BEGIN:VCALENDAR METHOD:REQUEST PRODID:Microsoft Exchange Server 2010 VERSION:2.0 BEGIN:VTIMEZONE TZID:Eastern Standard Time BEGIN:STANDARD DTSTART:16010101T020000 TZOFFSETFROM:-0400 TZOFFSETTO:-0500 RRULE:FREQ=YEARLY;INTERVAL=1;BYDAY=1SU;BYMONTH=11 END:STANDARD BEGIN:DAYLIGHT DTSTART:16010101T020000 TZOFFSETFROM:-0500 TZOFFSETTO:-0400 RRULE:FREQ=YEARLY;INTERVAL=1;BYDAY=2SU;BYMONTH=3 END:DAYLIGHT END:VTIMEZONE BEGIN:VEVENT ORGANIZER;CN="Satterfield, Mary Ann":mailto:msaterfi@purdue.edu ATTENDEE;ROLE=REQ-PARTICIPANT;PARTSTAT=NEEDS-ACTION;RSVP=TRUE;CN=ecefaculty @ecn.purdue.edu:mailto:ecefaculty@ecn.purdue.edu ATTENDEE;ROLE=REQ-PARTICIPANT;PARTSTAT=NEEDS-ACTION;RSVP=TRUE;CN=ececourtes y-list@ecn.purdue.edu:mailto:ececourtesy-list@ecn.purdue.edu ATTENDEE;ROLE=REQ-PARTICIPANT;PARTSTAT=NEEDS-ACTION;RSVP=TRUE;CN=ecegradstu dent-list@ecn.purdue.edu:mailto:ecegradstudent-list@ecn.purdue.edu ATTENDEE;ROLE=REQ-PARTICIPANT;PARTSTAT=NEEDS-ACTION;RSVP=TRUE;CN=ecepostdoc s-list@ecn.purdue.edu:mailto:ecepostdocs-list@ecn.purdue.edu ATTENDEE;ROLE=REQ-PARTICIPANT;PARTSTAT=NEEDS-ACTION;RSVP=TRUE;CN='CE Area F aculty':mailto:ececompfaculty-list@ecn.purdue.edu ATTACH:CID:image001.jpg@01D81F6B.530751E0 ATTACH:CID:7ADC6E9AEEA41044AC663474164D0A30@namprd22.prod.outlook.com ATTACH:CID:image002.jpg@01D81F6B.C2AE1560 ATTACH:CID:image003.jpg@01D81F6B.C2C5E320 ATTACH:CID:image002.jpg@01D81F6B.C2CC99E0 DESCRIPTION;LANGUAGE=en-US:If you’d like to meet with this candidate\, pl ease contact Philip E. Paré\nphilpare@purdue.edu or (765) 496-4818\n________________________________\n\nFaculty Candida te Seminar – Autonomous and Connected Systems\n\n[cid:image002.jpg@01D81 F6B.C2CC99E0]Lars Lindemann\nPostdoctoral Researcher\nUniversity of Pennsy lvania\n\nMonday\, February 21\, 2022\nPresentation: 10:30 A.M. – 11:30 A.M.\nQ & A: 11:30 A.M. – 12:00 P.M.\nPurdue Graduate Student Center\n 504 Northwestern Ave. ~ Room 105A & B\nhttps://purdue-edu.zoom.us/j/985870 59936\n\nSafe AI-Enabled Autonomy\n\nAbstract: AI-enabled autonomous syst ems show great promise to enable many future technologies such as autonomo us driving\, intelligent transportation\, and robotics. Over the past year s\, there has been tremendous success in the development of autonomous sys tems\, which was especially accelerated by the computational advances in m achine learning and AI. At the same time\, however\, new fundamental quest ions were raised regarding the safety and reliability of these increasingl y complex systems that often operate in uncertain and dynamic environments . In this seminar\, I will provide new insights and exciting opportunities to address these challenges.