{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T13:07:28Z","timestamp":1784120848594,"version":"3.55.0"},"reference-count":41,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T00:00:00Z","timestamp":1784073600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Robot. AI"],"abstract":"<jats:p>Imitation learning in complex, unstructured environments remains challenging due to the difficulty of grounding perception in physically meaningful representations and the need to model multimodal action distributions. Existing approaches often rely on unstructured pixel-level feature encodings or stochastic latent-variable decoders, which can lead to brittle attention in cluttered scenes. In this work, we present a novel integration of detector-based visual representations with conditional diffusion modeling (DINO + CDP) for real-world robotic imitation learning. Our framework utilizes a DINO object detection transformer to extract spatially-grounded object-query embeddings that serve as the conditioning signal for a diffusion-based policy. A primary contribution of this work is the systematic quantification of how scene complexity\u2014measured via image entropy\u2014affects robotic policy performance. By comparing rigid-object baselines with complex biological plant scenes, we demonstrate that organic morphology induces a measurable increase in pixel-level uncertainty that degrades standard pixel-centric models. Our results show that DINO + CDP mitigates this degradation by grounding action generation in stable object-level features. We evaluate our approach using a fully real-world manipulation dataset collected without simulation or synthetic pre-training. To isolate the impact of our architectural choices, we conduct a comparative study within a unified framework against convolutional (CNN-MLP), transformer-patch (ViT), and latent-variable (DETR + CVAE) variants. Experimental results in a robotic-arm biocell setup demonstrate that object-query-conditioned diffusion significantly improves task success rates, produces smoother trajectories, and exhibits superior robustness to high-entropy visual inputs, establishing a scalable pathway for imitation learning in challenging agricultural domains.<\/jats:p>","DOI":"10.3389\/frobt.2026.1829436","type":"journal-article","created":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T12:38:58Z","timestamp":1784119138000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Object-centric diffusion policies for real-world robotic-arm imitation learning"],"prefix":"10.3389","volume":"13","author":[{"given":"Prashant Reddy","family":"Kasu","sequence":"first","affiliation":[{"name":"College of Computer Science and Engineering, Computer Science, Texas A&M University - Corpus Christi","place":["Corpus Christi, TX, United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dugan","family":"Um","sequence":"additional","affiliation":[{"name":"College of Computer Science and Engineering, Mechanical Engineering, Texas A&M University - Corpus Christi","place":["Corpus Christi, TX, United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,7,15]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"105798","DOI":"10.1016\/j.compag.2020.105798","article-title":"Machine learning for automation in agriculture: state of the art and future directions","volume":"179","author":"Arguello","year":"2020","journal-title":"Comput. Electron. Agric."},{"key":"B3","doi-asserted-by":"publisher","first-page":"1107","DOI":"10.1007\/s11119-020-09747-8","article-title":"Robotic pruning and harvesting: a review of challenges and solutions","volume":"21","author":"Bello","year":"2020","journal-title":"Precis. Agric."},{"key":"B4","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2212.06817","article-title":"RT-1: robotics transformer for real-world control at scale","author":"Brohan","year":"2022","journal-title":"arXiv preprint arXiv:2212.06817"},{"key":"B5","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.026","article-title":"\u201cDiffusion policy: visuomotor policy learning via action diffusion","author":"Chi","year":"2023","journal-title":"Proceedings of Robotics Sci. Syst. (RSS)"},{"key":"B6","doi-asserted-by":"publisher","first-page":"229","DOI":"10.1016\/j.aiia.2020.10.002","article-title":"Towards autonomous agricultural robots: a review of machine learning approaches","volume":"4","author":"Das","year":"2021","journal-title":"Artif. Intell. Agric."