{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,19]],"date-time":"2025-12-19T15:11:05Z","timestamp":1766157065658,"version":"3.48.0"},"reference-count":23,"publisher":"Fuji Technology Press Ltd.","issue":"6","funder":[{"DOI":"10.13039\/501100001691","name":"Japan Society for the Promotion of Science","doi-asserted-by":"publisher","award":["21H05104a"],"award-info":[{"award-number":["21H05104a"]}],"id":[{"id":"10.13039\/501100001691","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002241","name":"Japan Science and Technology Agency","doi-asserted-by":"publisher","award":["JPMJPS2032"],"award-info":[{"award-number":["JPMJPS2032"]}],"id":[{"id":"10.13039\/501100002241","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["JRM","J. Robot. Mechatron."],"published-print":{"date-parts":[[2025,12,20]]},"abstract":"<jats:p>Swarm robotic systems consist of a large number of distributed autonomous robots that coordinate their actions to accomplish diverse tasks beyond the capabilities of a single robot.  These systems have recently been considered for deployment in disaster scenarios, where communication is often unstable, making it necessary to achieve adaptive cooperative behavior without relying on explicit communication between robots.  In the context of multi-robot systems\u2014including swarm robotic systems\u2014some studies have explored approaches utilizing large language models (LLMs) or other learning-based methods, but few have proposed systems that enable communication-free coordination.   In this paper, we propose a system incorporating a novel method that combines high-level decision-making via LLM-based policy selection\u2014guided by questionnaire-style prompts\u2014with low-level control using multiple MARL-trained policies.   We consider a complex task scenario in which robots search for a target object and transport it to a designated destination.   To evaluate the method, we define implicit consensus as a condition in which a robot selects the same policy as its nearby robots without any explicit communication.   The effectiveness of the proposed method is demonstrated through simulated task execution, with particular emphasis on implicit consensus as a key evaluation metric.<\/jats:p>","DOI":"10.20965\/jrm.2025.p1452","type":"journal-article","created":{"date-parts":[[2025,12,19]],"date-time":"2025-12-19T15:02:07Z","timestamp":1766156527000},"page":"1452-1460","source":"Crossref","is-referenced-by-count":0,"title":["Communication-Free Adaptive Swarm Robotic System: LLM-Based Decision Making and MARL-Based Multi-Policy Control"],"prefix":"10.20965","volume":"37","author":[{"given":"Takahiro","family":"Yoshida","sequence":"first","affiliation":[{"name":"Department of Mechanical Engineering, Graduate School of Engineering, The University of Osaka, 2-1 Yamadaoka, Suita, Osaka 565-0871, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5716-6365","authenticated-orcid":true,"given":"Yuichiro","family":"Sueoka","sequence":"additional","affiliation":[{"name":"Department of Mechanical Engineering, Graduate School of Engineering, The University of Osaka, 2-1 Yamadaoka, Suita, Osaka 565-0871, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"8550","published-online":{"date-parts":[[2025,12,20]]},"reference":[{"key":"key-10.20965\/jrm.2025.p1452-1","doi-asserted-by":"crossref","unstructured":"E. \u015eahin, \u201cSwarm robotics: From sources of inspiration to domains of application,\u201d Int. Workshop on Swarm Robotics, pp. 10-20, 2004. https:\/\/doi.org\/10.1007\/978-3-540-30552-1_2","DOI":"10.1007\/978-3-540-30552-1_2"},{"key":"key-10.20965\/jrm.2025.p1452-2","doi-asserted-by":"crossref","unstructured":"K. Nagatani, M. Abe, K. Osuka, P. jo Chun, T. Okatani, M. Nishio, S. Chikushi, T. Matsubara, Y. Ikemoto, and H. Asama, \u201cInnovative technologies for infrastructure construction and maintenance through collaborative robots based on an open design approach,\u201d Advanced Robotics, Vol.35, No.11, pp. 715-722, 