BEGIN:VCALENDAR
VERSION:2.0
PRODID:IEEE vTools.Events//EN
CALSCALE:GREGORIAN
BEGIN:VTIMEZONE
TZID:America/Los_Angeles
BEGIN:DAYLIGHT
DTSTART:20250309T030000
TZOFFSETFROM:-0800
TZOFFSETTO:-0700
RRULE:FREQ=YEARLY;BYDAY=2SU;BYMONTH=3
TZNAME:PDT
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:20251102T010000
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11
TZNAME:PST
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20250621T165457Z
UID:273863D3-DCCC-422E-941A-7B9C622A755A
DTSTART;TZID=America/Los_Angeles:20250618T103000
DTEND;TZID=America/Los_Angeles:20250618T113000
DESCRIPTION:Abstract: Environmental perception is fundamental to safe and e
 fficient autonomous driving. With Cooperative Perception (CP) enabled by V
 2X networks\, connected vehicles can exchange perceptual information to se
 e through blind zones and deal with long-tail scenarios. In this talk\, we
  propose a robust\, reliable\, and resilient CP framework for connected au
 tonomous driving under V2X Communication Limitations. First\, for robustne
 ss to localization error and communication delay\, a calibration-free two-
 stage CP paradigm is proposed using deep metric learning. This fusion meth
 od only requires image data and is adaptive to the transmission rate. Then
 \, to guarantee high reliability\, hard AoI constraints are considered in 
 sensor scheduling of CP to guarantee the timeliness of perceptual informat
 ion. The required channel resources are minimized in asynchronous status u
 pdate settings. Next\, to resiliently adapt to the dynamic traffic environ
 ment\, we propose a learning-while-scheduling approach to trade off explor
 ation and exploitation. An online sensor scheduling algorithm is designed 
 based on restless MAB (Multi-Armed Bandit) theory to maximize the average 
 CP gain with low scheduling overhead. Finally\, a large-scale multi-view m
 ulti-modality dataset\, called Dolphins\, is presented to assist further r
 esearches and verification of CP systems.\n\nRoom: 660\, Bldg: ECS \, Univ
 ersity of Victoria\, Victoria\, British Columbia\, Canada\, V8P5C2
LOCATION:Room: 660\, Bldg: ECS \, University of Victoria\, Victoria\, Briti
 sh Columbia\, Canada\, V8P5C2
ORGANIZER:cai@ece.uvic.ca
SEQUENCE:1
SUMMARY:Robust and Resilient Cooperative Perception under V2X Communication
  Limitations
URL;VALUE=URI:https://events.vtools.ieee.org/m/484601
X-ALT-DESC:Description: <br /><p class="MsoNormal"><strong style="mso-bidi-
 font-weight: normal\;"><span style="font-size: 10.0pt\; mso-bidi-font-size
 : 10.5pt\; font-family: 'Times New Roman'\,serif\; color: black\; backgrou
 nd: white\;">Abstract: </span></strong><span style="font-size: 10.0pt\; ms
 o-bidi-font-size: 11.0pt\; font-family: 'Times New Roman'\,serif\;">Enviro
 nmental perception is fundamental to safe and efficient autonomous driving
 . With Cooperative Perception (CP) enabled by V2X networks\, connected veh
 icles can exchange perceptual information to see through blind zones and d
 eal with long-tail scenarios. In this talk\, we propose a robust\, reliabl
 e\, and resilient CP framework for connected autonomous driving under V2X 
 Communication Limitations. First\, for robustness to localization error an
 d communication delay\, a calibration-free two-stage CP paradigm is propos
 ed using deep metric learning. This fusion method only requires image data
  and is adaptive to the transmission rate. Then\, to guarantee high reliab
 ility\, hard AoI constraints are considered in sensor scheduling of CP to 
 guarantee </span><span style="font-size: 10.0pt\; mso-bidi-font-size: 11.0
 pt\; font-family: 'Times New Roman'\,serif\;">the timeliness of perceptual
  information. The required channel resources are minimized in asynchronous
  status update settings. Next\, to resiliently adapt to the dynamic traffi
 c environment\, we propose a learning-while-scheduling approach to trade o
 ff exploration and exploitation. An online sensor scheduling algorithm is 
 designed based on restless MAB (Multi-Armed Bandit) theory to maximize the
  average CP gain with low scheduling overhead. Finally\, a large-scale mul
 ti-view multi-modality dataset\, called Dolphins\, is presented to assist 
 further researches and verification of CP systems.</span></p>
END:VEVENT
END:VCALENDAR