BEGIN:VCALENDAR VERSION:2.0 PRODID:IEEE vTools.Events//EN CALSCALE:GREGORIAN BEGIN:VTIMEZONE TZID:US/Eastern BEGIN:DAYLIGHT DTSTART:20220313T030000 TZOFFSETFROM:-0500 TZOFFSETTO:-0400 RRULE:FREQ=YEARLY;BYDAY=2SU;BYMONTH=3 TZNAME:EDT END:DAYLIGHT BEGIN:STANDARD DTSTART:20221106T010000 TZOFFSETFROM:-0400 TZOFFSETTO:-0500 RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11 TZNAME:EST END:STANDARD END:VTIMEZONE BEGIN:VEVENT DTSTAMP:20220524T110056Z UID:F12DF61E-D17D-4669-8D3A-FF5F2419E427 DTSTART;TZID=US/Eastern:20220521T093000 DTEND;TZID=US/Eastern:20220521T103000 DESCRIPTION:IEEE North Jersey Section: RAS Chapter and SMC Chapter joint se minar on\n\nHuman-Robot Collaborative Learning of Human Welder Intelligenc e for Enhancing Human Welder Skills and Robotizing Complex Welding Process es\n\nYuMing Zhang\n\nJames R. Boyd Professor of Electrical Engineering\, University of Kentuck\n\nPlace: https://njit.webex.com/meet/zhou\n\nTime: 9:30am-10:30am\, May 21\, 2022\n\nFor precision joining\, skilled welders currently overperform welding robots due to their adaptation to the proces s. This is a kind of human intelligence that may be used to equip welding robots for them to become more intelligent and help welders to reduce the needed training time. A major challenge in learning such intelligence aris es from the specular nature of pool surface that disqualifies diffuse refl ection-based laser triangulation methods. To overcome this issue\, the mir ror surface is advantageously used to reflect a laser pattern away from th e arc\, simultaneously eliminating the arc illumination problem. To allow welders to freely demonstrate their skills\, a human-robot collaborative s ystem has been established where a welder carries a virtual torch\, simila rly as operating an actual one\, without a sensor. The movement is measure d at the virtual system and then followed by a robot which carries the sen sor and performs the actual welding. The measured weld pool is displayed t o the operator at the virtual site such that the welder can observe the ch ange in the operation result to adjust his/her torch movement and other pa rameters. The true intelligence of the welder is thus contained in and can thus be extracted from the resultant data. For more complex welding proce sses that require operations of multiple welding torches/tools\, their rob otization are more challenging complex. A possible solution is also to lea rn from human welders as they are quicker learners who can adjust their op erations to stabilize the complex welding process. This involves simultane ous operations from multiple welders and capture of the data needed to lea rn. Human-robot collaboration again provides an environment to enable the operation and capture the “true” data for learning of the intelligence needed despite the complexity of multiple operations.\n\nBio: Dr. YuMing Zhang’s research focuses on intelligent robotic and human-robot collabor ative welding systems. His research has been supported by the NSF\, Navy\, National Labs and industry\, brought him 12 US patents\, and over 200 jou rnal publications. His recognition includes Fellow of the American Welding Society (AWS)\, Fellow of the American Society of Mechanical Engineers (A SME)\, and Fellow of the Society of Manufacturing Engineers (SME)\; Dean ’s Award for Excellence in Research from the College of Engineering. Fiv e of his graduate students won the IIW (International Welding Institute) H enry Granjon Prize on behalf of the US against IIW member countries’ nat ional winners for dissertation/thesis research. Dr. Zhang is currently one of the two Editors for the Journal of Manufacturing Processes published b y the SME. He is\, and has been\, Associate Editor/Editorial Board Member for a number of major international journals including the IEEE Transactio ns on Automation Science and Engineering.\n\nSpeaker(s): Yuming Zhang\, \n \n323 Dr Martin Luther King Jr Blvd.\, ECE-NJIT\, Newark\, New Jersey\, Un ited States\, 07102-1982 LOCATION:323 Dr Martin Luther King Jr Blvd.\, ECE-NJIT\, Newark\, New Jerse y\, United States\, 07102-1982 ORGANIZER:zhou@njit.edu SEQUENCE:1 SUMMARY:IEEE North Jersey Section: RAS Chapter and SMC Chapter joint semina r URL;VALUE=URI:https://events.vtools.ieee.org/m/314212 X-ALT-DESC:Description: <br /><p>IEEE North Jersey Section: RAS Chapter and SMC Chapter joint seminar on</p>\n<p>Human-Robot Collaborative Learning o f Human Welder Intelligence for Enhancing Human Welder Skills and Robotizi ng Complex Welding Processes</p>\n<p>YuMing Zhang</p>\n<p>James R. Boyd Pr ofessor of Electrical Engineering\, University of Kentuck</p>\n<p>Place: h ttps://njit.webex.com/meet/zhou</p>\n<p>Time: 9:30am-10:30am\, May 21\, 20 22</p>\n<p>For precision joining\, skilled welders currently overperform w elding robots due to their adaptation to the process. This is a kind of hu man intelligence that may be used to equip welding robots for them to beco me more intelligent and help welders to reduce the needed training time. A major challenge in learning such intelligence arises from the specular na ture of pool surface that disqualifies diffuse reflection-based laser tria ngulation methods. To overcome this issue\, the mirror surface is advantag eously used to reflect a laser pattern away from the arc\, simultaneously eliminating the arc illumination problem.&nbsp\;To allow welders to freely demonstrate their skills\, a human-robot collaborative system has been es tablished where a welder carries a virtual torch\, similarly as operating an actual one\, without a sensor. The movement is measured at the virtual system and then followed by a robot which carries the sensor and performs the actual welding. The measured weld pool is displayed to the operator at the virtual site such that the welder can observe the change in the opera tion result to adjust his/her torch movement and other parameters. The tru e intelligence of the welder is thus contained in and can thus be extracte d from the resultant data. For more complex welding processes that require operations of multiple welding torches/tools\, their robotization are mor e challenging complex. A possible solution is also to learn from human wel ders as they are quicker learners who can adjust their operations to stabi lize the complex welding process. This involves simultaneous operations fr om multiple welders and capture of the data needed to learn. Human-robot c ollaboration again provides an environment to enable the operation and cap ture the &ldquo\;true&rdquo\; data for learning of the intelligence needed despite the complexity of multiple operations.</p>\n<p>Bio: Dr. YuMing Zh ang&rsquo\;s research focuses on intelligent robotic and human-robot colla borative welding systems. His research has been supported by the NSF\, Nav y\, National Labs and industry\, brought him 12 US patents\, and over 200 journal publications. His recognition includes Fellow of the American Weld ing Society (AWS)\, Fellow of the American Society of Mechanical Engineers (ASME)\, and Fellow of the Society of Manufacturing Engineers (SME)\; Dea n&rsquo\;s Award for Excellence in Research from the College of Engineerin g. Five of his graduate students won the IIW (International Welding Instit ute) Henry Granjon Prize on behalf of the US against IIW member countries& rsquo\; national winners for dissertation/thesis research. Dr. Zhang is cu rrently one of the two Editors for the Journal of Manufacturing Processes published by the SME.&nbsp\; He is\, and has been\, Associate Editor/Edito rial Board Member for a number of major international journals including t he IEEE Transactions on Automation Science and Engineering. &nbsp\;</p> END:VEVENT END:VCALENDAR