{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,13]],"date-time":"2026-10-13T17:06:06Z","timestamp":1791911166638,"version":"4.3.4"},"reference-count":94,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2023,4,6]],"date-time":"2023-04-06T00:00:00Z","timestamp":1680739200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,4,6]],"date-time":"2023-04-06T00:00:00Z","timestamp":1680739200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["1564080"],"award-info":[{"award-number":["1564080"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["1650044"],"award-info":[{"award-number":["1650044"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100007297","name":"Office of Naval Research Global","doi-asserted-by":"publisher","award":["N00014-16-1-2835"],"award-info":[{"award-number":["N00014-16-1-2835"]}],"id":[{"id":"10.13039\/100007297","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Auton Robot"],"published-print":{"date-parts":[[2023,6]]},"DOI":"10.1007\/s10514-023-10099-4","type":"journal-article","created":{"date-parts":[[2023,4,6]],"date-time":"2023-04-06T10:03:23Z","timestamp":1680775403000},"page":"529-547","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["Learning instance-level N-ary semantic knowledge at scale for robots operating in everyday environments"],"prefix":"10.1007","volume":"47","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2113-5612","authenticated-orcid":false,"given":"Weiyu","family":"Liu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dhruva","family":"Bansal","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Angel","family":"Daruna","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sonia","family":"Chernova","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,4,6]]},"reference":[{"key":"10099_CR1","unstructured":"Abboud, R., Ceylan, I., Lukasiewicz, T., & Salvatori, T. (2020). Boxe: A box embedding model for knowledge base completion. In Neurips proceedings."},{"key":"10099_CR2","doi-asserted-by":"crossref","unstructured":"Amiri, S., Wei, S., Zhang, S., Sinapov, J., Thomason, J., & Stone, P. (2018). Multi-modal predicate identification using dynamically learned robot controllers. In IJCAI.","DOI":"10.24963\/ijcai.2018\/645"},{"key":"10099_CR3","doi-asserted-by":"publisher","first-page":"4571","DOI":"10.1109\/LRA.2019.2933815","volume":"4","author":"P Ard\u00f3n","year":"2019","unstructured":"Ard\u00f3n, P., Pairet, \u00c8., Petrick, R. P., Ramamoorthy, S., & Lohan, K. S. (2019). Learning grasp affordance reasoning through semantic relations. IEEE Robotics and Automation Letters, 4, 4571\u20134578.","journal-title":"IEEE Robotics and Automation Letters"},{"key":"10099_CR4","doi-asserted-by":"publisher","first-page":"1279","DOI":"10.1177\/0278364920917755","volume":"39","author":"J Arkin","year":"2020","unstructured":"Arkin, J., Park, D., Roy, S., Walter, M. R., Roy, N., Howard, T. M., & Paul, R. (2020). Multimodal estimation and communication of latent semantic knowledge for robust execution of robot instructions. The International Journal of Robotics Research, 39, 1279\u20131304.","journal-title":"The International Journal of Robotics Research"},{"key":"10099_CR5","unstructured":"Ba, J. L., Kiros, J. R., & Hinton, G. E. (2016). Layer normalization. arXiv preprint arXiv:1607.06450."},{"key":"10099_CR6","doi-asserted-by":"crossref","unstructured":"Balazevic, I., Allen, C., & Hospedales, T. (2019). TuckER: Tensor factorization for knowledge graph completion. In Emnlp-ijcnlp.","DOI":"10.18653\/v1\/D19-1522"},{"key":"10099_CR7","unstructured":"Banerjee, S., Daruna, A., Kent, D., Liu, W., Balloch, J., Jain, A., & Chernova, S. (2019). Taking recoveries to task: Recovery-driven development for recipe-based robot tasks. In ISRR."