\n\nIn the first part of the seminar\, I will present a data-driven optimization framework to learn safe control laws f or dynamical systems. For most safety-critical systems such as self-drivin g cars\, safe expert demonstrations in the form of system trajectories tha t show safe system behavior are readily available or can easily be collect ed. At the same time\, accurate models of these systems can be identified from data or obtained from first order modeling principles. To learn safe control laws\, I present a constrained optimization problem with constrain ts on the expert demonstrations and the system model. Safety guarantees ar e provided in terms of the density of the data and the smoothness of the s ystem model. Two case studies on a self-driving car and a bipedal walking robot illustrate the presented method. In the past years\, it was shown th at neural networks are fragile and that their use in AI-enabled systems ha s resulted in systems taking excessive risk. The second part of the semina r is motivated by this fact and presents a data-driven verification framew ork to quantify and assess the risk of AI-enabled systems. I particularly show how risk measures\, classically used in finance\, can be used to quan tify the risk of not being robust to failure\, and how we can estimate thi s risk from data. We will compare and verify four different neural network controllers in terms of their risk for a self-driving car. I will conclud e by sharing exciting research directions in this area.\n\nBio: Lars Lind emann is currently a Postdoctoral Researcher in the Department of Electric al and Systems Engineering at the University of Pennsylvania. He received his B.Sc. degrees in Electrical and Information Engineering and his B.Sc. degree in Engineering Management in 2014 from the Christian-Albrechts-Univ ersity (CAU)\, Kiel\, Germany. He received his M.Sc. degree in Systems\, C ontrol and Robotics in 2016 and his Ph.D. degree in Electrical Engineering in 2020\, both from KTH Royal Institute of Technology\, Stockholm\, Swede n. His current research interests include systems and control theory\, for mal methods\, data-driven control\, and autonomous systems. Lars received the Outstanding Student Paper Award at the 58th IEEE Conference on Decisio n and Control and was a Best Student Paper Award Finalist at the 2018 Amer ican Control Conference. He also received the Student Best Paper Award as a co-author at the 60th IEEE Conference on Decision and Control.\n\n\n UID:040000008200E00074C5B7101A82E0080000000070C9FC9B661FD801000000000000000 010000000C1E387ACB5431544BA88B0756E76265C SUMMARY;LANGUAGE=en-US:ACS Faculty Candidate Lars Lindemann DTSTART;TZID=Eastern Standard Time:20220221T103000 DTEND;TZID=Eastern Standard Time:20220221T120000 CLASS:PUBLIC PRIORITY:5 DTSTAMP:20220211T222109Z TRANSP:OPAQUE STATUS:CONFIRMED SEQUENCE:0 LOCATION;LANGUAGE=en-US:PGSC Room 105A & B X-MICROSOFT-CDO-APPT-SEQUENCE:0 X-MICROSOFT-CDO-OWNERAPPTID:-1037359130 X-MICROSOFT-CDO-BUSYSTATUS:TENTATIVE X-MICROSOFT-CDO-INTENDEDSTATUS:BUSY X-MICROSOFT-CDO-ALLDAYEVENT:FALSE X-MICROSOFT-CDO-IMPORTANCE:1 X-MICROSOFT-CDO-INSTTYPE:0 X-MICROSOFT-DONOTFORWARDMEETING:FALSE X-MICROSOFT-DISALLOW-COUNTER:FALSE X-MICROSOFT-LOCATIONS:[{"DisplayName":"PGSC Room 105A & B"\,"LocationAnnota tion":""\,"LocationUri":""\,"LocationStreet":""\,"LocationCity":""\,"Locat ionState":""\,"LocationCountry":""\,"LocationPostalCode":""\,"LocationFull Address":""}] BEGIN:VALARM DESCRIPTION:REMINDER TRIGGER;RELATED=START:-PT15M ACTION:DISPLAY END:VALARM END:VEVENT END:VCALENDAR