BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:Towards more accurate and robust vehicle trajectory prediction
DTSTART:20230914T150000
DTEND:20230914T170000
DTSTAMP:20260511T073005Z
UID:d1c8aa206c7906c59156ea5179534cb50a29bcd48f88d6f1bc844607
CATEGORIES:Conferences - Seminars
DESCRIPTION:Ahmad Rahimi\nEDIC candidacy exam\nExam president: Prof. Rober
 t West\nThesis advisor: Prof. Alexandre Alahi\nCo-examiner: Prof. Antoine 
 Bosselut\n\nAbstract\nThis thesis focuses on enhancing the precision and r
 obustness of vehicle trajectory prediction. Leveraging cutting-edge algori
 thms and data-driven techniques\, the research delves deep into understand
 ing the complexities of vehicular movements in diverse environments. By ac
 counting for various factors like traffic conditions\, roadway geometry\, 
 and driver behaviors\, we aim to predict future trajectories with reduced 
 error margins\, paving the way for safer and more efficient transportation
  systems.\n\nBackground papers\n1. Latent Variable Sequential Set Transfor
 mers For Joint Multi-Agent Motion Prediction\nRoger Girgis\, Florian Golem
 o\, Felipe Codevilla\, Martin Weiss\, Jim A. D’Souza\, Samira E. Kahou\,
  Felix Heide\, and Christopher Pal\nhttps://arxiv.org/abs/2104.00563\n\n2.
  Multimodal Trajectory Prediction Conditioned on Lane-Graph Traversals\nNa
 chiket Deo\, Eric M. Wolff\, and Oscar Beijbom\nhttps://arxiv.org/abs/2106
 .15004\n\n3. Learning to summarize from human feedback\nNisan Stiennon\, 
 Long Ouyang\, Jeff Wu\, Daniel M. Ziegler\, Ryan Lowe\, Chelsea Voss\,
  Alec Radford\, Dario Amodei\, and Paul Christiano\nhttps://arxiv.org/ab
 s/2009.01325\n 
LOCATION:GC B2 424 https://plan.epfl.ch/?room==GC%20B2%20424
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR