{"ID":2892359,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.15782","arxiv_id":"2507.15782","title":"Interleaved LLM and Motion Planning for Generalized Multi-Object Collection in Large Scene Graphs","abstract":"Household robots have been a longstanding research topic, but they still lack human-like intelligence, particularly in manipulating open-set objects and navigating large environments efficiently and accurately. To push this boundary, we consider a generalized multi-object collection problem in large scene graphs, where the robot needs to pick up and place multiple objects across multiple locations in a long mission of multiple human commands. This problem is extremely challenging since it requires long-horizon planning in a vast action-state space under high uncertainties. To this end, we propose a novel interleaved LLM and motion planning algorithm Inter-LLM. By designing a multimodal action cost similarity function, our algorithm can both reflect the history and look into the future to optimize plans, striking a good balance of quality and efficiency. Simulation experiments demonstrate that compared with latest works, our algorithm improves the overall mission performance by 30% in terms of fulfilling human commands, maximizing mission success rates, and minimizing mission costs.","short_abstract":"Household robots have been a longstanding research topic, but they still lack human-like intelligence, particularly in manipulating open-set objects and navigating large environments efficiently and accurately. To push this boundary, we consider a generalized multi-object collection problem in large scene graphs, where...","url_abs":"https://arxiv.org/abs/2507.15782","url_pdf":"https://arxiv.org/pdf/2507.15782v1","authors":"[\"Ruochu Yang\",\"Yu Zhou\",\"Fumin Zhang\",\"Mengxue Hou\"]","published":"2025-07-21T16:37:50Z","proceeding":"cs.RO","tasks":"[\"cs.RO\"]","methods":"[\"Large Language Model\"]","has_code":false}