{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,14]],"date-time":"2026-09-14T18:53:00Z","timestamp":1789411980210,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":74,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032375919","type":"print"},{"value":"9783032375926","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":[[2026]]},"DOI":"10.1007\/978-3-032-37592-6_18","type":"book-chapter","created":{"date-parts":[[2026,9,13]],"date-time":"2026-09-13T16:43:41Z","timestamp":1789317821000},"page":"314-333","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Towards Generalizable Robotic Manipulation in\u00a0Dynamic Environments"],"prefix":"10.1007","author":[{"given":"Heng","family":"Fang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shangru","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuhan","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xuanyang","family":"Xi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dingkang","family":"Liang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiang","family":"Bai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,14]]},"reference":[{"key":"18_CR1","unstructured":"Bai, S., et al.: Qwen3-VL technical report. arXiv preprint arXiv:2511.21631 (2025)"},{"key":"18_CR2","doi-asserted-by":"crossref","unstructured":"Belkhale, S., et al.: RT-H: action hierarchies using language. In: Proceedings of Robotics: Science and Systems (2024)","DOI":"10.15607\/RSS.2024.XX.049"},{"key":"18_CR3","unstructured":"Bjorck, J., et\u00a0al.: GR00T N1: an open foundation model for generalist humanoid robots. arXiv preprint arXiv:2503.14734 (2025)"},{"key":"18_CR4","unstructured":"Black, K., et\u00a0al.: $$\\pi _{0.5}$$: a vision-language-action model with open-world generalization. In: 9th Annual Conference on Robot Learning (2025)"},{"key":"18_CR5","doi-asserted-by":"crossref","unstructured":"Black, K., et al.: $$\\pi _{0}$$: a vision-language-action flow model for general robot control. In: Proceedings of Robotics: Science and Systems (2025)","DOI":"10.15607\/RSS.2025.XXI.010"},{"key":"18_CR6","unstructured":"Brohan, A., et al.: RT-1: robotics transformer for real-world control at scale. Robot.: Sci. Syst. XIX (2023)"},{"key":"18_CR7","unstructured":"Bu, Q., et\u00a0al.: AgiBot world colosseo: a large-scale manipulation platform for scalable and intelligent embodied systems. In: IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS) (2025)"},{"key":"18_CR8","doi-asserted-by":"crossref","unstructured":"Bu, Q., Yang, Y., Cai, J., Gao, S., Ren, G., Yao, M., Luo, P., Li, H.: UniVLA: learning to act anywhere with task-centric latent actions. In: Proceedings of Robotics: Science and Systems (2025)","DOI":"10.15607\/RSS.2025.XXI.014"},{"key":"18_CR9","unstructured":"Cen, J., et\u00a0al.: WorldVLA: towards autoregressive action world model. arXiv preprint arXiv:2506.21539 (2025)"},{"key":"18_CR10","unstructured":"Chen, T., et\u00a0al.: RobotWin 2.0: a scalable data generator and benchmark with strong domain randomization for robust bimanual robotic manipulation. arXiv preprint arXiv:2506.18088 (2025)"},{"key":"18_CR11","unstructured":"Community, S.: StarVLA: a lego-like codebase for vision-language-action model developing. arXiv preprint arXiv:2604.05014 (2026)"},{"key":"18_CR12","unstructured":"Contributors, I.M.: InternVLA-M1: a spatially guided vision-language-action framework for generalist robot policy. arXiv preprint arXiv:2510.13778 (2025)"},{"key":"18_CR13","unstructured":"Cui, C., et al.: OpenHelix: a short survey, empirical analysis, and open-source dual-system VLA model for robotic manipulation. arXiv preprint arXiv:2505.03912 (2025)"},{"key":"18_CR14","unstructured":"Driess, D., et al.: PaLM-E: an embodied multimodal language model. In: International Conference on Machine Learning, pp. 8469\u20138488. PMLR (2023)"},{"key":"18_CR15","doi-asserted-by":"crossref","unstructured":"Ehsani, K., et al.: Manipulathor: a framework for visual object manipulation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4497\u20134506 (2021)","DOI":"10.1109\/CVPR46437.2021.00447"},{"key":"18_CR16","unstructured":"Fan, C., et al.: Interleave-VLA: enhancing robot manipulation with interleaved image-text instructions. arXiv preprint arXiv:2505.02152 (2025)"},{"key":"18_CR17","doi-asserted-by":"crossref","unstructured":"Fu, H., et al.: Orion: a holistic end-to-end autonomous driving framework by vision-language instructed action generation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (2025)","DOI":"10.1109\/ICCV51701.2025.02302"},{"key":"18_CR18","doi-asserted-by":"crossref","unstructured":"Fu, H., et al.: MindDrive: a vision-language-action model for autonomous driving via online reinforcement learning. arXiv preprint arXiv:2512.13636 (2025)","DOI":"10.1007\/978-3-032-37026-6_28"},{"key":"18_CR19","unstructured":"Guan, Y., et al.: Video streaming thinking: videoLLMs can watch and think simultaneously. arXiv preprint arXiv:2603.12262 (2026)"},{"key":"18_CR20","doi-asserted-by":"crossref","unstructured":"James, S., Ma, Z., Rovick\u00a0Arrojo, D., Davison, A.J.: RLBench: the robot learning benchmark & learning environment. IEEE Robot. Autom. Lett. (2020)","DOI":"10.1109\/LRA.2020.2974707"},{"key":"18_CR21","unstructured":"Jang, H., Yu, S., Kwon, H., Jeon, H., Seo, Y., Shin, J.: ContextVLA: vision-language-action model with amortized multi-frame context. arXiv preprint arXiv:2510.04246 (2025)"},{"key":"18_CR22","unstructured":"Jiang, Y., et al.: VIMA: robot manipulation with multimodal prompts. In: International Conference on Machine Learning, pp. 14975\u201315022. PMLR (2023)"},{"key":"18_CR23","doi-asserted-by":"crossref","unstructured":"Jiang, Z., et al.: DexMimicGen: automated data generation for bimanual dexterous manipulation via imitation learning. In: 2025 IEEE International Conference on Robotics and Automation (ICRA), pp. 16923\u201316930. IEEE (2025)","DOI":"10.1109\/ICRA55743.2025.11127809"},{"issue":"1\u20132","key":"18_CR24","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1016\/S0004-3702(98)00023-X","volume":"101","author":"LP Kaelbling","year":"1998","unstructured":"Kaelbling, L.P., Littman, M.L., Cassandra, A.R.: Planning and acting in partially observable stochastic domains. Artif. Intell. 101(1\u20132), 99\u2013134 (1998)","journal-title":"Artif. Intell."},{"key":"18_CR25","unstructured":"Khazatsky, A., et al.: Droid: a large-scale in-the-wild robot manipulation dataset. In: Proceedings of Robotics: Science and Systems (2024)"},{"key":"18_CR26","doi-asserted-by":"crossref","unstructured":"Kim, M.J., Finn, C., Liang, P.: Fine-tuning vision-language-action models: optimizing speed and success. In: Proceedings of Robotics: Science and Systems (2025)","DOI":"10.15607\/RSS.2025.XXI.017"},{"key":"18_CR27","unstructured":"Kim, M.J., et\u00a0al.: OpenVLA: an open-source vision-language-action model. In: 8th Annual Conference on Robot Learning (2024)"},{"key":"18_CR28","unstructured":"Koo, M., et al.: Hamlet: switch your vision-language-action model into a history-aware policy. In: ICLR (2026)"},{"key":"18_CR29","unstructured":"Li, X., et al.: Evaluating real-world robot manipulation policies in simulation. In: Conference on Robot Learning (2024)"},{"key":"18_CR30","doi-asserted-by":"crossref","unstructured":"Liang, D., Feng, T., Zhou, X., Zhang, Y., Zou, Z., Bai, X.: