V2X collective perception for autonomous mobility

• Autor(a) principal: Almeida, Pedro Alves de
• Data de Publicação: 2022
• Tipo de documento: Dissertação
• Idioma: eng
• Título da fonte: Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
• Texto Completo: http://hdl.handle.net/10773/38856
• topic: Vehicular network; Collective perception; Autonomous mobility; Smart city

The urban population is growing rapidly, and cities are becoming bigger and more complex to manage. Therefore, new strategies are needed to control traffic congestion efficiently and improve road safety. With the evolution of smart cities and sensing devices, in addition to connected and autonomous vehicles, and vehicular communication, real-time information about the status of the smart city is now available. This dissertation proposes implementing the Collective Perception Service (CPS), a system defined by the European Telecommunications Standards Institute (ETSI), which aims at enabling Intelligent Transportation Systems (ITSs) to cooperate and exchange information about road users, obstacles on the road, and sensing information. The Collective Perception Message (CPM) is the message defined to share information regarding the disseminating Intelligent Transportation System Station (ITS-S), its sensory capabilities and perceived objects. The algorithms to generate CPMs and decide the relevant information from sensors to be integrated, taking into account the state of the road and the network congestion, as well as the information to be included in each message, are proposed. The developed system was evaluated and tested in both laboratory and real-world scenarios using the already existing infrastructure of the Aveiro Tech City Living Lab in Aveiro, Portugal. Results show that the developed system fulfills its goals, allowing ITS-Ss to cooperate and exchange information regarding perceived objects in a useful time. Envisioned use cases are services to detect safety problems on the road and the support for autonomous vehicles. Furthermore, a temporal analysis outlined the influence of the message size on the dissemination process of a CPM, and the need of a mechanism that decides if specific information shall be sent in the CPM. The scalability tests showed the effect of network congestion, testing the limits of the system. The system has already been integrated with an autonomous vehicle, taking advantage of the additional information from the Vehicle to Everything (V2X) communication. With this demonstration, it was shown a real example where more perception information could lead to a better decision making on the navigation plan, improving road safety.