},{"key":"10099_CR8","doi-asserted-by":"publisher","first-page":"2523","DOI":"10.1109\/LRA.2018.2810956","volume":"3","author":"T Bhattacharjee","year":"2018","unstructured":"Bhattacharjee, T., Clever, H. M., Wade, J., & Kemp, C. C. (2018). Multimodal tactile perception of objects in a real home. IEEE Robotics and Automation Letters, 3, 2523\u20132530.","journal-title":"IEEE Robotics and Automation Letters"},{"key":"10099_CR9","doi-asserted-by":"publisher","first-page":"1273","DOI":"10.1109\/TRO.2017.2721939","volume":"33","author":"J Bohg","year":"2017","unstructured":"Bohg, J., Hausman, K., Sankaran, B., Brock, O., Kragic, D., Schaal, S., & Sukhatme, G. S. (2017). Interactive perception: Leveraging action in perception and perception in action. IEEE Transactions on Robotics, 33, 1273\u20131291.","journal-title":"IEEE Transactions on Robotics"},{"key":"10099_CR10","doi-asserted-by":"crossref","unstructured":"Bosselut, A., Rashkin, H., Sap, M., Malaviya, C., Celikyilmaz, A., & Choi, Y. (2019). Comet: Commonsense transformers for automatic knowledge graph construction. In ACL.","DOI":"10.18653\/v1\/P19-1470"},{"key":"10099_CR11","doi-asserted-by":"crossref","unstructured":"Chao, Y.-W., Wang, Z., Mihalcea, R., & Deng, J. (2015). Mining semantic affordances of visual object categories. In CVPR.","DOI":"10.1109\/CVPR.2015.7299054"},{"key":"10099_CR12","doi-asserted-by":"crossref","unstructured":"Chen, H., Tan, H., Kuntz, A., Bansal, M., & Alterovitz, R. (2020). Enabling robots to understand incomplete natural language instructions using commonsense reasoning. In ICRA.","DOI":"10.1109\/ICRA40945.2020.9197315"},{"key":"10099_CR13","unstructured":"Chernova, S., Chu, V., Daruna, A., Garrison, H., Hahn, M., Khante, P., & Thomaz, A. (2017). Situated bayesian reasoning framework for robots operating in diverse everyday environments. In ISRR."},{"key":"10099_CR14","doi-asserted-by":"crossref","unstructured":"Chu, V., Fitzgerald, T., & Thomaz, A. L. (2016). Learning object affordances by leveraging the combination of human-guidance and self-exploration. In HRI.","DOI":"10.1109\/HRI.2016.7451755"},{"key":"10099_CR15","doi-asserted-by":"crossref","unstructured":"Chuang, C.-Y., Li, J., Torralba, A., & Fidler, S. (2018). Learning to act properly: Predicting and explaining affordances from images. In CVPR.","DOI":"10.1109\/CVPR.2018.00108"},{"key":"10099_CR16","doi-asserted-by":"publisher","first-page":"279","DOI":"10.1016\/j.robot.2014.09.021","volume":"63","author":"V Chu","year":"2015","unstructured":"Chu, V., McMahon, I., Riano, L., McDonald, C. G., He, Q., Perez-Tejada, J. M., & Kuchenbecker, K. J. (2015). Robotic learning of haptic adjectives through physical interaction. Robotics and Autonomous Systems, 63, 279\u2013292.","journal-title":"Robotics and Autonomous Systems"},{"key":"10099_CR17","doi-asserted-by":"crossref","unstructured":"Daruna, A., Liu, W., Kira, Z., & Chetnova, S. (2019). Robocse: Robot common sense embedding. In 2019 international conference on robotics and automation.","DOI":"10.1109\/ICRA.2019.8794070"},{"key":"10099_CR18","doi-asserted-by":"crossref","unstructured":"Daruna, A., Nair, L. V., Liu, W., & Chernova, S. (2021). Towards robust one-shot task execution using knowledge graph embeddings. In International conference on robotics and automation.","DOI":"10.1109\/ICRA48506.2021.9561782"},{"key":"10099_CR19","doi-asserted-by":"crossref","unstructured":"Dettmers, T., Minervini, P., Stenetorp, P., & Riedel, S. (2018). Convolutional 2d knowledge graph embeddings. In Proceedings of the AAAI conference on artificial intelligence (Vol\u00a032).","DOI":"10.1609\/aaai.v32i1.11573"},{"key":"10099_CR20","unstructured":"Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019). Bert: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of the 2019 conference of the north American chapter of the association for computational linguistics: Human language technologies (Vol. 1, pp. 4171\u20134186)."},{"key":"10099_CR21","doi-asserted-by":"crossref","unstructured":"Do, T.