{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T22:40:37Z","timestamp":1743028837791,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":23,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819607822"},{"type":"electronic","value":"9789819607839"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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":[[2025]]},"DOI":"10.1007\/978-981-96-0783-9_29","type":"book-chapter","created":{"date-parts":[[2025,1,21]],"date-time":"2025-01-21T19:32:02Z","timestamp":1737487922000},"page":"424-436","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Active Target Location and\u00a0Grasping Based on\u00a0Language-Vision-Action"],"prefix":"10.1007","author":[{"given":"Xinxin","family":"Zhu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jin","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jialong","family":"Xie","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chaoqun","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fengyu","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,1,22]]},"reference":[{"key":"29_CR1","doi-asserted-by":"crossref","unstructured":"Zhou, Z., Li, S.: Self-sustained and coordinated rhythmic deformations with SMA for controller-free locomotion. In: Advanced Intelligent Systems, p. 2300667 (2024)","DOI":"10.1002\/aisy.202300667"},{"issue":"2","key":"29_CR2","doi-asserted-by":"publisher","first-page":"415","DOI":"10.1017\/S0263574723001510","volume":"42","author":"S Wang","year":"2024","unstructured":"Wang, S., Zhou, Z., Li, B., Li, Z., Kan, Z.: Multi-modal interaction with transformers: bridging robots and human with natural language. Robotica 42(2), 415\u2013434 (2024)","journal-title":"Robotica"},{"key":"29_CR3","doi-asserted-by":"crossref","unstructured":"Korekata, R., et al.: Switching head-tail funnel uniter for dual referring expression comprehension with fetch-and-Carry tasks. In: 2023 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 3865\u20133872. IEEE (2023)","DOI":"10.1109\/IROS55552.2023.10342165"},{"key":"29_CR4","doi-asserted-by":"crossref","unstructured":"Cheang, C., Lin, H., Fu, Y., Xue, X.: Learning 6-DOF object poses to grasp category-level objects by language instructions. In: 2022 International Conference on Robotics and Automation (ICRA), pp. 8476\u20138482. IEEE (2022)","DOI":"10.1109\/ICRA46639.2022.9811367"},{"key":"29_CR5","doi-asserted-by":"crossref","unstructured":"Sun, Q., Lin, H., Fu, Y., Fu, Y., Xue, X.: Language guided robotic grasping with fine-grained instructions. In: 2023 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 1319\u20131326. IEEE (2023)","DOI":"10.1109\/IROS55552.2023.10342331"},{"key":"29_CR6","doi-asserted-by":"crossref","unstructured":"Sun, Y., Bo, L., Fox, D.: Attribute based object identification. In: 2013 IEEE International Conference on Robotics and Automation, pp. 2096\u20132103. IEEE (2013)","DOI":"10.1109\/ICRA.2013.6630858"},{"issue":"2","key":"29_CR7","doi-asserted-by":"publisher","first-page":"116","DOI":"10.1049\/csy2.12049","volume":"4","author":"Z Liu","year":"2022","unstructured":"Liu, Z., Ding, K., Xu, Q., Song, Y., Yuan, X., Li, Y.: Scene images and text information-based object location of robot grasping. IET Cyber Syst. Robot. 4(2), 116\u2013130 (2022)","journal-title":"IET Cyber Syst. Robot."},{"key":"29_CR8","doi-asserted-by":"crossref","unstructured":"Qi, Y., et al.: Reverie: Remote embodied visual referring expression in real indoor environments. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9982\u20139991 (2020)","DOI":"10.1109\/CVPR42600.2020.01000"},{"key":"29_CR9","doi-asserted-by":"crossref","unstructured":"Kahn, G., et al.: Active exploration using trajectory optimization for robotic grasping in the presence of occlusions. In: 2015 IEEE International Conference on Robotics and Automation (ICRA), pp. 4783\u20134790. IEEE (2015)","DOI":"10.1109\/ICRA.2015.7139864"},{"issue":"2\u20133","key":"29_CR10","doi-asserted-by":"publisher","first-page":"217","DOI":"10.1177\/0278364919897133","volume":"39","author":"M Shridhar","year":"2020","unstructured":"Shridhar, M., Mittal, D., Hsu, D.: Ingress: interactive visual grounding of referring expressions. Int. J. Robot.Res. 39(2\u20133), 217\u2013232 (2020)","journal-title":"Int. J. Robot.Res."