{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T14:52:50Z","timestamp":1773154370848,"version":"3.50.1"},"publisher-location":"Cham","reference-count":31,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783031210891","type":"print"},{"value":"9783031210907","type":"electronic"}],"license":[{"start":{"date-parts":[[2022,12,15]],"date-time":"2022-12-15T00:00:00Z","timestamp":1671062400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2022,12,15]],"date-time":"2022-12-15T00:00:00Z","timestamp":1671062400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023]]},"DOI":"10.1007\/978-3-031-21090-7_27","type":"book-chapter","created":{"date-parts":[[2022,12,14]],"date-time":"2022-12-14T18:11:35Z","timestamp":1671041495000},"page":"454-469","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Flock Navigation by Coordinated Shepherds via Reinforcement Learning"],"prefix":"10.1007","author":[{"given":"Yazied","family":"Hasan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"John E. G.","family":"Baxter","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"C\u00e9sar A.","family":"Salcedo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Elena","family":"Delgado","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lydia","family":"Tapia","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,12,15]]},"reference":[{"key":"27_CR1","doi-asserted-by":"crossref","unstructured":"Aiba, C., Fujioka, K.: A suggestion for effective shepherding models with two sheepdogs. In: Proceedings of the Conference of Industrial Electronics Society (IECON), pp. 77\u201381 (2020)","DOI":"10.1109\/IECON43393.2020.9254432"},{"key":"27_CR2","unstructured":"Baumann, M., Buning, H.: Learning shepherding behavior. Ph.D. thesis, University of Paderborn (2016)"},{"key":"27_CR3","unstructured":"Brul\u00e9, J., Engel, K., Fung, N., Julien, I.: Evolving shepherding behavior with genetic programming algorithms. Computing Research Repository (CoRR) in arXiv (2016)"},{"key":"27_CR4","doi-asserted-by":"publisher","first-page":"214658","DOI":"10.1109\/ACCESS.2020.3037325","volume":"8","author":"H El-Fiqi","year":"2020","unstructured":"El-Fiqi, H., Campbell, B., Elsayed, S., Perry, A., Singh, H.K., Hunjet, R., Abbass, H.A.: The limits of reactive shepherding approaches for swarm guidance. IEEE Access 8, 214658\u2013214671 (2020)","journal-title":"IEEE Access"},{"key":"27_CR5","doi-asserted-by":"crossref","unstructured":"Fingas, M.: The Basics of Oil Spill Cleanup. CRC Press\/Taylor | & Francis, Boca Raton, FL (2013)","DOI":"10.1201\/b13686"},{"key":"27_CR6","doi-asserted-by":"crossref","unstructured":"Foerster, J.N., Farquhar, G., Afouras, T., Nardelli, N., Whiteson, S.: Counterfactual multi-agent policy gradients. In: Proceedings AAAI Conference on Artificial Intelligence, pp. 2974\u20132982, Feb. 2017","DOI":"10.1609\/aaai.v32i1.11794"},{"key":"27_CR7","doi-asserted-by":"crossref","unstructured":"Gade, S., Paranjape, A.A., Chung, S.J.: Robotic Herding Using Wavefront Algorithm: Performance and Stability, pp. 1\u201316. AIAA (2016)","DOI":"10.2514\/6.2016-1378"},{"key":"27_CR8","unstructured":"Gadre, A.S.: Learning strategies in multi-agent systems-applications to the herding problem. Ph.D. thesis, Virginia Tech (2001)"},{"key":"27_CR9","doi-asserted-by":"crossref","unstructured":"Georgiev, M., Tanev, I., Shimohara, K., Ray, T.: Evolution, robustness and generality of a team of simple agents with asymmetric morphology in predator-prey pursuit problem. Information 10(2) (2019)","DOI":"10.3390\/info10020072"},{"key":"27_CR10","doi-asserted-by":"crossref","unstructured":"Go, C.K., Lao, B., Yoshimoto, J., Ikeda, K.: A reinforcement learning approach to the shepherding task using SARSA. In: Proceedings of the 2016 International Joint Conference on Neural Networks (IJCNN), pp. 3833\u20133836 (2016)","DOI":"10.1109\/IJCNN.2016.7727694"},{"issue":"4","key":"27_CR11","doi-asserted-by":"publisher","first-page":"5645","DOI":"10.1109\/LRA.2020.3010203","volume":"5","author":"YA Hasan","year":"2020","unstructured":"Hasan, Y.A., Garg, A., Sugaya, S., Tapia, L.: Defensive escort teams for navigation in crowds via multi-agent deep reinforcement learning. Robot. Automat. Lett. 5(4), 5645\u20135652 (2020)","journal-title":"Robot. Automat. Lett."