{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,14]],"date-time":"2026-01-14T13:42:01Z","timestamp":1768398121976,"version":"3.49.0"},"reference-count":75,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,1,14]],"date-time":"2026-01-14T00:00:00Z","timestamp":1768348800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100010661","name":"Framework Programme","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100010661","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Robot. AI"],"abstract":"<jats:p>The ability to track the 6D pose distribution of an object while a mobile manipulator is still approaching it can enable the robot to pre-plan grasps, thereby improving both the time efficiency and robustness of mobile manipulation. However, tracking a 6D object pose distribution on approach can be challenging due to the limited view of the robot camera. In this study, we present a particle filter-based multi-view 6D pose distribution tracking framework that compensates for the limited view of the moving robot camera while it approaches the object by fusing observations from external stationary cameras in the environment. We extend the single-view pose distribution tracking framework (PoseRBPF) to fuse observations from external cameras. We model the object pose posterior as a multi-modal distribution and introduce techniques for fusion, re-sampling, and pose estimation from the tracked distribution to effectively handle noisy and conflicting observations from different cameras. To evaluate our framework, we also contribute a real-world benchmark dataset. Our experiments demonstrate that the proposed framework yields a more accurate quantification of object pose and associated uncertainty than previous research. Finally, we apply our framework for pre-grasp planning on mobile robots, demonstrating its practical utility.<\/jats:p>","DOI":"10.3389\/frobt.2025.1683931","type":"journal-article","created":{"date-parts":[[2026,1,14]],"date-time":"2026-01-14T08:21:51Z","timestamp":1768378911000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Multi-view object pose distribution tracking for pre-grasp planning on mobile robots"],"prefix":"10.3389","volume":"12","author":[{"given":"Lakshadeep","family":"Naik","sequence":"first","affiliation":[{"name":"SDU Robotics, M\u00e6rsk Mc-Kinney M\u00f8ller Institute (MMMI), Faculty of Engineering, University of Southern Denmark","place":["Odense, Denmark"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Thorbj\u00f8rn Mosekj\u00e6r","family":"Iversen","sequence":"additional","affiliation":[{"name":"SDU Robotics, M\u00e6rsk Mc-Kinney M\u00f8ller Institute (MMMI), Faculty of Engineering, University of Southern Denmark","place":["Odense, Denmark"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jakob","family":"Wilm","sequence":"additional","affiliation":[{"name":"SDU Robotics, M\u00e6rsk Mc-Kinney M\u00f8ller Institute (MMMI), Faculty of Engineering, University of Southern Denmark","place":["Odense, Denmark"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Norbert","family":"Kr\u00fcger","sequence":"additional","affiliation":[{"name":"SDU Robotics, M\u00e6rsk Mc-Kinney M\u00f8ller Institute (MMMI), Faculty of Engineering, University of Southern Denmark","place":["Odense, Denmark"]},{"name":"Danish Institute for Advanced Studies (DIAS)","place":["Odense, Denmark"]}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1965","published-online":{"date-parts":[[2026,1,14]]},"reference":[{"key":"B1","doi-asserted-by":"crossref","DOI":"10.1109\/ICRA57147.2024.10610690","article-title":"Rgbmanip: monocular image-based robotic manipulation through active object pose estimation","volume-title":"2024 IEEE international conference on robotics and automation (ICRA)","author":"An","year":"2024"},{"key":"B2","doi-asserted-by":"publisher","first-page":"36","DOI":"10.1109\/mra.2015.2448951","article-title":"Benchmarking in manipulation research: using the yale-cmu-berkeley object and model set","volume":"22","author":"Calli","year":"2015","journal-title":"IEEE Robotics and Automation Mag."