Collective Perception Messages: New Low Complexity Fusion and V2X Connectivity Analysis
Nadia Mouawad, Valérian Mannoni
Abstract
Connected vehicles are equipped with sensors that can detect surrounding objects. However, vehicles perception is limited by sensors range or by the presence of other obstacles. Collective perception can improve vehicles perception by allowing them to exchange information about detected obstacles. In this context, vehicles rely on on-board sensors in order to generate Collective Perception Messages (CPM) that are exchanged by means of LTE-V2X connectivity. In order to reveal hidden obstacles and obtain a coherent visualization about the environment, CPM fusion is then crucial. In this work, we propose a novel low complexity fusion algorithm for CPM. Moreover, we evaluate the impact of LTE-V2X connectivity performance, specially in terms of packets loss, on the fusion. Simulation results in a smart junction demonstrate the relevance and efficiency of our algorithm in terms of obstacles detection capabilities.