-T., Nguyen, A., & Reid, I. (2018). Affordancenet: An end-to-end deep learning approach for object affordance detection. In 2018 IEEE international conference on robotics and automation (pp. 5882\u20135889).","DOI":"10.1109\/ICRA.2018.8460902"},{"key":"10099_CR22","unstructured":"Dyke, R. M., Zhou, F., Lai, Y.-K., & Rosin, P. L. (2020). Shrec 2020 track: Non-rigid shape correspondence of physically-based deformations. In 13th eurographics workshop on 3d object retrieval, 3dor 2020-short papers, Graz, Austria, September 4\u20135, 2020. Eurographics Association."},{"key":"10099_CR23","doi-asserted-by":"crossref","unstructured":"Eppe, M., Kerzel, M., Strahl, E., & Wermter, S. (2018). Deep neural object analysis by interactive auditory exploration with a humanoid robot. In 2018 IEEE\/RSJ international conference on intelligent robots and systems (IROS) (pp. 284\u2013289).","DOI":"10.1109\/IROS.2018.8593838"},{"key":"10099_CR24","doi-asserted-by":"publisher","first-page":"700","DOI":"10.1109\/LRA.2019.2892593","volume":"42","author":"Z Erickson","year":"2019","unstructured":"Erickson, Z., Luskey, N., Chernova, S., & Kemp, C. C. (2019). Classification of household materials via spectroscopy. IEEE Robotics and Automation Letters, 42, 700\u2013707.","journal-title":"IEEE Robotics and Automation Letters"},{"key":"10099_CR25","doi-asserted-by":"crossref","unstructured":"Farhadi, A., Endres, I., Hoiem, D., & Forsyth, D. (2009). Describing objects by their attributes. In 2009 IEEE conference on computer vision and pattern recognition (pp. 1778\u20131785).","DOI":"10.1109\/CVPR.2009.5206772"},{"key":"10099_CR26","first-page":"433","volume":"20","author":"V Ferrari","year":"2007","unstructured":"Ferrari, V., & Zisserman, A. (2007). Learning visual attributes. Advances in Neural Information Processing Systems, 20, 433\u2013440.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10099_CR27","doi-asserted-by":"crossref","unstructured":"Galkin, M., Trivedi, P., Maheshwari, G., Usbeck, R., & Lehmann, J. (2020). Message passing for hyper-relational knowledge graphs. In Proceedings of the 2020 conference on empirical methods in natural language processing (EMNLP) (pp. 7346\u20137359).","DOI":"10.18653\/v1\/2020.emnlp-main.596"},{"key":"10099_CR28","doi-asserted-by":"crossref","unstructured":"Gandhi, D., Mulam, H., & Pinto, L. (2020). Swoosh! rattle! thump!\u2014actions that sound. In Proceedings of robotics: Science and systems.","DOI":"10.15607\/RSS.2020.XVI.002"},{"key":"10099_CR29","unstructured":"Gao, R., Chang, Y.-Y., Mall, S., Fei-Fei, L., & Wu, J. (2021). Objectfolder: A dataset of objects with implicit visual, auditory, and tactile representations."},{"key":"10099_CR30","doi-asserted-by":"crossref","unstructured":"Guan, S., Jin, X., Wang, Y., & Cheng, X. (2019). Link prediction on n-ARY relational data. In The world wide web conference (pp. 583\u2013593).","DOI":"10.1145\/3308558.3313414"},{"key":"10099_CR31","doi-asserted-by":"publisher","first-page":"12","DOI":"10.1016\/j.robot.2018.08.016","volume":"110","author":"M G\u00fcnther","year":"2018","unstructured":"G\u00fcnther, M., Ruiz-Sarmiento, J., Galindo, C., Gonzalez-Jimenez, J., & Hertzberg, J. (2018). Context-aware 3d object anchoring for mobile robots. Robotics and Autonomous Systems, 110, 12\u201332.","journal-title":"Robotics and Autonomous Systems"},{"key":"10099_CR32","unstructured":"Gupta, R., Kochenderfer, M. J., Mcguinness, D., & Ferguson, G. (2004). Common sense data acquisition for indoor mobile robots. In AAAI (pp. 605\u2013610)."},{"key":"10099_CR33","unstructured":"Hamp, B., & Feldweg, H. (1997). Germanet\u2014A lexical-semantic net for German. In Automatic information extraction and building of lexical semantic resources for NLP applications."