},{"key":"B3","first-page":"3342","article-title":"3d pose estimation of daily objects using an rgb-d camera","volume-title":"2012 IEEE\/RSJ international conference on intelligent robots and systems","author":"Choi","year":""},{"key":"B4","first-page":"3877","article-title":"3d textureless object detection and tracking: an edge-based approach","volume-title":"2012 IEEE\/RSJ international conference on intelligent robots and systems","author":"Choi","year":""},{"key":"B5","doi-asserted-by":"crossref","first-page":"2050","DOI":"10.1109\/ROBOT.2010.5509615","article-title":"Efficient multi-view object recognition and full pose estimation","volume-title":"2010 IEEE international conference on robotics and automation","author":"Collet","year":"2010"},{"key":"B6","doi-asserted-by":"publisher","first-page":"1284","DOI":"10.1177\/0278364911401765","article-title":"The moped framework: object recognition and pose estimation for manipulation","volume":"30","author":"Collet","year":"2011","journal-title":"Nternational Journal Robotics Research"},{"key":"B7","doi-asserted-by":"crossref","first-page":"7215","DOI":"10.1109\/IROS.2018.8594282","article-title":"Pose estimation for objects with rotational symmetry","volume-title":"2018 IEEE\/RSJ international conference on intelligent robots and systems (IROS)","author":"Corona","year":"2018"},{"key":"B8","volume-title":"Poserbpf: a rao-blackwellized particle filter for 6d object pose tracking","author":"Deng","year":"2019"},{"key":"B9","doi-asserted-by":"crossref","first-page":"3665","DOI":"10.1109\/ICRA40945.2020.9196714","article-title":"Self-supervised 6d object pose estimation for robot manipulation","volume-title":"2020 IEEE international conference on robotics and automation (ICRA)","author":"Deng","year":"2020"},{"key":"B10","doi-asserted-by":"publisher","first-page":"1328","DOI":"10.1109\/tro.2021.3056043","article-title":"Poserbpf: a rao\u2013blackwellized particle filter for 6-d object pose tracking","volume":"37","author":"Deng","year":"2021","journal-title":"IEEE Trans. Robotics"},{"key":"B11","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4757-3437-9","volume-title":"Sequential monte carlo methods in practice, vol. 1","author":"Doucet","year":"2001"},{"key":"B12","doi-asserted-by":"crossref","first-page":"998","DOI":"10.1109\/CVPR.2010.5540108","article-title":"Model globally, match locally: efficient and robust 3d object recognition","volume-title":"2010 IEEE computer society conference on computer vision and pattern recognition","author":"Drost","year":"2010"},{"key":"B13","doi-asserted-by":"crossref","first-page":"867","DOI":"10.1007\/978-3-319-32552-1_35","article-title":"Multisensor data fusion","volume-title":"Springer handbook of robotics","author":"Durrant-Whyte","year":"2016"},{"key":"B14","first-page":"154","article-title":"Integration of probabilistic pose estimates from multiple views","volume-title":"European conference on computer vision","author":"Erkent","year":"2016"},{"key":"B15","doi-asserted-by":"publisher","first-page":"47","DOI":"10.3390\/electronics10010047","article-title":"Service robots in catering applications: a review and future challenges","volume":"10","author":"Garcia-Haro","year":"2020","journal-title":"Electronics"},{"key":"B16","doi-asserted-by":"publisher","first-page":"97","DOI":"10.7551\/mitpress\/9481.003.0018","article-title":"Monte carlo pose estimation with quaternion kernels and the bingham distribution","volume":"7","author":"Glover","year":"2012","journal-title":"Robotics Science Systems"},{"key":"B17","first-page":"6749","article-title":"Surfemb: dense and continuous correspondence distributions for object pose estimation with learnt surface embeddings","volume-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","author":"Haugaard","year":"2022"},{"key":"B18","doi-asserted-by":"crossref","first-page":"1786","DOI":"10.1109\/ICRA48891.2023.10161514","article-title":"Multi-view object pose estimation from correspondence distributions and epipolar geometry","volume-title":"2023 IEEE international conference on robotics and automation (ICRA)","author":"Haugaard","year":"2023"},{"key":"B19","volume-title":"Spyropose: importance sampling pyramids for object pose distribution estimation in se (3)","author":"Haugaard","year":"2023"},{"key":"B20","first-page":"464","article-title":"Multiple viewpoint recognition and localization","volume-title":"Asian conference on computer vision","author":"Helmer","year":"2010"},{"key":"B21","doi-asserted-by":"publisher","first-page":"3595","DOI":"10.1080\/03610929008830400","article-title":"A class of invariant consistent tests for multivariate normality","volume":"19","author":"Henze","year":"1990","journal-title":"Commun. Statistics-Theory Methods"},{"key":"B22","doi-asserted-by":"crossref","first-page":"858","DOI":"10.1109\/ICCV.2011.6126326","article-title":"Multimodal templates for real-time detection of texture-less objects in heavily cluttered scenes","volume-title":"2011 international conference on computer