{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,2]],"date-time":"2025-08-02T04:33:59Z","timestamp":1754109239243,"version":"3.41.2"},"reference-count":46,"publisher":"ASME International","issue":"2","license":[{"start":{"date-parts":[[2023,8,29]],"date-time":"2023-08-29T00:00:00Z","timestamp":1693267200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.asme.org\/publications-submissions\/publishing-information\/legal-policies"}],"funder":[{"DOI":"10.13039\/100000084","name":"Directorate for Engineering","doi-asserted-by":"publisher","award":["1925084"],"award-info":[{"award-number":["1925084"]}],"id":[{"id":"10.13039\/100000084","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["asmedigitalcollection.asme.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,2,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>This article presents a self-supervised learning approach for a robot to learn spatially varying process parameter models for contact-based finishing tasks. In many finishing tasks, a part has spatially varying stiffness. Some regions of the part enable the robot to efficiently execute the task. On the other hand, some other regions on the part may require the robot to move cautiously in order to prevent damage and ensure safety. Compared to the constant process parameter models, spatially varying process parameter models are more complex and challenging to learn. Our self-supervised learning approach consists of utilizing an initial parameter space exploration method, surrogate modeling, selection of region sequencing policy, and development of process parameter selection policy. We showed that by carefully selecting and optimizing learning components, this approach enables a robot to efficiently learn spatially varying process parameter models for a given contact-based finishing task. We demonstrated the effectiveness of our approach through computational simulations and physical experiments with a robotic sanding case study. Our work shows that the learning approach that has been optimized based on task characteristics significantly outperforms an unoptimized learning approach based on the overall task completion time.<\/jats:p>","DOI":"10.1115\/1.4063276","type":"journal-article","created":{"date-parts":[[2023,8,29]],"date-time":"2023-08-29T07:24:15Z","timestamp":1693293855000},"update-policy":"https:\/\/doi.org\/10.1115\/crossmarkpolicy-asme","source":"Crossref","is-referenced-by-count":2,"title":["Self-Supervised Learning of Spatially Varying Process Parameter Models for Robotic Finishing Tasks"],"prefix":"10.1115","volume":"24","author":[{"given":"Yeo","family":"Jung Yoon","sequence":"first","affiliation":[{"name":"University of Southern California Center for Advanced Manufacturing, , Los Angeles, CA 90007"}]},{"given":"Santosh V.","family":"Narayan","sequence":"additional","affiliation":[{"name":"University of Southern California Center for Advanced Manufacturing, , Los Angeles, CA 90007"}]},{"given":"Satyandra K.","family":"Gupta","sequence":"additional","affiliation":[{"name":"University of Southern California Center for Advanced Manufacturing, , Los Angeles, CA 90007 ,"}]}],"member":"33","published-online":{"date-parts":[[2023,10,10]]},"reference":[{"key":"2024101000020291000_CIT0001","doi-asserted-by":"crossref","DOI":"10.1115\/DETC2021-67627","article-title":"Learning to Improve Performance During Non-Repetitive Tasks Performed by Robots","author":"Yoon","year":"2021"},{"issue":"1","key":"2024101000020291000_CIT0002","doi-asserted-by":"publisher","first-page":"45","DOI":"10.1016\/S0003-6870(84)90121-2","article-title":"Robots in Industry: An Overview","volume":"15","author":"Edwards","year":"1984","journal-title":"Appl. Ergon."},{"issue":"2","key":"2024101000020291000_CIT0003","doi-asserted-by":"crossref","first-page":"45","DOI":"10.1109\/MRA.2003.1213616","article-title":"Welding Robots","volume":"10","author":"Norberto Pires","year":"2003","journal-title":"IEEE Robot. Autom. Mag."},{"key":"2024101000020291000_CIT0004","doi-asserted-by":"publisher","first-page":"101","DOI":"10.1016\/j.rcim.2014.08.008","article-title":"A Multi-Bead Overlapping Model for Robotic Wire and Arc Additive Manufacturing (WAAM)","volume":"31","author":"Ding","year":"2015","journal-title":"Rob. Computer-Integrated Manuf."