Berkeley Humanoid Lite

This repository has no parts list Robotheca can read yet.

How complete the published files are for rebuilding this robot, measured by Robotheca at commit 984741a. It isn't a rating of the robot. Counted out of 80 points and scaled to 100: the parts that don't apply to this robot are left out.

1. 13D and CAD filesNo printable parts or CAD files.Most points to gain: Add the parts to print (STL or 3MF files). Add the CAD source (STEP, or the CAD program's own files) so people can change the design.0/20
2. –Robot descriptionNo URDF. Not counted: the score is made of the parts that apply.Optional: add a URDF, and the robot can be seen in 3D and tried in the browser.Not counted
3. 2Parts listNo parts list in the repository or linked.Link to your parts list, or add it to the repository (a CSV or a Markdown table) with quantities, prices and where to buy each part.0/20
4. 3SoftwareCode in this repository, instructions to install or run it.Say which software framework it uses (ROS 2, LeRobot, Arduino…).10/15
5. 4DocumentationREADME of 2,862 characters with 0 pictures; 0 build steps.Split the build into at least 3 steps. Show the robot and its assembly in pictures in the README.5/15
6. –SimulationNo simulation files. Not counted: the score is made of the parts that apply.Optional: add a simulation model (MuJoCo, Gazebo, Webots or Isaac).Not counted
7. 5LicensesHardware: MIT; software: MIT.10/10

• Open-source humanoid robot with modular 3D-printed gearboxes, designed for research and under about $5,000 in cost.
• Repository covers policy training, sim2sim validation, real-world deployment, motion capture and teleoperated manipulation.
• Real robot runs the lowlevel code in source/berkeley_humanoid_lite_lowlevel/.

Found by Robotheca in the project's files at commit 984741a, its robot.yaml and Robotheca's notes on its documents. Never guessed; Robotheca doesn't run the code.

• Ships trained model files: policy_biped_25hz_a.onnx and 5 more

  In the project files: checkpoints/policy_biped_25hz_a.onnx

• Uses reinforcement learning: rsl_rl

  In the project files: scripts/rsl_rl