vision","author":"Hinterstoisser","year":"2011"},{"key":"B23","doi-asserted-by":"crossref","first-page":"548","DOI":"10.1007\/978-3-642-37331-2_42","article-title":"Model based training, detection and pose estimation of texture-less 3d objects in heavily cluttered scenes","volume-title":"Computer Vision\u2013ACCV 2012: 11th Asian conference on computer vision, Daejeon, Korea, November 5-9, 2012, revised selected papers, part I 11","author":"Hinterstoisser","year":"2013"},{"key":"B24","doi-asserted-by":"crossref","DOI":"10.1109\/WACV.2017.103","article-title":"T-LESS: an RGB-D dataset for 6D pose estimation of texture-less objects","volume-title":"IEEE winter conference on applications of computer vision (WACV)","author":"Hoda\u0148","year":"2017"},{"key":"B25","doi-asserted-by":"publisher","first-page":"120","DOI":"10.1108\/01439911211201582","article-title":"Autonomous industrial mobile manipulation (aimm): past, present and future","volume":"39","author":"Hvilsh\u00f8j","year":"2012","journal-title":"Industrial Robot Int. J."},{"key":"B26","volume-title":"Ki-pode: keypoint-Based implicit pose distribution estimation of rigid objects","author":"Iversen","year":"2022"},{"key":"B27","doi-asserted-by":"publisher","first-page":"8399","DOI":"10.1109\/LRA.2022.3188109","article-title":"Robot learning of Mobile manipulation with reachability behavior priors","volume":"7","author":"Jauhri","year":"","journal-title":"IEEE Robotics Automation Lett."},{"key":"B28","doi-asserted-by":"publisher","first-page":"8399","DOI":"10.1109\/lra.2022.3188109","article-title":"Robot learning of Mobile manipulation with reachability BehaviorPriors","volume":"7","author":"Jauhri","year":"","journal-title":"IEEE RA-L"},{"key":"B29","doi-asserted-by":"crossref","first-page":"5094","DOI":"10.1109\/CVPR.2017.541","article-title":"A reinforcement learning approach to the view planning problem","volume-title":"2017 IEEE conference on computer vision and pattern recognition (CVPR)","author":"Kaba","year":"2017"},{"key":"B30","first-page":"5010","article-title":"Rotationnet: joint object categorization and pose estimation using multiviews from unsupervised viewpoints","volume-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","author":"Kanezaki","year":"2018"},{"key":"B31","first-page":"1521","article-title":"Ssd-6d: making rgb-based 3d detection and 6d pose estimation great again","volume-title":"Proceedings of the IEEE international conference on computer vision","author":"Kehl","year":"2017"},{"key":"B32","first-page":"2938","article-title":"Posenet: a convolutional network for real-time 6-dof camera relocalization","volume-title":"Proceedings of the IEEE international conference on computer vision","author":"Kendall","year":"2015"},{"key":"B33","doi-asserted-by":"publisher","first-page":"28","DOI":"10.1016\/j.inffus.2011.08.001","article-title":"Multisensor data fusion: a review of the state-of-the-art","volume":"14","author":"Khaleghi","year":"2013","journal-title":"Inf. Fusion"},{"key":"B34","first-page":"3258","article-title":"Physically-based grasp quality evaluation under uncertainty","volume-title":"2012 IEEE international conference on robotics and automation","author":"Kim","year":"2012"},{"key":"B35","first-page":"1097","article-title":"Imagenet classification with deep convolutional neural networks","volume-title":"Advances in neural information processing systems","author":"Krizhevsky","year":"2012"},{"key":"B36","first-page":"574","article-title":"Cosypose: consistent multi-view multi-object 6d pose estimation","volume-title":"European conference on computer vision","author":"Labb\u00e9","year":"2020"},{"key":"B37","first-page":"254","article-title":"A unified framework for multi-view multi-class object pose estimation","volume-title":"Proceedings of the European conference on computer vision","author":"Li","year":""},{"key":"B38","first-page":"683","article-title":"Deepim: deep iterative matching for 6d pose estimation","volume-title":"Proceedings of the European conference on computer vision","author":"Li","year":""},{"key":"B39","first-page":"478","article-title":"Fpm: fine pose parts-based model with 3d cad models","volume-title":"European conference on computer vision","author":"Lim","year":"2014"},{"key":"B40","doi-asserted-by":"crossref","DOI":"10.1109\/IRC.2018.00028","article-title":"Reuleaux: robot base placement by reachability analysis","volume-title":"IEEE int. Conf. On robotic computing","author":"Makhal","year":"2018"},{"key":"B41","first-page":"800","article-title":"Deep model-based 6d pose refinement in rgb","volume-title":"Proceedings of the European conference on computer vision","author":"Manhardt","year":"2018"},{"key":"B42","first-page":"6841","article-title":"Explaining the ambiguity of object detection and 6d pose from visual data","volume-title":"Proceedings of the IEEE international conference on computer vision","author":"Manhardt","year":"2019"},{"key":"B43","doi-asserted-by":"crossref","first-page":"195","DOI":"10.1109\/SSRR.2016.7784298","article-title":"Icp-based pose-graph slam","volume-title":"2016 IEEE international symposium on safety, security, and rescue robotics (SSRR)","author":"Mendes","year":"2016"},{"key":"B44","doi-asserted-by":"crossref","first-page":"499","DOI":"10.1007\/978-1-4757-3437-9_24","article-title":"Rao-blackwellised particle filtering for dynamic bayesian networks","volume-title":"Sequential monte carlo methods in practice","author":"Murphy","year":"2001"},{"key":"B45","first-page":"7882","article-title":"Implicit-pdf: non-Parametric representation of probability distributions on the rotation manifold","volume-title":"International conference on machine learning","author":"Murphy","year":"2021"},{"key":"B46","volume-title":"Pre-grasp planning for time-efficient and robust mobile manipulation","author":"Naik","year":"2024"},{"key":"B47","doi-asserted-by":"crossref","DOI":"10.1109\/ICRA46639.2022.9812339","article-title":"Multi-view object pose distribution tracking for pre-grasp planning on mobile robots","volume-title":"2022 IEEE international conference on robotics and automation (ICRA)","author":"Naik","year":"2022"},{"key":"B48","doi-asserted-by":"publisher","first-page":"2606","DOI":"10.1109\/lra.2024.3358077","article-title":"Pre-grasp approaching on mobile robots: a pre-active layered approach","volume":"9","author":"Naik","year":"","journal-title":"IEEE Robotics Automation Lett."},{"key":"B49","first-page":"3666","article-title":"Basenet: a learning-based mobile manipulator base pose sequence planning for pickup tasks","volume-title":"2024 IEEE\/RSJ international conference on Intelligent robots and systems (IROS)","author":"Naik","year":""},{"key":"B50","doi-asserted-by":"publisher","first-page":"651","DOI":"10.1108\/ir-10-2024-0467","article-title":"Robotic task success evaluation under multi-modal non-parametric object pose uncertainty","volume":"52","author":"Naik","year":"2025","journal-title":"Industrial Robot The International Journal Robotics Research Application"},{"key":"B51","volume-title":"Deep learning approaches to grasp synthesis: a review","author":"Newbury","year":"2022"},{"key":"B52","doi-asserted-by":"crossref","first-page":"10580","DOI":"10.1109\/IROS45743.2020.9340860","article-title":"Learning orientation distributions for object pose estimation","volume-title":"2020 IEEE\/RSJ international conference on intelligent robots and systems (IROS)","author":"Okorn","year":"2020"},{"key":"B53","doi-asserted-by":"crossref","first-page":"2011","DOI":"10.1109\/ICRA.2017.7989233","article-title":"6-dof object pose from semantic keypoints","volume-title":"2017 IEEE international conference on robotics and automation (ICRA)","author":"Pavlakos","year":"2017"},{"key":"B54","first-page":"4561","article-title":"Pvnet: pixel-wise voting network for 6dof pose estimation","volume-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","author":"Peng","year":"2019"},{"key":"B55","first-page":"3828","article-title":"Bb8: a scalable, accurate, robust to partial occlusion method for predicting the 3d poses of challenging objects without using depth","volume-title":"Proceedings of the IEEE international conference on computer vision","author":"Rad","year":"2017"},{"key":"B56","first-page":"1352","article-title":"Slam++: simultaneous localisation and mapping at the level of objects","volume-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","author":"Salas-Moreno","year":"2013"},{"key":"B57","volume-title":"Introduction to information retrieval, vol. 39","author":"Sch\u00fctze","year":"2008"},{"key":"B58","doi-asserted-by":"publisher","first-page":"297","DOI":"10.1007\/s00502-020-00823-8","article-title":"A review of the challenges in Mobile manipulation: systems design and robocup challenges","volume":"137","author":"Sereinig","year":"2020","journal-title":"Elektrotech. Inf."