{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T13:08:39Z","timestamp":1788959319398,"version":"build-2803163510"},"reference-count":44,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T00:00:00Z","timestamp":1784160000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T00:00:00Z","timestamp":1788912000000},"content-version":"vor","delay-in-days":55,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"DOI":"10.1038\/s41598-026-62831-6","type":"journal-article","created":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T10:05:30Z","timestamp":1784196330000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Depth-augmented diffusion policy with pseudo-depth for robust robotic manipulation"],"prefix":"10.1038","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4957-1512","authenticated-orcid":false,"given":"Lesia","family":"Hentosh","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yaroslav","family":"Hladun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ivan","family":"Tsmots","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Oleh","family":"Bisikalo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,7,16]]},"reference":[{"key":"62831_CR1","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2024.104812","volume":"182","author":"A Correia","year":"2024","unstructured":"Correia, A. & Alexandre, L. A. A survey of demonstration learning. Robot. Auton. Syst. 182, 104812. https:\/\/doi.org\/10.1016\/j.robot.2024.104812 (2024).","journal-title":"Robot. Auton. Syst."},{"key":"62831_CR2","doi-asserted-by":"publisher","first-page":"588","DOI":"10.1007\/s11633-025-1542-8","volume":"22","author":"Y Zheng","year":"2025","unstructured":"Zheng, Y. et al. A survey of embodied learning for object-centric robotic manipulation. Mach. Intell. Res. 22, 588\u2013626. https:\/\/doi.org\/10.1007\/s11633-025-1542-8 (2025).","journal-title":"Mach. Intell. Res."},{"key":"62831_CR3","doi-asserted-by":"publisher","first-page":"129963","DOI":"10.1016\/j.neucom.2025.129963","volume":"638","author":"X Xiao","year":"2025","unstructured":"Xiao, X. et al. Robot learning in the era of foundation models: a survey. Neurocomputing 638, 129963. https:\/\/doi.org\/10.1016\/j.neucom.2025.129963 (2025).","journal-title":"Neurocomputing"},{"key":"62831_CR4","doi-asserted-by":"publisher","first-page":"1684","DOI":"10.1177\/02783649241273668","volume":"44","author":"C Chi","year":"2025","unstructured":"Chi, C. et al. Diffusion policy: Visuomotor policy learning via action diffusion. Int. J. Robot. Res. 44, 1684\u20131704. https:\/\/doi.org\/10.1177\/02783649241273668 (2025).","journal-title":"Int. J. Robot. Res."},{"key":"62831_CR5","doi-asserted-by":"publisher","first-page":"69","DOI":"10.3390\/bdcc7020069","volume":"7","author":"L Mochurad","year":"2023","unstructured":"Mochurad, L., Hladun, Y., Zasoba, Y. & Gregus, M. An approach for opening doors with a mobile robot using machine learning methods. BDCC 7, 69. https:\/\/doi.org\/10.3390\/bdcc7020069 (2023).","journal-title":"BDCC"},{"key":"62831_CR6","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3677327","volume":"56","author":"U Rajapaksha","year":"2024","unstructured":"Rajapaksha, U., Sohel, F., Laga, H., Diepeveen, D. & Bennamoun, M. Deep learning-based depth estimation methods from monocular image and videos: A comprehensive survey. ACM Comput. Surv. 56, 1\u201351. https:\/\/doi.org\/10.1145\/3677327 (2024).","journal-title":"ACM Comput. Surv."