{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,26]],"date-time":"2026-06-26T16:47:28Z","timestamp":1782492448063,"version":"3.54.5"},"publisher-location":"Cham","reference-count":26,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031590566","type":"print"},{"value":"9783031590573","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":[[2024]]},"DOI":"10.1007\/978-3-031-59057-3_28","type":"book-chapter","created":{"date-parts":[[2024,5,7]],"date-time":"2024-05-07T22:02:19Z","timestamp":1715119339000},"page":"441-456","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Intuitive Multi-modal Human-Robot Interaction via\u00a0Posture and\u00a0Voice"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-9976-7422","authenticated-orcid":false,"given":"Yuzhi","family":"Lai","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-4823-9626","authenticated-orcid":false,"given":"Mario","family":"Radke","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-2867-4030","authenticated-orcid":false,"given":"Youssef","family":"Nassar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Atmaraaj","family":"Gopal","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Thomas","family":"Weber","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"ZhaoHua","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yihong","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Matthias","family":"R\u00e4tsch","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,5,8]]},"reference":[{"key":"28_CR1","unstructured":"Alpha Cephei: Vosk homepage. https:\/\/alphacephei.com\/vosk\/"},{"issue":"1","key":"28_CR2","first-page":"20220076","volume":"32","author":"A Babour","year":"2023","unstructured":"Babour, A., et al.: Intelligent gloves: an IT intervention for deaf-mute people. J. Intell. Syst. 32(1), 20220076 (2023)","journal-title":"J. Intell. Syst."},{"key":"28_CR3","doi-asserted-by":"crossref","unstructured":"Cao, Z., Simon, T., Wei, S.E., Sheikh, Y.: Realtime multi-person 2D pose estimation using part affinity fields. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7291\u20137299 (2017)","DOI":"10.1109\/CVPR.2017.143"},{"issue":"10","key":"28_CR4","doi-asserted-by":"publisher","first-page":"9610","DOI":"10.1109\/JSEN.2022.3163730","volume":"22","author":"H Cheng","year":"2022","unstructured":"Cheng, H., Wang, Y., Meng, M.Q.H.: A vision-based robot grasping system. IEEE Sens. J. 22(10), 9610\u20139620 (2022)","journal-title":"IEEE Sens. J."},{"key":"28_CR5","doi-asserted-by":"crossref","unstructured":"Enan, S.S., Fulton, M., Sattar, J.: Robotic detection of a human-comprehensible gestural language for underwater multi-human-robot collaboration. In: 2022 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 3085\u20133092. IEEE (2022)","DOI":"10.1109\/IROS47612.2022.9981450"},{"key":"28_CR6","doi-asserted-by":"crossref","unstructured":"Ende, T., Haddadin, S., Parusel, S., W\u00fcsthoff, T., Hassenzahl, M., Albu-Sch\u00e4ffer, A.: A human-centered approach to robot gesture based communication within collaborative working processes. In: 2011 IEEE\/RSJ International Conference on Intelligent Robots and Systems, pp. 3367\u20133374. IEEE (2011)","DOI":"10.1109\/IROS.2011.6048257"},{"key":"28_CR7","unstructured":"Fujii, T., Lee, J.H., Okamoto, S.: Gesture recognition system for human-robot interaction and its application to robotic service task. In: Proceedings of the International Multi-Conference of Engineers and Computer Scientists (IMECS), vol. 1 (2014)"},{"key":"28_CR8","doi-asserted-by":"crossref","unstructured":"Krupke, D., Steinicke, F., Lubos, P., Jonetzko, Y., G\u00f6rner, M., Zhang, J.: Comparison of multimodal heading and pointing gestures for co-located mixed reality human-robot interaction. In: 2018 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 1\u20139. IEEE (2018)","DOI":"10.1109\/IROS.2018.8594043"},{"key":"28_CR9","doi-asserted-by":"crossref","unstructured":"Mahler, J., Matl, M., Liu, X., Li, A., Gealy, D., Goldberg, K.: Dex-Net 3.0: computing robust robot suction grasp targets in point clouds using a new analytic model and deep learning. arXiv preprint arXiv:1709.06670 (2017)","DOI":"10.1109\/ICRA.2018.8460887"},{"key":"28_CR10","doi-asserted-by":"crossref","unstructured":"Mazhar, O., Ramdani, S., Navarro, B., Passama, R., Cherubini, A.: Towards real-time physical human-robot interaction using skeleton information and hand gestures. In: 2018 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 1\u20136. IEEE (2018)","DOI":"10.1109\/IROS.2018.8594385"},{"key":"28_CR11","doi-asserted-by":"crossref","unstructured":"Mikawa, M., Morimoto, Y., Tanaka, K.: Guidance method using laser pointer and gestures for librarian robot. In: 19th International Symposium in Robot and Human Interactive Communication, pp. 373\u2013378. IEEE (2010)","DOI":"10.1109\/ROMAN.2010.5598714"},{"key":"28_CR12","unstructured":"Moon, I., Lee, M., Ryu, J., Mun, M.: Intelligent robotic wheelchair with EMG-, gesture-, and voice-based interfaces. In: Proceedings 2003 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS 2003) (Cat. No. 03CH37453), vol. 4, pp. 3453\u20133458. IEEE (2003)"},{"key":"28_CR13","doi-asserted-by":"crossref","unstructured":"Mousavian, A., Eppner, C., Fox, D.: 6-DOF GraspNet: variational grasp generation for object manipulation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 2901\u20132910 (2019)","DOI":"10.1109\/ICCV.2019.00299"},{"key":"28_CR14","unstructured":"Radford, A., Kim, J.W., Xu, T., Brockman, G., McLeavey, C., Sutskever, I.: