This is the main repository storing the meals knowledge base. If you are looking for the API, please check it out here: https://knowledgedb.informatik.uni-bremen.de/mealprepDB/#/
There are example queries in the example queries folder to try out some queries a robot would pose to the knowledge base.
If you are searching for the project website with description (mostly based on the prior version focusing only on describing cutting actions), this is here: https://food-ninja.github.io/WebKat-MealRobot/
If you are searching for the recipe to action parameters example, this is here: https://vrb.ease-crc.org/explore-labs/meal-preparation-laboratory/
Finally, if you are searching for the robot simulation, this is here: https://vrb.ease-crc.org/explore-labs/action-cores/
The meals knowledge base connects the Recipe1M dataset to an ingredient classification based on the FoodOn ontology, linking to task-relevant object properties, tools, and actions that can be translated to motion parameters. More information on the motivation behind the model of the graph can be found here:
@article{kuempel2025cookingactions,
author={Kümpel, Michaela and Scheibl, Manuel and Töberg, Jan-Philipp and Hassouna, Vanessa and Cimiano, Philipp and Wrede, Britta and Beetz, Michael},
title={Everything Robots Need to Know About Cooking Actions: Creating Actionable Knowledge Graphs to Support Robotic Meal Preparation},
journal={Frontiers in Robotics and AI},
year={2025},
publisher={Frontiers},
VOLUME={Volume 12 - 2025},
DOI={10.3389/frobt.2025.1682031},
ISSN={2296-9144},
url={https://www.frontiersin.org/journals/robotics-and-ai/articles/10.3389/frobt.2025.1682031/full}
}The knowledge graph is made available under the Open Data Commons Attribution License.
This work has been created by the Institute for Artificial Intelligence at the University of Bremen. Please contact Michaela Kümpel (michaela(dot)kuempel(at)uni-bremen(dot)de) for further information or collaboration.