{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,5]],"date-time":"2026-08-05T01:43:54Z","timestamp":1785894234008,"version":"3.56.0"},"reference-count":44,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100006469","name":"Fund for the Development of Science and Technology","doi-asserted-by":"publisher","award":["0057\/2024\/RIB1"],"award-info":[{"award-number":["0057\/2024\/RIB1"]}],"id":[{"id":"10.13039\/501100006469","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Knowledge-Based Systems"],"published-print":{"date-parts":[[2026,9]]},"DOI":"10.1016\/j.knosys.2026.116478","type":"journal-article","created":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T06:49:44Z","timestamp":1781851784000},"page":"116478","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Multi-scale semantics meet SE(3) geometry: A sequence-aware hierarchical VLA for long-horizon manipulation"],"prefix":"10.1016","volume":"349","author":[{"given":"Zhitao","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiangtao","family":"Wen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Roberto","family":"Horowitz","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1740-5269","authenticated-orcid":false,"given":"Yanke","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3553-6764","authenticated-orcid":false,"given":"Yuxing","family":"Han","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.knosys.2026.116478_b1","doi-asserted-by":"crossref","first-page":"113","DOI":"10.1016\/j.autcon.2015.07.022","article-title":"The future of construction automation: Technological disruption and the upcoming ubiquitous transformation","volume":"59","author":"Bock","year":"2015","journal-title":"Autom. Constr."},{"key":"10.1016\/j.knosys.2026.116478_b2","doi-asserted-by":"crossref","unstructured":"R.A. Knepper, T. Layton, J. Romanishin, D. Rus, Ikeabot: An autonomous multi-robot coordinated furniture assembly system, in: Proc. IEEE Int. Conf. Robot. Autom., ICRA, 2013, pp. 855\u2013862.","DOI":"10.1109\/ICRA.2013.6630673"},{"key":"10.1016\/j.knosys.2026.116478_b3","doi-asserted-by":"crossref","first-page":"7134","DOI":"10.1109\/ACCESS.2024.3350773","article-title":"A review of computer vision-based monitoring approaches for construction workers\u2019 work-related behaviors","volume":"12","author":"Li","year":"2024","journal-title":"IEEE Access"},{"key":"10.1016\/j.knosys.2026.116478_b4","doi-asserted-by":"crossref","first-page":"128","DOI":"10.1016\/j.autcon.2015.06.002","article-title":"Vision guided autonomous robotic assembly and as-built scanning on unstructured construction sites","volume":"59","author":"Feng","year":"2015","journal-title":"Autom. Constr."},{"issue":"3","key":"10.1016\/j.knosys.2026.116478_b5","first-page":"589","article-title":"Cognitive reasoning for compliant robot manipulation","volume":"35","author":"Leidner","year":"2019","journal-title":"IEEE Trans. Robot."},{"issue":"6","key":"10.1016\/j.knosys.2026.116478_b6","doi-asserted-by":"crossref","DOI":"10.1061\/(ASCE)CP.1943-5487.0000408","article-title":"Motion planning and coordination for mobile construction machinery","volume":"29","author":"Lin","year":"2015","journal-title":"J. Comput. Civ. Eng."},{"key":"10.1016\/j.knosys.2026.116478_b7","unstructured":"D. Kalashnikov, et al., QT-Opt: Scalable deep reinforcement learning for vision-based robotic manipulation, in: Proc. Conf. Robot Learn. (CoRL), 2018, pp. 651\u2013673."},{"key":"10.1016\/j.knosys.2026.116478_b8","unstructured":"A. Brohan, et al., RT-1: Robotics transformer for real-world control at scale, in: Proc. Robot.: Sci. Syst., RSS, 2023."},{"key":"10.1016\/j.knosys.2026.116478_b9","unstructured":"D. Driess, et al., PaLM-E: An embodied multimodal language model, in: Proc. Int. Conf. Mach. Learn., ICML, 2023."},{"key":"10.1016\/j.knosys.2026.116478_b10","unstructured":"E. Jang, et al., BC-Z: Zero-shot task generalization with robotic imitation learning, in: Proc. Conf. Robot Learn. (CoRL), 2022."},{"key":"10.1016\/j.knosys.2026.116478_b11","unstructured":"T. Cohen, M. Welling, Group equivariant convolutional networks, in: Proc. Int. Conf. Mach. Learn., ICML, 2016."},{"key":"10.1016\/j.knosys.2026.116478_b12","unstructured":"H. Ryu, H.-i. Lee, J.