BEGIN:VCALENDAR
VERSION:2.0
PRODID:icalendar-ruby
CALSCALE:GREGORIAN
X-WR-CALNAME:MS Thesis Final Exam - Viacheslav Tekaev
X-WR-TIMEZONE:Pacific Time (US & Canada)
BEGIN:VEVENT
DTSTAMP:20260714T134634Z
UID:tag:localist.com\,2008:EventInstance_52188399191968
DTSTART:20260303T170000Z
DTEND:20260303T180000Z
DESCRIPTION:TITLE: Integrating Augmented Reality and Artificial Intelligenc
 e for Adaptive Real-Time Task Guidance\n\nABSTRACT: This thesis presents a
 n augmented reality (AR) task guidance system enhanced by artificial intel
 ligence (AI)\, demonstrated through two distinct scenarios: an indoor appl
 ication guiding a user to open a door handle\, and an outdoor application 
 supporting spatial navigation and interactive object identification on a u
 niversity campus. Leveraging a modular architecture\, the system integrate
 s a mass-market AR headset with an AI backend that employs real-time objec
 t detection\, 3D spatial tracking\, and conversational interaction powered
  by a large language model. A key contribution of this work lies in the sy
 stem-level design of a flexible AR task guidance architecture that integra
 tes perception\, tracking\, navigation\, and natural language interaction\
 , and supports multiple deployment modes across edge and cloud resources. 
 The system supports on-edge (offline) and hybrid deployment configurations
 \, enabling the same task guidance pipeline to adapt to connectivity const
 raints\, computational availability\, and interaction requirements without
  modification of the core design. Further\, a quantitative system-level em
 pirical evaluation of the system consistently shows processing times below
  100 ms for simultaneous tracking of multiple objects\, visualization late
 ncy within acceptable real-time thresholds\, and positional accuracy withi
 n centimeters in indoor scenarios. This research work establishes a measur
 ed performance baseline and provides a scalable\, adaptable framework for 
 low-latency\, context-aware AR task guidance suitable for diverse real-wor
 ld applications.\n\n \n\nMAJOR ADVISOR: Raffaele De Amicis\nCOMMITTEE: Mik
 e Bailey\nCOMMITTEE: Eugene Zhang\nCOMMITTEE: Stefan Lee\nMINOR ADVISOR: S
 tefan Lee\nGCR: Leonard Coop
GEO:44.567164;-123.278692
LOCATION:Kelley Engineering Center\, 1007
SUMMARY:MS Thesis Final Exam - Viacheslav Tekaev
URL;VALUE=URI:https://events.oregonstate.edu/event/ms-thesis-final-exam-via
 cheslav-tekaev
CATEGORIES:Lecture or Presentation
END:VEVENT
END:VCALENDAR
