PetoiCamp/OpenCat-Quadruped-Robot

An open source quadruped robot pet framework for developing Boston Dynamics-style four-legged robots that are perfect for STEM, coding & robotics education, IoT robotics applications, AI-enhanced robotics application services, research, and DIY robotics kit development.

What it solves

OpenCat provides an accessible, open-source framework for building and programming agile quadruped robots. It removes the complexity of low-level robotics tasks—such as gait coordination, servo control, and IMU integration—allowing developers and researchers to focus on higher-level behaviors and AI applications without needing a massive budget or a specialized lab.

How it works

The framework is built for Arduino and Raspberry Pi, supporting multiple languages including C/C++, Python, and block-based coding. It manages the coordination of servos (up to 12 on the NyBoard platform) and integrates sensors like cameras and IMUs to enable walking, running, and balancing. The platform is designed for "sim-to-real" workflows, meaning users can train reinforcement learning models in simulation and deploy them to the physical robot.

Who it’s for

  • Researchers and Educators: Those using the platform for embodied robotics experiments, K-12 STEM education, and university-level research.
  • Makers and Hobbyists: Individuals building custom 3D-printed robot pets or participating in hackathons.
  • AI Developers: People implementing computer vision, SLAM, and imitation learning on a physical platform.

Highlights

  • Multi-platform Support: Compatible with Arduino, Raspberry Pi, and ROS for SLAM and navigation pipelines.
  • Sim-to-Real Capability: Supports reinforcement learning and NVIDIA Isaac simulations.
  • Extensible Hardware: Compatible with various sensor packs, intelligent camera modules, and AI co-processors like Nvidia Jetson Nano.
  • Open Ecosystem: Fully open-source hardware and software to prevent vendor lock-in.

Related

  • Project
    PetoiCamp/OpenCat-Old

    An open-source platform for affordable quadruped mini robots used for physical AI education, gait research, and reinforcement learning.

  • Project
    PetoiCamp/OpenCatEsp32-Quadruped-Robot

    An open-source quadruped robotics framework for ESP32-based boards, enabling affordable gait research, reinforcement learning, and physical AI development.

  • Project
    genkit-ai/genkit

    An open-source framework for building full-stack AI applications with unified APIs for multiple model providers and cross-language SDKs.

  • Project
    dorianborian/sesame-robot

    An open-source quadruped robot project based on the ESP32, featuring 3D-printable parts, an emotive OLED face, and a full software suite for animation and ML-based control.

  • Project
    ShiqiYu/OpenGait

    OpenGait is an open‑source PyTorch toolbox for gait‑recognition research. It bundles many public gait datasets, implements dozens of state‑of‑the‑art models (appearance, pose, LiDAR, foundation‑model‑based), provides DDP/AMP training, and hosts pre‑trained checkpoints on Hugging Face. The repo includes clear tutorials, a model zoo, and links to the associated CVPR/TPAMI papers.