-H. Lee, J. Choi, Equivariant descriptor fields: SE(3)-equivariant energy-based models for end-to-end visual robotic manipulation learning, in: Proc. Int. Conf. Learn. Represent., ICLR, 2023."},{"key":"10.1016\/j.knosys.2026.116478_b13","series-title":"Proc. IEEE Int. Conf. Autom. Sci. Eng.","first-page":"3164","article-title":"Hybrid perception and equivariant diffusion for robust multi-node rebar tying","author":"Wang","year":"2025"},{"key":"10.1016\/j.knosys.2026.116478_b14","doi-asserted-by":"crossref","unstructured":"H. Ryu, et al., Diffusion-EDFs: Bi-equivariant denoising generative modeling on SE(3) for visual robotic manipulation, in: Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit., CVPR, 2024.","DOI":"10.1109\/CVPR52733.2024.01705"},{"key":"10.1016\/j.knosys.2026.116478_b15","unstructured":"C. Tie, Y. Chen, R. Wu, B. Dong, Z. Li, C. Gao, H. Dong, ET-SEED: Efficient trajectory-level SE(3) equivariant diffusion policy, in: Proc. Int. Conf. Learn. Represent., ICLR, 2025."},{"key":"10.1016\/j.knosys.2026.116478_b16","unstructured":"T.-W. Ke, N. Gkanatsios, K. Fragkiadaki, 3D diffuser actor: Policy diffusion with 3D scene representations, in: Proc. Conf. Robot Learn. (CoRL), 2024."},{"key":"10.1016\/j.knosys.2026.116478_b17","unstructured":"M. Shridhar, L. Manuelli, D. Fox, Perceiver-actor: A multi-task transformer for robotic manipulation, in: Proc. Conf. Robot Learn. (CoRL), 2022."},{"key":"10.1016\/j.knosys.2026.116478_b18","unstructured":"W. Huang, et al., VoxPoser: Composable 3D value maps for robotic manipulation with language models, in: Proc. Conf. Robot Learn. (CoRL), 2023."},{"key":"10.1016\/j.knosys.2026.116478_b19","series-title":"Open X-Embodiment: Robotic learning datasets and RT-x models","author":"Padalkar","year":"2023"},{"key":"10.1016\/j.knosys.2026.116478_b20","series-title":"Openvla: An open-source vision-language-action model","author":"Kim","year":"2024"},{"key":"10.1016\/j.knosys.2026.116478_b21","unstructured":"M. Shridhar, L. Manuelli, D. Fox, CLIPort: What and where pathways for robotic manipulation, in: Proc. Conf. Robot Learn. (CoRL), 2022."},{"key":"10.1016\/j.knosys.2026.116478_b22","unstructured":"M. Ahn, et al., Do as I can, not as I say: Grounding language in robotic affordances, in: Proc. Conf. Robot Learn. (CoRL), 2022."},{"issue":"4","key":"10.1016\/j.knosys.2026.116478_b23","doi-asserted-by":"crossref","first-page":"11205","DOI":"10.1109\/LRA.2022.3196123","article-title":"What matters in language conditioned robotic imitation learning over unstructured data","volume":"7","author":"Mees","year":"2022","journal-title":"IEEE Robot. Autom. Lett."},{"key":"10.1016\/j.knosys.2026.116478_b24","unstructured":"S. Stepputtis, et al., Language-conditioned imitation learning for robot manipulation tasks, in: Proc. Adv. Neural Inf. Process. Syst. (NeurIPS), 2020."},{"key":"10.1016\/j.knosys.2026.116478_b25","unstructured":"T. Gervet, Z. Xian, N. Gkanatsios, K. Fragkiadaki, Act3D: 3D feature field transformers for multi-task robotic manipulation, in: Proc. Conf. Robot Learn. (CoRL), 2023."},{"key":"10.1016\/j.knosys.2026.116478_b26","doi-asserted-by":"crossref","unstructured":"Y. Ze, G. Zhang, K. Zhang, C. Hu, M. Wang, H. Xu, 3D diffusion policy: Generalizable visuomotor policy learning via simple 3D representations, in: Proc. Robot.: Sci. Syst., RSS, 2024.","DOI":"10.15607\/RSS.2024.XX.067"},{"key":"10.1016\/j.knosys.2026.116478_b27","doi-asserted-by":"crossref","unstructured":"C. Lynch, P. Sermanet, Language conditioned imitation learning over unstructured data, in: Proc. Robot.: Sci. Syst., RSS, 2021.","DOI":"10.15607\/RSS.2021.XVII.047"},{"key":"10.1016\/j.knosys.2026.116478_b28","unstructured":"P. Florence, et al., Implicit behavioral cloning, in: Proc. Conf. Robot Learn. (CoRL), 2022."},{"key":"10.1016\/j.knosys.2026.116478_b29","unstructured":"A. Xie, et al., Language-conditioned path planning, in: Proc. Conf. Robot Learn. (CoRL), 2023."