},{"key":"2024101000020291000_CIT0005","doi-asserted-by":"publisher","first-page":"66","DOI":"10.1016\/j.cad.2015.12.003","article-title":"Towards an Automated Robotic Arc-Welding-Based Additive Manufacturing System From CAD to Finished Part","volume":"73","author":"Ding","year":"2016","journal-title":"Computer-Aided Design"},{"issue":"8","key":"2024101000020291000_CIT0006","doi-asserted-by":"publisher","first-page":"3126","DOI":"10.1109\/TIE.2011.2114311","article-title":"An Arc Welding Robot Control for a Shaped Metal Deposition Plant: Modular Software Interface and Sensors","volume":"58","author":"Bonaccorso","year":"2011","journal-title":"IEEE. Trans. Ind. Electron."},{"issue":"2","key":"2024101000020291000_CIT0007","doi-asserted-by":"publisher","first-page":"89","DOI":"10.3390\/app7020089","article-title":"Welding Robot Collision-Free Path Optimization","volume":"7","author":"Wang","year":"2017","journal-title":"Appl. Sci."},{"key":"2024101000020291000_CIT0008","doi-asserted-by":"crossref","DOI":"10.1115\/MSEC2018-6624","article-title":"Robotic Finishing of Interior Regions of Geometrically Complex Parts","author":"Kabir","year":"2018"},{"issue":"4","key":"2024101000020291000_CIT0009","doi-asserted-by":"publisher","first-page":"371","DOI":"10.1016\/j.rcim.2006.04.004","article-title":"Robotic Sanding System for New Designed Furniture With Free-Formed Surface","volume":"23","author":"Nagata","year":"2007","journal-title":"Rob. Computer-Integrated Manuf."},{"issue":"4","key":"2024101000020291000_CIT0010","doi-asserted-by":"publisher","first-page":"556","DOI":"10.1299\/jsmec1993.36.556","article-title":"Automation of Polishing Work by an Industrial Robot: System of Polishing Robot","volume":"36","author":"Takeuchi","year":"1993","journal-title":"JSME Int. J. Ser. C, Dynamics, Control, Robotics, Design Manuf."},{"issue":"1","key":"2024101000020291000_CIT0011","doi-asserted-by":"crossref","first-page":"69","DOI":"10.1016\/j.jmatprotec.2004.01.045","article-title":"Process Modeling for Robotic Polishing","volume":"159","author":"M\u00e1rquez","year":"2005","journal-title":"J. Mater. Process. Technol."},{"key":"2024101000020291000_CIT0012","doi-asserted-by":"publisher","first-page":"102482","DOI":"10.1016\/j.rcim.2022.102482","article-title":"Review on Robot-Assisted Polishing: Status and Future Trends","volume":"80","author":"Ke","year":"2023","journal-title":"Rob. Computer-Integrated Manuf."},{"key":"2024101000020291000_CIT0013","doi-asserted-by":"publisher","first-page":"391","DOI":"10.1016\/j.rcim.2018.12.019","article-title":"Contact Force Control and Vibration Suppression in Robotic Polishing With a Smart End Effector","volume":"57","author":"Chen","year":"2019","journal-title":"Rob. Computer-Integrated Manuf."},{"key":"2024101000020291000_CIT0014","first-page":"450","article-title":"Automated Robot Trajectory Planning for Spray Painting of Free-Form Surfaces in Automotive Manufacturing","author":"Chen","year":"2002"},{"key":"2024101000020291000_CIT0015","first-page":"522","article-title":"Automated Industrial Robot Path Planning for Spray Painting Process: A Review","author":"Chen","year":"2008"},{"key":"2024101000020291000_CIT0016","doi-asserted-by":"crossref","DOI":"10.1088\/1757-899X\/310\/1\/012108","article-title":"Optimization of Robotic Spray Painting Process Parameters Using Taguchi Method","author":"Chidhambara","year":"2018"},{"key":"2024101000020291000_CIT0017","doi-asserted-by":"publisher","first-page":"101923","DOI":"10.1016\/j.rcim.2019.101923","article-title":"Accurate Dynamic Modeling and Control Parameters Design of an Industrial Hybrid Spray-Painting Robot","volume":"63","author":"Zhang","year":"2020","journal-title":"Rob. Computer-Integrated Manuf."},{"key":"2024101000020291000_CIT0018","first-page":"278","article-title":"A Robotic Cell for Performing Sheet Lamination-Based Additive Manufacturing","volume":"27","author":"Bhatt","year":"2019","journal-title":"Addit. Manuf."