learn.buildrobots.io · 3 paths · 29 resources

Learn by building.
Arm, legs, then a body.

Each path is a short sequence of skills. Every step says what done looks like, links the best free material we found, and names a robot you can practise on, picked by the same difficulty index as the ladder.

Paths

Ordered by the class they start at. Robots are computed from the registry, easiest buildable first; nothing is hand-placed.

Path 1 of 3
Arm
A 5 or 6 DOF desktop arm. Kinematics, calibration and teleoperation, then your first learned policy.
1. 01
  Run a robot in simulation
  2 resources
2. 02
  Build the arm
  3 resources · practise on SO-101 (SO-ARM101)
3. 03
  Kinematics and planning
  3 resources
4. 04
  Record demonstrations
  2 resources
5. 05
  Train and run a policy
  2 resources
Open the arm path
Path 2 of 3
Quadruped
Four legs and a robot that can fall. Actuators, gaits, state estimation, then sim-to-real walking.
1. 01
  Start with a servo quadruped
  3 resources · practise on Pupper v3
2. 02
  Understand the motor
  3 resources
3. 03
  Gaits and balance
  3 resources
4. 04
  Learn to walk in sim
  3 resources
Open the quadruped path
Path 3 of 3
Humanoid
Everything below at once, standing up. Small biped first, then a full humanoid with a published package.
1. 01
  A desk-scale biped
  2 resources
2. 02
  Build a humanoid
  2 resources · practise on Z-Bot (Zeroth Bot)
3. 03
  Locomotion policies
  4 resources
4. 04
  Hands and manipulation
  3 resources
Open the humanoid path

Courses, docs and repos

Links checked 2026-09-25. Free means readable without paying. We list what a resource teaches, not how long it takes, unless its author says.