},{"key":"62831_CR7","doi-asserted-by":"publisher","unstructured":"Ze, Y. et al. Generalizable Visuomotor Policy Learning via Simple 3D Representations. Robotics: Science and Systems XX [Internet]. https:\/\/doi.org\/10.15607\/RSS.2024.XX.067 (Robotics: Science and Systems Foundation, 2024).","DOI":"10.15607\/RSS.2024.XX.067"},{"key":"62831_CR8","doi-asserted-by":"publisher","unstructured":"Yang, L. et al. Depth Anything V2 [Internet]. arXiv. https:\/\/doi.org\/10.48550\/ARXIV.2406.09414 (2024).","DOI":"10.48550\/ARXIV.2406.09414"},{"key":"62831_CR9","doi-asserted-by":"publisher","first-page":"709","DOI":"10.1108\/EBHRM-01-2022-0010","volume":"11","author":"J Alwali","year":"2023","unstructured":"Alwali, J. How high-involvement work practices, leadership and job crafting influence nurses\u2019 innovative work behavior. EBHRM 11, 709\u201324. https:\/\/doi.org\/10.1108\/EBHRM-01-2022-0010 (2023).","journal-title":"EBHRM"},{"key":"62831_CR10","doi-asserted-by":"publisher","first-page":"928","DOI":"10.1108\/LODJ-10-2021-0486","volume":"43","author":"J Alwali","year":"2022","unstructured":"Alwali, J. & Alwali, W. The relationship between emotional intelligence, transformational leadership, and performance: a test of the mediating role of job satisfaction. LODJ 43, 928\u2013952. https:\/\/doi.org\/10.1108\/LODJ-10-2021-0486 (2022).","journal-title":"LODJ"},{"key":"62831_CR11","doi-asserted-by":"publisher","first-page":"1077","DOI":"10.1108\/IJIS-11-2022-0211","volume":"16","author":"J Alwali","year":"2024","unstructured":"Alwali, J. The innovative\u2013performance connection: how dynamic capabilities empower nurses. IJIS 16, 1077\u20131099. https:\/\/doi.org\/10.1108\/IJIS-11-2022-0211 (2024).","journal-title":"IJIS"},{"key":"62831_CR12","first-page":"305","volume-title":"Advances in Neural Information Processing Systems 1","author":"DA Pomerleau","year":"1988","unstructured":"Pomerleau, D. A. An autonomous land vehicle in a neural network. In Advances in Neural Information Processing Systems 1 (ed. Touretzky, D. S.) 305\u201313 (Morgan Kaufmann, 1988)."},{"key":"62831_CR13","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1011.0686","author":"S Ross","year":"2010","unstructured":"Ross, S., Gordon, G. J. & Bagnell, J. A. A Reduction of Imitation Learning and Structured Prediction to No-Regret Online Learning [Internet]. arXiv.\u00a0https:\/\/doi.org\/10.48550\/ARXIV.1011.0686 (2010)."},{"key":"62831_CR14","doi-asserted-by":"publisher","unstructured":"Eigen, D., Puhrsch, C. & Fergus, R. Depth Map Prediction from a Single Image using a Multi-Scale Deep Network [Internet]. arXiv. https:\/\/doi.org\/10.48550\/ARXIV.1406.2283 (2014).","DOI":"10.48550\/ARXIV.1406.2283"},{"key":"62831_CR15","doi-asserted-by":"publisher","first-page":"1623","DOI":"10.1109\/TPAMI.2020.3019967","volume":"44","author":"R Ranftl","year":"2022","unstructured":"Ranftl, R., Lasinger, K., Hafner, D., Schindler, K. & Koltun, V. Towards robust monocular depth estimation: Mixing datasets for zero-shot cross-dataset transfer. IEEE Trans. Pattern Anal. Mach. Intell. 44, 1623\u201337. https:\/\/doi.org\/10.1109\/TPAMI.2020.3019967 (2022).","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"62831_CR16","doi-asserted-by":"publisher","unstructured":"Birkl, R., Wofk, D. & M\u00fcller, M. MiDaS v3.1: A Model Zoo for Robust Monocular Relative Depth Estimation [Internet]. arXiv. https:\/\/doi.org\/10.48550\/ARXIV.2307.14460 (2023).","DOI":"10.48550\/ARXIV.2307.14460"},{"key":"62831_CR17","doi-asserted-by":"publisher","unstructured":"Bhat, S. F. et al. Zero-shot Transfer by Combining Relative and Metric Depth [Internet]. arXiv. https:\/\/doi.org\/10.48550\/ARXIV.2302.12288 (2023).","DOI":"10.48550\/ARXIV.2302.12288"},{"key":"62831_CR18","doi-asserted-by":"publisher","unstructured":"Yang, L. et al. Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data. In 2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) [Internet]. Seattle, WA, USA, 10371\u201381. https:\/\/doi.org\/10.1109\/CVPR52733.2024.00987 (IEEE, 2024).","DOI":"10.1109\/CVPR52733.2024.00987"},{"key":"62831_CR19","doi-asserted-by":"publisher","unstructured":"Ke, B. et al. Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation. In 2024\u00a0IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) [Internet]. Seattle, WA, USA, 9492\u2013502. https:\/\/doi.org\/10.1109\/CVPR52733.2024.00907 (IEEE, 2024).","DOI":"10.1109\/CVPR52733.2024.00907"},{"key":"62831_CR20","doi-asserted-by":"publisher","unstructured":"Yin, W. et al. Metric3D: Towards Zero-shot Metric 3D Prediction from A Single Image [Internet]. arXiv. https:\/\/doi.org\/10.48550\/ARXIV.2307.10984 (2023).","DOI":"10.48550\/ARXIV.2307.10984"},{"key":"62831_CR21","doi-asserted-by":"publisher","unstructured":"Lin, H. et al. Depth Anything 3: Recovering the Visual Space from Any Views [Internet]. arXiv. https:\/\/doi.org\/10.48550\/ARXIV.2511.10647 (2025).","DOI":"10.48550\/ARXIV.2511.10647"},{"key":"62831_CR22","doi-asserted-by":"publisher","unstructured":"Zhang, M., Feng, Y., Chen, Q. & Fan, R. DCPI-Depth: Explicitly Infusing Dense Correspondence Prior to Unsupervised Monocular Depth Estimation [Internet]. arXiv. https:\/\/doi.org\/10.48550\/ARXIV.2405.16960 (2024).","DOI":"10.48550\/ARXIV.2405.16960"},{"key":"62831_CR23","doi-asserted-by":"publisher","unstructured":"Tang, G. et al. TiCoSS: Tightening the Coupling between Semantic Segmentation and Stereo Matching within A Joint Learning Framework [Internet]. arXiv. https:\/\/doi.org\/10.48550\/ARXIV.2407.18038 (2024).","DOI":"10.48550\/ARXIV.2407.18038"},{"key":"62831_CR24","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2411.03717","author":"C-W Liu","year":"2024","unstructured":"Liu, C-W., Zhang, Y., Chen, Q., Pitas, I. & Fan, R. These Maps Are Made by Propagation: Adapting Deep Stereo Networks to Road Scenarios with Decisive Disparity Diffusion [Internet]. arXiv. https:\/\/doi.org\/10.48550\/ARXIV.2411.03717 (2024)."},{"key":"62831_CR25","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2412.11210","author":"Y Feng","year":"2024","unstructured":"Feng, Y. et al. Leveraging Visual Priors from Vision Foundation Models for Single-View 3D Occupancy Prediction [Internet]. arXiv.\u00a0https:\/\/doi.org\/10.48550\/ARXIV.2412.11210 (2024)."},{"key":"62831_CR26","doi-asserted-by":"publisher","unstructured":"Janner, M., Du, Y., Tenenbaum, J. B. & Levine, S. Planning with Diffusion for Flexible Behavior Synthesis [Internet]. arXiv. https:\/\/doi.org\/10.48550\/ARXIV.2205.09991 (2022).","DOI":"10.48550\/ARXIV.2205.09991"},{"key":"62831_CR27","doi-asserted-by":"publisher","unstructured":"Mahler, J. et al. Dex-Net 2.0: Deep Learning to Plan Robust Grasps with Synthetic Point Clouds and Analytic Grasp Metrics. In Robotics: Science and Systems XIII [Internet]. Robotics: Science and Systems Foundation. https:\/\/doi.org\/10.15607\/RSS.2017.XIII.058\u00a0(2017).","DOI":"10.15607\/RSS.2017.XIII.058"},{"key":"62831_CR28","doi-asserted-by":"publisher","unstructured":"Zeng, A. et al. Learning Synergies Between Pushing and Grasping with Self-Supervised Deep Reinforcement Learning. In 2018 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), 4238\u201345.