},{"key":"10099_CR34","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 770\u2013778).","DOI":"10.1109\/CVPR.2016.90"},{"key":"10099_CR35","doi-asserted-by":"publisher","first-page":"879","DOI":"10.1177\/0278364919849091","volume":"38","author":"Y Huang","year":"2019","unstructured":"Huang, Y., & Sun, Y. (2019). A dataset of daily interactive manipulation. The International Journal of Robotics Research, 38, 879\u2013886.","journal-title":"The International Journal of Robotics Research"},{"key":"10099_CR36","unstructured":"Jain, A., Wojcik, B., Joachims, T., & Saxena, A. (2013). Learning trajectory preferences for manipulators via iterative improvement. In Advances in neural information processing systems (pp. 575\u2013583)."},{"key":"10099_CR37","unstructured":"Jenkins, P., Sachdeva, R., Kebe, G. Y., Higgins, P., Darvish, K., Raff, E., & Matuszek, C. (2020). Presentation and analysis of a multimodal dataset for grounded language learning. arXiv preprint arXiv:2007.14987."},{"key":"10099_CR38","doi-asserted-by":"publisher","first-page":"94","DOI":"10.1016\/j.eswa.2017.10.045","volume":"94","author":"E Kerr","year":"2018","unstructured":"Kerr, E., McGinnity, T. M., & Coleman, S. (2018). Material recognition using tactile sensing. Expert Systems with Applications, 94, 94\u2013111.","journal-title":"Expert Systems with Applications"},{"key":"10099_CR39","unstructured":"Kingma, D. P., & Ba, J. (2015). Adam: A method for stochastic optimization. In Y.\u00a0Bengio & Y.\u00a0LeCun (Eds.), 3rd international conference on learning representations, ICLR 2015, San Diego, CA, USA, May 7\u20139, 2015, conference track proceedings."},{"key":"10099_CR40","unstructured":"Kolve, E., Mottaghi, R., Gordon, D., Zhu, Y., Gupta, A., & Farhadi, A. (2017). Ai2-thor: An interactive 3d environment for visual AI. arXiv preprint arXiv:1712.05474."},{"key":"10099_CR41","doi-asserted-by":"crossref","unstructured":"Kunze, L., Burbridge, C., Alberti, M., Thippur, A., Folkesson, J., Jensfelt, P., & Hawes, N. (2014). Combining top-down spatial reasoning and bottom-up object class recognition for scene understanding. In 2014 IEEE\/RSJ international conference on intelligent robots and systems (pp. 2910\u20132915).","DOI":"10.1109\/IROS.2014.6942963"},{"key":"10099_CR42","doi-asserted-by":"publisher","first-page":"3465","DOI":"10.1109\/LRA.2018.2853639","volume":"34","author":"SR Lakani","year":"2018","unstructured":"Lakani, S. R., Rodr\u00edguez-S\u00e1nchez, A. J., & Piater, J. (2018). Exercising affordances of objects: A part-based approach. IEEE Robotics and Automation Letters, 34, 3465\u20133472.","journal-title":"IEEE Robotics and Automation Letters"},{"key":"10099_CR43","unstructured":"Lee, J., Lee, Y., Kim, J., Kosiorek, A., Choi, S., & Teh, Y. W. (2019). Set transformer: A framework for attention-based permutation-invariant neural networks. In International conference on machine learning (pp. 3744\u20133753)."},{"key":"10099_CR44","doi-asserted-by":"publisher","first-page":"45","DOI":"10.1016\/j.artint.2016.07.002","volume":"247","author":"S Lemaignan","year":"2017","unstructured":"Lemaignan, S., Warnier, M., Sisbot, E. A., Clodic, A., & Alami, R. (2017). Artificial cognition for social human-robot interaction: An implementation. Artificial Intelligence, 247, 45\u201369.","journal-title":"Artificial Intelligence"},{"issue":"11","key":"10099_CR45","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1145\/219717.219745","volume":"38","author":"DB Lenat","year":"1995","unstructured":"Lenat, D. B. (1995). Cyc: A large-scale investment in knowledge infrastructure. Communications of the ACM, 38(11), 33\u201338.","journal-title":"Communications of the ACM"},{"key":"10099_CR46","doi-asserted-by":"crossref","unstructured":"Levine, S., Pastor, P., Krizhevsky, A., & Quillen, D. (2016). Learning hand-eye coordination for robotic grasping with deep learning and large-scale data collection.","DOI":"10.1007\/978-3-319-50115-4_16"},{"issue":"6","key":"10099_CR47","doi-asserted-by":"publisher","first-page":"1619","DOI":"10.1109\/TRO.2020.3003230","volume":"36","author":"Q