{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T05:02:51Z","timestamp":1784350971368,"version":"3.55.0"},"reference-count":37,"publisher":"MDPI AG","issue":"14","license":[{"start":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T00:00:00Z","timestamp":1784160000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100013318","name":"Department of Science and Technology of Shanxi Province","doi-asserted-by":"publisher","award":["202503021212300"],"award-info":[{"award-number":["202503021212300"]}],"id":[{"id":"10.13039\/501100013318","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100013794","name":"Shanxi Provincial Department of Education","doi-asserted-by":"publisher","award":["2025LJ017"],"award-info":[{"award-number":["2025LJ017"]}],"id":[{"id":"10.13039\/501100013794","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>In complex backgrounds and under severe occlusions, the accuracy of vision-based robotic grasping pose estimation decreases significantly, further making objects difficult to manipulate and grasp. This paper proposes an iterative closed-loop optimization framework that deeply couples SAM with FoundationPose. The framework breaks through the open-loop logic bottleneck of \u201csegmentation first, then estimation\u201d found in traditional vision algorithms and constructs a mask correction mechanism based on rendered projection. By performing 3D rendering of the initially estimated 6D pose, a geometric prior mask of the object is generated and then fed back into SAM\u2019s prompt encoder, thereby guiding the model to achieve pixel-level refinement of the target\u2019s boundary in the next perception cycle. Meanwhile, to overcome the blind spots of a single metric, the framework designs a multi-dimensional confidence assessment module that integrates both the 2D image domain and the 3D geometric domain to comprehensively evaluate the reliability of the current pose. The SAM prior, the closed-loop iterative mechanism, and the multi-dimensional confidence assessment module work in synergy to form a complete optimization loop. In robustness experiments on pose estimation under cluttered and stacked scenes, the proposed method achieves an overall ADD-S recall rate of 91.7%, with the average translation and rotation errors reduced to as low as 3.5 mm and 2.1\u00b0. In 200 real-world robotic grasping verification trials, the overall grasping success rate reaches 96.5%. These experimental results demonstrate the effectiveness and enhanced robustness of the proposed closed-loop optimization framework in the tested unstructured environments.<\/jats:p>","DOI":"10.3390\/s26144524","type":"journal-article","created":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T03:12:38Z","timestamp":1784257958000},"page":"4524","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A Robust Visual Grasping Method for Robots in Cluttered and Stacked Scenes"],"prefix":"10.3390","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-9748-3577","authenticated-orcid":false,"given":"Zhiqiang","family":"Gao","sequence":"first","affiliation":[{"name":"Department of Automation, Taiyuan Institute of Technology, Taiyuan 030008, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mengqi","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Automation, Taiyuan Institute of Technology, Taiyuan 030008, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huihui","family":"Bai","sequence":"additional","affiliation":[{"name":"Department of Automation, Taiyuan Institute of Technology, Taiyuan 030008, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jinze","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Automation, Taiyuan Institute of Technology, Taiyuan 030008, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sifan","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Automation, Taiyuan Institute of Technology, Taiyuan 030008, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jing","family":"Han","sequence":"additional","affiliation":[{"name":"College of Mechatronic Engineering, North University of China, Taiyuan 030051, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhengkai","family":"Wang","sequence":"additional","affiliation":[{"name":"College of Mechatronic Engineering, North University of China, Taiyuan 030051, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,7,16]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Lee, J., Kim, H., Kwon, J.W., Yun, S.J., Lee, N.H., Choi, Y.H., Chung, G., and Suh, J. (2025). Model-Free Transformer Framework for 6-DoF Pose Estimation of Textureless Tableware Objects. Sensors, 25.","DOI":"10.3390\/s25196167"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Sampath, S.K., Wang, N., Yang, C., Wu, H., Liu, C., and Pearson, M. (2025). A Vision-Guided Deep Learning Framework for Dexterous Robotic Grasping Using Gaussian Processes and Transformers. Appl. Sci., 15.","DOI":"10.3390\/app15052615"},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Sun, H., Zhang, Y., Sun, H., and Hashimoto, K. (2024). Refined Prior Guided Category-Level 6D Pose Estimation and Its Application on Robotic Grasping. Appl. Sci., 14.","DOI":"10.3390\/app14178009"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Wang, Y., Wu, T., and Zou, Q. (2026). 