},{"key":"27_CR12","doi-asserted-by":"crossref","unstructured":"K.\u00a0Gupta, J., Egorov, M., Kochenderfer, M.: Cooperative multi-agent control using deep reinforcement learning. In: Proceedings of the International Conference on Autonomous Agents and Multiagent Systems (AAMAS), pp. 66\u201383, May 2017)","DOI":"10.1007\/978-3-319-71682-4_5"},{"key":"27_CR13","doi-asserted-by":"crossref","unstructured":"Kirkland, J., Maciejewski, A.: A simulation of attempts to influence crowd dynamics. In: Proceedings of the 2003 IEEE International Conference on Systems, Man and Cybernetics, (Cat. No.03CH37483), vol.\u00a05, pp. 4328\u20134333 (2003)","DOI":"10.1109\/ICSMC.2003.1245665"},{"key":"27_CR14","doi-asserted-by":"crossref","unstructured":"Kowalczuk, Z., J\u0119druch, W., Szyma\u0144ski, K.: The use of an autoencoder in the problem of shepherding. In: Proceedings of the 2018 23rd International Conference on Methods Models in Automation Robotics (MMAR), pp. 947\u2013952 (2018)","DOI":"10.1109\/MMAR.2018.8486067"},{"key":"27_CR15","doi-asserted-by":"crossref","unstructured":"Lee, W., Kim, D.: Autonomous shepherding behaviors of multiple target steering robots. Sensors 17(12) (2017)","DOI":"10.3390\/s17122729"},{"key":"27_CR16","unstructured":"Lien, J.M., Bayazit, O., Sowell, R., Rodriguez, S., Amato, N.: Shepherding behaviors. In: Proceedings of the IEEE International Conference on Robotics and Automation (ICRA), vol.\u00a04, pp. 4159\u20134164 (2004)"},{"key":"27_CR17","unstructured":"Lien, J.M., Rodriguez, S., Malric, J., Amato, N.: Shepherding behaviors with multiple shepherds. In: Proceedings of the IEEE International Conference on Robotics and Automation (ICRA), pp. 3402\u20133407 (2005)"},{"key":"27_CR18","doi-asserted-by":"crossref","unstructured":"Mahdavimoghaddam, M., Nikanjam, A., Abdoos, M.: Improved reinforcement learning in cooperative multi-agent environments using knowledge transfer. Computing Research Repository (CoRR) in arXiv (2022)","DOI":"10.1007\/s11227-022-04305-w"},{"key":"27_CR19","doi-asserted-by":"crossref","unstructured":"Nguyen, H.T., Nguyen, T.D., Garratt, M., Kasmarik, K., Anavatti, S., Barlow, M., Abbass, H.A.: A deep hierarchical reinforcement learner for aerial shepherding of ground swarms. In: Proceedings of the Neural Information Processing: 26th International Conference, ICONIP 2019, Part I, pp. 658\u2013669 (2019)","DOI":"10.1007\/978-3-030-36708-4_54"},{"key":"27_CR20","doi-asserted-by":"crossref","unstructured":"Nguyen, T., Liu, J., Nguyen, H., Kasmarik, K., Anavatti, S., Garratt, M., Abbass, H.: Perceptron-learning for scalable and transparent dynamic formation in swarm-on-swarm shepherding. In: Proceedings of the 2020 IEEE International Joint Conference on Neural Network (IJCNN), pp. 1\u20138 (2020)","DOI":"10.1109\/IJCNN48605.2020.9207539"},{"key":"27_CR21","doi-asserted-by":"crossref","unstructured":"\u00d6zdemir, A., Gauci, M., Gro\u00df, R.: Shepherding with robots that do not compute. In: Proceedings of the ECAL 2017, the Fourteenth European Conference on Artificial Life, pp. 332\u2013339. MIT Press (2017)","DOI":"10.7551\/ecal_a_056"},{"key":"27_CR22","doi-asserted-by":"crossref","unstructured":"Pierson, A., Schwager, M.: Bio-inspired non-cooperative multi-robot herding. In: Proceedings of International Conference on Robotics and Automation (ICRA), pp. 1843\u20131849 (2015)","DOI":"10.1109\/ICRA.2015.7139438"},{"key":"27_CR23","unstructured":"Potter, M.A., Meeden, L.A., Schultz, A.C.: Heterogeneity in the coevolved behaviors of mobile robots: The emergence of specialists. In: Proceedings of the International Joint Conference on Artificial Intelligence, vol.