Li","year":"2020","unstructured":"Li, Q., Kroemer, O., Su, Z., Veiga, F. F., Kaboli, M., & Ritter, H. J. (2020). A review of tactile information: Perception and action through touch. IEEE Transactions on Robotics, 36(6), 1619\u20131634.","journal-title":"IEEE Transactions on Robotics"},{"issue":"3","key":"10099_CR48","doi-asserted-by":"publisher","first-page":"492","DOI":"10.1109\/TSMCA.2010.2076404","volume":"41","author":"GH Lim","year":"2011","unstructured":"Lim, G. H., Suh, I. H., & Suh, H. (2011). Ontology-based unified robot knowledge for service robots in indoor environments. IEEE Transactions on Systems, Man, and Cybernetics-Part A: Systems and Humans, 41(3), 492\u2013509.","journal-title":"IEEE Transactions on Systems, Man, and Cybernetics-Part A: Systems and Humans"},{"key":"10099_CR49","doi-asserted-by":"crossref","unstructured":"Liu, W., Bansal, D., Daruna, A., & Chernova, S. (2021). Learning instance-level N-Ary semantic knowledge at scale for robots operating in everyday environments. In Proceedings of robotics: Science and systems. Virtual.","DOI":"10.15607\/RSS.2021.XVII.035"},{"key":"10099_CR50","doi-asserted-by":"crossref","unstructured":"Liu, W., Daruna, A., & Chernova, S. (2020). Cage: Context-aware grasping engine. In International conference on robotics and automation (ICRA).","DOI":"10.1109\/ICRA40945.2020.9197289"},{"key":"10099_CR51","doi-asserted-by":"crossref","unstructured":"Liu, Y., Yao, Q., & Li, Y. (2020). Generalizing tensor decomposition for n-ARY relational knowledge bases. In Proceedings of the web conference 2020 (pp. 1104\u20131114).","DOI":"10.1145\/3366423.3380188"},{"issue":"4","key":"10099_CR52","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1023\/B:BTTJ.0000047600.45421.6d","volume":"22","author":"H Liu","year":"2004","unstructured":"Liu, H., & Singh, P. (2004). Conceptnet\u2014A practical commonsense reasoning tool-kit. BT Technology Journal, 22(4), 211\u2013226.","journal-title":"BT Technology Journal"},{"key":"10099_CR53","doi-asserted-by":"publisher","first-page":"54","DOI":"10.1016\/j.mechatronics.2017.11.002","volume":"48","author":"S Luo","year":"2017","unstructured":"Luo, S., Bimbo, J., Dahiya, R., & Liu, H. (2017). Robotic tactile perception of object properties: A review. Mechatronics, 48, 54\u201367.","journal-title":"Mechatronics"},{"issue":"2","key":"10099_CR54","doi-asserted-by":"publisher","first-page":"558","DOI":"10.3758\/BRM.41.2.558","volume":"41","author":"D Lynott","year":"2009","unstructured":"Lynott, D., & Connell, L. (2009). Modality exclusivity norms for 423 object properties. Behavior Research Methods, 41(2), 558\u2013564.","journal-title":"Behavior Research Methods"},{"issue":"11","key":"10099_CR55","doi-asserted-by":"publisher","first-page":"39","DOI":"10.1145\/219717.219748","volume":"38","author":"GA Miller","year":"1995","unstructured":"Miller, G. A. (1995). Wordnet: A lexical database for English. Communications of the ACM, 38(11), 39\u201341.","journal-title":"Communications of the ACM"},{"issue":"1\u20133","key":"10099_CR56","doi-asserted-by":"publisher","first-page":"281","DOI":"10.1177\/0278364915602060","volume":"35","author":"DK Misra","year":"2016","unstructured":"Misra, D. K., Sung, J., Lee, K., & Saxena, A. (2016). Tell me DAVE: Context-sensitive grounding of natural language to manipulation instructions. The International Journal of Robotics Research, 35(1\u20133), 281\u2013300.","journal-title":"The International Journal of Robotics Research"},{"key":"10099_CR57","doi-asserted-by":"crossref","unstructured":"Moldovan, B., & Raedt, L. D. (2014). Occluded object search by relational affordances. In IEEE international conference on robotics and automation (ICRA) (pp. 169\u2013174).","DOI":"10.1109\/ICRA.2014.6906605"},{"key":"10099_CR58","doi-asserted-by":"crossref","unstructured":"Nazarczuk, M., & Mikolajczyk, K. (2020). Shop-VRB: A visual reasoning