A hybrid approach for intersection management in V2X-enabled connected vehicles

Autonomous Vehicles (AVs) have the potential to revolutionize transportation by enhancing safety, efficiency, and convenience. However, AVs face significant challenges in complex urban environments, particularly in accurately perceiving and navigating through intersections mainly due to occlusions. This thesis addresses these challenges by integrating Vehicle-to-Everything (V2X) communication with onboard sensors to improve AV perception and decision-making capabilities. In particular, this thesis proposes a hybrid centralized-decentralized management system, which maximizes the benefits of centralized control for strategic traffic management and the responsiveness of decentralized decision-making, using edge nodes as a traffic coordinators helps reduces the computational needs on the vehicle. Such a system leverages V2X data to enhance situational awareness, optimize traffic flow, and improve overall safety and efficiency in urban environments. The methodology involves using Simultaneous Localisation and Mapping - SLAM for mapping, particle filters for localization, and waypoint generation for planning and control. The hybrid system’s performance was evaluated through simulations and real-world experiments using scaled-down vehicles equipped with advanced sensing and communication technologies. Compared to purely centralized or decentralized approaches, the hybrid system achieved up to a 14% reduction in average travel times through intersections and a 20% improvement in overall traffic flow efficiency. This thesis contributes to the development of intelligent transportation systems by demonstrating the efficacy of hybrid intersection management in enhancing AV performance in urban environments.

Name thesis:degree_name

Master of Applied Science (MASc)

Discipline thesis:degree_discipline

Electrical and Computer Engineering

Grantor

University of Ontario Institute of Technology

Year dc:date.issued

2024

Author dc:creator

• Elmoghazy, Ammar

Advisors dc:contributor.advisor

• Elgazzar, Khalid
• AlWidian, Sanaa

Language dc:language.iso

en

Handle dc:identifier.uri

https://hdl.handle.net/10155/1824

OAI identifier oai:identifier

oai:ontariotechu.scholaris.ca:10155/1824