2021. https:\/\/doi.org\/10.1080\/01691864.2021.1929471","DOI":"10.1080\/01691864.2021.1929471"},{"key":"key-10.20965\/jrm.2025.p1452-3","unstructured":"P. Li, Z. An, S. Abrar, and L. Zhou, \u201cLarge language models for multi-robot systems: A survey,\u201d arXiv preprint, arXiv:2502.03814, 2025. https:\/\/doi.org\/10.48550\/arXiv.2502.03814"},{"key":"key-10.20965\/jrm.2025.p1452-4","unstructured":"J. Chen, C. Yu, X. Zhou, T. Xu, Y. Mu, M. Hu, W. Shao, Y. Wang, G. Li, and L. Shao, \u201cEmos: Embodiment-aware heterogeneous multi-robot operating system with llm agents,\u201d arXiv preprint, arXiv:2410.22662, 2024. https:\/\/doi.org\/10.48550\/arXiv.2410.22662"},{"key":"key-10.20965\/jrm.2025.p1452-5","unstructured":"K. Liu, Z. Tang, D. Wang, Z. Wang, X. Li, and B. Zhao, \u201cCoherent: Collaboration of heterogeneous multi-robot system with large language models,\u201d arXiv preprint, arXiv:2409.15146, 2024. https:\/\/doi.org\/10.48550\/arXiv.2409.15146"},{"key":"key-10.20965\/jrm.2025.p1452-6","unstructured":"V. Strobel, M. Dorigo, and M. Fritz, \u201cLlm2swarm: Robot swarms that responsively reason, plan, and collaborate through llms,\u201d arXiv preprint, arXiv:2410.11387, 2024. https:\/\/doi.org\/10.48550\/arXiv.2410.11387"},{"key":"key-10.20965\/jrm.2025.p1452-7","unstructured":"B. Yu, H. Kasaei, and M. Cao, \u201cCo-navgpt: Multi-robot cooperative visual semantic navigation using large language models,\u201d arXiv preprint, arXiv:2310.07937, 2023. https:\/\/doi.org\/10.48550\/arXiv.2310.07937"},{"key":"key-10.20965\/jrm.2025.p1452-8","unstructured":"Y. Wang, R. Xiao, J. Y. L. Kasahara, R. Yajima, K. Nagatani, A. Yamashita, and H. Asama, \u201cDart-llm: Dependency-aware multi-robot task decomposition and execution using large language models,\u201d arXiv preprint, arXiv:2411.09022, 2024. https:\/\/doi.org\/10.48550\/arXiv.2411.09022"},{"key":"key-10.20965\/jrm.2025.p1452-9","doi-asserted-by":"crossref","unstructured":"S. S. Kannan, V. L. N. Venkatesh, and B.-C. Min, \u201cSmart-llm: Smart multi-agent robot task planning using large language models,\u201d arXiv preprint, arXiv:2309.10062, 2023. https:\/\/doi.org\/10.48550\/arXiv.2309.10062","DOI":"10.1109\/IROS58592.2024.10802322"},{"key":"key-10.20965\/jrm.2025.p1452-10","doi-asserted-by":"crossref","unstructured":"Y. Lakhnati, M. Pascher, and J. Gerken, \u201cExploring a gpt-based large language model for variable autonomy in a VR-based human-robot teaming simulation,\u201d Frontiers in Robotics and AI, Vol.11, Article No.1347538, 2024. https:\/\/doi.org\/10.3389\/frobt.2024.1347538","DOI":"10.3389\/frobt.2024.1347538"},{"key":"key-10.20965\/jrm.2025.p1452-11","unstructured":"M. Ahn, M. G. Arenas, M. Bennice, N. Brown, C. Chan, B. David, A. Francis, G. Gonzalez, R. Hessmer, T. Jackson, N. J. Joshi, D. Lam, T.-W. E. Lee, A. Luong, S. Maddineni, H. Patel, J. Peralta, J. Quiambao, D. Reyes, R. M. J. Ruano, D. Sadigh, P. Sanketi, L. Takayama, P. Vodenski, and F. Xia, \u201cVader: Visual affordance detection and error recovery for multi robot human collaboration,\u201d arXiv preprint, arXiv:2405.16021, 2024. https:\/\/doi.org\/10.48550\/arXiv.2405.16021"},{"key":"key-10.20965\/jrm.2025.p1452-12","unstructured":"K. Garg, S. Zhang, J. Arkin, and C. Fan, \u201cFoundation models to the rescue: Deadlock resolution in connected multi-robot systems,\u201d arXiv preprint, arXiv:2404.06413, 2024. https:\/\/doi.org\/10.48550\/arXiv.2404.06413"},{"key":"key-10.20965\/jrm.2025.p1452-13","doi-asserted-by":"crossref","unstructured":"S. Morad, A. Shankar, J. Blumenkamp, and A. Prorok, \u201cLanguage-conditioned offline RL for multi-robot navigation,\u201d arXiv preprint, arXiv:2407.20164, 2024. https:\/\/doi.org\/10.48550\/arXiv.2407.20164","DOI":"10.1109\/ICRA55743.2025.11127288"},{"key":"key-10.20965\/jrm.2025.p1452-14","unstructured":"T. Godfrey, W. Hunt, and M. D. Soorati, \u201cMarlin: Multi-agent reinforcement learning guided by language-based inter-robot negotiation,\u201d arXiv preprint, arXiv:2410.14383, 2025. https:\/\/doi.org\/10.48550\/arXiv.2410.14383"},{"key":"key-10.20965\/jrm.2025.p1452-15","doi-asserted-by":"crossref","unstructured":"J. Orr