{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,15]],"date-time":"2026-05-15T20:16:38Z","timestamp":1778876198844,"version":"3.51.4"},"reference-count":26,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2026,4,27]],"date-time":"2026-04-27T00:00:00Z","timestamp":1777248000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,4,27]],"date-time":"2026-04-27T00:00:00Z","timestamp":1777248000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100005405","name":"Ritsumeikan University","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100005405","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Artif Life Robotics"],"published-print":{"date-parts":[[2026,5]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    It is crucial to efficiently execute instructions such as \u201cFind an apple and a banana.\u201d or \u201cGet ready for a field trip,\u201d which require searching for multiple objects or understanding context-dependent commands. This study addresses the challenging problem of determining which robot should be assigned to which part of a task when each robot possesses different situational on-site knowledge, specifically, room-wise object presence probabilities learned from the area designated to it by the user. We infer room-wise object presence probabilities via Bayesian inference using a spatial concept model. The inference results are then converted into prompts. Large language models (LLMs) use these prompts to decompose instructions into tasks and assign them to multiple robots. We designed a novel few-shot prompting strategy that enables LLMs to infer required objects from ambiguous commands and decompose them into appropriate subtasks. In our experiments, the proposed method achieved 47\/50 successful assignments, outperforming random (28\/50) and commonsense-based assignment (26\/50). Furthermore, we conducted qualitative evaluations using two actual mobile manipulators. The results demonstrated that our framework could handle instructions, including underspecified instructions such as \u201cGet ready for a field trip.\u201d, by successfully performing task decomposition, assignment, sequential planning, and execution. For reproducibility, we release the full set of prompts on the project website at\n                    <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" xlink:href=\"https:\/\/kentomurata0610.github.io\/multi-robot-task-planning\" ext-link-type=\"uri\">https:\/\/kentomurata0610.github.io\/multi-robot-task-planning<\/jats:ext-link>\n                    .\n                  <\/jats:p>","DOI":"10.1007\/s10015-026-01123-8","type":"journal-article","created":{"date-parts":[[2026,4,27]],"date-time":"2026-04-27T10:19:16Z","timestamp":1777285156000},"page":"418-432","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Multi-robot task planning for multi-object retrieval tasks with distributed on-site knowledge via large language models"],"prefix":"10.1007","volume":"31","author":[{"given":"Kento","family":"Murata","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shoichi","family":"Hasegawa","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tomochika","family":"Ishikawa","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yoshinobu","family":"Hagiwara","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Akira","family":"Taniguchi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lotfi","family":"El Hafi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tadahiro","family":"Taniguchi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,4,27]]},"reference":[{"key":"1123_CR1","doi-asserted-by":"crossref","unstructured":"Kannan SS et\u00a0al. (2024) SMART-LLM: Smart Multi-Agent Robot Task Planning using Large Language Models. In: IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 12,140\u201312,147","DOI":"10.1109\/IROS58592.2024.10802322"},{"key":"1123_CR2","unstructured":"Bommasani R et\u00a0al. (2021) On the Opportunities and Risks of Foundation Models. arXiv