6DoF Pose Estimation of Transparent Objects: Dataset and Method. Sensors, 26.","DOI":"10.3390\/s26030898"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"095407","DOI":"10.1088\/2631-8695\/ae6230","article-title":"6D pose estimation method based on hybrid attention mechanism and vector-based local consistency enhancement","volume":"8","author":"Lou","year":"2026","journal-title":"Eng. Res. Express"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Zheng, D., and Chen, Y. (2026). Enhancing Robotic Grasping Detection Using Visual\u2013Tactile Fusion Perception. Sensors, 26.","DOI":"10.3390\/s26020724"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"111464","DOI":"10.1016\/j.patcog.2025.111464","article-title":"Weakly supervised 3D human pose estimation based on PnP projection model","volume":"163","author":"Zhang","year":"2025","journal-title":"Pattern Recognit."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"2620","DOI":"10.1007\/s11263-024-02317-y","article-title":"Object Pose Estimation Based on Multi-precision Vectors and Seg-Driven PnP","volume":"133","author":"Wang","year":"2024","journal-title":"Int. J. Comput. Vis."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"81","DOI":"10.1007\/s11263-025-02646-6","article-title":"Deep Learning-Based Object Pose Estimation: A Comprehensive Survey","volume":"134","author":"Liu","year":"2026","journal-title":"Int. J. Comput. Vis."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Wang, C., Xu, D., Zhu, Y., Mart\u00edn-Mart\u00edn, R., Lu, C., Fei-Fei, L., and Savarese, S. (2019). DenseFusion: 6D Object Pose Estimation by Iterative Dense Fusion. arXiv.","DOI":"10.1109\/CVPR.2019.00346"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Sijin, L., Yu, L., Zhehao, L., Guoyuan, L., Can, W., and Xinyu, W. (2022). Vision-Guided Object Recognition and 6D Pose Estimation System Based on Deep Neural Network for Unmanned Aerial Vehicles towards Intelligent Logistics. Appl. Sci., 13.","DOI":"10.3390\/app13010115"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"6895","DOI":"10.1109\/TIP.2025.3620666","article-title":"PVNet: Point-Voxel Interaction LiDAR Scene Upsampling Via Diffusion Models","volume":"34","author":"Cheng","year":"2025","journal-title":"IEEE Trans. Image Process."},{"key":"ref_13","first-page":"3959","article-title":"GDR-Net: A Geometric Detail Recovering Network for 3D Scanned Objects","volume":"28","author":"Wanquan","year":"2021","journal-title":"IEEE Trans. Vis. Comput. Graph."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"103459","DOI":"10.1016\/j.rineng.2024.103459","article-title":"A comprehensive RGB-D dataset for 6D pose estimation for industrial robots pick and place: Creation and real-world validation","volume":"24","author":"Nguyen","year":"2024","journal-title":"Results Eng."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"106347","DOI":"10.1016\/j.dsp.2026.106347","article-title":"HAND-S3T: Real-time 3D hand pose estimation via hierarchical mesh refinement","volume":"183","author":"Tian","year":"2026","journal-title":"Digit. Signal Process."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"103514","DOI":"10.1016\/j.displa.2026.103514","article-title":"ResFuNet: A robust vision-based detection framework for robotic grasp pose estimation","volume":"94","author":"Wang","year":"2026","journal-title":"Displays"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Wang, Y., Wang, M., Cao, J., Wang, C., Wu, Z., and Gao, H. (2025). A Novel Fish Pose Estimation Method Based on Semi-Supervised Temporal Context Network. Biomimetics, 10.","DOI":"10.3390\/biomimetics10090566"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Liu, W., and Di, N. (2025). RSCS6D: Keypoint Extraction-Based 6D Pose Estimation. Appl. Sci., 15.","DOI":"10.3390\/app15126729"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"331","DOI":"10.1007\/s00521-026-12088-x","article-title":"Reading recognition for pointer meters based on SAM and MLLM","volume":"38","author":"Li","year":"2026","journal-title":"Neural Comput. Appl."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"111296","DOI":"10.1016\/j.measurement.2022.111296","article-title":"HCCG: Efficient high compatibility correspondence grouping for 3D object recognition and 6D pose estimation in cluttered scenes","volume":"197","author":"Lang","year":"2022","journal-title":"Measurement"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"165","DOI":"10.1007\/s11760-026-05216-6","article-title":"Towards geometry-aware attention: Key shift adjustment in vision transformers for image feature extraction","volume":"20","author":"Rawat","year":"2026","journal-title":"Signal Image Video Process."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"200103","DOI":"10.1016\/j.sasc.2024.200103","article-title":"Exploring End-to-End object detection with transformers versus YOLOv8 for enhanced citrus fruit detection within trees","volume":"6","author":"Jrondi","year":"2024","journal-title":"Syst. Soft Comput."