Parameter-efficient fine-tuning in spectral domain for point cloud learning. IEEE Trans. Pattern Anal. Mach. Intell. (2025)","DOI":"10.1109\/TPAMI.2025.3594749"},{"key":"18_CR31","doi-asserted-by":"crossref","unstructured":"Liang, D., Zhang, C., Xu, X., Ju, J., Luo, Z., Bai, X.: Cook and clean together: teaching embodied agents for parallel task execution. In: Proceedings of the AAAI Conference on Artificial Intelligence (2026)","DOI":"10.1609\/aaai.v40i22.38906"},{"key":"18_CR32","unstructured":"Liang, D., et al.: UniFuture: a 4D driving world model for future generation and perception. In: IEEE International Conference on Robotics and Automation (2026)"},{"key":"18_CR33","doi-asserted-by":"crossref","unstructured":"Liang, D., et al.: PointMamba: a simple state space model for point cloud analysis. In: Advances in Neural Information Processing Systems (2024)","DOI":"10.52202\/079017-1026"},{"key":"18_CR34","unstructured":"Lin, M., et al.: HiF-VLA: hindsight, insight and foresight through motion representation for vision-language-action models. In: CVPR (2026)"},{"key":"18_CR35","doi-asserted-by":"publisher","first-page":"44776","DOI":"10.52202\/075280-1939","volume":"36","author":"B Liu","year":"2023","unstructured":"Liu, B., et al.: LIBERO: benchmarking knowledge transfer for lifelong robot learning. Adv. Neural. Inf. Process. Syst. 36, 44776\u201344791 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"18_CR36","doi-asserted-by":"crossref","unstructured":"Liu, C., et al.: TTF-VLA: temporal token fusion via pixel-attention integration for vision-language-action models. In: AAAI (2026)","DOI":"10.1609\/aaai.v40i22.38910"},{"key":"18_CR37","doi-asserted-by":"crossref","unstructured":"Liu, S., et\u00a0al.: Grounding DINO: marrying DINO with grounded pre-training for open-set object detection. In: ECCV (2024)","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"18_CR38","unstructured":"Liu, S., et al.: RDT-1B: a diffusion foundation model for bimanual manipulation. In: ICLR (2025)"},{"key":"18_CR39","unstructured":"Makoviychuk, V., et\u00a0al.: Isaac gym: high performance GPU based physics simulation for robot learning. In: Thirty-Fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 2) (2021)"},{"issue":"3","key":"18_CR40","doi-asserted-by":"publisher","first-page":"7327","DOI":"10.1109\/LRA.2022.3180108","volume":"7","author":"O Mees","year":"2022","unstructured":"Mees, O., Hermann, L., Rosete-Beas, E., Burgard, W.: CALVIN: a benchmark for language-conditioned policy learning for long-horizon robot manipulation tasks. IEEE Robot. Autom. Lett. 7(3), 7327\u20137334 (2022)","journal-title":"IEEE Robot. Autom. Lett."},{"key":"18_CR41","unstructured":"Mu, T., et al.: ManiSkill: generalizable manipulation skill benchmark with large-scale demonstrations. In: Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 2) (2021)"},{"key":"18_CR42","doi-asserted-by":"crossref","unstructured":"Nasiriany, S., et al.: RoboCasa: large-scale simulation of everyday tasks for generalist robots. In: Proceedings of Robotics: Science and Systems (2024)","DOI":"10.15607\/RSS.2024.XX.050"},{"key":"18_CR43","unstructured":"O\u2019Neill, A., et\u00a0al.: Open X-embodiment: robotic learning datasets and RT-X models: open X-embodiment collaboration 0, pp. 6892\u20136903. IEEE (2024)"},{"issue":"Suppl 1","key":"18_CR44","doi-asserted-by":"publisher","first-page":"S72","DOI":"10.3103\/S1060992X25601654","volume":"34","author":"MA Patratskiy","year":"2025","unstructured":"Patratskiy, M.A., Kovalev, A.K., Panov, A.I.: Spatial traces: enhancing VLA models with spatial-temporal understanding. Opt. Mem. Neural Netw. 34(Suppl 1), S72\u2013S82 (2025)","journal-title":"Opt. Mem. Neural Netw."