preprint arXiv:2108.07258"},{"key":"1123_CR3","unstructured":"Achiam J et\u00a0al. (2023) GPT-4 Technical Report. arXiv preprint arXiv:2303.08774"},{"key":"1123_CR4","doi-asserted-by":"crossref","unstructured":"Hasegawa S et al (2025) (2025) Spatial Concepts-based Prompts with Large Language Models for Robot Action Planning. IEEE Access 13:216,937-216,955","DOI":"10.1109\/ACCESS.2025.3647727"},{"key":"1123_CR5","doi-asserted-by":"publisher","first-page":"55682","DOI":"10.1109\/ACCESS.2024.3387941","volume":"12","author":"SH Vemprala","year":"2024","unstructured":"Vemprala SH et al (2024) ChatGPT for Robotics: Design Principles and Model Abilities. IEEE Access 12:55682\u201355696","journal-title":"IEEE Access"},{"key":"1123_CR6","unstructured":"Chen B et\u00a0al. (2023) Open-Vocabulary Queryable Scene Representations for Real World Planning. In: IEEE International Conference on Robotics and Automation (ICRA), pp. 11,509\u201311,522"},{"key":"1123_CR7","doi-asserted-by":"crossref","unstructured":"Chen Y et\u00a0al. (2024) Scalable Multi-Robot Collaboration with Large Language Models: Centralized or Decentralized Systems? In: IEEE International Conference on Robotics and Automation (ICRA), pp. 4311\u20134317","DOI":"10.1109\/ICRA57147.2024.10610676"},{"key":"1123_CR8","doi-asserted-by":"crossref","unstructured":"Mandi Z et\u00a0al. (2024) RoCo: Dialectic Multi-Robot Collaboration with Large Language Models. In: IEEE International Conference on Robotics and Automation (ICRA), pp. 286\u2013299","DOI":"10.1109\/ICRA57147.2024.10610855"},{"issue":"7","key":"1123_CR9","doi-asserted-by":"publisher","first-page":"703","DOI":"10.7210\/jrsj.43.703","volume":"43","author":"S Hasegawa","year":"2025","unstructured":"Hasegawa S et al (2025) Reducing Cost of On-site Learning by Multi-robot Knowledge Integration and Task Allocation via Large Language Models. J Robot Soc Jpn 43(7):703\u2013706","journal-title":"J Robot Soc Jpn"},{"key":"1123_CR10","unstructured":"Zhang H et\u00a0al. (2024) Building Cooperative Embodied Agents Modularly with Large Language Models. In: International Conference on Learning Representations (ICLR)"},{"key":"1123_CR11","doi-asserted-by":"publisher","first-page":"927","DOI":"10.1007\/s10514-020-09905-0","volume":"44","author":"A Taniguchi","year":"2020","unstructured":"Taniguchi A et al (2020) Improved and Scalable Online Learning of Spatial Concepts and Language Models with Mapping. Auton Robot 44:927\u2013946","journal-title":"Auton Robot"},{"issue":"1","key":"1123_CR12","doi-asserted-by":"publisher","first-page":"400","DOI":"10.1080\/18824889.2023.2283954","volume":"16","author":"S Hasegawa","year":"2023","unstructured":"Hasegawa S et al (2023) Integrating Probabilistic Logic and Multimodal Spatial Concepts for Efficient Robotic Object Search in Home Environments. SICE J Control Meas Syst Integr 16(1):400\u2013422","journal-title":"SICE J Control Meas Syst Integr"},{"key":"1123_CR13","doi-asserted-by":"publisher","first-page":"113","DOI":"10.1016\/j.arcontrol.2020.02.002","volume":"49","author":"Z Feng","year":"2020","unstructured":"Feng Z et al (2020) An Overview of Collaborative Robotic Manipulation in Multi-Robot Systems. Annu Rev Control 49:113\u2013127","journal-title":"Annu Rev Control"},{"key":"1123_CR14","unstructured":"Ahn M et\u00a0al. (2022) Do As I Can, Not As I Say: Grounding Language in Robotic Affordances. arXiv preprint arXiv:2204.01691"},{"key":"1123_CR15","doi-asserted-by":"crossref","unstructured":"Schillinger P et\u00a0al. (2016) Human-Robot Collaborative High-Level Control with Application to Rescue Robotics. In: IEEE International Conference on Robotics and Automation (ICRA), pp. 2796\u20132802","DOI":"10.1109\/ICRA.2016.7487442"},{"key":"1123_CR16","unstructured":"Kojima T et\u00a0al. (2022) Large Language Models Are Zero-Shot Reasoners. In: Advances in Neural Information Processing Systems (NeurIPS), vol.