},{"key":"29_CR11","doi-asserted-by":"crossref","unstructured":"Yu, H., Lou, X., Yang, Y., Choi, C.: IOSG: image-driven object searching and grasping. In: 2023 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 3145\u20133152. IEEE (2023)","DOI":"10.1109\/IROS55552.2023.10342009"},{"key":"29_CR12","doi-asserted-by":"crossref","unstructured":"Fu, L., et al.: Legs: Learning efficient grasp sets for exploratory grasping. In: 2022 International Conference on Robotics and Automation (ICRA), pp. 8259\u20138265. IEEE (2022)","DOI":"10.1109\/ICRA46639.2022.9812138"},{"key":"29_CR13","doi-asserted-by":"crossref","unstructured":"Xu, K., et al.: A joint modeling of vision-language-action for target-oriented grasping in clutter. In: 2023 IEEE International Conference on Robotics and Automation (ICRA), pp. 11597\u201311604. IEEE (2023)","DOI":"10.1109\/ICRA48891.2023.10161041"},{"key":"29_CR14","doi-asserted-by":"crossref","unstructured":"Jiang, Y., Jia, Y., Li, X.: Contact-aware non-prehensile manipulation for object retrieval in cluttered environments. In: 2023 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 10604\u201310611. IEEE (2023)","DOI":"10.1109\/IROS55552.2023.10341476"},{"key":"29_CR15","doi-asserted-by":"crossref","unstructured":"Wang, Y., Wang, K., Wang, Y., Guo, D., Liu, H., Sun, F.: Audio-visual grounding referring expression for robotic manipulation. In: 2022 International Conference on Robotics and Automation (ICRA), pp. 9258\u20139264. IEEE (2022)","DOI":"10.1109\/ICRA46639.2022.9811895"},{"key":"29_CR16","doi-asserted-by":"crossref","unstructured":"Behrens, J.K., Nazarczuk, M., Stepanova, K., Hoffmann, M., Demiris, Y., Mikolajczyk, K.: Embodied reasoning for discovering object properties via manipulation. In: 2021 IEEE International Conference on Robotics and Automation (ICRA), pp. 10139\u201310145. IEEE (2021)","DOI":"10.1109\/ICRA48506.2021.9561212"},{"key":"29_CR17","doi-asserted-by":"crossref","unstructured":"Yang, Y., Lou, X., Choi, C.: Interactive robotic grasping with attribute-guided disambiguation. In: 2022 International Conference on Robotics and Automation (ICRA), pp. 8914\u20138920. IEEE (2022)","DOI":"10.1109\/ICRA46639.2022.9812360"},{"key":"29_CR18","doi-asserted-by":"crossref","unstructured":"Mo, Y., Zhang, H., Kong, T.: Towards open-world interactive disambiguation for robotic grasping. In: 2023 IEEE International Conference on Robotics and Automation (ICRA), pp. 8061\u20138067. IEEE (2023)","DOI":"10.1109\/ICRA48891.2023.10161333"},{"key":"29_CR19","first-page":"1877","volume":"33","author":"T Brown","year":"2020","unstructured":"Brown, T., et al.: Language models are few-shot learners. Adv. Neural. Inf. Process. Syst. 33, 1877\u20131901 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"29_CR20","doi-asserted-by":"crossref","unstructured":"Du, Z., et al: GLM: general language model pretraining with autoregressive blank infilling. arXiv preprint arXiv:2103.10360 (2021)","DOI":"10.18653\/v1\/2022.acl-long.26"},{"key":"29_CR21","doi-asserted-by":"publisher","unstructured":"Zhou, X., Girdhar, R., Joulin, A., Kr\u00e4henb\u00fchl, P., Misra, I.: Detecting twenty-thousand classes using image-level supervision. In: European Conference on Computer Vision. pp. 350\u2013368. Springer (2022). https:\/\/doi.org\/10.1007\/978-3-031-20077-9_21","DOI":"10.1007\/978-3-031-20077-9_21"},{"key":"29_CR22","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"key":"29_CR23","doi-asserted-by":"crossref","unstructured":"Vuong, A.D., et al.: Grasp-anything: large-scale grasp dataset from foundation models. arXiv preprint arXiv:2309.09818 (2023)","DOI":"10.1109\/ICRA57147.2024.10611277"}],"container-title":["Lecture Notes in Computer Science","Intelligent Robotics and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-0783-9_29","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,21]],"date-time":"2025-01-21T19:32:13Z","timestamp":1737487933000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-0783-9_29"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9789819607822","9789819607839"],"references-count":23,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-0783-9_29","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"22 January 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIRA","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Intelligent Robotics and Applications","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Xi'an","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","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":"31 July 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2 August 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icira2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.icira2024.org","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}