BEGIN:VCALENDAR METHOD:REQUEST PRODID:Microsoft Exchange Server 2010 VERSION:2.0 BEGIN:VTIMEZONE TZID:Central Standard Time BEGIN:STANDARD DTSTART:16010101T020000 TZOFFSETFROM:-0500 TZOFFSETTO:-0600 RRULE:FREQ=YEARLY;INTERVAL=1;BYDAY=1SU;BYMONTH=11 END:STANDARD BEGIN:DAYLIGHT DTSTART:16010101T020000 TZOFFSETFROM:-0600 TZOFFSETTO:-0500 RRULE:FREQ=YEARLY;INTERVAL=1;BYDAY=2SU;BYMONTH=3 END:DAYLIGHT END:VTIMEZONE BEGIN:VEVENT ORGANIZER;CN="Eulenfeld, Menda":mailto:menda.eulenfeld@tamucc.edu ATTENDEE;ROLE=REQ-PARTICIPANT;PARTSTAT=NEEDS-ACTION;RSVP=TRUE;CN="Izzat Ulla h, Syed":mailto:sizzatullah@islander.tamucc.edu ATTENDEE;ROLE=OPT-PARTICIPANT;PARTSTAT=NEEDS-ACTION;RSVP=TRUE;CN=Cynthia vi a COECS-List Williams:mailto:coecs-list@listserv.tamucc.edu ATTENDEE;ROLE=OPT-PARTICIPANT;PARTSTAT=NEEDS-ACTION;RSVP=TRUE;CN="Brundrett, Bridget":mailto:bridget.brundrett1@tamucc.edu ATTENDEE;ROLE=OPT-PARTICIPANT;PARTSTAT=NEEDS-ACTION;RSVP=TRUE;CN="Chu, Tianx ing":mailto:tianxing.chu@tamucc.edu ATTENDEE;ROLE=OPT-PARTICIPANT;PARTSTAT=NEEDS-ACTION;RSVP=TRUE;CN="Demir, Kad ir Alpaslan":mailto:kadiralpaslan.demir@tamucc.edu ATTENDEE;ROLE=OPT-PARTICIPANT;PARTSTAT=NEEDS-ACTION;RSVP=TRUE;CN="Gillis, Br yan":mailto:bryan.gillis@tamucc.edu ATTENDEE;ROLE=OPT-PARTICIPANT;PARTSTAT=NEEDS-ACTION;RSVP=TRUE;CN="Hadimliogl u, Alihan":mailto:alihan.hadimlioglu@tamucc.edu ATTENDEE;ROLE=OPT-PARTICIPANT;PARTSTAT=NEEDS-ACTION;RSVP=TRUE;CN="Haghparast , Mahboobeh":mailto:mahboobeh.haghparast@tamucc.edu ATTENDEE;ROLE=OPT-PARTICIPANT;PARTSTAT=NEEDS-ACTION;RSVP=TRUE;CN="Heuermann, Lewis":mailto:lewis.heuermann@tamucc.edu ATTENDEE;ROLE=OPT-PARTICIPANT;PARTSTAT=NEEDS-ACTION;RSVP=TRUE;CN="Holland, S eneca":mailto:seneca.holland@tamucc.edu ATTENDEE;ROLE=OPT-PARTICIPANT;PARTSTAT=NEEDS-ACTION;RSVP=TRUE;CN="Huang, Luc y":mailto:lucy.huang@tamucc.edu ATTENDEE;ROLE=OPT-PARTICIPANT;PARTSTAT=NEEDS-ACTION;RSVP=TRUE;CN="Huang, Min hua":mailto:minhua.huang@tamucc.edu ATTENDEE;ROLE=OPT-PARTICIPANT;PARTSTAT=NEEDS-ACTION;RSVP=TRUE;CN="Ji, Taoran" :mailto:taoran.ji@tamucc.edu ATTENDEE;ROLE=OPT-PARTICIPANT;PARTSTAT=NEEDS-ACTION;RSVP=TRUE;CN="Kar, Dulal" :mailto:dulal.kar@tamucc.edu ATTENDEE;ROLE=OPT-PARTICIPANT;PARTSTAT=NEEDS-ACTION;RSVP=TRUE;CN="King, Scot t":mailto:scott.king@tamucc.edu ATTENDEE;ROLE=OPT-PARTICIPANT;PARTSTAT=NEEDS-ACTION;RSVP=TRUE;CN="Le, Huyen": mailto:huyen.le@tamucc.edu ATTENDEE;ROLE=OPT-PARTICIPANT;PARTSTAT=NEEDS-ACTION;RSVP=TRUE;CN="Liu, Bozhe n":mailto:bozhen.liu@tamucc.edu ATTENDEE;ROLE=OPT-PARTICIPANT;PARTSTAT=NEEDS-ACTION;RSVP=TRUE;CN="Liu, Zhihu i":mailto:zhihui.liu@tamucc.edu ATTENDEE;ROLE=OPT-PARTICIPANT;PARTSTAT=NEEDS-ACTION;RSVP=TRUE;CN="Rubio Medr ano, Carlos":mailto:carlos.rubiomedrano@tamucc.edu ATTENDEE;ROLE=OPT-PARTICIPANT;PARTSTAT=NEEDS-ACTION;RSVP=TRUE;CN="Sekharan, Chandra":mailto:chandra.sekharan@tamucc.edu ATTENDEE;ROLE=OPT-PARTICIPANT;PARTSTAT=NEEDS-ACTION;RSVP=TRUE;CN="Senol, Hab ib":mailto:habib.senol@tamucc.edu ATTENDEE;ROLE=OPT-PARTICIPANT;PARTSTAT=NEEDS-ACTION;RSVP=TRUE;CN="Serice, Jo hn":mailto:john.serice@tamucc.edu ATTENDEE;ROLE=OPT-PARTICIPANT;PARTSTAT=NEEDS-ACTION;RSVP=TRUE;CN="Song, Hong