A Software Architecture Proposal for Autonomous Vehicles

• Autor(a) principal: Gomes, Iago Pacheco
• Data de Publicação: 2019
• Tipo de documento: Dissertação
• Idioma: eng
• Título da fonte: Biblioteca Digital de Teses e Dissertações da USP
• Texto Completo: https://www.teses.usp.br/teses/disponiveis/55/55134/tde-06012020-122648/
• topic: Arquiteturas de software; Autonomous vehicle; Behavior planning; Descrição de mapas; Detecção e diagnóstico de falhas; Fault detection and diagnosis; Planejamento de comportamento; Road network description; Software architecture; Veículos autônomos

Autonomous Vehicles should transform the urban transport scenario, increasing its efficiency, making it more accessible and safe, reducing environmental impact, among other benefits. To do so, they are composed of a set of hardware and algorithms, which allow them to understand the external environment, their own state and interact with other traffic agents. In turn, these components need to collaborate with each other to ensure the full operation of the vehicle, which makes its architectural design an essential step for the project and development. The software architecture presents the structure and organization of the components, enabling evaluations and making decisions prior to implementation. Another important aspect is that such systems are subject to faults that can affect the whole performance of the vehicle, therefore, it is essential to detect and diagnose them. In this way, the objective of this work is to develop a new architecture for the CaRINA 2, the autonomous vehicle of the University of São Paulo, adding new functionalities developed by the research group and focusing mainly on safety requirements, which consists of detecting and diagnosing faults. In addition, new map structure and a new method for behavior and maneuver development were also included to the architecture.