BEGIN:VCALENDAR VERSION:2.0 PRODID:IEEE vTools.Events//EN CALSCALE:GREGORIAN BEGIN:VTIMEZONE TZID:America/Los_Angeles BEGIN:DAYLIGHT DTSTART:20260308T030000 TZOFFSETFROM:-0800 TZOFFSETTO:-0700 RRULE:FREQ=YEARLY;BYDAY=2SU;BYMONTH=3 TZNAME:PDT END:DAYLIGHT BEGIN:STANDARD DTSTART:20261101T010000 TZOFFSETFROM:-0700 TZOFFSETTO:-0800 RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11 TZNAME:PST END:STANDARD END:VTIMEZONE BEGIN:VEVENT DTSTAMP:20260501T001219Z UID:CDC990BA-2059-4C3D-9F91-070B446DA94B DTSTART;TZID=America/Los_Angeles:20260429T170000 DTEND;TZID=America/Los_Angeles:20260429T183000 DESCRIPTION:Autonomous mobility is largely approached as a vehicle-centric problem. Persistent challenges in safety\,\n\nscalability\, and public tru st suggest a deeper issue: “intelligence” is often considered in isola tion rather than as\n\ndistributed. This presentation argues that truly sa fe and trustworthy autonomy will emerge only through\n\nsymbiotic computat ional systems\, where perception\, decision-making\, and control are distr ibuted across\n\nhumans\, machines\, and infrastructure.\n\nThe presentati on starts with an overview of the four decades-long progress in autonomous driving and related\n\nadvancements in driver assistance technologies. It is followed by a discussion of the central thesis: that many\n\nfailures in autonomous mobility stem not from algorithms alone\, but from how syste m boundaries are defined—\n\nwhat is sensed\, where intelligence resides \, and how responsibility is shared. Framing autonomy as a systems-\n\nlev el problem\, the talk draws on principles of distributed and embodied cogn ition to unify perspectives from\n\nrobotics\, artificial intelligence\, h uman–computer interaction\, and transportation engineering.\n\nConcrete examples from multidisciplinary research by the CVRR and LISA teams at UC San Diego\, conducted\n\non real vehicles in real-world driving environmen ts and validated through both quantitative benchmarks and\n\nqualitative s tudies in collaboration with industry partners\, illustrate how shared aut onomy can tightly couple\n\nhuman state (e.g.\, intent\, attention\, readi ness) with environmental context to enable safer and more adaptive\n\nhuma n–AI interaction. The lecture also discusses how advances in foundation models\, self-supervised learning\,\n\nand active learning can improve gen eralization and robustness in safety-critical settings.\n\nThe talk conclu des with key open challenges\, including multimodal foundation models for traffic ecosystems\,\n\nhuman–AI co-adaptation\, and continual learning under domain shift\, important problems to realize scalable\,\n\ntrustwort hy autonomous mobility.\n\nCo-sponsored by: Vishnu S. Pendyala\, San Jose State University\n\nSpeaker(s): Professor Mohan Trivedi\, Dr. Vishnu S Pen dyala\n\nRoom: MLK Room 225\, Dr. Martin Luther King\, Jr. Library (SJSU)\ , 150 E San Fernando St San Jose\, California 95112\, San Jose\, Californi a\, United States\, Virtual: https://events.vtools.ieee.org/m/556950 LOCATION:Room: MLK Room 225\, Dr. Martin Luther King\, Jr. Library (SJSU)\, 150 E San Fernando St San Jose\, California 95112\, San Jose\, California \, United States\, Virtual: https://events.vtools.ieee.org/m/556950 ORGANIZER:pendyala@ieee.org SEQUENCE:36 SUMMARY:Distinguished Lecture: Safe\, Trustworthy Autonomous Mobility: A Hu man-Centered Symbiotic Systems Perspective URL;VALUE=URI:https://events.vtools.ieee.org/m/556950 X-ALT-DESC:Description: <br /><p class="p1">Autonomous mobility is largely approached as a vehicle-centric problem. Persistent challenges in safety\, </p>\n<p class="p1">scalability\, and public trust suggest a deeper issue: &ldquo\;intelligence&rdquo\; is often considered in isolation rather than as</p>\n<p class="p1">distributed. This presentation argues that truly sa fe and trustworthy autonomy will emerge only through</p>\n<p class="p1">sy mbiotic computational systems\, where perception\, decision-making\, and c ontrol are distributed across</p>\n<p class="p1">humans\, machines\, and i nfrastructure.</p>\n<p class="p1">&nbsp\;</p>\n<p class="p1">The presentat ion starts with an overview of the four decades-long progress in autonomou s driving and related</p>\n<p class="p1">advancements in driver assistance technologies. It is followed by a discussion of the central thesis: that many</p>\n<p class="p1">failures in autonomous mobility stem not from algo rithms alone\, but from how system boundaries are defined&mdash\;</p>\n<p class="p1">what is sensed\, where intelligence resides\, and how responsib ility is shared. Framing autonomy as a systems-</p>\n<p class="p1">level p roblem\, the talk draws on principles of distributed and embodied cognitio n to unify perspectives from</p>\n<p class="p1">robotics\, artificial inte lligence\, human&ndash\;computer interaction\, and transportation engineer ing.</p>\n<p class="p1">&nbsp\;</p>\n<p class="p1">Concrete examples from multidisciplinary research by the CVRR and LISA teams at UC San Diego\, co nducted</p>\n<p class="p1">on real vehicles in real-world driving environm ents and validated through both quantitative benchmarks and</p>\n<p class= "p1">qualitative studies in collaboration with industry partners\, illustr ate how shared autonomy can tightly couple</p>\n<p class="p1">human state (e.g.\, intent\, attention\, readiness) with environmental context to enab le safer and more adaptive</p>\n<p class="p1">human&ndash\;AI interaction. The lecture also discusses how advances in foundation models\, self-super vised learning\,</p>\n<p class="p1">and active learning can improve genera lization and robustness in safety-critical settings.</p>\n<p class="p1">&n bsp\;</p>\n<p class="p1">The talk concludes with key open challenges\, inc luding multimodal foundation models for traffic ecosystems\,</p>\n<p class ="p1">human&ndash\;AI co-adaptation\, and continual learning under domain shift\, important problems to realize scalable\,</p>\n<p class="p1">trustw orthy autonomous mobility.</p> END:VEVENT END:VCALENDAR