Rhoban/microban

Microban is an affordable, fully 3D-printable, and 100% open-source humanoid robot. Powered by a Raspberry Pi Zero 2W and 19 Dynamixel servomotors, it serves as an accessible DIY platform for learning, experimentation, and research in robotics.

What it solves

Microban is an open-source, compact humanoid robot designed to make robotics experimentation and learning accessible to makers, students, and enthusiasts. It removes the barrier of high cost and proprietary hardware by providing a fully 3D-printable design and using affordable, easily sourced components.

How it works

The robot is approximately 30cm tall and features 19 degrees of freedom, allowing for a wide range of motion. It is powered by 19 Dynamixel XL330-M288-T servo motors and controlled by a Raspberry Pi Zero 2W with a Pollen RPI Robot Hat. The structure is primarily 3D-printed using PLA filament and is powered by two 18650 lithium-ion batteries via a USB-C charging system.

Who it’s for

It is designed for hobbyists, makers, students, and academic researchers who want a hands-on platform for programming, mechanical design, and robotics experimentation.

Highlights

  • 100% Open-Design: All mechanics, 3D models, and documentation are free to use and modify.
  • DIY-Friendly: Includes guided assembly instructions and a detailed Bill of Materials (BOM) to keep costs between $550-$600.
  • Compact Form Factor: A desktop-sized robot that is rechargeble via USB-C.
  • Cabling and Safety: Integrated cable routing and design stops to prevent self-collision and damage.

Related

  • Project
    ReinFlow/ReinFlow

    A policy gradient framework for fine-tuning flow matching policies using online reinforcement learning, enabling efficient optimization of robotic control policies with minimal denoising steps.

  • Project
    pypose/bae

    bae is a PyTorch library for exact, GPU-accelerated bundle adjustment and pose graph optimization, built on PyPose and designed for robotics and vision applications.

  • Project
    google-research/language-table

    A suite of human-collected datasets and a benchmark for open vocabulary visuolinguomotor learning, enabling robots to execute a vast array of natural language instructions.

  • Project
    UniflexAI/tinynav

    A lightweight, hackable navigation system for robots that provides real-time mapping, localization, and planning across multiple robot and compute platforms.