BEGIN:VCALENDAR

VERSION:2.0

PRODID:-//wp-events-plugin.com//6.6.4.4//EN

TZID:Asia/Jerusalem

X-WR-TIMEZONE:Asia/Jerusalem
BEGIN:VEVENT

UID:0-1518@aerospace.technion.ac.il

DTSTART;TZID=Asia/Jerusalem:20251229T133000

DTEND;TZID=Asia/Jerusalem:20251229T143000

DTSTAMP:20251211T103102Z

URL:https://aerospace.technion.ac.il/events/seminar-slot-2025-12-29/

SUMMARY:Colloquium Series: Towards Scalable Online Planning Under Uncertain
 ty in Partially Observable Environments
DESCRIPTION:Lecturer:Vadim Indelman\n Faculty:The Stephen B. Klein Faculty 
 of Aerospace Engineering and the Faculty of Data and Decision Sciences (Se
 condary Appointment)\n Institute:Technion – Israel Institute of Technolo
 gy\n Location: Auditorium 235\, The Faculty of Aerospace Engineering\, Tec
 hnion\n Zoom: https://technion.zoom.us/j/93549691766\n Abstract: Decision-
 making under uncertainty in partially observable environments is a central
  challenge in AI and robotics. \n\nIt is fundamental to the operation of a
 utonomous systems that must act reliably and safely despite incomplete\, i
 mperfect\, or ambiguous information. This talk will present recent advance
 s in scalable online planning in such settings\, where the problem is comm
 only formulated as a Partially Observable Markov Decision Process (POMDP) 
 or addressed through belief space planning. These include POMDP planning w
 ith hybrid belief representations\, which capture real-world complexities 
 such as viewpoint-dependent semantic observations and ambiguous data assoc
 iations\, as well as methods for leveraging past experience to accelerate 
 online POMDP planning in continuous spaces significantly. \n\nThe second p
 art of the talk will focus on a recently developed framework for simplifyi
 ng decision-making under uncertainty problems with formal performance guar
 antees. This framework will be presented from multiple perspectives\, show
 ing how it enables fast and adaptive online POMDP planning. Finally\, its 
 extension to multi-agent systems will be presented\, highlighting how it s
 upports provably consistent decision-making even when agents maintain inco
 nsistent beliefs due to limited data-sharing.\n\n&nbsp\;\n\n&nbsp\;\n Deta
 ils: \n 
CATEGORIES:Seminars,סמינרים
LOCATION: Auditorium 235\, The Faculty of Aerospace Engineering\, Technion

END:VEVENT

BEGIN:VTIMEZONE

TZID:Asia/Jerusalem

X-LIC-LOCATION:Asia/Jerusalem

BEGIN:STANDARD

DTSTART:20251026T010000

TZOFFSETFROM:+0300

TZOFFSETTO:+0200

TZNAME:IST

END:STANDARD

END:VTIMEZONE
END:VCALENDAR