and A. Dutta, \u201cMulti-agent deep reinforcement learning for multi-robot applications: A survey,\u201d Sensors, Vol.23, No.7, Article No.3625, 2023. https:\/\/doi.org\/10.3390\/s23073625","DOI":"10.3390\/s23073625"},{"key":"key-10.20965\/jrm.2025.p1452-16","doi-asserted-by":"crossref","unstructured":"T. Niwa, K. Shibata, and T. Jimbo, \u201cMulti-agent reinforcement learning and individuality analysis for cooperative transportation with obstacle\tremoval,\u201d F. Matsuno, S. Azuma, and M. Yamamoto (Eds.), \u201cDistributed Autonomous Robotic Systems,\u201d pp. 202-213, Springer, 2022. https:\/\/doi.org\/10.1007\/978-3-030-92790-5_16","DOI":"10.1007\/978-3-030-92790-5_16"},{"key":"key-10.20965\/jrm.2025.p1452-17","doi-asserted-by":"crossref","unstructured":"G. Eoh and T.-H. Park, \u201cCooperative object transportation using curriculum-based deep reinforcement learning,\u201d Sensors, Vol.21, No.14, Article No.4780, 2021. https:\/\/doi.org\/10.3390\/s21144780","DOI":"10.3390\/s21144780"},{"key":"key-10.20965\/jrm.2025.p1452-18","doi-asserted-by":"crossref","unstructured":"L. Zhang, Y. Sun, A. Barth, and O. Ma, \u201cDecentralized control of multi-robot system in cooperative object transportation using deep reinforcement learning,\u201d IEEE Access, Vol.8, pp. 184109-184119, 2020. https:\/\/doi.org\/10.1109\/ACCESS.2020.3025287","DOI":"10.1109\/ACCESS.2020.3025287"},{"key":"key-10.20965\/jrm.2025.p1452-19","doi-asserted-by":"crossref","unstructured":"Y. Sueoka, T. Yoshida, and K. Osuka, \u201cReinforcement learning of scalable, flexible and robust cooperative transport behavior using the transformer encoder,\u201d A. Nilles, K. H. Petersen, T. L. Lam, A. Prorok, M. Rubenstein, and M. Otte (Eds.), \u201cDistributed Autonomous Robotic Systems,\u201d Springer, 2025. https:\/\/doi.org\/10.1007\/978-3-032-04584-3_20","DOI":"10.1007\/978-3-032-04584-3_20"},{"key":"key-10.20965\/jrm.2025.p1452-20","unstructured":"A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A. N. Gomez, \u0141. Kaiser, and I. Polosukhin, \u201cAttention is all you need,\u201d 31st Conf. on Neural Information Processing Systems (NIPS 2017), 2017."},{"key":"key-10.20965\/jrm.2025.p1452-21","doi-asserted-by":"crossref","unstructured":"G. Serapio-Garc\u00eda, M. Safdari, C. Crepy, L. Sun, S. Fitz, P. Romero, M. Abdulhai, A. Faust, and M. Matari\u0107, \u201cPersonality traits in large language models,\u201d arXiv preprint, arXiv:2307.00184, 2023. https:\/\/doi.org\/10.48550\/arXiv.2307.00184","DOI":"10.21203\/rs.3.rs-3296728\/v1"},{"key":"key-10.20965\/jrm.2025.p1452-22","unstructured":"C. Yu, A. Velu, E. Vinitsky, J. Gao, Y. Wang, A. Bayen, and Y. Wu, \u201cThe surprising effectiveness of PPO in cooperative, multi-agent games,\u201d arXiv preprint, arXiv:2103.01955, 2021. https:\/\/doi.org\/10.48550\/arXiv.2103.01955"},{"key":"key-10.20965\/jrm.2025.p1452-23","unstructured":"J. Schulman, P. Moritz, S. Levine, M. Jordan, and P. Abbeel, \u201cHigh-dimensional continuous control using generalized advantage estimation,\u201d arXiv preprint, arXiv:1506.02438, 2015. https:\/\/doi.org\/10.48550\/arXiv.1506.02438"}],"container-title":["Journal of Robotics and Mechatronics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.fujipress.jp\/main\/wp-content\/themes\/Fujipress\/hyosetsu.php?ppno=robot003700060016","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,19]],"date-time":"2025-12-19T15:03:14Z","timestamp":1766156594000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.fujipress.jp\/jrm\/rb\/robot003700061452"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,20]]},"references-count":23,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2025,12,20]]},"published-print":{"date-parts":[[2025,12,20]]}},"URL":"https:\/\/doi.org\/10.20965\/jrm.2025.p1452","relation":{},"ISSN":["1883-8049","0915-3942"],"issn-type":[{"value":"1883-8049","type":"electronic"},{"value":"0915-3942","type":"print"}],"subject":[],"published":{"date-parts":[[2025,12,20]]}}}