PiDog

12 count

Aluminum-alloy structure.

Robot HAT hardware control board.

Integrated sound-direction-recognition module.

Integrated camera module.

Integrated 6-DOF IMU module.

Dedicated touch sensors for interaction response.

Head-mounted ultrasonic obstacle-detection module.

3.3 V

Multi-LLM interaction supports ChatGPT-4o, Gemini, Grok, DeepSeek, Qwen, Doubao, and Ollama.

Raspberry Pi 3B+/4B/5 or Zero 2W; Raspberry Pi is not included.

OpenCV-supported computer-vision development.

MediaPipe-supported computer-vision development.

SPI communication for the sound-direction sensor.

PH2.0 7P connector for the sound-direction sensor.

11-channel chest light board.

Microphone-supported hearing input.

3 count

Mobile-app control with real-time FPV.

0–360 degrees

10 degrees

20 degrees

Speaker integrated with the Robot HAT.

Real-time first-person video transmission through the mobile app.

Color-recognition projects documented for the camera module.

Face-detection projects documented for the camera module.

Gesture-recognition interaction is documented in the current product description.

Recognizes sounds for interactive responses.

Speech-to-text and text-to-speech voice interaction.

32 documented dog-like actions, including walking, sitting, standing, head shaking, and tail wagging.

Python programming support.

Official open-source PiDog Python library and examples.