benchmark for object perception. In 2020 IEEE international conference on robotics and automation (ICRA) (pp. 6898\u20136904).","DOI":"10.1109\/ICRA40945.2020.9197332"},{"issue":"1","key":"10099_CR59","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1109\/JPROC.2015.2483592","volume":"104","author":"M Nickel","year":"2015","unstructured":"Nickel, M., Murphy, K., Tresp, V., & Gabrilovich, E. (2015). A review of relational machine learning for knowledge graphs. Proceedings of the IEEE, 104(1), 11\u201333.","journal-title":"Proceedings of the IEEE"},{"key":"10099_CR60","doi-asserted-by":"crossref","unstructured":"Nyga, D., Balint-Benczedi, F., & Beetz, M. (2014). Pr2 looking at things\u2014Ensemble learning for unstructured information processing with Markov logic networks. In 2014 IEEE international conference on robotics and automation (ICRA) (pp. 3916\u20133923).","DOI":"10.1109\/ICRA.2014.6907427"},{"key":"10099_CR61","unstructured":"Nyga, D., Picklum, M., & Beetz, M., et al. (2013). Pracmln\u2014Markov logic networks in Python. Online Accessed 2022."},{"key":"10099_CR62","unstructured":"Nyga, D., Roy, S., Paul, R., Park, D., Pomarlan, M., Beetz, M., & Roy, N. (2018). Grounding robot plans from natural language instructions with incomplete world knowledge. In Conference on robot learning (pp. 714\u2013723)."},{"key":"10099_CR63","unstructured":"Pelikan, M., Goldberg, D.E., & Cant\u00fa-Paz, E., et al. (1999). Boa: The bayesian optimization algorithm. In Proceedings of the genetic and evolutionary computation conference GECCO-99 (Vol\u00a01, pp. 525\u2013532)."},{"issue":"1","key":"10099_CR64","doi-asserted-by":"publisher","first-page":"107","DOI":"10.1007\/s10994-006-5833-1","volume":"62","author":"M Richardson","year":"2006","unstructured":"Richardson, M., & Domingos, P. (2006). Markov logic networks. Machine Learning, 62(1), 107\u2013136.","journal-title":"Machine Learning"},{"key":"10099_CR65","doi-asserted-by":"crossref","unstructured":"Rosso, P., Yang, D., & Cudr\u00e9-Mauroux, P. (2020). Beyond triplets: Hyper-relational knowledge graph embedding for link prediction. In Proceedings of the web conference 2020 (pp. 1885\u20131896).","DOI":"10.1145\/3366423.3380257"},{"key":"10099_CR66","unstructured":"Saxena, A., Jain, A., Sener, O., Jami, A., Misra, D. K., & Koppula, H. S. (2014). Robobrain: Large-scale knowledge engine for robots. arXiv preprint arXiv:1412.0691."},{"key":"10099_CR67","doi-asserted-by":"crossref","unstructured":"She, Q., Feng, F., Hao, X., Yang, Q., Lan, C., & Lomonaco, V. (2020). Openloris-object: A robotic vision dataset and benchmark for lifelong deep learning. In 2020 IEEE international conference on robotics and automation (ICRA) (pp. 4767\u20134773).","DOI":"10.1109\/ICRA40945.2020.9196887"},{"key":"10099_CR68","doi-asserted-by":"crossref","unstructured":"Shridhar, M. , & Hsu, D. (2018). Interactive visual grounding of referring expressions for human\u2013robot interaction. In Proceedings of robotics: Science and systems.","DOI":"10.15607\/RSS.2018.XIV.028"},{"issue":"5","key":"10099_CR69","doi-asserted-by":"publisher","first-page":"632","DOI":"10.1016\/j.robot.2012.10.007","volume":"62","author":"J Sinapov","year":"2014","unstructured":"Sinapov, J., Schenck, C., Staley, K., Sukhoy, V., & Stoytchev, A. (2014). Grounding semantic categories in behavioral interactions: Experiments with 100 objects. Robotics and Autonomous Systems, 62(5), 632\u2013645.","journal-title":"Robotics and Autonomous Systems"},{"key":"10099_CR70","doi-asserted-by":"crossref","unstructured":"Singh, A., Sha, J., Narayan, K.S., Achim, T., & Abbeel, P. (2014). Bigbird: A large-scale 3d database of object instances. In 2014 IEEE international conference on robotics and automation (ICRA) (pp. 509\u2013516).","DOI":"10.1109\/ICRA.2014.6906903"},{"key":"10099_CR71","doi-asserted-by":"crossref","unstructured":"Sinha, K., Jia, R., Hupkes, D., Pineau, J., Williams, A., & Kiela, D. (2021). Masked language modeling and the distributional hypothesis: Order word matters pre-training for little. In Proceedings of the 2021 conference on empirical methods in natural language processing (pp. 2888\u20132913). Association for Computational Linguistics.","DOI":"10.18653\/v1\/2021.emnlp-main.230"},{"key":"10099_CR72","unstructured":"Snoek, J., Larochelle, H., & Adams, R. P. (2012). Practical bayesian optimization of machine learning algorithms. Advances in Neural Information Processing Systems, 25."