End-to-end machine learning for soccer-playing robots. We are experimenting with diffusion-models to generate robot motions based on recent sensor measurements.
Important
This is still an ongioing research project.
Note
This repository contains the source code for our DDLitLab project Fußballspielende Roboter: Ende-zu-Ende-KI für Wahrnehmung und Steuerung im RoboCup for the fourth funding round.
Note
The following installation steps are tested on Ubuntu 22.04 and 24.04. Please note, that these steps might fail on other systems.
-
Download this repo:
git clone https://github.com/bit-bots/ddlitlab2024.git
-
Go into the downloaded directory:
cd ddlitlab2024
-
Install dependencies using poetry:
poetry install --without test,dev
Remove
test
ordev
if you want to also install those optional dependencies. -
Enter the poetry environment and run the code:
poetry shell cli --help
Some tools contained in this repository require additional system-dependencies.
-
recording2mcap
: Requires a ROS 2 environment to work. -
bhuman_importer
: Requires additional system dependencies to compile their Python-library for reading log files. (See here)sudo apt install ccache clang cmake libstdc++-12-dev llvm mold ninja-build
Then build the Python package as described in this document.