},{"key":"2024101000020291000_CIT0019","doi-asserted-by":"crossref","DOI":"10.1115\/DETC2018-85975","article-title":"Trajectory Planning for Conformal 3D Printing Using Non-Planar Layers","author":"Shembekar","year":"2018"},{"key":"2024101000020291000_CIT0020","doi-asserted-by":"crossref","DOI":"10.1109\/ICRA.2019.8793730","article-title":"A Robotic Cell for Multi-resolution Additive Manufacturing","author":"Bhatt","year":"2019"},{"issue":"9","key":"2024101000020291000_CIT0021","doi-asserted-by":"crossref","first-page":"978","DOI":"10.1080\/10426914.2011.602792","article-title":"Parameter Optimization of Machining Processes Using a New Optimization Algorithm","volume":"27","author":"Rao","year":"2012","journal-title":"Mater. Manuf. Processes."},{"issue":"5","key":"2024101000020291000_CIT0022","doi-asserted-by":"publisher","first-page":"517","DOI":"10.1016\/j.rcim.2010.04.001","article-title":"Improving Feasibility of Robotic Milling Through Robot Placement Optimisation","volume":"26","author":"Vosniakos","year":"2010","journal-title":"Rob. Computer-Integrated Manuf."},{"key":"2024101000020291000_CIT0023","doi-asserted-by":"publisher","first-page":"69","DOI":"10.1016\/j.rcim.2015.02.006","article-title":"Stiffness-Oriented Posture Optimization in Robotic Machining Applications","volume":"35","author":"Guo","year":"2015","journal-title":"Rob. Computer-Integrated Manuf."},{"issue":"2","key":"2024101000020291000_CIT0024","doi-asserted-by":"publisher","first-page":"100","DOI":"10.5772\/53940","article-title":"Automated Trajectory Planner of Industrial Robot for Pick-and-Place Task","volume":"10","author":"Perumaal","year":"2013","journal-title":"Int. J. Adv. Robotic Syst."},{"key":"2024101000020291000_CIT0025","doi-asserted-by":"publisher","first-page":"102140","DOI":"10.1016\/j.rcim.2021.102140","article-title":"Generic Development Methodology for Flexible Robotic Pick-and-Place Workcells Based on Digital Twin","volume":"71","author":"Tipary","year":"2021","journal-title":"Rob. Computer-Integrated Manuf."},{"issue":"4","key":"2024101000020291000_CIT0026","doi-asserted-by":"publisher","first-page":"530","DOI":"10.1016\/j.rcim.2011.12.001","article-title":"Multirobot Coordination in Pick-and-Place Tasks on a Moving Conveyor","volume":"28","author":"Bozma","year":"2012","journal-title":"Rob. Computer-Integrated Manuf."},{"key":"2024101000020291000_CIT0027","doi-asserted-by":"crossref","DOI":"10.1115\/MSEC2016-8660","article-title":"Automated Learning of Operation Parameters for Robotic Cleaning by Mechanical Scrubbing","author":"Kabir","year":"2016"},{"issue":"1","key":"2024101000020291000_CIT0028","doi-asserted-by":"publisher","first-page":"352","DOI":"10.1109\/LRA.2017.2749280","article-title":"Integration of Planning and Deformation Model Estimation for Robotic Cleaning of Elastically Deformable Objects","volume":"3","author":"Langsfeld","year":"2018","journal-title":"IEEE Rob. Automation Lett."},{"key":"2024101000020291000_CIT0029","first-page":"132","article-title":"Determining Task Optimal Modular Robot Assembly Configurations","author":"Chen","year":"1995"},{"key":"2024101000020291000_CIT0030","first-page":"1067","article-title":"Dual Arm Robot for Packaging and Assembling of IT Products","author":"Do","year":"2012"},{"key":"2024101000020291000_CIT0031","doi-asserted-by":"crossref","DOI":"10.1115\/MSEC2018-6626","article-title":"Integrating Impedance Control and Learning Based Search Scheme for Robotic Assemblies Under Uncertainty","author":"Malhan","year":"2018"},{"key":"2024101000020291000_CIT0032","doi-asserted-by":"publisher","first-page":"292","DOI":"10.1016\/j.rcim.2018.12.007","article-title":"Trajectory Generation for Robotic Assembly Operations Using Learning by Demonstration","volume":"57","author":"Duque","year":"2019","journal-title":"Rob. Computer-Integrated Manuf."},{"key":"2024101000020291000_CIT0033","first-page":"2526","article-title":"Assembly Control Parameter Learning for Complex Robotic Assembly Processes","author":"Hong","year":"2018"},{"key":"2024101000020291000_CIT0034","first-page":"3465","article-title":"Online Parameter Optimization in Robotic Force Controlled Assembly Processes","author":"Cheng","year":"2014"},{"key":"2024101000020291000_CIT0035","first-page":"1794","article-title":"Real Time Welding Parameter Prediction for Desired Character Performance","author":"Dong","year":"2017"},{"key":"2024101000020291000_CIT0036","first-page":"351","article-title":"A Systematic Approach for Minimizing Physical Experiments to Identify Optimal Trajectory Parameters for Robots","author":"Kabir","year":"2017"},{"issue":"2","key":"2024101000020291000_CIT0037","doi-asserted-by":"publisher","first-page":"111","DOI":"10.3233\/ICA-180563","article-title":"Identifying Optimal Trajectory Parameters in Robotic Finishing Operations Using Minimum Number of Physical Experiments","volume":"25","author":"Kabir","year":"2018","journal-title":"Integrated Computer-Aided Eng."},{"key":"2024101000020291000_CIT0038","first-page":"626","article-title":"Robotic Bimanual Cleaning of Deformable Objects With Online Learning of Part and Tool Models","author":"Langsfeld","year":"2016"},{"key":"2024101000020291000_CIT0039","first-page":"958","article-title":"Improving Efficiency With Orthogonal Exploration for Online Robotic Assembly Parameter Optimization","author":"Wu","year":"2015"},{"key":"2024101000020291000_CIT0040","first-page":"87","article-title":"Automatic Parameter Learning for Easy Instruction of Industrial Collaborative Robots","author":"Srensen","year":"2018"},{"issue":"23","key":"2024101000020291000_CIT0041","doi-asserted-by":"publisher","first-page":"10052","DOI":"10.1016\/j.apm.2016.06.055","article-title":"Mathematical Modeling and Fdm Process Parameters Optimization Using Response Surface Methodology Based on Q-Optimal Design","volume":"40","author":"Mohamed","year":"2016","journal-title":"Appl. Math. Model."},{"key":"2024101000020291000_CIT0042","doi-asserted-by":"publisher","first-page":"164","DOI":"10.1016\/j.jmapro.2018.09.025","article-title":"Investigating the Effect of Fused Deposition Modeling Processing Parameters Using Taguchi Design of Experiment Method","volume":"36","author":"Alafaghani","year":"2018","journal-title":"J. Manuf. Process."},{"issue":"3","key":"2024101000020291000_CIT0043","first-page":"64","article-title":"A Systematic Survey of Fdm Process Parameter Optimization and Their Influence on Part Characteristics","volume":"3","author":"Dey","year":"2019","journal-title":"J. Manuf. Mater.Process."},{"issue":"8","key":"2024101000020291000_CIT0044","doi-asserted-by":"publisher","first-page":"1917","DOI":"10.1007\/s10514-019-09842-7","article-title":"Active Learning Via Informed Search in Movement Parameter Space for Efficient Robot Task Learning and Transfer","volume":"43","author":"Rakicevic","year":"2019","journal-title":"Auton. Robot"},{"issue":"1","key":"2024101000020291000_CIT0045","doi-asserted-by":"publisher","first-page":"391","DOI":"10.1109\/TASE.2016.2594147","article-title":"Dynamic Task Execution Using Active Parameter Identification With the Baxter Research Robot","volume":"14","author":"Wilson","year":"2017","journal-title":"IEEE Trans. Automation Sci. Eng."},{"key":"2024101000020291000_CIT0046","first-page":"25","article-title":"Active Exploration for Robot Parameter Selection in Episodic Reinforcement Learning","author":"Kroemer","year":"2011"}],"container-title":["Journal of Computing and Information Science in Engineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/asmedigitalcollection.asme.org\/computingengineering\/article-pdf\/24\/2\/021008\/7049083\/jcise_24_2_021008.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/asmedigitalcollection.asme.org\/computingengineering\/article-pdf\/24\/2\/021008\/7049083\/jcise_24_2_021008.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,10]],"date-time":"2024-10-10T11:59:54Z","timestamp":1728561594000},"score":1,"resource":{"primary":{"URL":"https:\/\/asmedigitalcollection.asme.org\/computingengineering\/article\/24\/2\/021008\/1166532\/Self-Supervised-Learning-of-Spatially-Varying"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,10]]},"references-count":46,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2024,2,1]]}},"URL":"https:\/\/doi.org\/10.1115\/1.4063276","relation":{},"ISSN":["1530-9827","1944-7078"],"issn-type":[{"type":"print","value":"1530-9827"},{"type":"electronic","value":"1944-7078"}],"subject":[],"published":{"date-parts":[[2023,10,10]]},"article-number":"021008"}}