Class

Level

Format

29 of 29 shown

LeRobot documentation
Hugging Face · huggingface.co/docs/lerobot/index
Install LeRobot, record datasets, train and evaluate policies on low-cost arms.
DocsFirst robotfreearmhumanoid
SO-101 setup guide
Hugging Face LeRobot · huggingface.co/docs/lerobot/so101
Source parts, configure Feetech servos, assemble and calibrate the SO-101 leader and follower arms.
DocsFirst robotfreearm
Imitation learning on real-world robots
Hugging Face LeRobot · huggingface.co/docs/lerobot/il_robots
Teleoperate, record episodes, push a dataset to the Hub, train a policy and run it on the arm.
DocsNext stepfreearm
Robotics course
Hugging Face Learn · huggingface.co/learn/robotics-course
Robot learning from the ground up with LeRobot: data, policies, real hardware.
CourseFirst robotfreearmhumanoid
SO-ARM100 / SO-101 hardware repo
The Robot Studio · github.com/TheRobotStudio/SO-ARM100
STL files, BOM with vendor links and assembly notes for the open 5-DOF arm plus gripper.
RepoFirst robotfreearm
Low-cost robot arm (Koch v1.1)
Alexander Koch · github.com/AlexanderKoch-Koch/low_cost_robot
A Dynamixel-based leader/follower arm: printed parts, BOM and wiring.
RepoFirst robotfreearm
MuJoCo documentation
Google DeepMind · mujoco.readthedocs.io/en/stable/overview.html
The physics engine behind most open robot sims: MJCF models, actuators, contacts, sensors.
DocsFirst robotfreeany class
MuJoCo Python tutorial notebook
Google DeepMind · colab.research.google.com/github/google-deepmind/mujoco/blob
Load a model, step physics, render, read sensors and contacts, all in a browser notebook.
NotebookFirst robotfreeany class
MuJoCo Playground
Google DeepMind · playground.mujoco.org
GPU-accelerated RL environments for quadrupeds, humanoids and hands, with sim-to-real examples.
ToolDeep endfreequadrupedhumanoid
ROS 2 tutorials (Jazzy)
Open Robotics · docs.ros.org/en/jazzy/Tutorials.html
Nodes, topics, services, launch files, tf2 and URDF: the plumbing most robot software sits on.
DocsNext stepfreearmroverquadrupedhumanoid
MoveIt 2 tutorials
PickNik Robotics · moveit.picknik.ai/main/doc/tutorials/tutorials.html
Motion planning for arms in ROS 2: planning scenes, collision checking, trajectories.
DocsNext stepfreearm
Modern Robotics: Mechanics, Planning, and Control
Kevin Lynch & Frank Park, Northwestern · hades.mech.northwestern.edu/index.php/Modern_Robotics
Rigid-body motion, forward and inverse kinematics, dynamics, trajectory generation. Book, videos and code.
The companion Coursera specialization is separate; the book PDF and videos are free on this page.
BookNext stepfreearmhand
Modern Robotics specialization
Northwestern University on Coursera · coursera.org/specializations/modernrobotics
The same material as the book as a six-course sequence with graded assignments.
CourseNext steparmhand
Underactuated Robotics
Russ Tedrake, MIT · underactuated.mit.edu
Walking, balance and control of robots that can fall over: the theory behind legged locomotion.
BookDeep endfreequadrupedhumanoid
Robotic Manipulation
Russ Tedrake, MIT · manipulation.mit.edu
Perception, planning and control for picking things up, with runnable notebooks.
BookDeep endfreearmhandhumanoid
ODrive getting started
ODrive Robotics · docs.odriverobotics.com/v/latest/guides/getting-started.html
Wiring, configuring and calibrating a BLDC motor driver: the core of every quasi-direct-drive leg.
DocsNext stepfreequadrupedhumanoid
moteus brushless controller
mjbots · github.com/mjbots/moteus
Open firmware and docs for a small high-rate BLDC controller used in many legged robots.
RepoNext stepfreequadrupedhumanoid
Open robot actuator hardware
Open Dynamic Robot Initiative · github.com/open-dynamic-robot-initiative/open_robot_actuator
An open, printable brushless actuator module and leg: CAD, BOM and assembly.
RepoDeep endfreequadruped
Petoi documentation
Petoi · docs.petoi.com
Assemble, calibrate and program the Bittle and Nybble servo quadrupeds (OpenCat firmware).
DocsFirst robotfreequadruped
OpenCat firmware
Petoi · github.com/PetoiCamp/OpenCat
Open quadruped firmware for Arduino and ESP32 boards: gaits, skills, serial protocol.
RepoNext stepfreequadruped
Pupper v3 documentation
Stanford Student Robotics · pupper-v3-documentation.readthedocs.io/en/latest
Build and program a brushless quadruped with ROS 2 and a learned walking policy.
DocsNext stepfreequadruped
Pupper independent study
Stanford · pupper-independent-study.readthedocs.io/en/latest
A self-paced course: build Stanford Pupper, then learn kinematics and gaits on it.
CourseFirst robotfreequadruped
StanfordQuadruped code
Stanford Student Robotics · github.com/stanfordroboticsclub/StanfordQuadruped
The original Pupper controller: inverse kinematics, gait scheduler, joystick control.
RepoNext stepfreequadruped
legged_gym
ETH Zurich Robotic Systems Lab · github.com/leggedrobotics/legged_gym
The reference RL setup for learning to walk in parallel sim, used by many open policies.
RepoDeep endfreequadrupedhumanoid
Isaac Lab documentation
NVIDIA · isaac-sim.github.io/IsaacLab/main/index.html
GPU robot-learning framework: environments, RL and imitation workflows, sim-to-real.
Needs an NVIDIA RTX GPU.
DocsDeep endfreequadrupedhumanoid
unitree_rl_gym
Unitree Robotics · github.com/unitreerobotics/unitree_rl_gym
Train, sim2sim-check in MuJoCo and deploy walking policies for Unitree G1, H1 and Go2.
RepoDeep endfreehumanoidquadruped
Open Duck Mini
Antoine Pirrone · github.com/apirrone/Open_Duck_Mini
A small, printable bipedal robot with an RL walking policy: legged bring-up at desk scale.
RepoNext stepfreehumanoid
Berkeley Humanoid Lite docs
UC Berkeley Hybrid Robotics · berkeley-humanoid-lite.gitbook.io/docs
Build an open, printed-gearbox humanoid: actuators, electronics, assembly and RL locomotion.
DocsDeep endfreehumanoid
LeRobot source
Hugging Face · github.com/huggingface/lerobot
The code behind the docs: robot drivers, dataset format, ACT, Diffusion Policy, SmolVLA.
RepoNext stepfreearmhumanoid

Missing a good one? It has to be public, maintained and teach something a step needs. Suggest it on GitHub.

Paths

Arm

Quadruped

Humanoid

Courses, docs and repos