\u00a017, pp. 1337\u20131343. Citeseer (2001)"},{"key":"27_CR24","doi-asserted-by":"crossref","unstructured":"Reynolds, C.W.: Flocks, herds and schools: a distributed behavioral model. In: Proceedings of the ACM SIGGRAPH, pp. 25\u201334 (1987)","DOI":"10.1145\/37402.37406"},{"key":"27_CR25","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms. Comput. Res Repos. (CoRR) in arXiv (2017)"},{"key":"27_CR26","unstructured":"Schultz, A., Grefenstette, J., Adams, W.: Roboshepherd: learning a complex behavior. In: Proceedings of International Conference on Robotics and Automation (1996)"},{"key":"27_CR27","doi-asserted-by":"crossref","unstructured":"Shell, D., Mataric, M.: Directional audio beacon deployment: an assistive multi-robot application. In: Proceedings of the IEEE International Conference on Robotics and Automation (ICRA), vol.\u00a03, pp. 2588\u20132594 (2004)","DOI":"10.1109\/ROBOT.2004.1307451"},{"key":"27_CR28","doi-asserted-by":"publisher","first-page":"613","DOI":"10.1007\/s10514-021-09975-8","volume":"45","author":"H Song","year":"2021","unstructured":"Song, H., Varava, A., Kravchenko, O., Kragic, D., Wang, M.Y., Pokorny, F.T., Hang, K.: Herding by caging: a formation-based motion planning framework for guiding mobile agents. Auton. Robot. 45, 613\u2013631 (2021)","journal-title":"Auton. Robot."},{"issue":"20140719","key":"27_CR29","first-page":"1","volume":"11","author":"D Str\u00f6mbom","year":"2014","unstructured":"Str\u00f6mbom, D., Mann, R.P., Wilson, A.M., Hailes, S., Morton, A.J., Sumpter, D.J.T., King, A.J.: Solving the shepherding problem: heuristics for herding autonomous, interacting agents. J. R. Soc. Interface 11(20140719), 1\u20139 (2014)","journal-title":"J. R. Soc. Interface"},{"key":"27_CR30","doi-asserted-by":"crossref","unstructured":"Varava, A., Hang, K., Kragic, D., Pokorny, F.: Herding by caging: a topological approach towards guiding moving agents via mobile robots. In: Proceedings of the Robotics: Science and Systems (RSS) (2017)","DOI":"10.15607\/RSS.2017.XIII.074"},{"issue":"2","key":"27_CR31","doi-asserted-by":"publisher","first-page":"4163","DOI":"10.1109\/LRA.2021.3068955","volume":"6","author":"J Zhi","year":"2021","unstructured":"Zhi, J., Lien, J.M.: Learning to herd agents amongst obstacles: training robust shepherding behaviors using deep reinforcement learning. Robot. Automat. Lett. 6(2), 4163\u20134168 (2021)","journal-title":"Robot. Automat. Lett."}],"container-title":["Springer Proceedings in Advanced Robotics","Algorithmic Foundations of Robotics XV"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-21090-7_27","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,10]],"date-time":"2024-10-10T10:41:57Z","timestamp":1728556917000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-21090-7_27"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,12,15]]},"ISBN":["9783031210891","9783031210907"],"references-count":31,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-21090-7_27","relation":{},"ISSN":["2511-1256","2511-1264"],"issn-type":[{"value":"2511-1256","type":"print"},{"value":"2511-1264","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,12,15]]},"assertion":[{"value":"15 December 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"WAFR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Workshop on the Algorithmic Foundations of Robotics","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":", MD","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"USA","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 June 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24 June 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"wafr2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/wafr2022.github.io","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}