},{"key":"ref_23","first-page":"17868","article-title":"Foundationpose: Unified 6d pose estimation and tracking of novel objects","volume":"2024","author":"Wen","year":"2024","journal-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit."},{"key":"ref_24","unstructured":"Zhang, H., He, L., He, R., Kadkhodamohammadi, A., Stoyanov, D., Davidson, B.R., Mazomenos, E.B., and Clarkson, M.J. (2026). FoundationPose-Initialized 3D-2D Liver Registration for Surgical Augmented Reality. arXiv."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Lee, P.K., Jang, S., Kim, C.J., Kim, G., and Yun, H. (Int. J. Precis. Eng. Manuf., 2026). 6D Pose Estimation of Reflective and Textureless Object with Improved Accuracy through Multi-view Scanning Using Mobile and Stationary Cameras, Int. J. Precis. Eng. Manuf., prepublish.","DOI":"10.1007\/s12541-026-01488-7"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"1447","DOI":"10.1007\/s11760-025-05035-1","article-title":"High-Fidelity Object Detection and 6D Pose Estimation for Vision-Guided 6-DoF Grasping of Chemical Vials","volume":"19","author":"Li","year":"2025","journal-title":"Signal Image Video Process."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"103069","DOI":"10.1016\/j.displa.2025.103069","article-title":"From visual understanding to 6D pose reconstruction: A cutting-edge review of deep learning-based object pose estimation","volume":"89","author":"Wang","year":"2025","journal-title":"Displays"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Hwang, H.J., Cho, J.H., and Kim, Y.T. (2024). Deep Learning-Based Real-Time 6D Pose Estimation and Multi-Mode Tracking Algorithms for Citrus-Harvesting Robots. Machines, 12.","DOI":"10.3390\/machines12090642"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"104130","DOI":"10.1016\/j.compind.2024.104130","article-title":"Addressing challenges in industrial pick and place: A deep learning-based 6 Degrees-of-Freedom pose estimation solution","volume":"161","author":"Govi","year":"2024","journal-title":"Comput. Ind."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Song, Z., Tang, W., Deng, W., Wang, H., Huang, G., Wu, H., Guo, Y., Liu, J., Jin, K., and Ma, Z. (2026). An FPGA-Based YOLOv5n Accelerator for Online Multi-Track Particle Localization. Electronics, 15.","DOI":"10.3390\/electronics15040810"},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"113515","DOI":"10.1016\/j.patcog.2026.113515","article-title":"Boosting cross-domain semi-supervised medical image segmentation with internal and external regularizations","volume":"179","author":"Wang","year":"2026","journal-title":"Pattern Recognit."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"3150","DOI":"10.1109\/TMI.2026.3668785","article-title":"QuPaS: SAM-based Semi-supervised Histopathological Image Segmentation with Quantum Force Field Finetuning and Adversarial Estimation","volume":"45","author":"Feng","year":"2026","journal-title":"IEEE Trans. Med. Imaging"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"614","DOI":"10.1364\/BOE.579532","article-title":"Brain-SAM: A general automatic SAM-based segmentation model for brain science images","volume":"17","author":"Zhang","year":"2026","journal-title":"Biomed. Opt. Express"},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Guoyuan, L., Fan, C., Yu, L., Yachun, F., Can, W., and Xinyu, W. (2021). A Manufacturing-Oriented Intelligent Vision System Based on Deep Neural Network for Object Recognition and 6D Pose Estimation. Front. Neurorobot., 14.","DOI":"10.3389\/fnbot.2020.616775"},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Nasim, H., Gabriel, L.B., Harsh, S., and Irene, C. (2020). Marker-Less 3d Object Recognition and 6d Pose Estimation for Homogeneous Textureless Objects: An RGB-D Approach. Sensors, 20.","DOI":"10.3390\/s20185098"},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Ren, J., Li, L., Li, S., Liu, M., Fang, M., Zhang, S., Liu, W., Liu, Y., and Yu, H. (2024). Confidence relative off-targets distance-based multi-dimensional transparency evaluation of distribution station area. Front. Energy Res., 11.","DOI":"10.3389\/fenrg.2023.1283775"},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"39","DOI":"10.1109\/MRA.2025.3639825","article-title":"Leveraging Embodied Mechanical Intelligence for Learning Decluttering Tasks: Gripper Design Boosts Learning","volume":"33","author":"Turco","year":"2026","journal-title":"IEEE Robot. Autom. Mag."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/14\/4524\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T04:20:29Z","timestamp":1784348429000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/14\/4524"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,16]]},"references-count":37,"journal-issue":{"issue":"14","published-online":{"date-parts":[[2026,7]]}},"alternative-id":["s26144524"],"URL":"https:\/\/doi.org\/10.3390\/s26144524","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,16]]}}}