{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T05:18:56Z","timestamp":1788239936717,"version":"build-2803163510"},"reference-count":58,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"\u201cMobile Information Networks-National Science and Technology Major Project\u201d","award":["2025ZD1303100"],"award-info":[{"award-number":["2025ZD1303100"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Automat. Sci. Eng."],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tase.2026.3724338","type":"journal-article","created":{"date-parts":[[2026,8,17]],"date-time":"2026-08-17T19:12:37Z","timestamp":1786993957000},"page":"15065-15080","source":"Crossref","is-referenced-by-count":0,"title":["PointLIBERO: Unlocking Spatial Awareness in VLAs With a Novel 3-D Dataset and a Lightweight Framework"],"prefix":"10.1109","volume":"23","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-3630-6208","authenticated-orcid":false,"given":"Meng","family":"Li","sequence":"first","affiliation":[{"name":"Beihang University","place":["Beijing, China"],"department":["Department of Electronics and Information Engineering"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7732-3527","authenticated-orcid":false,"given":"Lijiang","family":"Chen","sequence":"additional","affiliation":[{"name":"Beihang University","place":["Beijing, China"],"department":["Department of Electronics and Information Engineering"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3508-027X","authenticated-orcid":false,"given":"Qi","family":"Zhao","sequence":"additional","affiliation":[{"name":"Beihang University","place":["Beijing, China"],"department":["Department of Electronics and Information Engineering"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-6099-5844","authenticated-orcid":false,"given":"Jun","family":"Jiang","sequence":"additional","affiliation":[{"name":"Pengcheng Laboratory","place":["Shenzhen, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Longhao","family":"Zou","sequence":"additional","affiliation":[{"name":"Pengcheng Laboratory","place":["Shenzhen, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mingcheng","family":"Luo","sequence":"additional","affiliation":[{"name":"Pengcheng Laboratory","place":["Shenzhen, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9769-7083","authenticated-orcid":false,"given":"Shuchang","family":"Lyu","sequence":"additional","affiliation":[{"name":"Beihang University","place":["Beijing, China"],"department":["Department of Electronics and Information Engineering"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9610-8782","authenticated-orcid":false,"given":"Dingding","family":"Yao","sequence":"additional","affiliation":[{"name":"Institute of Acoustics, Chinese Academy of Sciences","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8686-9513","authenticated-orcid":false,"given":"Guangliang","family":"Cheng","sequence":"additional","affiliation":[{"name":"University of Liverpool","place":["Liverpool, U.K."],"department":["Department of Computer Science"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5255-5559","authenticated-orcid":false,"given":"Chenguang","family":"Yang","sequence":"additional","affiliation":[{"name":"The Hong Kong Polytechnic University","place":["Hong Kong, China"],"department":["Department of Computing"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2023.xix.025"},{"key":"ref2","first-page":"2165","article-title":"RT-2: Vision-language-action models transfer web knowledge to robotic control","volume-title":"Proc. Conf. Robot Learn. (CoRL)","author":"Brohan"},{"key":"ref3","first-page":"8469","article-title":"PaLM-E: An embodied multimodal language model","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Driess"},{"key":"ref4","first-page":"1","article-title":"Open X-embodiment: Robotic learning datasets and RT-X models","volume-title":"Proc. IEEE Int. Conf. Robot. Autom. (ICRA)","author":"Padalkar"},{"key":"ref5","first-page":"1723","article-title":"BridgeData v2: A dataset for robot learning at scale","volume-title":"Proc. Conf. Robot Learn. (CoRL)","author":"Walke"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2024.xx.120"},{"key":"ref7","first-page":"2679","article-title":"OpenVLA: An open-source vision-language-action model","volume-title":"Proc. Conf. Robot Learn. (CoRL)","author":"Kim"},{"key":"ref8","article-title":"DexVLA: Vision-language model with plug-in diffusion expert for general robot control","volume-title":"Proc. Conf. Robot Learn. (CoRL)","author":"Wen"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2025.xxi.010"},{"key":"ref10","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"139","author":"Radford"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"ref12","article-title":"LLaMA: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv:2302.13971"},{"key":"ref13","article-title":"Qwen2-VL: Enhancing vision-language Model\u2019s perception of the world at any resolution","author":"Wang","year":"2024","journal-title":"arXiv:2409.12191"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2025.xxi.011"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2473"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.067"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1554"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2026.3653303"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2025.XXI.021"},{"key":"ref20","article-title":"RoboCasa: Large-scale simulation of everyday tasks for generalist robots","volume-title":"Proc. Robot., Sci. Syst. Workshop","author":"Nasiriany"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02558"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1939"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref24","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Hu"},{"key":"ref25","first-page":"5099","article-title":"PointNet++: Deep hierarchical feature learning on point sets in a metric space","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Qi"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525087"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00966"},{"key":"ref28","article-title":"LLaMA-adapter: Efficient fine-tuning of language models with zero-init attention","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Zhang"},{"key":"ref29","article-title":"GPT-4 technical report","volume-title":"arXiv:2303.08774","author":"Achiam","year":"2023"},{"key":"ref30","article-title":"Octo: An open-source generalist robot policy","volume-title":"Proc. Robot., Sci. Syst. (RSS)","author":"Team"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1266"},{"key":"ref32","article-title":"Efficiently modeling long sequences with structured state spaces","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Gu"},{"key":"ref33","article-title":"Vision-language foundation models as effective robot imitators","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Li"},{"key":"ref34","first-page":"14975","article-title":"VIMA: General robot manipulation with multimodal prompts","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Jiang"},{"key":"ref35","first-page":"37321","article-title":"PIVOT: Iterative visual prompting elicits actionable knowledge for VLMs","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Campos"},{"key":"ref36","article-title":"RDT-1B: A diffusion foundation model for bimanual manipulation","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Liu"},{"key":"ref37","article-title":"GR-2: A generative video-language-action model with web-scale knowledge for robot manipulation","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Wang"},{"key":"ref38","first-page":"2828","article-title":"HumanPlus: Humanoid shadowing and imitation from humans","volume-title":"Proc. Conf. Robot Learn. (CoRL)","author":"Li"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01710"},{"key":"ref40","first-page":"2344","article-title":"3DS-VLA: A 3D spatial-aware vision language action model for robust multi-task manipulation","volume-title":"Proc. Conf. Robot Learn. (CoRL)","author":"Li"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01617"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01871"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20086-1_35"},{"key":"ref44","first-page":"785","article-title":"Perceiver-actor: A multi-task transformer for robotic manipulation","volume-title":"Proc. Conf. Robot Learn. (CoRL)","author":"Shridhar"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00084"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611615"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2025.3581422"},{"key":"ref48","article-title":"The midas touch for metric depth","volume-title":"arXiv:2605.11578","author":"Ma"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2025.3586286"},{"key":"ref50","first-page":"540","article-title":"VoxPoser: Composable 3D value maps for robotic manipulation with language models","volume-title":"Proc. Conf. Robot Learn. (CoRL)","author":"Huang"},{"key":"ref51","first-page":"61229","article-title":"3D-VLA: A 3D vision-language-action generative world model","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Zhen"},{"key":"ref52","article-title":"Point-bind & point-LLM: Aligning point cloud with multi-modality for 3D understanding, generation, and instruction following","author":"Guo","year":"2023","journal-title":"arXiv:2309.00615"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.emnlp-main.273"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00625"},{"key":"ref55","article-title":"Sparse4D v3: Advancing end-to-end 3D detection and tracking","author":"Lin","year":"2023","journal-title":"arXiv:2311.11722"},{"key":"ref56","article-title":"Uni3D: Exploring unified 3D representation at scale","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Zhou"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01595"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2415"}],"container-title":["IEEE Transactions on Automation Science and Engineering"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/8856\/11323516\/11657410.pdf?arnumber=11657410","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T04:59:36Z","timestamp":1788238776000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11657410\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":58,"URL":"https:\/\/doi.org\/10.1109\/tase.2026.3724338","relation":{},"ISSN":["1545-5955","1558-3783"],"issn-type":[{"value":"1545-5955","type":"print"},{"value":"1558-3783","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}