ISEP - DM - Engenharia de Sistemas Computacionais Críticos
URI permanente para esta coleção:
Navegar
Percorrer ISEP - DM - Engenharia de Sistemas Computacionais Críticos por assunto "Au tonomous Vehicles"
A mostrar 1 - 1 de 1
Resultados por página
Opções de ordenação
- Explorar comunicação V2X para reforçar a segurança em colisões de veículos autónomosPublication . MOREIRA, RODRIGO OLIVEIRA SANTOS; Severino, Ricardo Augusto Rodrigues da SilvaEnsuring safety in autonomous vehicles in complex traffic scenarios is arguably still one of the most important intelligent transport system challenges. Conventional perception systems that depend on sensors such as cameras, LiDAR, and radar are prone to line-of-sight-relevant constraints, adverse weather conditions, and occlusions that can impede threat detection in scenarios of blind turns or obstructed intersections. Vehicle-to-Everything (V2X) communication is also hailed as the hopeful add-on to enhance situational awareness outside vehicle sensor range, where cars may exchange position, velocity, brake, and intent data in real-time. This thesis investigates the application of V2X communication to enhance crash safety by developing a simulation infrastructure that integrates Unreal Engine 5 for photo-realistic scenario simulation and the eCAL middleware for lightweight, low-latency message passing. The infrastructure was developed to simulate cooperative perception for low-visibility scenarios, aiming to establish whether early communication introduces longer reaction times and allows for earlier pre-crash safety system activation, i.e., airbags. Even though the integration of a network simulator (OMNeT++) is incomplete as the compilers and toolchains are not compatible, the project has a simulated working environment using Unreal Engine 5 and ensures eCAL’s role in passing structured data using Protobuf. Experimental results indicate seamless communication between virtual vehicles with near-zero latency, which depicts the potential as well as the limitations of shared-memory communication without real-world network simulation. This parer results provide a clearer vision of the role played by V2X in complementing legacy perception systems on autonomous vehicles. They also herald the need for toolchain synchronizations and simulator compatibilities in follow-on efforts. While the framework is incomplete, it is structured to naturally generalize to more complicated scenarios, heterogeneous sensor fusion, and full real-time synchronization with network simulators. Lastly, this research confirms the standing of V2X as one of the foremost enablers of cooperative safety applications in the quest for safer autonomous driving.