Gemini Dog Trainers
This project transforms a standard Unitree robot dog into an intelligent, visually-aware companion powered by the Gemini Live API.
Core trick
Gemini Live API streams robot camera frames and voice to a Unitree dog, which answers visual questions and runs actions.
Description
This project transforms a standard Unitree robot dog into an intelligent, visually-aware companion powered by the Gemini Live API. By connecting the robot to its multimodal Gemini-based brain, it easily understands its environment and allows users to ask visual questions and perform actions.
README excerpt
# Gemini Dog Trainers <img src="https://upload.wikimedia.org/wikipedia/commons/thumb/1/1d/Google_Gemini_icon_2025.svg/960px-Google_Gemini_icon_2025.svg.png" width="100" align="right"> ## Project Overview This project transforms a standard Unitree robot dog into an intelligent, visually-aware companion powered by the Gemini Live API. By connecting the robot to its multimodal Gemini-based brain, it easily understands its environment and allows users to ask visual questions and perform actions. ## Hackathon Submission Details **Team Name:** Gemini Dog Trainers **Team Members:** 3 ### Team Members - Abdallah Nassur (nassur1607@gmail.com) - Titouan Verhille (titouan.verhille@gmail.com) - Jorge Arrese (jorge.arrese@gmail.com) ### Links - **GitHub Repository:** https://github.com/arresejo/robotdog - **Demo Video:** https://youtube.com/shorts/cCP1iuVv5ds?feature=share ## Setup Install dependencies: ```sh uv sync ``` Set the required environment variables: ```sh export GEMINI_API_KEY='your-api-key' export ROBOT_CONNECTION_METHOD='local_sta' export ROBOT_IP='192.168.8.181' ``` Optional variables: ```sh export GEMINI_LIVE_MODEL='gemini-live-2.5-flash-preview' export ROBOT_SERIAL_NUMBER='B42D2000XXXXXXXX' export ROBOT_USERNAME='your-unitree-login' export ROBOT_PASSWORD='your-unitree-password' export ROBOT_DRY_RUN='true' export ROBOT_VIDEO_FPS='1.0' export ROBOT_VIDEO_JPEG_QUALITY='85' export ROBOT_VIDEO_DEBUG_DIR='.debug/robot-video' export ROBOT_PLAY_AUDIO='true' expor