INHA-United Robocup

introduction

This repository is developed on top of the official Booster K1 RoboCup demo provided by Booster.

While the original demo allows the robot to autonomously make decisions and complete a full RoboCup match, we have extended and customized the system with our own implementations.

The overall system is composed of three main programs: vision, brain, and game_controller.

• vision

  • The Robocup vision recognition program, based on Yolo-v8, detects objects such as robots, soccer balls, and the field, and calculates their positions in the robot's coordinate system using geometric relationships.

• brain

  • The Robocup decision-making program reads visual data and GameController game control data, integrates all available information, makes judgments, and controls the robot to perform corresponding actions, completing the match process.

• game_controller

  • Reads the game control data packets broadcast by the referee machine on the local area network, converts them into ROS2 topic messages, and makes them available for the brain to use.

Install extra dependency

sudo apt-get install ros-humble-backward-ros

Note

This repo support jetpack 6.2. Adapted to the default TRT model in src/vision/config/vision.yaml.

vision.yaml for jetpack 6.2 machine

detection_model:
    model_path: ./src/vision/model/best_digua_second_10.3.engine
    confidence_threshold: 0.2

Build and Run

#Build the programs
./scripts/build.sh

#Run on the actual robot
./scripts/start.sh

Booster Documents

Chinese Version English version