Architectures for Collaborative Driving Vehicles: From a Review to a Proposal

Collaborative driving is an important sub-component of Intelligent Transportation Systems (ITS) and it strives to create vehicles that are able to cooperate in order to navigate through urban traffic by using communications. In this paper, we present an overview of different architecture from the field of artificial intelligence and robotic systems, related to collaborative driving, and analyze their relevance to our AUTO’21 project. The report is divided in three parts. The first part presents the background sustaining the collaborative driving vehicle. Precisely, this part describes three degrees of collaborative driving: longitudinal, lateral driving and completely autonomous system. The second part details the main architectures with their different fields of action, while focusing on collaboration and coordination. This part is itself divided in three sections. The first section refers to how agent oriented approaches can be related to intelligent vehicle highway system (IVHS). The second section overviews architectures from the robotic research field. As those architecture are often related to behavior based controllers, a more reactive aspect emerges, different from the deliberative and reasoning aspects that we can find in agent oriented approaches. The third section refers to architectures created specifically for vehicle guidance. These architectures incorporates (sometimes) previous models from Automated Highway System (AHS) environment. In the context of this section, projects on collaborative driving systems in other countries and specifically in USA, Japan and Europe, are presented. Finally considering our goals in the context of AUTO’21 project, all architectures are analyzed to find out their complexity, ability to handle unexpected events and required communications. The global recommended architecture in the context of AUTO’21 project, is then be described, detailing its different components.