\u00a0https:\/\/doi.org\/10.1109\/IROS.2018.8593986 (IEEE, Madrid, 2018).","DOI":"10.1109\/IROS.2018.8593986"},{"issue":"1","key":"62831_CR29","doi-asserted-by":"publisher","first-page":"15759","DOI":"10.1038\/s41598-024-66864-7","volume":"14","author":"L Mochurad","year":"2024","unstructured":"Mochurad, L. & Hladun, Y. Neural network-based algorithm for door handle recognition using RGBD cameras. Sci. Rep. 1415759. https:\/\/doi.org\/10.1038\/s41598-024-66864-7 (2024).","journal-title":"Sci. Rep."},{"key":"62831_CR30","doi-asserted-by":"publisher","first-page":"43","DOI":"10.3390\/bdcc7010043","volume":"7","author":"L Mochurad","year":"2023","unstructured":"Mochurad, L., Hladun, Y. & Tkachenko, R. An obstacle-finding approach for autonomous mobile robots using 2D LiDAR data. BDCC 7, 43. https:\/\/doi.org\/10.3390\/bdcc7010043 (2023).","journal-title":"BDCC"},{"key":"62831_CR31","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3713070","volume":"57","author":"Y Yuan","year":"2025","unstructured":"Yuan, Y., Li, Z. & Zhao, B. A survey of multimodal learning: methods, applications, and future. ACM Comput. Surv. 57, 1\u201334. https:\/\/doi.org\/10.1145\/3713070 (2025).","journal-title":"ACM Comput. Surv."},{"key":"62831_CR32","doi-asserted-by":"publisher","unstructured":"Li, H. et al. See, Hear, and Feel: Smart Sensory Fusion for Robotic Manipulation [Internet]. arXiv. https:\/\/doi.org\/10.48550\/ARXIV.2212.03858 (2022).","DOI":"10.48550\/ARXIV.2212.03858"},{"key":"62831_CR33","doi-asserted-by":"publisher","unstructured":"Jiang, Y. et al. VIMA: General Robot Manipulation with Multimodal Prompts [Internet]. arXiv. https:\/\/doi.org\/10.48550\/ARXIV.2210.03094 (2022).","DOI":"10.48550\/ARXIV.2210.03094"},{"key":"62831_CR34","unstructured":"Srivastava, N. et al. Dropout: A simple way to prevent neural networks from overfitting. JMLR,\u00a01929\u20131958 (2014)."},{"key":"62831_CR35","doi-asserted-by":"publisher","unstructured":"Dosovitskiy, A. et al. An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale [Internet]. arXiv. https:\/\/doi.org\/10.48550\/ARXIV.2010.11929 (2020).","DOI":"10.48550\/ARXIV.2010.11929"},{"key":"62831_CR36","unstructured":"Wightman, R. Apr. PyTorch image models [Internet]. GitHub repository. (Accessed 5 Apr 2026). https:\/\/github.com\/rwightman\/pytorch-image-models\u00a0(2019)."},{"key":"62831_CR37","doi-asserted-by":"publisher","unstructured":"Radford, A. et al. Learning Transferable Visual Models From Natural Language Supervision [Internet]. arXiv. https:\/\/doi.org\/10.48550\/ARXIV.2103.00020 (2021).","DOI":"10.48550\/ARXIV.2103.00020"},{"key":"62831_CR38","doi-asserted-by":"publisher","unstructured":"Zhou, Y., Barnes, C., Lu, J., Yang, J. & Li, H. On the Continuity of Rotation Representations in Neural Networks. In 2019\u00a0IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) [Internet]. Long Beach, CA, USA, 5738\u201346. https:\/\/doi.org\/10.1109\/CVPR.2019.00589 (IEEE, 2019).","DOI":"10.1109\/CVPR.2019.00589"},{"key":"62831_CR39","doi-asserted-by":"publisher","unstructured":"Perez, E., Strub, F., De Vries, H., Dumoulin, V. & Courville, A. FiLM: Visual Reasoning with a General Conditioning Layer. AAAI [Internet]. 