[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-120974-en":3,"doc-seo-120974-105":30,"detail-sidebar-cat-0-en-105":92},{"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":27,"seo_description":14,"update_tm":28,"read_time":29},120974,137441390410,"Hazel","https://ap-avatar.wpscdn.com/avatar/2000252f4ab5702993?_k=1776741390130283984",8,"Research & Report","ROBUSTNESS EVALUATION OF MACHINE LEARNING MODELS FOR ROBOT ARM ACTION RECOGNITION IN NOISY ENVIRONMENTS","Robot action recognition in noisy environments requires distinguishing distinct but spatially close arm movements from vision signals, which is challenging when uncertainty corrupts the observed trajectories. This paper evaluates machine learning models for robot arm action recognition under noise by tracking robot motion, extracting arm key points with deep learning, and comparing multiple approaches. Experiments using a Franka Emika arm in a constrained 3-by-3 grid Tic-Tac-Toe setting show accurate key point detection and action classification despite noisy and uncertain data.","ROBUSTNESS EVALUATION OF MACHINE LEARNING MODELS FOR ROBOT ARM ACTION RECOGNITION IN NOISY ENVIRONMENTS  \nElaheh Motamedi †, Kian Behzad †, Rojin Zandi †, Hojjat Salehinejad ‡⋆, and Milad Siami †  \n†Department of Electrical & Computer Engineering, Northeastern University, Boston, MA, USA ‡Kern Center for the Science of Health Care Delivery, Mayo Clinic, Rochester, MN, USA ⋆Department of Artificial Intelligence and Informatics, Mayo Clinic, Rochester, MN, USA  \narXiv :2401 .09606v1 [ cs .CV] 17 Jan 2024  \nABSTRACT  \nIn the realm of robot action recognition, identifying distinct but spatially proximate arm movements using vision systems in noisy environments poses a significant challenge. This paper studies robot arm action recognition in noisy environments using machine learning techniques. Specifically, a vision system is used to track the robot’s movements followed by a deep learning model to extract the arm’s key points. Through a comparative analysis of machine learning methods, the effectiveness and robustness of this model are assessed in noisy environments. A case study was conducted using the Tic-Tac-Toe game in a 3-by-3 grid environment, where the focus is to accurately identify the actions of the arms in selecting specific locations within this constrained environment. Experimental results show that our approach can achieve precise key point detection and action classification despite the addition of noise and uncertainties to the dataset.  \nIndex Terms— Franka Emika robot arm, deep learning, key point extraction, noisy environment, robot arm action recognition.  \n1. INTRODUCTION  \nRobotic systems are widely used in diverse sectors such as healthcare, manufacturing, and automation [1, 2] . Central to the performance and utility of these systems is the accurate determination of the robot’s spatial orientation, commonly known as pose estimation, in an uncertain environment. Typically, pose estimation involves using regression models to detect the key points of a robot, which are the joints that makeup its skeleton. Accurate pose estimation is crucial for various tasks, ranging from object manipulation to navigation and interaction with the environment [1, 3, 4] .  \nThis material is based upon work supported in part at Northeastern University by grants ONR N00014-21-1-2431, NSF 2121121, the U.S. Department of Homeland Security under Grant Award Number 22STESE00001- 01-00, and by the Army Research Laboratory under Cooperative Agreement Number W911NF-22-2-0001 . The views and conclusions contained in this document are solely those of the authors and should not be interpreted as representing the official policies, either expressed or implied, of the U.S. Department of Homeland Security, the Army Research Office, or the U.S. Government.  \nWith the advancement of machine learning, significant progress has been made in the field of robot pose detection [5–8] . As an example, convolutional neural networks (CNNs) have been widely developed to address the pose estimation problem of robot arms in ideal environment [9–13] . However, such solutions often overlook the challenges of noisy and real-world environments, leading to models that excel theoretically but struggle in everyday scenarios.  \nIn this paper, a pretrained ResNet-50 [14] is utilized as a standard tool for pose recognition. The output of this model is a time series of pose locations prone to noise. A CNN is proposed for robot arm action recognition from the noisy time series and its performance is compared with the stateof-the-art models such as transformers [15] and Rocket [16] . The dataset for the experiments was collected using a Franka Emika [17] robot arm. This study makes a significant contribution to the field of robot action recognition by introducing a model for robot arm action recognition with minimal error margins in noisy environments. The insights gained from this study have the potential to inform the development of more reliable robotic systems for va","cbCaii2iW7GysBPu","https://ap.wps.com/l/cbCaii2iW7GysBPu","pdf",7219485,1,5,"English","en",105,"# Introduction\n# Method\n## Robot Arm Pose Recognition\n## Robot Arm Action Recognition","[{\"question\":\"What problem does the paper address in robot action recognition?\",\"answer\":\"It targets recognizing distinct arm actions from vision in noisy environments, where uncertainty can degrade pose trajectories and make similar movements hard to distinguish.\"},{\"question\":\"How are robot arm poses and key points obtained?\",\"answer\":\"A pretrained ResNet-50 processes video streams from multiple cameras to estimate robot arm key points over time, producing key-point trajectories used for later recognition.\"},{\"question\":\"How does the proposed method recognize actions under noise?\",\"answer\":\"The approach uses a CNN over the noisy time series of extracted key points to classify actions, and its performance is compared with other state-of-the-art model families.\"}]","ROBUSTNESS EVALUATION OF MACHINE LEARNING MODELS FOR ROBOT ARM ACTION RECOGNITION IN NOISY ENVIRONMENTS | PDF",1785733144,13,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":87,"head_meta":89,"extra_data":91,"updated_unix":28},"robustness-evaluation-of-machine-learning-models-for-robot-arm-action-recognition-in-noisy-environments","",{"@graph":36,"@context":86},[37,54,69],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/robustness-evaluation-of-machine-learning-models-for-robot-arm-action-recognition-in-noisy-environments/120974/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-04","2026-08-03",true,{"@type":66,"interactionType":67,"userInteractionCount":20},"InteractionCounter",{"@type":68},"ViewAction",{"@type":70,"mainEntity":71},"FAQPage",[72,78,82],{"name":73,"@type":74,"acceptedAnswer":75},"What problem does the paper address in robot action recognition?","Question",{"text":76,"@type":77},"It targets recognizing distinct arm actions from vision in noisy environments, where uncertainty can degrade pose trajectories and make similar movements hard to distinguish.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"How are robot arm poses and key points obtained?",{"text":81,"@type":77},"A pretrained ResNet-50 processes video streams from multiple cameras to estimate robot arm key points over time, producing key-point trajectories used for later recognition.",{"name":83,"@type":74,"acceptedAnswer":84},"How does the proposed method recognize actions under noise?",{"text":85,"@type":77},"The approach uses a CNN over the noisy time series of extracted key points to classify actions, and its performance is compared with other state-of-the-art model families.","https://schema.org",{"og:url":52,"og:type":88,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":90,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":93},[94,98,102,106,110,115,120,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":95,"show_sort_weight":96,"slug":97},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":99,"show_sort_weight":100,"slug":101},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":103,"show_sort_weight":104,"slug":105},"Exam",70,"exam",{"id":21,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":21,"slug":138},19,"General","general"]