Eurobot-2026-Vision

This repository contains the vision system for the Eurobot 2026 competition.

Quick Start

On x86 computer:

bash start_docker.sh

On nvidia jetson computer:

bash start_docker_jetson.sh

change the LAUNCH_SCRIPT in .env if you only want to launch camera or hazelnut detect

Start with Docker

Build image and container

On x86 computer:

cd docker/
docker compose up -d

On nvidia jetson computer:

cd docker/
docker compose -f compose.jetson.yaml up -d 

Build workspace

Attach to the running container:

docker exec -it vision-ws bash

Inside the container, build the workspace:

source /opt/ros/humble/setup.bash
colcon build
source install/setup.bash

Realsense

Check device info

rs-enumerate-devices

Launch realsense node

Make sure the RealSense camera is connected via USB to your computer, then run:

ros2 launch realsense2_camera rs_launch.py

Check launched camera info

After launch the camera node in ros, you can check the camera info using following command:

ros2 topic echo /<your_camera_name>/<color or depth>/camera_info

If you want to launch three camera at the same time, please run:

ros2 launch realsense2_camera rs_triple_camera_launch.py

Aruco

Launch Robot / Sima detect node (solvePnP, Depth)

ros2 launch aruco_robot robot_launch.py

ros2 launch aruco_sima sima_launch.py

Optional Arguments:

• camera:=true: Also launch the RealSense camera node. (default: false)
• rviz:=true: Also launch RViz for visualization. (default: false)
• team:=blue: Select team. (default: blue)

Example launching with both:

ros2 launch aruco_robot robot_launch.py camera:=true rviz:=true team:=blue

ros2 launch aruco_sima sima_launch.py camera:=true rviz:=true team:=blue

Launch by script

bash camera_localization.sh <mode> <team>

Necessary Arguments:

• mode: [robot|sima|all]: Choose which mode to launch.
• team: [blue|yellow]: Select team.

Example launching with both:

bash camera_localization.sh all blue

Launch Robot / Sima detect node (homography)

bash aruco_robot.sh

bash aruco_sima.sh

GUI

Run rivz

Open RViz to visualize camera images and TF frames:

rviz2

Yolo

Run hazelnut detection

ros2 launch yolo hazelnut_detect_launch.py

Launch Parameters

Parameter	Default	Description
team	blue	Team color (blue/yellow)
color_modes	rgb	Input image color
debug	True	Enable debug window

Example:

ros2 launch yolo hazelnut_detect_launc_h.py team:=yellow debug:=False

Related topics

Topic Name	Type
pantry_status	Int32MultiArray
collection_status	Int32MultiArray
hazelnut_storage_score	Int32
hazelnut_bonus_score	Int32

Save Picture

Save RGB pictures for yolo training datasets

ros2 run yolo save_color_training_data.py

Save Depth pictures for yolo training datasets

ros2 run yolo save_depth_training_data.py