ISEP - DM - Engenharia de Sistemas Computacionais Críticos
URI permanente para esta coleção:
Navegar
Percorrer ISEP - DM - Engenharia de Sistemas Computacionais Críticos por orientador "Severino, Ricardo Augusto Rodrigues da Silva"
A mostrar 1 - 3 de 3
Resultados por página
Opções de ordenação
- Co-simulation of vehicle distributed perception for road safety applicationsPublication . COSTA, TIAGO FILIPE LONGO; Severino, Ricardo Augusto Rodrigues da SilvaThe fast evolution of autonomous vehicles has introduced many new challenges, especially in perception, communication reliability, and energy efficiency. Traditional autonomous vehicles rely on onboard sensors, which are traditionally limited by range, computational cost, and occlusions. The goal of this thesis is to explore the integration of distributed perception systems to enhance situational awareness and improve autonomous vehicles decision-making. This work introduces an extension of the previously established co-simulation framework of Oliveira 2023 and Ribeiro 2024. The solution expands the capabilities of autonomous vehicles to sense beyond the onboard sensors while facilitating safe and efficient merging under different traffic conditions using roadside cameras and a roadside unit. The framework incorporates YOLO-based object detection with trilateration to combine data from a multicamera setup for improved localization accuracy and detection robustness across various traffic conditions. The experimental results show that compared to single-camera configurations, multi-camera fusion significantly increased recall and improved localization levels in conditions with different traffic and perception conditions. The roadside unit can also identify gaps for a safe and efficient merging and provide a target speed to the ego-vehicle via a simulated V2X communication. Overall, the proposed framework demonstrates the feasibility of infrastructure-assisted cooperative perception, providing a realistic and extensible testbed for future research in distributed perception, sensor fusion, and V2X communication for road safety applications.
- 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.
- Towards the simulation of cooperative perception applications by leveraging distributed sensing infrastructuresPublication . Oliveira, Miguel Ferreira; Severino, Ricardo Augusto Rodrigues da SilvaWith the rapid development of Automated Vehicles (AV), the boundaries of their function alities are being pushed and new challenges are being imposed. In increasingly complex and dynamic environments, it is fundamental to rely on more powerful onboard sensors and usually AI. However, there are limitations to this approach. As AVs are increasingly being integrated in several industries, expectations regarding their cooperation ability is growing, and vehicle-centric approaches to sensing and reasoning, become hard to integrate. The proposed approach is to extend perception to the environment, i.e. outside of the vehicle, by making it smarter, via the deployment of wireless sensors and actuators. This will vastly improve the perception capabilities in dynamic and unpredictable scenarios and often in a cheaper way, relying mostly in the use of lower cost sensors and embedded devices, which rely on their scale deployment instead of centralized sensing abilities. Consequently, to support the development and deployment of such cooperation actions in a seamless way, we require the usage of co-simulation frameworks, that can encompass multiple perspectives of control and communications for the AVs, the wireless sensors and actuators and other actors in the environment. In this work, we rely on ROS2 and micro-ROS as the underlying technologies for integrating several simulation tools, to construct a framework, capable of supporting the development, test and validation of such smart, cooperative environments. This endeavor was undertaken by building upon an existing simulation framework known as AuNa. We extended its capabilities to facilitate the simulation of cooperative scenarios by incorporat ing external sensors placed within the environment rather than just relying on vehicle-based sensors. Moreover, we devised a cooperative perception approach within this framework, showcasing its substantial potential and effectiveness. This will enable the demonstration of multiple cooperation scenarios and also ease the deployment phase by relying on the same software architecture.