Edge-Assisted Relevance-Aware Perception Dissemination in Vehicular Networks

Vehicles are equipped with various sensors such as LiDAR, which enable them to perceive the surrounding environment and enhance driver safety through advanced driver assistance systems. However, these sensors are limited by line-of-sight, preventing them from seeing beyond occlusions. One solution is to leverage the edge server which can collect and share perception data with other vehicles. Most existing research focuses on improve the performance of uploading perception data to the server, and the problem of perception dissemination remains largely unexplored, despite the challenges posed by the large volume of perception data and the limited wireless bandwidth. In this paper, we propose an edge-assisted relevance-aware perception dissemination system that collects perception data from multiple vehicles and selectively disseminates only the necessary data to appropriate vehicles. The necessity of dissem-ination is determined by evaluating the relevance of perception data, which quantifies the probability of potential collisions between corresponding objects. We then formulate and solve the relevance-aware perception dissemination problem whose goal is to maximize the relevance of disseminated data under bandwidth constraints. Extensive evaluation results demonstrate that our system can significantly enhance traffic safety while reducing the overall bandwidth consumption.