Robust speech recognition via large-scale weak supervision. In: International Conference on Machine Learning, pp. 28492\u201328518. PMLR (2023)"},{"key":"28_CR15","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: unified, real-time object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 779\u2013788 (2016)","DOI":"10.1109\/CVPR.2016.91"},{"key":"28_CR16","doi-asserted-by":"crossref","unstructured":"Ren, Z., Meng, J., Yuan, J.: Depth camera based hand gesture recognition and its applications in human-computer-interaction. In: 2011 8th International Conference on Information, Communications & Signal Processing, pp. 1\u20135. IEEE (2011)","DOI":"10.1109\/ICICS.2011.6173545"},{"key":"28_CR17","doi-asserted-by":"crossref","unstructured":"Rossi, S., Leone, E., Fiore, M., Finzi, A., Cutugno, F.: An extensible architecture for robust multimodal human-robot communication. In: 2013 IEEE\/RSJ International Conference on Intelligent Robots and Systems, pp. 2208\u20132213. IEEE (2013)","DOI":"10.1109\/IROS.2013.6696665"},{"key":"28_CR18","doi-asserted-by":"crossref","unstructured":"Skrzypek, A., Panfil, W., Kosior, M., Przysta, P., et al.: Control system shell of mobile robot with voice recognition module. In: 2019 12th International Workshop on Robot Motion and Control (RoMoCo), pp. 191\u2013196. IEEE (2019)","DOI":"10.1109\/RoMoCo.2019.8787345"},{"key":"28_CR19","doi-asserted-by":"publisher","unstructured":"Song, C.S., Kim, Y.K.: The role of the human-robot interaction in consumers\u2019 acceptance of humanoid retail service robots. J. Bus. Res. 146, 489\u2013503 (2022). https:\/\/doi.org\/10.1016\/j.jbusres.2022.03.087. https:\/\/www.sciencedirect.com\/science\/article\/pii\/S014829632200323X","DOI":"10.1016\/j.jbusres.2022.03.087"},{"issue":"13\u201314","key":"28_CR20","doi-asserted-by":"crossref","first-page":"1455","DOI":"10.1177\/0278364917735594","volume":"36","author":"A Ten Pas","year":"2017","unstructured":"Ten Pas, A., Gualtieri, M., Saenko, K., Platt, R.: Grasp pose detection in point clouds. Int. J. Robot. Res. 36(13\u201314), 1455\u20131473 (2017)","journal-title":"Int. J. Robot. Res."},{"key":"28_CR21","doi-asserted-by":"publisher","first-page":"2242","DOI":"10.1016\/j.procs.2022.09.534","volume":"207","author":"A Trabelsi","year":"2022","unstructured":"Trabelsi, A., Warichet, S., Aajaoun, Y., Soussilane, S.: Evaluation of the efficiency of state-of-the-art speech recognition engines. Procedia Comput. Sci. 207, 2242\u20132252 (2022)","journal-title":"Procedia Comput. Sci."},{"key":"28_CR22","doi-asserted-by":"crossref","unstructured":"Vanc, P., Behrens, J.K., Stepanova, K., Hlavac, V.: Communicating human intent to a robotic companion by multi-type gesture sentences. arXiv preprint arXiv:2303.04451 (2023)","DOI":"10.1109\/IROS55552.2023.10341944"},{"issue":"3","key":"28_CR23","doi-asserted-by":"publisher","first-page":"8170","DOI":"10.1109\/LRA.2022.3187261","volume":"7","author":"S Wang","year":"2022","unstructured":"Wang, S., Zhou, Z., Kan, Z.: When transformer meets robotic grasping: exploits context for efficient grasp detection. IEEE Robot. Autom. Lett. 7(3), 8170\u20138177 (2022)","journal-title":"IEEE Robot. Autom. Lett."},{"key":"28_CR24","doi-asserted-by":"crossref","unstructured":"Wang, X., Shen, H., Yu, H., Guo, J., Wei, X.: Hand and arm gesture-based human-robot interaction: a review. In: Proceedings of the 6th International Conference on Algorithms, Computing and Systems, pp. 1\u20137 (2022)","DOI":"10.1145\/3564982.3564996"},{"issue":"5","key":"28_CR25","doi-asserted-by":"publisher","first-page":"6380","DOI":"10.3390\/s130506380","volume":"13","author":"F Weichert","year":"2013","unstructured":"Weichert, F., Bachmann, D., Rudak, B., Fisseler, D.: Analysis of the accuracy and robustness of the leap motion controller. Sensors 13(5), 6380\u20136393 (2013)","journal-title":"Sensors"},{"issue":"1","key":"28_CR26","doi-asserted-by":"publisher","first-page":"53","DOI":"10.1162\/coli_a_00368","volume":"46","author":"L Zhou","year":"2020","unstructured":"Zhou, L., Gao, J., Li, D., Shum, H.Y.: The design and implementation of xiaoice, an empathetic social chatbot. Comput. Linguist. 46(1), 53\u201393 (2020). https:\/\/doi.org\/10.1162\/coli_a_00368","journal-title":"Comput. Linguist."}],"container-title":["Communications in Computer and Information Science","Robotics, Computer Vision and Intelligent Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-59057-3_28","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,18]],"date-time":"2024-11-18T07:00:33Z","timestamp":1731913233000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-59057-3_28"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031590566","9783031590573"],"references-count":26,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-59057-3_28","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"value":"1865-0929","type":"print"},{"value":"1865-0937","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"8 May 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ROBOVIS","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Robotics, Computer Vision and Intelligent Systems","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Rome","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25 February 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 February 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"robovis2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/robovis.scitevents.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}