\u00a035, pp. 22,199\u201322,213"},{"key":"1123_CR17","unstructured":"Wei J et\u00a0al. (2022) Chain-of-Thought Prompting Elicits Reasoning in Large Language Models. In: Advances in Neural Information Processing Systems (NeurIPS), vol.\u00a035, pp. 24,824\u201324,837"},{"key":"1123_CR18","unstructured":"Liu K et\u00a0al. (2025) COHERENT: Collaboration of Heterogeneous Multi-Robot System with Large Language Models. In: IEEE International Conference on Robotics and Automation (ICRA), pp. 10,208\u201310,214"},{"issue":"2","key":"1123_CR19","doi-asserted-by":"publisher","first-page":"987","DOI":"10.1109\/TCCN.2025.3528892","volume":"11","author":"T Yang","year":"2025","unstructured":"Yang T et al (2025) AutoHMA-LLM: Efficient Task Coordination and Execution in Heterogeneous Multi-Agent Systems using Hybrid Large Language Models. IEEE Trans Cogn Commun Netw 11(2):987\u2013998","journal-title":"IEEE Trans Cogn Commun Netw"},{"issue":"2","key":"1123_CR20","doi-asserted-by":"publisher","first-page":"1122","DOI":"10.1109\/LRA.2024.3518105","volume":"10","author":"K Obata","year":"2025","unstructured":"Obata K et al (2025) LiP-LLM: Integrating Linear Programming and Dependency Graph With Large Language Models for Multi-Robot Task Planning. IEEE Robot Autom Lett 10(2):1122\u20131129","journal-title":"IEEE Robot Autom Lett"},{"key":"1123_CR21","doi-asserted-by":"crossref","unstructured":"El\u00a0Hafi L et\u00a0al. (2025) Public Evaluation on Potential Social Impacts of Fully Autonomous Cybernetic Avatars for Physical Support in Daily-Life Environments: Large-Scale Demonstration and Survey at Avatar Land. In: IEEE International Conference on Advanced Robotics and its Social Impacts (ARSO), pp. 182\u2013187","DOI":"10.1109\/ARSO64737.2025.11124957"},{"issue":"1\u20132","key":"1123_CR22","doi-asserted-by":"publisher","first-page":"83","DOI":"10.1002\/nav.3800020109","volume":"2","author":"HW Kuhn","year":"1955","unstructured":"Kuhn HW (1955) The Hungarian Method for the Assignment Problem. Nav Res Logist Q 2(1\u20132):83\u201397","journal-title":"Nav Res Logist Q"},{"key":"1123_CR23","unstructured":"Jocher G et\u00a0al. (2025) ultralytics\/yolov5: v7.0\u2013yolov5 SOTA Realtime Instance Segmentation"},{"key":"1123_CR24","doi-asserted-by":"crossref","unstructured":"El Hafi L et al (2022) Software Development Environment for Collaborative Research Workflow in Robotic System Integration. Adv Robot 36(11):533\u2013547","DOI":"10.1080\/01691864.2022.2068353"},{"key":"1123_CR25","doi-asserted-by":"crossref","unstructured":"Yamamoto T et al (2019) Development of Human Support Robot as the Research Platform of a Domestic Mobile Manipulator. ROBOMECH J 6(1):1-15","DOI":"10.1186\/s40648-019-0132-3"},{"key":"1123_CR26","doi-asserted-by":"crossref","unstructured":"Kohlbrecher S et\u00a0al. (2011) A Flexible and Scalable SLAM System with Full 3D Motion Estimation. In: IEEE International Symposium on Safety, Security, and Rescue Robotics (SSRR), pp. 155\u2013160","DOI":"10.1109\/SSRR.2011.6106777"}],"container-title":["Artificial Life and Robotics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10015-026-01123-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10015-026-01123-8","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10015-026-01123-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,15]],"date-time":"2026-05-15T19:43:17Z","timestamp":1778874197000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10015-026-01123-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,27]]},"references-count":26,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2026,5]]}},"alternative-id":["1123"],"URL":"https:\/\/doi.org\/10.1007\/s10015-026-01123-8","relation":{},"ISSN":["1433-5298","1614-7456"],"issn-type":[{"value":"1433-5298","type":"print"},{"value":"1614-7456","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,27]]},"assertion":[{"value":"31 August 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 March 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 April 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}