},{"key":"18_CR45","doi-asserted-by":"crossref","unstructured":"Pertsch, K., et al.: FAST: efficient action tokenization for vision-language-action models. In: Proceedings of Robotics: Science and Systems (2025)","DOI":"10.15607\/RSS.2025.XXI.012"},{"key":"18_CR46","unstructured":"Puig, X., et al.: Habitat 3.0: a co-habitat for humans, avatars and robots. In: ICLR (2024)"},{"key":"18_CR47","doi-asserted-by":"crossref","unstructured":"Pumacay, W., Singh, I., Duan, J., Krishna, R., Thomason, J., Fox, D.: The colosseum: a benchmark for evaluating generalization for robotic manipulation. In: Proceedings of Robotics: Science and Systems (2024)","DOI":"10.15607\/RSS.2024.XX.133"},{"key":"18_CR48","unstructured":"Qiu, W., Huang, T., Feng, A., Ying, R.: Efficient long-horizon vision-language-action models via static-dynamic disentanglement. arXiv preprint (2026). arXiv:2602.03983"},{"key":"18_CR49","unstructured":"Ravi, N., et al.: SAM 2: segment anything in images and videos. In: ICLR (2025)"},{"key":"18_CR50","unstructured":"Reed, S., et\u00a0al.: A generalist agent. Trans. Mach. Learn. Res. (2022)"},{"key":"18_CR51","unstructured":"Ren, T., et al.: Grounded SAM: assembling open-world models for diverse visual tasks (2024)"},{"key":"18_CR52","unstructured":"Shi, H., et al.: MemoryVLA: perceptual-cognitive memory in vision-language-action models for robotic manipulation. In: ICLR (2026)"},{"key":"18_CR53","unstructured":"Shridhar, M., Manuelli, L., Fox, D.: CLIPort: what and where pathways for robotic manipulation. In: Conference on robot learning, pp. 894\u2013906. PMLR (2022)"},{"key":"18_CR54","doi-asserted-by":"crossref","unstructured":"Song, W., et al.: ReconVLA: reconstructive vision-language-action model as effective robot perceiver. In: AAAI (2026)","DOI":"10.1609\/aaai.v40i22.38921"},{"key":"18_CR55","unstructured":"Team, O.M., et al.: Octo: an open-source generalist robot policy. In: Proceedings of Robotics: Science and Systems (2024)"},{"key":"18_CR56","unstructured":"Walke, H.R., et al.: BridgeData v2: a dataset for robot learning at scale. In: Conference on Robot Learning, pp. 1723\u20131736. PMLR (2023)"},{"key":"18_CR57","doi-asserted-by":"crossref","unstructured":"Wang, Y., et al.: VLA-adapter: an effective paradigm for tiny-scale vision-language-action model. In: AAAI (2026)","DOI":"10.1609\/aaai.v40i22.38931"},{"key":"18_CR58","doi-asserted-by":"crossref","unstructured":"Wang, Y., Yue, Z., Zeng, H., Wang, D., McAuley, J.: Train once, deploy anywhere: matryoshka representation learning for multimodal recommendation. In: Findings of the Association for Computational Linguistics: EMNLP 2024, pp. 13461\u201313472 (2024)","DOI":"10.18653\/v1\/2024.findings-emnlp.786"},{"key":"18_CR59","doi-asserted-by":"crossref","unstructured":"Wu, K., et\u00a0al.: RoboMind: benchmark on multi-embodiment intelligence normative data for robot manipulation. In: Proceedings of Robotics: Science and Systems (2025)","DOI":"10.15607\/RSS.2025.XXI.152"},{"key":"18_CR60","unstructured":"Wu, X., et al.: Generation models know space: unleashing implicit 3D priors for scene understanding. arXiv preprint arXiv:2603.19235 (2026)"},{"key":"18_CR61","doi-asserted-by":"crossref","unstructured":"Xiang, F., et al.: SAPIEN: a simulated part-based interactive environment. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2020)","DOI":"10.1109\/CVPR42600.2020.01111"},{"key":"18_CR62","unstructured":"Yakefu, A., et\u00a0al.: RoboChallenge: large-scale real-robot evaluation of embodied policies. arXiv preprint arXiv:2510.17950 (2025)"},{"key":"18_CR63","unstructured":"Ye, J., et al.: Dream-VL & dream-VLA: open vision-language and vision-language-action models with diffusion language model backbone. arXiv preprint arXiv:2512.22615 (2025)"},{"key":"18_CR64","unstructured":"Yu, T., et al.: Meta-world: a benchmark and evaluation for multi-task and meta reinforcement learning. In: Conference on Robot Learning, pp. 1094\u20131100. PMLR (2020)"},{"key":"18_CR65","doi-asserted-by":"crossref","unstructured":"Zhang, J., et al.: NaVid: video-based VLM plans the next step for vision-and-language navigation. In: Proceedings of Robotics: Science and Systems (2024)","DOI":"10.15607\/RSS.2024.XX.079"},{"key":"18_CR66","doi-asserted-by":"crossref","unstructured":"Zhang, S., et al.: VLABench: a large-scale benchmark for language-conditioned robotics manipulation with long-horizon reasoning tasks. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 11142\u201311152 (2025)","DOI":"10.1109\/ICCV51701.2025.01037"},{"key":"18_CR67","doi-asserted-by":"crossref","unstructured":"Zhang, W., et\u00a0al.: DreamVLA: a vision-language-action model dreamed with comprehensive world knowledge. In: NeurIPS (2025)","DOI":"10.52202\/085713-0818"},{"key":"18_CR68","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Wang, R., Chen, X.: Dynamic behavior cloning with temporal feature prediction: enhancing robotic arm manipulation in moving object tasks. IEEE Robot. Autom. Lett. (2025)","DOI":"10.1109\/LRA.2025.3557746"},{"key":"18_CR69","doi-asserted-by":"crossref","unstructured":"Zhao, T., Kumar, V., Levine, S., Finn, C.: Learning fine-grained bimanual manipulation with low-cost hardware. Robot.: Sci. Syst. XIX (2023)","DOI":"10.15607\/RSS.2023.XIX.016"},{"key":"18_CR70","unstructured":"Zheng, R., et al.: TraceVLA: visual trace prompting enhances spatial-temporal awareness for generalist robotic policies. In: ICLR (2025)"},{"key":"18_CR71","doi-asserted-by":"crossref","unstructured":"Zhou, X., et al.: Hermes++: toward a unified driving world model for 3D scene understanding and generation. arXiv preprint arXiv:2604.28196 (2026)","DOI":"10.1109\/ICCV51701.2025.02582"},{"key":"18_CR72","doi-asserted-by":"crossref","unstructured":"Zhou, X., et al.: Hermes: a unified self-driving world model for simultaneous 3D scene understanding and generation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (2025)","DOI":"10.1109\/ICCV51701.2025.02582"},{"key":"18_CR73","unstructured":"Zhu, Y., et al.: robosuite: a modular simulation framework and benchmark for robot learning. arXiv preprint arXiv:2009.12293 (2020)"},{"key":"18_CR74","unstructured":"Zitkovich, B., et\u00a0al.: RT-2: vision-language-action models transfer web knowledge to robotic control. In: Conference on Robot Learning, pp. 2165\u20132183. PMLR (2023)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2026"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-37592-6_18","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,13]],"date-time":"2026-09-13T16:43:54Z","timestamp":1789317834000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37592-6_18"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032375919","9783032375926"],"references-count":74,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37592-6_18","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"14 September 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Malm\u00f6","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Sweden","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 September 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 September 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}