zhi":mailto:hongzhi.song@tamucc.edu ATTENDEE;ROLE=OPT-PARTICIPANT;PARTSTAT=NEEDS-ACTION;RSVP=TRUE;CN="Sookhak, M ehdi":mailto:mehdi.sookhak@tamucc.edu ATTENDEE;ROLE=OPT-PARTICIPANT;PARTSTAT=NEEDS-ACTION;RSVP=TRUE;CN="Starek, Mi chael":mailto:michael.starek@tamucc.edu ATTENDEE;ROLE=OPT-PARTICIPANT;PARTSTAT=NEEDS-ACTION;RSVP=TRUE;CN="Wang, Wenl u":mailto:wenlu.wang@tamucc.edu ATTENDEE;ROLE=OPT-PARTICIPANT;PARTSTAT=NEEDS-ACTION;RSVP=TRUE;CN="Yadav, Mam ta":mailto:mamta.yadav@tamucc.edu ATTENDEE;ROLE=OPT-PARTICIPANT;PARTSTAT=NEEDS-ACTION;RSVP=TRUE;CN="Starek, Mi chael via Cs-phd-student":mailto:cs-phd-student@listserv.tamucc.edu ATTENDEE;ROLE=OPT-PARTICIPANT;PARTSTAT=NEEDS-ACTION;RSVP=TRUE;CN="Eulenfeld, Menda via cosc-grad-students-list":mailto:cosc-grad-students-list@listserv .tamucc.edu DESCRIPTION;LANGUAGE=en-US:RESEARCH DISSERTATION SEMINAR NOTICE\nCOMPUTER S CIENCE DOCTORAL PROGRAM\nCOLLEGE OF ENGINEERING AND COMPUTER SCIENCE\nTEXA S A&M UNIVERSITY-CORPUS CHRISTI\n\nSUBJECT:\nUncertainty-Aware Probabilist ic Forecasting of Non-Cooperative Dynamic Obstacles for Safe Autonomous Ae rial Navigation\nSPEAKER:\nSyed Izzat Ullah\nDATE:\nJune 10\, 2026\nTIME:\ n12:00 p.m.\nPLACE:\nRFEB 108\nZOOM LINK:\nhttps://tamucc.zoom.us/meetings /98210035860/\n\n ABSTRACT\nUnmanned Aerial Vehicles (UAVs) are increasingly deployed in com plex\, dynamic environments for applications such as urban air mobility\, surveillance\, emergency response\, and package delivery. Safe autonomous navigation in airspace shared with non-cooperative dynamic obstacles\, suc h as birds\, unregistered drones\, and other uninformed aerial agents\, re mains a fundamental challenge in aerial robotics. Existing motion planning methods are constrained by significant limitations that undermine their e ffectiveness in real-world scenarios. First\, they often rely on linear or constant-velocity motion models that do not capture the nonlinear and con text-dependent behavior of dynamic obstacles\, which can lead to delayed o r inadequate avoidance maneuvers. Second\, most trajectory planning framew orks lack modularity\, treating obstacle prediction and planning as separa te processes\, which hinders proactive decision-making and limits the inte gration of advanced prediction models. Third\, the absence of standardized benchmarking infrastructure to characterize the platform-level uncertaint ies such as actuator nonlinearities\, estimator drift\, and battery-depend ent thrust degradation on resource-constrained aerial systems\, that affec t the perception-prediction-planning pipeline.\n\nThis dissertation addres ses these limitations through four contributions within a modular framewor k for uncertainty-aware UAV trajectory planning. First\, POF+MADER integra tes a decentralized Kalman filter-based Probabilistic Obstacle Filter with optimization-based trajectory planners\, replacing the assumption of perf ect obstacle trajectory knowledge with real-time uncertainty-aware forecas ts embedded as dynamic constraints. Evaluation across 800 simulation runs yields a 38.75% improvement in success rate with a 0.8% increase