32. https:\/\/doi.org\/10.1609\/aaai.v32i1.11671 (2018).","DOI":"10.1609\/aaai.v32i1.11671"},{"key":"62831_CR40","doi-asserted-by":"publisher","unstructured":"Song, J., Meng, C. & Ermon, S. Denoising Diffusion Implicit Models [Internet]. arXiv. https:\/\/doi.org\/10.48550\/ARXIV.2010.02502 (2020).","DOI":"10.48550\/ARXIV.2010.02502"},{"key":"62831_CR41","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2301.11706","author":"M Ning","year":"2023","unstructured":"Ning, M., Sangineto, E., Porrello, A., Calderara, S. & Cucchiara, R. Input Perturbation Reduces Exposure Bias in Diffusion Models [Internet]. arXiv.\u00a0https:\/\/doi.org\/10.48550\/ARXIV.2301.11706 (2023)."},{"key":"62831_CR42","doi-asserted-by":"publisher","first-page":"125","DOI":"10.3390\/info11020125","volume":"11","author":"A Buslaev","year":"2020","unstructured":"Buslaev, A. et al. Albumentations: Fast and flexible image augmentations. Information 11, 125. https:\/\/doi.org\/10.3390\/info11020125 (2020).","journal-title":"Information"},{"key":"62831_CR43","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2306.03310","author":"B Liu","year":"2023","unstructured":"Liu, B. et al. LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learning [Internet]. arXiv.\u00a0https:\/\/doi.org\/10.48550\/ARXIV.2306.03310 (2023)."},{"key":"62831_CR44","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2503.14734","author":"NVIDIA Bjorck","year":"2025","unstructured":"Bjorck, N. V. I. D. I. A., Casta\u00f1eda, J., Cherniadev, F. & Da, N. X, et al. GR00T N1: An Open Foundation Model for Generalist Humanoid Robots [Internet]. arXiv.\u00a0https:\/\/doi.org\/10.48550\/ARXIV.2503.14734 (2025)."}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-62831-6","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-62831-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-62831-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T12:46:19Z","timestamp":1788957979000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-62831-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,16]]},"references-count":44,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["62831"],"URL":"https:\/\/doi.org\/10.1038\/s41598-026-62831-6","relation":{"references":[{"id-type":"doi","id":"10.48550\/ARXIV.1011.0686","asserted-by":"subject"},{"id-type":"doi","id":"10.48550\/ARXIV.2411.03717","asserted-by":"subject"},{"id-type":"doi","id":"10.48550\/ARXIV.2412.11210","asserted-by":"subject"},{"id-type":"doi","id":"10.48550\/ARXIV.2301.11706","asserted-by":"subject"},{"id-type":"doi","id":"10.48550\/ARXIV.2306.03310","asserted-by":"subject"},{"id-type":"doi","id":"10.48550\/ARXIV.2503.14734","asserted-by":"subject"}]},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,16]]},"assertion":[{"value":"15 April 2026","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 July 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 July 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","label":"Competing interests","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"This study did not involve experiments on human participants, human tissue, or human personal data. The dataset used in this work consists solely of robot observations, robot proprioceptive states, and robot action trajectories collected during teleoperation of the robotic platform for the manipulation task. No identifiable human data were collected, used, or analyzed. Therefore, the journal\u2019s requirements regarding ethics approval and informed consent for research involving human participants are not applicable to this study.","order":2,"name":"Ethics","label":"Ethics statement","group":{"name":"EthicsHeading","label":"Declarations"}}],"article-number":"28233"}}