AICP: Augmented Informative Cooperative Perception

Connected vehicles, whether equipped with advanced driver-assistance systems or fully autonomous, require human driver supervision and are currently constrained to visual information in their line-of-sight. A cooperative perception system among vehicles increases situational awareness by extending range. Existing solutions focus on improving perspective transformation fast collection. However, such fail filter out large amounts of less relevant data thus impose significant network computation load. Moreover, presenting all this can overwhelm the actually hinder them. To address issues, we present Augmented Informative Cooperative Perception (AICP), first fast-filtering which optimizes informativeness shared at improve fused presentation. end, an maximization problem is presented for select a subset display drivers. Specifically, propose (i) dedicated design custom structure lightweight routing protocol convenient encapsulation, interpretation transmission, (ii) comprehensive formulation efficient fitness-based sorting algorithm most valuable application layer. We implement proof-of-concept prototype AICP bandwidth-hungry, latency-constrained real-life augmented reality application. The adds only 12.6 milliseconds latency current informativeness-unaware system. Next, test networking performance scale show that effectively filters packets decreases channel busy time.