BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//132.216.98.100//NONSGML kigkonsult.se iCalcreator 2.20.4//
BEGIN:VEVENT
UID:20260921T131404EDT-1096vd8ea1@132.216.98.100
DTSTAMP:20260921T171404Z
DESCRIPTION:Abstract\n\nThe autonomous driving industry's rapid growth high
 lights the necessity for advanced technologies to guarantee safety\, comfo
 rt\, and efficiency. This thesis focuses on three fundamental aspects of a
 utonomous driving systems: trajectory prediction\, trajectory planning\, a
 nd control adaptation. The first contribution of this study is the introdu
 ction of a new technique for trajectory prediction that utilizes spatial-t
 emporal graphs to capture historical traffic interactions. The use of a de
 pthwise graph encoder network and sequential Gated Recurrent Unit decoder 
 improves vehicle trajectory prediction compared to other deep learning met
 hods. Next\, an innovative online graph planner is introduced for generati
 ng feasible and comfortable trajectories. The planner creates a spatial-te
 mporal graph that integrates the autonomous vehicle\, nearby vehicles\, an
 d virtual road nodes. The graph is then processed using a sequential netwo
 rk with a behavioral layer for kinematic constraint compliance. Testing th
 e planner on complex driving tasks demonstrates its effectiveness\, surpas
 sing existing state-of-the-art approaches. Finally\, a novel approach for 
 online learning in vehicle modeling and lateral control is introduced\, us
 ing heterogeneous graphs and Graph Neural Networks. This technique enables
  the vehicle model and lateral controller to adapt to dynamic conditions\,
  enhancing performance under perturbations. The self-learning model-based 
 lateral controller is evaluated on the CARLA simulator\, showing promising
  results. These contributions improve trajectory prediction\, planning\, a
 nd control adaptability\, advancing autonomous driving technology and enha
 ncing safety and efficiency of autonomous vehicles.\n
DTSTART:20241125T193000Z
DTEND:20241125T213000Z
LOCATION:Room 603\, McConnell Engineering Building\, CA\, QC\, Montreal\, H
 3A 0E9\, 3480 rue University
SUMMARY:PhD defence of Jilan Samiuddin – Decision making in self-driving ca
 rs using Graph Neural Networks
URL:https://www.mcgill.ca/ece/channels/event/phd-defence-jilan-samiuddin-de
 cision-making-self-driving-cars-using-graph-neural-networks-361283
END:VEVENT
END:VCALENDAR