in naviga tion time\, and hardware experiments on Crazyflie 2.1 UAVs show a 25% redu ction in collision rate under realistic sensing conditions. Second\, SynTr aG introduces a parametric trajectory generator that produces configurable three-dimensional corpora of non-cooperative aerial obstacle motion using randomized kinematic primitives with heteroscedastic noise\, and releases 47\,894 trajectories to address the lack of public training data in this domain. Building on this data foundation\, the third contribution\, AeroCa st\, combines a Pre-LN Transformer encoder with a Mixture Density Network output head to predict per-timestep Gaussian mixture distributions over fu ture three-dimensional displacements. On a hybrid real-and-synthetic corpu s of 90\,116 sequences spanning nine motion categories\, AeroCast reduces Average Displacement Error and Final Displacement Error by approximately 5 0% relative to the strongest recurrent baseline\, achieves the lowest nega tive log-likelihood among all compared methods\, and completes inference i n 0.1 ms per sample. Finally\, NanoBench introduces a multi-task benchmark for the Crazyflie 2.1 nano-quadrotor comprising over 170 flight trajector ies with synchronized Vicon ground truth\, raw IMU measurements\, onboard EKF estimates\, PID controller internals\, and motor PWM commands at 100 H z. NanoBench defines standardized protocols for system identification\, co ntroller benchmarking\, and state estimation\, and establishes the first o pen dataset to jointly expose actuator-level and estimator-level signals w ith millimeter-accurate external ground truth on a commercially available nano-scale platform.\n\nThese contributions show that uncertainty in auton omous UAV navigation must be addressed across the full pipeline rather tha n within any single module. In this dissertation\, uncertainty is treated at the planning level through probabilistic trajectory generation\, at the data level through synthetic corpus construction with realistic localizat ion noise\, at the prediction level through calibrated multi-modal forecas ting\, and at the platform level through benchmarked characterization of a ctuation and estimation effects on resource-constrained hardware.\n\n UID:040000008200E00074C5B7101A82E0080000000020C5419106F4DC01000000000000000 01000000045B601159E559543B70A0B57168CA050 SUMMARY;LANGUAGE=en-US:RESEARCH DISSERTATION SEMINAR NOTICE - Syed Izzat Ul lah DTSTART;TZID=Central Standard Time:20260610T120000 DTEND;TZID=Central Standard Time:20260610T130000 CLASS:PUBLIC PRIORITY:5 DTSTAMP:20260604T144634Z TRANSP:OPAQUE STATUS:CONFIRMED SEQUENCE:0 LOCATION;LANGUAGE=en-US:RFEB 108 X-MICROSOFT-CDO-APPT-SEQUENCE:0 X-MICROSOFT-CDO-OWNERAPPTID:1095002090 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-REQUESTEDATTENDANCEMODE:DEFAULT X-MICROSOFT-ISRESPONSEREQUESTED:TRUE X-MICROSOFT-LOCATIONS:[ { "DisplayName" : "RFEB 108"\, "LocationAnnotation" : ""\, "LocationSource" : 0\, "Unresolved" : false\, "LocationUri" : "" } ] BEGIN:VALARM DESCRIPTION:REMINDER TRIGGER;RELATED=START:-PT15M ACTION:DISPLAY END:VALARM END:VEVENT END:VCALENDAR