},{"key":"B7","doi-asserted-by":"publisher","first-page":"45","DOI":"10.1016\/j.jaer.2021.03.004","article-title":"Teleoperation and machine learning for autonomous agricultural robots","volume":"74","author":"Das","year":"2021","journal-title":"J. Agric. Eng. Res."},{"key":"B8","article-title":"Implicit behavioral cloning","author":"Florence","year":"2021"},{"key":"B9","doi-asserted-by":"publisher","first-page":"1","DOI":"10.3390\/agronomy11061013","article-title":"Development of robotic systems for indoor farming: a systematic review","volume":"11","author":"Frison","year":"2021","journal-title":"Agronomy"},{"key":"B10","doi-asserted-by":"publisher","first-page":"1","DOI":"10.3390\/robotics10010007","article-title":"Challenges in agricultural robotics: a pathway towards sustainable solutions","volume":"10","author":"Gonzalez","year":"2021","journal-title":"Robotics"},{"key":"B11","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2105.03655","article-title":"FlingBot: the unreasonable effectiveness of dynamic manipulation for cloth unfolding","author":"Ha","year":"2021","journal-title":"arXiv preprint arXiv:2105.03655"},{"key":"B12","doi-asserted-by":"publisher","first-page":"106028","DOI":"10.1016\/j.compag.2021.106028","article-title":"Automated harvesting robots: current developments and future challenges","volume":"182","author":"Henke","year":"2021","journal-title":"Comput. Electron. Agric."},{"key":"B15","first-page":"2345","article-title":"Dexpilot: vision-based teleoperation of dexterous robotic hand-arm system","volume-title":"IEEE International Conference on Robotics and Automation (ICRA)","author":"Jeffrey","year":"2020"},{"key":"B16","doi-asserted-by":"publisher","first-page":"123","DOI":"10.25165\/j.ijabe.2021.08.6979","article-title":"Robotic solutions to labor shortages in agriculture: a global perspective","volume":"14","author":"Joshi","year":"2021","journal-title":"Int. J. Agric. Biol. Eng."},{"key":"B17","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1312.6114","article-title":"Auto-encoding variational bayes","author":"Kingma","year":"2013","journal-title":"arXiv preprint arXiv:1312.6114"},{"key":"B18","article-title":"\u201cDART: noise injection for robust imitation learning","volume-title":"Conference on Robot Learning (CoRL)","author":"Laskey","year":"2017"},{"key":"B19","doi-asserted-by":"publisher","first-page":"48512","DOI":"10.1109\/ACCESS.2022.3172041","article-title":"Teleoperation in agricultural robotics: applications and challenges","volume":"10","author":"Lopes","year":"2022","journal-title":"IEEE Access"},{"key":"B20","article-title":"What matters in learning from offline human demonstrations for robot manipulation","volume-title":"Conference on Robot Learning (CoRL)","author":"Mandlekar","year":"2021"},{"key":"B21","doi-asserted-by":"publisher","first-page":"747823","DOI":"10.3389\/frobt.2022.747823","article-title":"Towards autonomous robots for agricultural harvesting: a comprehensive review","volume":"9","author":"Martinez","year":"2022","journal-title":"Front. Robotics AI"},{"key":"B22","doi-asserted-by":"publisher","first-page":"103824","DOI":"10.1016\/j.robot.2020.103824","article-title":"Swarm robotics in agriculture: a review","volume":"139","author":"Meireles","year":"2021","journal-title":"Robotics Aut. Syst."},{"key":"B23","first-page":"2113","article-title":"EnsembleDAgger: a bayesian approach to safe imitation learning","volume-title":"IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","author":"Menda","year":"2018"},{"key":"B24","doi-asserted-by":"publisher","first-page":"856","DOI":"10.1002\/rob.22145","article-title":"Control architectures for agricultural robots","volume":"38","author":"Miller","year":"2021","journal-title":"J. Robotic Syst."},{"key":"B25","doi-asserted-by":"publisher","first-page":"112642","DOI":"10.1016\/j.dib.2026.112642","article-title":"TomatoPGT: a 3D point cloud dataset of tomato plants for segmentation and plant-trait extraction","volume":"66","author":"Nethala","year":"2026","journal-title":"Data Brief"},{"key":"B26","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1007\/978-3-030-58452-8_13","article-title":"End-to-End object detection with transformers","author":"Nicolas","year":"2020","journal-title":"European Conference on Computer Vision (ECCV)"},{"key":"B27","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.biosystemseng.2021.11.012","article-title":"Collaborative swarm robotics for precision agriculture","volume":"211","author":"Noor","year":"2022","journal-title":"Biosyst. Eng."