},{"key":"10.1016\/j.knosys.2026.116478_b30","doi-asserted-by":"crossref","unstructured":"C. Chi, S. Feng, Y. Du, Z. Xu, E. Cousineau, B. Burchfiel, S. Song, Diffusion policy: Visuomotor policy learning via action diffusion, in: Proc. Robot.: Sci. Syst., RSS, 2023.","DOI":"10.15607\/RSS.2023.XIX.026"},{"key":"10.1016\/j.knosys.2026.116478_b31","series-title":"Mobile ALOHA: Learning bimanual mobile manipulation with low-cost whole-body teleoperation","author":"Zhao","year":"2024"},{"key":"10.1016\/j.knosys.2026.116478_b32","series-title":"Advances in Neural Information Processing Systems (NeurIPS)","first-page":"15084","article-title":"Decision transformer: Reinforcement learning via sequence modeling","volume":"vol. 34","author":"Chen","year":"2021"},{"key":"10.1016\/j.knosys.2026.116478_b33","unstructured":"M. Janner, Y. Du, J.B. Tenenbaum, S. Levine, Planning with Diffusion for Flexible Behavior Synthesis, in: International Conference on Machine Learning, ICML, 2022, pp. 9902\u20139915."},{"key":"10.1016\/j.knosys.2026.116478_b34","unstructured":"A. Gupta, et al., Relay policy learning: Solving long-horizon tasks via imitation and reinforcement learning, in: Proc. Conf. Robot Learn. (CoRL), 2019."},{"key":"10.1016\/j.knosys.2026.116478_b35","unstructured":"K. Pertsch, Y. Lee, J.J. Lim, Accelerating reinforcement learning with learned skill priors, in: Proc. Conf. Robot Learn. (CoRL), 2020."},{"key":"10.1016\/j.knosys.2026.116478_b36","doi-asserted-by":"crossref","unstructured":"J. Liang, et al., Code as policies: Language model programs for embodied control, in: Proc. IEEE Int. Conf. Robot. Autom., ICRA, 2023.","DOI":"10.1109\/ICRA48891.2023.10160591"},{"key":"10.1016\/j.knosys.2026.116478_b37","series-title":"Proc. IEEE Int. Conf. Robot. Autom.","first-page":"10462","article-title":"Open X-Embodiment: Robotic learning datasets and RT-X models","author":"Padalkar","year":"2024"},{"key":"10.1016\/j.knosys.2026.116478_b38","doi-asserted-by":"crossref","unstructured":"A. Simeonov, et al., Neural descriptor fields: SE(3)-equivariant object representations for manipulation, in: Proc. IEEE Int. Conf. Robot. Autom., ICRA, 2022.","DOI":"10.1109\/ICRA46639.2022.9812146"},{"key":"10.1016\/j.knosys.2026.116478_b39","series-title":"The Eleventh International Conference on Learning Representations","article-title":"Equiformer: Equivariant graph attention transformer for 3D atomistic graphs","author":"Liao","year":"2023"},{"key":"10.1016\/j.knosys.2026.116478_b40","unstructured":"Y.-L. Liao, T. Smidt, EquiformerV2: Improved Equivariant Transformer for Scaling to Higher-Degree Representations, in: The Twelfth International Conference on Learning Representations, ICLR, 2024."},{"key":"10.1016\/j.knosys.2026.116478_b41","unstructured":"Y. Song, J. Sohl-Dickstein, D.P. Kingma, A. Kumar, S. Ermon, B. Poole, Score-Based Generative Modeling through Stochastic Differential Equations, in: International Conference on Learning Representations, ICLR, 2021."},{"key":"10.1016\/j.knosys.2026.116478_b42","unstructured":"E.J. Smith, et al., SE(3)-equivariant relational rearrangement with neural descriptor fields, in: Proc. Conf. Robot Learn. (CoRL), 2023."},{"issue":"4","key":"10.1016\/j.knosys.2026.116478_b43","first-page":"5138","article-title":"GeoTransformer: Fast and robust point cloud registration with geometric transformer","volume":"45","author":"Qin","year":"2023","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.knosys.2026.116478_b44","series-title":"International Conference on Machine Learning","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021"}],"container-title":["Knowledge-Based Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0950705126012049?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0950705126012049?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,8,5]],"date-time":"2026-08-05T00:45:08Z","timestamp":1785890708000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0950705126012049"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9]]},"references-count":44,"alternative-id":["S0950705126012049"],"URL":"https:\/\/doi.org\/10.1016\/j.knosys.2026.116478","relation":{},"ISSN":["0950-7051"],"issn-type":[{"value":"0950-7051","type":"print"}],"subject":[],"published":{"date-parts":[[2026,9]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Multi-scale semantics meet SE(3) geometry: A sequence-aware hierarchical VLA for long-horizon manipulation","name":"articletitle","label":"Article Title"},{"value":"Knowledge-Based Systems","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.knosys.2026.116478","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"116478"}}