fresh capability-scoped GPU smoke.

robiumreinforcement-learningisaac-labisaac-sim
A simulated TurtleBot3 follows a planned route through a mapped environment

Mapping and navigation with ROS 2, from one app

Map a simulated TurtleBot3 with SLAM Toolbox, reuse the map with AMCL, save waypoints, and send Nav2 goals from a browser.

robiumros2nav2gazebo
A simulated Franka Panda picks up a bowl and places it on a plate

Running a Pi0.5 VLA pick-and-place policy with a Franka Panda

See how Physical Intelligence's Pi0.5 turns camera views, robot state, and a language instruction into actions for a simulated Panda arm.

robiumlerobotvlapi0.5