},{"key":"B59","doi-asserted-by":"crossref","first-page":"5200","DOI":"10.1109\/ICRA48506.2021.9561483","article-title":"Fast uncertainty quantification for deep object pose estimation","volume-title":"2021 IEEE international conference on robotics and automation (ICRA)","author":"Shi","year":"2021"},{"key":"B60","first-page":"945","article-title":"Multi-view convolutional neural networks for 3d shape recognition","volume-title":"Proceedings of the IEEE international conference on computer vision","author":"Su","year":"2015"},{"key":"B61","first-page":"699","article-title":"Implicit 3d orientation learning for 6d object detection from rgb images","volume-title":"Proceedings of the European conference on computer vision","author":"Sundermeyer","year":"2018"},{"key":"B62","first-page":"93","article-title":"3d object detection with multiple kinects","volume-title":"European conference on computer vision","author":"Susanto","year":"2012"},{"key":"B63","doi-asserted-by":"publisher","first-page":"020801","DOI":"10.1115\/1.4054611","article-title":"A survey of wheeled mobile manipulation: a decision-making perspective","volume":"15","author":"Thakar","year":"2023","journal-title":"J. Mech. Robotics"},{"key":"B64","doi-asserted-by":"publisher","first-page":"52","DOI":"10.1145\/504729.504754","article-title":"Probabilistic robotics","volume":"45","author":"Thrun","year":"2002","journal-title":"Commun. ACM"},{"key":"B65","first-page":"306","article-title":"Deep object pose estimation for semantic robotic grasping of household objects","volume-title":"Conference on robot learning","author":"Tremblay","year":"2018"},{"key":"B66","doi-asserted-by":"crossref","DOI":"10.1109\/ICRA.2013.6630839","article-title":"Robot placement based on reachability inversion","volume-title":"IEEE ICRA","author":"Vahrenkamp","year":"2013"},{"key":"B67","first-page":"3343","article-title":"Densefusion: 6d object pose estimation by iterative dense fusion","volume-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","author":"Wang","year":"2019"},{"key":"B68","doi-asserted-by":"crossref","first-page":"10059","DOI":"10.1109\/ICRA40945.2020.9196679","article-title":"6-pack: category-level 6d pose tracker with anchor-based keypoints","volume-title":"2020 IEEE international conference on robotics and automation (ICRA)","author":"Wang","year":"2020"},{"key":"B69","doi-asserted-by":"crossref","first-page":"10367","DOI":"10.1109\/IROS45743.2020.9341314","article-title":"Se (3)-tracknet: data-Driven 6d pose tracking by calibrating image residuals in synthetic domains","volume-title":"2020 IEEE\/RSJ international conference on intelligent robots and systems (IROS)","author":"Wen","year":"2020"},{"key":"B70","unstructured":"Detectron2\n          \n          \n            \n              Wu\n              Y.\n            \n            \n              Kirillov\n              A.\n            \n            \n              Massa\n              F.\n            \n            \n              Lo\n              W.-Y.\n            \n            \n              Girshick\n              R.\n            \n          \n          \n          2019"},{"key":"B71","volume-title":"Posecnn: a convolutional neural network for 6d object pose estimation in cluttered scenes","author":"Xiang","year":"2017"},{"key":"B72","first-page":"2690","article-title":"Pix2vox: context-aware 3d reconstruction from single and multi-view images","volume-title":"Proceedings of the IEEE international conference on computer vision","author":"Xie","year":"2019"},{"key":"B73","first-page":"1941","article-title":"Dpod: 6d pose object detector and refiner","volume-title":"Proceedings of the IEEE international conference on computer vision","author":"Zakharov","year":"2019"},{"key":"B74","doi-asserted-by":"crossref","first-page":"1386","DOI":"10.1109\/ICRA.2017.7989165","article-title":"Multi-view self-supervised deep learning for 6d pose estimation in the amazon picking challenge","volume-title":"2017 IEEE international conference on robotics and automation (ICRA)","author":"Zeng","year":"2017"},{"key":"B75","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1155\/2022\/3883845","article-title":"Vision-based mobile manipulator for handling and transportation of supermarket products","volume":"2022","author":"Zia Ur Rahman","year":"2022","journal-title":"Math. Problems Eng."}],"container-title":["Frontiers in Robotics and AI"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frobt.2025.1683931\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,14]],"date-time":"2026-01-14T08:22:02Z","timestamp":1768378922000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frobt.2025.1683931\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,14]]},"references-count":75,"alternative-id":["10.3389\/frobt.2025.1683931"],"URL":"https:\/\/doi.org\/10.3389\/frobt.2025.1683931","relation":{},"ISSN":["2296-9144"],"issn-type":[{"value":"2296-9144","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,14]]},"article-number":"1683931"}}