[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-84480-en":3,"doc-seo-84480-105":29,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":13,"seo_description":14,"update_tm":27,"read_time":28},84480,687197100911,"Himbo","https://ap-avatar.wpscdn.com/avatar/a000239b6f1da00475?x-image-process=image/resize,m_fixed,w_180,h_180&k=1782698725881665579",8,"Research & Report","Pickalo: Leveraging 6D Pose Estimation for Low-Cost Industrial Bin Picking","Industrial bin picking in real environments remains difficult due to severe clutter, occlusions, and the high cost of conventional 3D sensing. Pickalo introduces a modular 6D pose-based bin-picking pipeline built on low-cost hardware, combining an active wrist RGB-D viewpoint exploration with stereo depth refinement via BridgeDepth. Object instances are segmented using a Mask-RCNN trained on photorealistic synthetic data and localized with a zero-shot SAM-6D pose estimator, then fused over time in a pose buffer for stability. On a UR5e system, it reaches up to 600 mean picks per hour with 96–99% grasp success over 30-minute runs.","Pickalo: Leveraging 6D Pose Estimation for Low-Cost Industrial Bin Picking  \nAlessandro Tarsi *, Matteo Mastrogiuseppe *, Saverio Taliani *, Simone Cortinovis *, Ugo Pattacini  \narXiv :2604 .04690v2 [ cs .RO] 12 Jul 2026  \nAbstract—Bin picking in real industrial environments remains challenging due to severe clutter, occlusions, and the high cost of traditional 3D sensing setups. We present Pickalo, a modular 6D pose-based bin-picking pipeline built entirely on low-cost hardware. A wrist-mounted RGB-D camera actively explores the scene from multiple viewpoints, while raw stereo streams are processed with BridgeDepth to obtain refined depth maps suitable for accurate collision reasoning. Object instances are segmented with a Mask-RCNN model trained purely on photorealistic synthetic data and localized using the zero-shot SAM-6D pose estimator. A pose buffer module fuses multiview observations over time, handling object symmetries and significantly reducing pose noise. Offline, we generate and curate large sets of antipodal grasp candidates per object; online, a utility-based ranking and fast collision checking are queried for the grasp planning. Deployed on a UR5e with a parallel-jaw gripper and an Intel RealSense D435i, Pickalo achieves up to 600 mean picks per hour with 96-99% grasp success and robust performance over 30-minute runs on densely filled euroboxes. Ablation studies demonstrate the benefits of enhanced depth estimation and of the pose buffer for long-term stability and throughput in realistic industrial conditions. Videos are available at [https://mesh-iit.github.io/project-jl2-camozzi/](https://mesh-iit.github.io/project-jl2-camozzi/)  \nIndex Terms—Bin picking, foundation models, depth enhancement, and 6D pose estimation.  \nI. INTRODUCTION  \nDESPITE decades of research, bin picking remains a cen  \ntral challenge in industrial automation. The task requires a robot to detect, localize, and extract objects from a cluttered container under varying object poses. In this work, we propose a modular 6D grasping pipeline for industrial bin picking that relies on multi-view acquisition and leverages the latest foundation models for pose and depth estimation.  \nConventionally, bin-picking systems adopt classical vision techniques such as 2D-3D feature matching, template matching, and vote-based pose estimation [1]–[5] . These approaches are either not robust enough or assume access to high-quality depth data, typically obtained from industrial-grade stereo cameras. Such sensors produce dense point clouds with rich  \n*Alessandro Tarsi, Matteo Mastrogiuseppe, Saverio Taliani, Simone Cortinovis equally contributed to this work. This work was supported by Camozzi Automation SpA. Alessandro Tarsi, Matteo Mastrogiuseppe, Simone Cortinovis were with the MESH Facility (formerly iCub Tech), Istituto Italiano di Tecnologia, Genova 16163, Italy. Saverio Taliani was with the AMI laboratory, Istituto Italiano di Tecnologia, Genova 16163, Italy. Alessandro Tarsi is now with Institut des Systmes Intelligents et de Robotique (ISIR), Paris 75005, France (email: [tarsi@isir.upmc.fr](tarsi@isir.upmc.fr)). Matteo Mastrogiuseppe, Saverio Taliani, Simone Cortinovis are now with Generative Bionics, Genova 16152, Italy (email: {matteo.mastrogiuseppe, saverio.taliani, [simone.cortinovis](simone.cortinovis}@gbionics.ai)[}](simone.cortinovis}@gbionics.ai)[@gbionics.ai](simone.cortinovis}@gbionics.ai)). Ugo Pattacini is with the MESH Facility (formerly iCub Tech), Istituto Italiano di Tecnologia, Genova 16163, Italy (email: ugo.pattacini@iit.it) .  \nFig. 1: The experimental setup consists of a UR5e manipulator with a consumer-grade camera attached to the wrist. The bin is a standard eurobox heavily filled with small metallic objects.  \ngeometric detail, enabling registration algorithms to reliably align object models with observations, even under partial occlusion. However, these solutions require a complex and expensive setup, posing a barrier to use","cbCaiujgTaHXFNGW","https://ap.wps.com/l/cbCaiujgTaHXFNGW","pdf",17945452,1,10,"English","en",105,"# Introduction\n## Motivation and challenges\n## Foundation models and depth quality\n## Proposed modular pipeline","[{\"question\":\"What problem does Pickalo target in industrial bin picking?\",\"answer\":\"Pickalo addresses failures in cluttered bin-picking scenarios caused by heavy occlusion and sensing limitations, where conventional high-end 3D setups are costly.\"},{\"question\":\"How does Pickalo obtain depth and improve its quality?\",\"answer\":\"Pickalo refines raw stereo streams using BridgeDepth to produce depth maps suitable for collision reasoning.\"},{\"question\":\"What components enable accurate grasp planning in Pickalo?\",\"answer\":\"It segments objects with a Mask-RCNN from photorealistic synthetic data, localizes poses using zero-shot SAM-6D, fuses multiview observations in a pose buffer, and ranks antipodal grasp candidates with utility-based scoring plus fast collision checking.\"}]",1784195944,25,{"code":4,"msg":30,"data":31},"ok",{"site_id":24,"language":23,"slug":32,"title":13,"keywords":33,"description":14,"schema_data":34,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":27},"pickalo-leveraging-6d-pose-estimation-for-low-cost-industrial-bin-picking","",{"@graph":35,"@context":85},[36,53,68],{"@type":37,"itemListElement":38},"BreadcrumbList",[39,43,47,50],{"item":40,"name":41,"@type":42,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":44,"name":45,"@type":42,"position":46},"https://docshare.wps.com/document/","Document",2,{"item":48,"name":12,"@type":42,"position":49},"https://docshare.wps.com/document/research-report/",3,{"item":51,"name":13,"@type":42,"position":52},"https://docshare.wps.com/document/pickalo-leveraging-6d-pose-estimation-for-low-cost-industrial-bin-picking/84480/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":23,"description":14,"dateModified":61,"datePublished":62,"encodingFormat":60,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":40,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-17","2026-07-16",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What problem does Pickalo target in industrial bin picking?","Question",{"text":75,"@type":76},"Pickalo addresses failures in cluttered bin-picking scenarios caused by heavy occlusion and sensing limitations, where conventional high-end 3D setups are costly.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does Pickalo obtain depth and improve its quality?",{"text":80,"@type":76},"Pickalo refines raw stereo streams using BridgeDepth to produce depth maps suitable for collision reasoning.",{"name":82,"@type":73,"acceptedAnswer":83},"What components enable accurate grasp planning in Pickalo?",{"text":84,"@type":76},"It segments objects with a Mask-RCNN from photorealistic synthetic data, localizes poses using zero-shot SAM-6D, fuses multiview observations in a pose buffer, and ranks antipodal grasp candidates with utility-based scoring plus fast collision checking.","https://schema.org",{"og:url":51,"og:type":87,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":89,"canonical":51},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,134],{"id":20,"doc_module":4,"doc_module_name":45,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":45,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":45,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":45,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":45,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":45,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":45,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":21,"doc_module":4,"doc_module_name":45,"category_name":132,"show_sort_weight":21,"slug":133},"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":45,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]