Reproduce “Generating Actionable Robot Knowledge Bases by Combining 3D Scene Graphs with Robot Ontologies” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Giang Nguyen, Mihai Pomarlan, Sascha Jongebloed, Nils Leusmann, Minh Nhat Vu, Michael Beetz
The authors present a pipeline that combines scene descriptions in a 3D representation, suggests object meanings from ontologies for human review, and converts reviewed labels into queryable knowledge. For a breakfast request, queries identify a milk box, cereal box, and bowl for retrieval; trajectories are simulated and applied to a real robot, demonstrating a task rather than general performance.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.