},{"key":"10099_CR73","doi-asserted-by":"crossref","unstructured":"Sun, Y., Bo, L., & Fox, D. (2013). Attribute based object identification. In 2013 IEEE international conference on robotics and automation (pp. 2096\u20132103).","DOI":"10.1109\/ICRA.2013.6630858"},{"key":"10099_CR74","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., & Wojna, Z. (2016). Rethinking the inception architecture for computer vision. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 2818\u20132826).","DOI":"10.1109\/CVPR.2016.308"},{"key":"10099_CR75","doi-asserted-by":"crossref","unstructured":"Tatiya, G. , & Sinapov, J. (2019). Deep multi-sensory object category recognition using interactive behavioral exploration. In 2019 international conference on robotics and automation (ICRA) (pp. 7872\u20137878).","DOI":"10.1109\/ICRA.2019.8794095"},{"key":"10099_CR76","unstructured":"Tatsuma, A., Koyanagi, H., & Aono, M. (2012). A large-scale shape benchmark for 3d object retrieval: Toyohashi shape benchmark. In Proceedings of the 2012 Asia pacific signal and information processing association annual summit and conference (pp. 1-10)."},{"key":"10099_CR77","doi-asserted-by":"publisher","first-page":"151","DOI":"10.1016\/j.artint.2015.05.010","volume":"247","author":"M Tenorth","year":"2017","unstructured":"Tenorth, M., & Beetz, M. (2017). Representations for robot knowledge in the Knowrob framework. Artificial Intelligence, 247, 151\u2013169.","journal-title":"Artificial Intelligence"},{"key":"10099_CR78","doi-asserted-by":"crossref","unstructured":"Thomason, J., Sinapov, J., Mooney, R.J., & Stone, P. (2018). Guiding exploratory behaviors for multi-modal grounding of linguistic descriptions. In Thirty-second AAAI conference on artificial intelligence.","DOI":"10.1609\/aaai.v32i1.11966"},{"key":"10099_CR79","doi-asserted-by":"publisher","first-page":"87","DOI":"10.3389\/frobt.2021.476084","volume":"8","author":"M Thosar","year":"2021","unstructured":"Thosar, M., Mueller, C. A., J\u00e4ger, G., Schleiss, J., Pulugu, N., Mallikarjun Chennaboina, R., & Zug, S. (2021). From multi-modal property dataset to robot-centric conceptual knowledge about household objects. Frontiers in Robotics and AI, 8, 87.","journal-title":"Frontiers in Robotics and AI"},{"issue":"1","key":"10099_CR80","first-page":"7184","volume":"17","author":"B Uria","year":"2016","unstructured":"Uria, B., C\u00f4t\u00e9, M.-A., Gregor, K., Murray, I., & Larochelle, H. (2016). Neural autoregressive distribution estimation. The Journal of Machine Learning Research, 17(1), 7184\u20137220.","journal-title":"The Journal of Machine Learning Research"},{"key":"10099_CR81","doi-asserted-by":"crossref","unstructured":"Varadarajan, K. M. , & Vincze, M. (2013). Afnet: The affordance network. In K. M.\u00a0Lee, Y.\u00a0Matsushita, J. M.\u00a0Rehg, & Z.\u00a0Hu (Eds.), Computer vision\u2014ACCV 2012 (pp. 512\u2013523). Springer.","DOI":"10.1007\/978-3-642-37331-2_39"},{"key":"10099_CR82","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., & Polosukhin, I. (2017). Attention is all you need. In Advances in neural information processing systems (pp. 5998\u20136008)."},{"key":"10099_CR83","unstructured":"Wade-McCue, S., Kelly-Boxall, N., McTaggart, M., Morrison, D., Tow, A. W., Erskine, J., & Leitner, J. (2018). Design of a multi-modal end-effector and grasping system: How integrated design helped win the amazon robotics challenge."