},{"key":"B28","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2210.06463","article-title":"Holo-dex: teaching dexterity with immersive mixed reality","author":"Pandian Arunachalam","year":"2022","journal-title":"arXiv Preprint arXiv:2210.06463"},{"key":"B29","first-page":"4233","article-title":"Self-Supervised correspondence in visuomotor policy learning","volume-title":"IEEE Robotics and Automation Letters (RA-L)","author":"Peter","year":"2019"},{"key":"B30","first-page":"305","article-title":"ALVINN:","volume-title":"an autonomous land vehicle in a neural networkAdvances in Neural Information Processing Systems","author":"Pomerleau","year":"1988"},{"key":"B31","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.jafr.2020.100143","article-title":"The role of robotics in agriculture: a review","volume":"5","author":"Rajput","year":"2021","journal-title":"J. Agric. Food Res."},{"key":"B32","doi-asserted-by":"publisher","first-page":"945","DOI":"10.1002\/rob.22011","article-title":"A teleoperated robotic system for precision agriculture tasks","volume":"38","author":"Rodrigues","year":"2021","journal-title":"J. Field Robotics"},{"key":"B33","first-page":"627","article-title":"A reduction of imitation learning and structured prediction to no-regret online learning","volume-title":"Artificial Intelligence and Statistics (AISTATS)","author":"Ross","year":"2010"},{"key":"B35","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2109.12098","article-title":"CLIPort: what and where pathways for robotic manipulation","author":"Shridhar","year":"2021","journal-title":"arXiv preprint arXiv:2109.12098"},{"key":"B34","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2209.05451","article-title":"Perceiver-actor: a multi-task transformer for robotic manipulation","author":"Shridhar","year":"2022","journal-title":"arXiv:2209.05451"},{"key":"B37","doi-asserted-by":"publisher","first-page":"1340","DOI":"10.1016\/j.robot.2012.03.005","article-title":"Dual arm manipulation \u2013 a survey","volume":"60","author":"Smith","year":"2012","journal-title":"Robotics Aut. Syst."},{"key":"B38","doi-asserted-by":"publisher","first-page":"454","DOI":"10.1002\/rob.21905","article-title":"Robust control techniques for robotics applications in agriculture","volume":"37","author":"Smith","year":"2020","journal-title":"J. Field Robotics"},{"key":"B39","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2011.13456","article-title":"Score-based generative modeling through stochastic differential equations","author":"Song","year":"2021","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"B40","doi-asserted-by":"publisher","first-page":"1","DOI":"10.3390\/s21051420","article-title":"Sensor integration in agricultural robots: a comprehensive review","volume":"21","author":"Tian","year":"2021","journal-title":"Sensors"},{"key":"B42","first-page":"5998","article-title":"Attention is all you need","volume-title":"Advances in Neural Information Processing Systems (NeurIPS)","author":"Vaswani","year":"2017"},{"key":"B44","first-page":"12011","article-title":"Implicit generation and generalization in energy-based models","volume-title":"Advances in Neural Information Processing Systems (NeurIPS)","year":"2019"},{"key":"B46","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1111\/agec.12653","article-title":"Impact of automation on labor in agriculture: a review","volume":"52","author":"Zhang","year":"","journal-title":"Agric. Econ."},{"key":"B47","doi-asserted-by":"publisher","first-page":"103854","DOI":"10.1016\/j.robot.2021.103854","article-title":"Remote control of agricultural robots in precision farming: a review","volume":"142","author":"Zhang","year":"","journal-title":"Robotics Aut. Syst."},{"key":"B48","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2301.08556","article-title":"NeRF in the palm of your hand: corrective augmentation for robotics via novel-view synthesis","author":"Zhou","year":"2023","journal-title":"arXiv preprint arXiv:2301.08556"}],"container-title":["Frontiers in Robotics and AI"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frobt.2026.1829436\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T12:39:02Z","timestamp":1784119142000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frobt.2026.1829436\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,15]]},"references-count":41,"alternative-id":["10.3389\/frobt.2026.1829436"],"URL":"https:\/\/doi.org\/10.3389\/frobt.2026.1829436","relation":{},"ISSN":["2296-9144"],"issn-type":[{"value":"2296-9144","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,15]]},"article-number":"1829436"}}