},{"key":"10099_CR84","unstructured":"Wang, Q., Huang, P., Wang, H., Dai, S., Jiang, W., Liu, J., & Wu, H. (2019). Coke: Contextualized knowledge graph embedding. arXiv preprint arXiv:1911.02168."},{"key":"10099_CR85","unstructured":"Watters, N., Matthey, L., Bosnjak, M., Burgess, C. P., & Lerchner, A. (2019). Cobra: Data-efficient model-based RL through unsupervised object discovery and curiosity-driven exploration."},{"key":"10099_CR86","unstructured":"Wen, J., Li, J., Mao, Y., Chen, S., & Zhang, R. (2016). On the representation and embedding of knowledge bases beyond binary relations. In IJCAI."},{"key":"10099_CR87","unstructured":"Wise, M., Ferguson, M., King, D., Diehr, E., & Dymesich, D. (2016). Fetch and freight: Standard platforms for service robot applications. In Workshop on autonomous mobile service robots."},{"key":"10099_CR88","doi-asserted-by":"crossref","unstructured":"Xu, P., Zhu, X., & Clifton, D. A. (2022). Multimodal learning with transformers: A survey.","DOI":"10.1109\/TPAMI.2023.3275156"},{"key":"10099_CR89","unstructured":"Yang, Z., Dai, Z., Yang, Y., Carbonell, J., Salakhutdinov, R. R., & Le, Q. V. (2019). Xlnet: Generalized autoregressive pretraining for language understanding. Advances in Neural Information Processing Systems, 32."},{"key":"10099_CR90","unstructured":"Yang, W., Wang, X., Farhadi, A., Gupta, A., & Mottaghi, R. (2019). Visual semantic navigation using scene priors. In Proceedings of seventh international conference on learning representations (ICLR 2019)."},{"key":"10099_CR91","unstructured":"Zeng, Z., R\u00f6fer, A., Lu, S., & Jenkins, O. C. (2019). Generalized object permanence for object retrieval through semantic linking maps. In IEEE ICRA 2019 workshop on high accuracy mobile manipulation in challenging environments."},{"key":"10099_CR92","doi-asserted-by":"crossref","unstructured":"Zhang, R., Li, J., Mei, J., & Mao, Y. (2018). Scalable instance reconstruction in knowledge bases via relatedness affiliated embedding. In Proceedings of the 2018 world wide web conference.","DOI":"10.1145\/3178876.3186017"},{"key":"10099_CR93","doi-asserted-by":"crossref","unstructured":"Zhang, H., Yang, D., Wang, H., Zhao, B., Lan, X., Ding, J., & Zheng, N. (2021). Regrad: A large-scale relational grasp dataset for safe and object-specific robotic grasping in clutter.","DOI":"10.1109\/LRA.2022.3142401"},{"key":"10099_CR94","doi-asserted-by":"crossref","unstructured":"Zhu, Y., Fathi, A., & Fei-Fei, L. (2014). Reasoning about object affordances in a knowledge base representation. In European conference on computer vision (pp. 408\u2013424).","DOI":"10.1007\/978-3-319-10605-2_27"}],"container-title":["Autonomous Robots"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10514-023-10099-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10514-023-10099-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10514-023-10099-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,6,30]],"date-time":"2023-06-30T19:06:00Z","timestamp":1688151960000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10514-023-10099-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,4,6]]},"references-count":94,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2023,6]]}},"alternative-id":["10099"],"URL":"https:\/\/doi.org\/10.1007\/s10514-023-10099-4","relation":{},"ISSN":["0929-5593","1573-7527"],"issn-type":[{"value":"0929-5593","type":"print"},{"value":"1573-7527","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,4,6]]},"assertion":[{"value":"17 June 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 February 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 April 2023","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors have no financial or proprietary interests in any material discussed in this article.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest:"}}]}}